{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "4a10768a2d2e480b98141b0e126361ac": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_57203d98432240beb78408ae427f3bf0", "IPY_MODEL_7cefcf4f54eb41438f34690c61bb1c38", "IPY_MODEL_c6994d8d9a644b7f9a63ace7d95ab9ee" ], "layout": "IPY_MODEL_515d0e82e8304e4a998b251e2acc255b" } }, "57203d98432240beb78408ae427f3bf0": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0b0dd05193024ed5bd34ebd6802e3b2d", "placeholder": "​", "style": "IPY_MODEL_a6566d3fd8ff4de698a9b5ed36a249f9", "value": "Preprocessing: 100%" } }, "7cefcf4f54eb41438f34690c61bb1c38": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0a8fdc1f3f1f4af0afe8f4e652053c96", "max": 801, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d41f2b1276ca4fa2a923e60dfdbe76f8", "value": 801 } }, "c6994d8d9a644b7f9a63ace7d95ab9ee": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_447a657e01cd417889f4e40e262ab1cf", "placeholder": "​", "style": "IPY_MODEL_d5458bc789c449c78b448193b0df4784", "value": " 801/801 [00:05<00:00, 248.28docs/s]" } }, "515d0e82e8304e4a998b251e2acc255b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0b0dd05193024ed5bd34ebd6802e3b2d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a6566d3fd8ff4de698a9b5ed36a249f9": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "0a8fdc1f3f1f4af0afe8f4e652053c96": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d41f2b1276ca4fa2a923e60dfdbe76f8": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "447a657e01cd417889f4e40e262ab1cf": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d5458bc789c449c78b448193b0df4784": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "12f44e0d47474b30b573252e134a4783": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_8f9ca54b20764861b0696085b13e3930", "IPY_MODEL_846dd88d155c41c1a8bdbf65b9c1d26f", "IPY_MODEL_4ff895eed55c4959948035e862fdfdf5" ], "layout": "IPY_MODEL_6b9b100d07cf447a9d15b46cf0aaad02" } }, "8f9ca54b20764861b0696085b13e3930": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_7840e2f3068a4fe3997ad8e1eac5cab1", "placeholder": "​", "style": "IPY_MODEL_9f5f394923654789b2f583c4fd1375c5", "value": "Converting files: 100%" } }, "846dd88d155c41c1a8bdbf65b9c1d26f": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6b5a1e59ae174a678a526b8da4f3866b", "max": 802, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_f84eaa63c2d24dd298c9e4b58fc1a02f", "value": 802 } }, "4ff895eed55c4959948035e862fdfdf5": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a01d6e7ae71f48f3a369ec145eab491b", "placeholder": "​", "style": "IPY_MODEL_082f8a3bc4834142b6a356901cb9e81a", "value": " 802/802 [00:15<00:00, 9.01it/s]" } }, "6b9b100d07cf447a9d15b46cf0aaad02": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "7840e2f3068a4fe3997ad8e1eac5cab1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "9f5f394923654789b2f583c4fd1375c5": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6b5a1e59ae174a678a526b8da4f3866b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f84eaa63c2d24dd298c9e4b58fc1a02f": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "a01d6e7ae71f48f3a369ec145eab491b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "082f8a3bc4834142b6a356901cb9e81a": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "d68936fd9cce42588a6c0423a5b3192c": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_603f8e489cb24b4a8b433447ba1f7564", "IPY_MODEL_439f28a5a7c041f18c37849b36d0f3f1", "IPY_MODEL_54930b13ead44e5b91ad541d1dcddf74" ], "layout": "IPY_MODEL_9e63b1f42ddd4446b8932d00db73a035" } }, "603f8e489cb24b4a8b433447ba1f7564": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a93e802692e54ddb95d480ce83bf330b", "placeholder": "​", "style": "IPY_MODEL_79821356690e4a8ab92c7b5ffa363756", "value": "Preprocessing: 100%" } }, "439f28a5a7c041f18c37849b36d0f3f1": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0f30b897b0654cf7a84ecc795bd95cd0", "max": 802, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_f4928435ec3647b486a5ebfddbb61b96", "value": 802 } }, "54930b13ead44e5b91ad541d1dcddf74": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a6f31a1c4dac48ce97aea9700afc441f", "placeholder": "​", "style": "IPY_MODEL_5844902e84d54f568f3725e0eacaff39", "value": " 802/802 [00:17<00:00, 341.27docs/s]" } }, "9e63b1f42ddd4446b8932d00db73a035": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a93e802692e54ddb95d480ce83bf330b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "79821356690e4a8ab92c7b5ffa363756": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "0f30b897b0654cf7a84ecc795bd95cd0": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f4928435ec3647b486a5ebfddbb61b96": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "a6f31a1c4dac48ce97aea9700afc441f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5844902e84d54f568f3725e0eacaff39": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "c85c5379917643479dc44fbdfeab7c94": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_003e8f4437ef4894a24e61ae9a0f1334", "IPY_MODEL_3dfc5007f2a0425c886bcb9a1bdf09cc", "IPY_MODEL_f974a387511f4074b8fc8c00ffe3218b" ], "layout": "IPY_MODEL_b24e77d4495c4080b4699f76ea215dfa" } }, "003e8f4437ef4894a24e61ae9a0f1334": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6ad9963dc0fc46f082a142dc53c17c77", "placeholder": "​", "style": "IPY_MODEL_1f878dfdf1b148889808c45a59e48000", "value": "Updating BM25 representation...: 100%" } }, "3dfc5007f2a0425c886bcb9a1bdf09cc": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_976badd3eded492eb07ad48d91a0b33f", "max": 24327, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_830885b65be2428aa0ed902fc67a2f00", "value": 24327 } }, "f974a387511f4074b8fc8c00ffe3218b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_19054b561ac040f3801a3f1564b2f796", "placeholder": "​", "style": "IPY_MODEL_ccf34bb2e6d344e6a00bf0ce241b703b", "value": " 24327/24327 [00:01<00:00, 12878.96 docs/s]" } }, "b24e77d4495c4080b4699f76ea215dfa": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6ad9963dc0fc46f082a142dc53c17c77": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1f878dfdf1b148889808c45a59e48000": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "976badd3eded492eb07ad48d91a0b33f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "830885b65be2428aa0ed902fc67a2f00": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "19054b561ac040f3801a3f1564b2f796": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ccf34bb2e6d344e6a00bf0ce241b703b": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "51c5432770f746499d39eabe90ea3b22": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_eab6be491a2b4626bce29cb25dd69996", "IPY_MODEL_799f93ec6e56423a8517c33221de66a8", "IPY_MODEL_b7d6dc1b527843e4ae253bff6d09042c" ], "layout": "IPY_MODEL_41dd5492e6504ef7aec30aec1aa0fac1" } }, "eab6be491a2b4626bce29cb25dd69996": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e248351c67e24939b879e51bb1acf8b1", "placeholder": "​", "style": "IPY_MODEL_be735c6903954cdc9598ae9503c9b687", "value": "Preprocessing dataset: 100%" } }, "799f93ec6e56423a8517c33221de66a8": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_fd15a5f5fd0b486f942c996d2ab14142", "max": 38, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_893457340de84d4c8f34153bb7a8a951", "value": 38 } }, "b7d6dc1b527843e4ae253bff6d09042c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8ae517ce456f4967b46e1c8efcf98309", "placeholder": "​", "style": "IPY_MODEL_c155cde688d04bdca473ce9fb2df4677", "value": " 38/38 [01:52<00:00, 2.53s/ Dicts]" } }, "41dd5492e6504ef7aec30aec1aa0fac1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e248351c67e24939b879e51bb1acf8b1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "be735c6903954cdc9598ae9503c9b687": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "fd15a5f5fd0b486f942c996d2ab14142": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "893457340de84d4c8f34153bb7a8a951": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "8ae517ce456f4967b46e1c8efcf98309": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c155cde688d04bdca473ce9fb2df4677": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "7e3445e1f55d4755b99dc3f38cb3739d": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_849eaa2172ac4b87b99b243d6f14ac73", "IPY_MODEL_e4f3fa94ab334d5cb17d1f400aa467af", "IPY_MODEL_d4d8f8701be743e59274545a8a0b01d4" ], "layout": "IPY_MODEL_20ed4923120c477eb64e79d528505dc1" } }, "849eaa2172ac4b87b99b243d6f14ac73": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0147700d0964475db0583ca6001af643", "placeholder": "​", "style": "IPY_MODEL_de89adfba1cc47a2b55d274d6ff7934d", "value": "Train epoch 0/0 (Cur. train loss: 1.3206): 100%" } }, "e4f3fa94ab334d5cb17d1f400aa467af": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e37e7144dfe54a4ea966dfba155d196a", "max": 24738, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_625da93559c64880bed38efec2addf54", "value": 24738 } }, "d4d8f8701be743e59274545a8a0b01d4": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_33724b8fe0524ee194a73cf3d48ae8c6", "placeholder": "​", "style": "IPY_MODEL_f243166fd8a94baba327fe072980ba60", "value": " 24738/24738 [1:32:39<00:00, 4.79it/s]" } }, "20ed4923120c477eb64e79d528505dc1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0147700d0964475db0583ca6001af643": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "de89adfba1cc47a2b55d274d6ff7934d": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e37e7144dfe54a4ea966dfba155d196a": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "625da93559c64880bed38efec2addf54": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "33724b8fe0524ee194a73cf3d48ae8c6": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f243166fd8a94baba327fe072980ba60": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "f7ca511ec6094ce19214afa7595a2628": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_4e3bd8b32d7d4f0782d4ea98b56b9f12", "IPY_MODEL_d1f6bab74bf2406887a09b13e8832179", "IPY_MODEL_732b35b8724f405097dd1643614e22ba" ], "layout": "IPY_MODEL_66a8b060e0814787b3577295402787dc" } }, "4e3bd8b32d7d4f0782d4ea98b56b9f12": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_55f8af3939234583aee786d9d0f26a5b", "placeholder": "​", "style": "IPY_MODEL_57715146fd794ed8ab9abd0f201dcd32", "value": "Inferencing Samples: 100%" } }, "d1f6bab74bf2406887a09b13e8832179": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_abdcce89c02840bdafd33cc5470cef09", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_63e56931b52d46a88a15d0b7e364417b", "value": 1 } }, "732b35b8724f405097dd1643614e22ba": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c474ecf6f231410f9d0279ee79026d50", "placeholder": "​", "style": "IPY_MODEL_fa7f60789f584bd6aa6ca0cc877063d2", "value": " 1/1 [00:00<00:00, 3.23 Batches/s]" } }, "66a8b060e0814787b3577295402787dc": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "55f8af3939234583aee786d9d0f26a5b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "57715146fd794ed8ab9abd0f201dcd32": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "abdcce89c02840bdafd33cc5470cef09": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "63e56931b52d46a88a15d0b7e364417b": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "c474ecf6f231410f9d0279ee79026d50": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "fa7f60789f584bd6aa6ca0cc877063d2": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } } } }, "accelerator": "GPU" }, "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "RJaSfA2F0oTo", "outputId": "52ba665a-03bb-4b78-9e84-66a42ebbc614" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Requirement already satisfied: pip in /usr/local/lib/python3.10/dist-packages (23.1.2)\n", "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting farm-haystack[colab]\n", " Downloading farm_haystack-1.17.1-py3-none-any.whl (719 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 719.5/719.5 kB 34.0 MB/s eta 0:00:00\n", "Collecting azure-ai-formrecognizer>=3.2.0b2 (from farm-haystack[colab])\n", " Downloading azure_ai_formrecognizer-3.3.0b1-py3-none-any.whl (299 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 299.9/299.9 kB 34.6 MB/s eta 0:00:00\n", "Collecting boilerpy3 (from farm-haystack[colab])\n", " Downloading boilerpy3-1.0.6-py3-none-any.whl (22 kB)\n", "Collecting canals==0.2.2 (from farm-haystack[colab])\n", " Downloading canals-0.2.2-py3-none-any.whl (31 kB)\n", "Collecting dill (from farm-haystack[colab])\n", " Downloading dill-0.3.6-py3-none-any.whl (110 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 110.5/110.5 kB 15.1 MB/s eta 0:00:00\n", "Collecting events (from farm-haystack[colab])\n", " Downloading Events-0.4.tar.gz (5.6 kB)\n", " Preparing metadata (setup.py): started\n", " Preparing metadata (setup.py): finished with status 'done'\n", "Collecting generalimport==0.3.1 (from farm-haystack[colab])\n", " Downloading generalimport-0.3.1-py3-none-any.whl (21 kB)\n", "Collecting huggingface-hub>=0.5.0 (from farm-haystack[colab])\n", " Downloading huggingface_hub-0.15.1-py3-none-any.whl (236 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 236.8/236.8 kB 27.1 MB/s eta 0:00:00\n", "Requirement already satisfied: jsonschema in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (4.3.3)\n", "Requirement already satisfied: more-itertools in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (9.1.0)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (3.1)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (1.5.3)\n", "Collecting posthog (from farm-haystack[colab])\n", " Downloading posthog-3.0.1-py2.py3-none-any.whl (37 kB)\n", "Collecting protobuf<=3.20.2 (from farm-haystack[colab])\n", " Downloading protobuf-3.20.2-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.1 MB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.1/1.1 MB 49.6 MB/s eta 0:00:00\n", "Requirement already satisfied: pydantic in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (1.10.7)\n", "Collecting quantulum3 (from farm-haystack[colab])\n", " Downloading quantulum3-0.9.0-py3-none-any.whl (10.7 MB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 10.7/10.7 MB 58.1 MB/s eta 0:00:00\n", "Collecting rank-bm25 (from farm-haystack[colab])\n", " Downloading rank_bm25-0.2.2-py3-none-any.whl (8.6 kB)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (2.27.1)\n", "Collecting requests-cache<1.0.0 (from farm-haystack[colab])\n", " Downloading requests_cache-0.9.8-py3-none-any.whl (48 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 48.7/48.7 kB 7.8 MB/s eta 0:00:00\n", "Requirement already satisfied: scikit-learn>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (1.2.2)\n", "Collecting sentence-transformers>=2.2.0 (from farm-haystack[colab])\n", " Downloading sentence-transformers-2.2.2.tar.gz (85 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 86.0/86.0 kB 14.0 MB/s eta 0:00:00\n", " Preparing metadata (setup.py): started\n", " Preparing metadata (setup.py): finished with status 'done'\n", "Collecting sseclient-py (from farm-haystack[colab])\n", " Downloading sseclient_py-1.7.2-py2.py3-none-any.whl (8.4 kB)\n", "Requirement already satisfied: tenacity in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (8.2.2)\n", "Collecting tiktoken>=0.3.2 (from farm-haystack[colab])\n", " Downloading tiktoken-0.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.7 MB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.7/1.7 MB 70.4 MB/s eta 0:00:00\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (4.65.0)\n", "Collecting transformers[torch]==4.29.1 (from farm-haystack[colab])\n", " Downloading transformers-4.29.1-py3-none-any.whl (7.1 MB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.1/7.1 MB 91.8 MB/s eta 0:00:00\n", "Requirement already satisfied: typing-extensions==4.5.0 in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (4.5.0)\n", "Requirement already satisfied: pillow<=9.0.0 in /usr/local/lib/python3.10/dist-packages (from farm-haystack[colab]) (8.4.0)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers[torch]==4.29.1->farm-haystack[colab]) (3.12.0)\n", "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]==4.29.1->farm-haystack[colab]) (1.22.4)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]==4.29.1->farm-haystack[colab]) (23.1)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]==4.29.1->farm-haystack[colab]) (6.0)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]==4.29.1->farm-haystack[colab]) (2022.10.31)\n", "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers[torch]==4.29.1->farm-haystack[colab])\n", " Downloading tokenizers-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.8/7.8 MB 89.1 MB/s eta 0:00:00\n", "Requirement already satisfied: torch!=1.12.0,>=1.9 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]==4.29.1->farm-haystack[colab]) (2.0.1+cu118)\n", "Collecting accelerate>=0.19.0 (from transformers[torch]==4.29.1->farm-haystack[colab])\n", " Downloading accelerate-0.20.3-py3-none-any.whl (227 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 227.6/227.6 kB 23.4 MB/s eta 0:00:00\n", "Collecting azure-core<2.0.0,>=1.23.0 (from azure-ai-formrecognizer>=3.2.0b2->farm-haystack[colab])\n", " Downloading azure_core-1.27.1-py3-none-any.whl (174 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 174.5/174.5 kB 23.4 MB/s eta 0:00:00\n", "Collecting msrest>=0.6.21 (from azure-ai-formrecognizer>=3.2.0b2->farm-haystack[colab])\n", " Downloading msrest-0.7.1-py3-none-any.whl (85 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 85.4/85.4 kB 12.3 MB/s eta 0:00:00\n", "Collecting azure-common~=1.1 (from azure-ai-formrecognizer>=3.2.0b2->farm-haystack[colab])\n", " Downloading azure_common-1.1.28-py2.py3-none-any.whl (14 kB)\n", "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.5.0->farm-haystack[colab]) (2023.4.0)\n", "Requirement already satisfied: appdirs>=1.4.4 in /usr/local/lib/python3.10/dist-packages (from requests-cache<1.0.0->farm-haystack[colab]) (1.4.4)\n", "Requirement already satisfied: attrs>=21.2 in /usr/local/lib/python3.10/dist-packages (from requests-cache<1.0.0->farm-haystack[colab]) (23.1.0)\n", "Collecting cattrs>=22.2 (from requests-cache<1.0.0->farm-haystack[colab])\n", " Downloading cattrs-23.1.2-py3-none-any.whl (50 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 50.8/50.8 kB 7.3 MB/s eta 0:00:00\n", "Collecting url-normalize>=1.4 (from requests-cache<1.0.0->farm-haystack[colab])\n", " Downloading url_normalize-1.4.3-py2.py3-none-any.whl (6.8 kB)\n", "Requirement already satisfied: urllib3>=1.25.5 in /usr/local/lib/python3.10/dist-packages (from requests-cache<1.0.0->farm-haystack[colab]) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->farm-haystack[colab]) (2022.12.7)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->farm-haystack[colab]) (2.0.12)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->farm-haystack[colab]) (3.4)\n", "Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.0.0->farm-haystack[colab]) (1.10.1)\n", "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.0.0->farm-haystack[colab]) (1.2.0)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.0.0->farm-haystack[colab]) (3.1.0)\n", "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (from sentence-transformers>=2.2.0->farm-haystack[colab]) (0.15.2+cu118)\n", "Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from sentence-transformers>=2.2.0->farm-haystack[colab]) (3.8.1)\n", "Collecting sentencepiece (from sentence-transformers>=2.2.0->farm-haystack[colab])\n", " Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 86.8 MB/s eta 0:00:00\n", "Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema->farm-haystack[colab]) (0.19.3)\n", "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->farm-haystack[colab]) (2.8.2)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->farm-haystack[colab]) (2022.7.1)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from posthog->farm-haystack[colab]) (1.16.0)\n", "Collecting monotonic>=1.5 (from posthog->farm-haystack[colab])\n", " Downloading monotonic-1.6-py2.py3-none-any.whl (8.2 kB)\n", "Collecting backoff>=1.10.0 (from posthog->farm-haystack[colab])\n", " Downloading backoff-2.2.1-py3-none-any.whl (15 kB)\n", "Requirement already satisfied: inflect in /usr/local/lib/python3.10/dist-packages (from quantulum3->farm-haystack[colab]) (6.0.4)\n", "Collecting num2words (from quantulum3->farm-haystack[colab])\n", " Downloading num2words-0.5.12-py3-none-any.whl (125 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 125.2/125.2 kB 17.2 MB/s eta 0:00:00\n", "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.19.0->transformers[torch]==4.29.1->farm-haystack[colab]) (5.9.5)\n", "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from cattrs>=22.2->requests-cache<1.0.0->farm-haystack[colab]) (1.1.1)\n", "Collecting isodate>=0.6.0 (from msrest>=0.6.21->azure-ai-formrecognizer>=3.2.0b2->farm-haystack[colab])\n", " Downloading isodate-0.6.1-py2.py3-none-any.whl (41 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 41.7/41.7 kB 6.0 MB/s eta 0:00:00\n", "Requirement already satisfied: requests-oauthlib>=0.5.0 in /usr/local/lib/python3.10/dist-packages (from msrest>=0.6.21->azure-ai-formrecognizer>=3.2.0b2->farm-haystack[colab]) (1.3.1)\n", "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch!=1.12.0,>=1.9->transformers[torch]==4.29.1->farm-haystack[colab]) (1.11.1)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch!=1.12.0,>=1.9->transformers[torch]==4.29.1->farm-haystack[colab]) (3.1.2)\n", "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch!=1.12.0,>=1.9->transformers[torch]==4.29.1->farm-haystack[colab]) (2.0.0)\n", "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch!=1.12.0,>=1.9->transformers[torch]==4.29.1->farm-haystack[colab]) (3.25.2)\n", "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch!=1.12.0,>=1.9->transformers[torch]==4.29.1->farm-haystack[colab]) (16.0.5)\n", "Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from nltk->sentence-transformers>=2.2.0->farm-haystack[colab]) (8.1.3)\n", "Collecting docopt>=0.6.2 (from num2words->quantulum3->farm-haystack[colab])\n", " Downloading docopt-0.6.2.tar.gz (25 kB)\n", " Preparing metadata (setup.py): started\n", " Preparing metadata (setup.py): finished with status 'done'\n", "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.5.0->msrest>=0.6.21->azure-ai-formrecognizer>=3.2.0b2->farm-haystack[colab]) (3.2.2)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch!=1.12.0,>=1.9->transformers[torch]==4.29.1->farm-haystack[colab]) (2.1.2)\n", "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch!=1.12.0,>=1.9->transformers[torch]==4.29.1->farm-haystack[colab]) (1.3.0)\n", "Building wheels for collected packages: sentence-transformers, events, docopt\n", " Building wheel for sentence-transformers (setup.py): started\n", " Building wheel for sentence-transformers (setup.py): finished with status 'done'\n", " Created wheel for sentence-transformers: filename=sentence_transformers-2.2.2-py3-none-any.whl size=125926 sha256=593fe45c7688debe3a80cf033ab45ea6f2f54623979eb3b13d9feec3d2b6db21\n", " Stored in directory: /root/.cache/pip/wheels/62/f2/10/1e606fd5f02395388f74e7462910fe851042f97238cbbd902f\n", " Building wheel for events (setup.py): started\n", " Building wheel for events (setup.py): finished with status 'done'\n", " Created wheel for events: filename=Events-0.4-py3-none-any.whl size=6273 sha256=a27cda926c4b1689d84dd257b6a976c9d29af7f206ad0ae5fd2a18d779546331\n", " Stored in directory: /root/.cache/pip/wheels/1b/34/cf/445b39702c5a25aa8ceccf99429f5855726be49d43ce31ec03\n", " Building wheel for docopt (setup.py): started\n", " Building wheel for docopt (setup.py): finished with status 'done'\n", " Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13707 sha256=b5cf0799a6fbfdd34ca5e5dae78348b4c73fbc44a0af7509ea99286e4165b89d\n", " Stored in directory: /root/.cache/pip/wheels/fc/ab/d4/5da2067ac95b36618c629a5f93f809425700506f72c9732fac\n", "Successfully built sentence-transformers events docopt\n", "Installing collected packages: tokenizers, sseclient-py, sentencepiece, monotonic, generalimport, events, docopt, azure-common, url-normalize, rank-bm25, protobuf, num2words, isodate, dill, cattrs, canals, boilerpy3, backoff, tiktoken, requests-cache, posthog, huggingface-hub, azure-core, transformers, quantulum3, msrest, azure-ai-formrecognizer, accelerate, sentence-transformers, farm-haystack\n", " Attempting uninstall: protobuf\n", " Found existing installation: protobuf 3.20.3\n", " Uninstalling protobuf-3.20.3:\n", " Successfully uninstalled protobuf-3.20.3\n", "Successfully installed accelerate-0.20.3 azure-ai-formrecognizer-3.3.0b1 azure-common-1.1.28 azure-core-1.27.1 backoff-2.2.1 boilerpy3-1.0.6 canals-0.2.2 cattrs-23.1.2 dill-0.3.6 docopt-0.6.2 events-0.4 farm-haystack-1.17.1 generalimport-0.3.1 huggingface-hub-0.15.1 isodate-0.6.1 monotonic-1.6 msrest-0.7.1 num2words-0.5.12 posthog-3.0.1 protobuf-3.20.2 quantulum3-0.9.0 rank-bm25-0.2.2 requests-cache-0.9.8 sentence-transformers-2.2.2 sentencepiece-0.1.99 sseclient-py-1.7.2 tiktoken-0.4.0 tokenizers-0.13.3 transformers-4.29.1 url-normalize-1.4.3\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", "tensorflow 2.12.0 requires protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3, but you have protobuf 3.20.2 which is incompatible.\n", "tensorflow-metadata 1.13.1 requires protobuf<5,>=3.20.3, but you have protobuf 3.20.2 which is incompatible.\n" ] } ], "source": [ "%%bash\n", "\n", "pip install --upgrade pip\n", "pip install farm-haystack[colab]" ] }, { "cell_type": "code", "source": [ "%%bash\n", "\n", "pip install malaya" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "E_M37ECdrn_N", "outputId": "96e16368-b55b-4c13-9d51-5af20b56ca69" }, "execution_count": 3, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting malaya\n", " Downloading malaya-5.0-py3-none-any.whl (3.1 MB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.1/3.1 MB 25.8 MB/s eta 0:00:00\n", "Collecting dateparser (from malaya)\n", " Downloading dateparser-1.1.8-py2.py3-none-any.whl (293 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 293.8/293.8 kB 32.7 MB/s eta 0:00:00\n", "Collecting ftfy (from malaya)\n", " Downloading ftfy-6.1.1-py3-none-any.whl (53 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 53.1/53.1 kB 7.2 MB/s eta 0:00:00\n", "Collecting herpetologist (from malaya)\n", " Downloading herpetologist-0.0.9-py3-none-any.whl (2.4 kB)\n", "Collecting malaya-boilerplate>=0.0.23 (from malaya)\n", " Downloading malaya_boilerplate-0.0.24-py3-none-any.whl (38 kB)\n", "Collecting networkx<=2.5.1 (from malaya)\n", " Downloading networkx-2.5.1-py3-none-any.whl (1.6 MB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 79.0 MB/s eta 0:00:00\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from malaya) (1.22.4)\n", "Requirement already satisfied: regex in /usr/local/lib/python3.10/dist-packages (from malaya) (2022.10.31)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from malaya) (2.27.1)\n", "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from malaya) (1.2.2)\n", "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from malaya) (1.10.1)\n", "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from malaya) (0.1.99)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from malaya) (4.65.0)\n", "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (from malaya) (4.29.1)\n", "Collecting unidecode (from malaya)\n", " Downloading Unidecode-1.3.6-py3-none-any.whl (235 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 235.9/235.9 kB 31.5 MB/s eta 0:00:00\n", "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from malaya-boilerplate>=0.0.23->malaya) (0.15.1)\n", "Requirement already satisfied: decorator<5,>=4.3 in /usr/local/lib/python3.10/dist-packages (from networkx<=2.5.1->malaya) (4.4.2)\n", "Requirement already satisfied: python-dateutil in /usr/local/lib/python3.10/dist-packages (from dateparser->malaya) (2.8.2)\n", "Requirement already satisfied: pytz in /usr/local/lib/python3.10/dist-packages (from dateparser->malaya) (2022.7.1)\n", "Requirement already satisfied: tzlocal in /usr/local/lib/python3.10/dist-packages (from dateparser->malaya) (4.3)\n", "Requirement already satisfied: wcwidth>=0.2.5 in /usr/local/lib/python3.10/dist-packages (from ftfy->malaya) (0.2.6)\n", "Collecting memoization (from herpetologist->malaya)\n", " Downloading memoization-0.4.0.tar.gz (41 kB)\n", " ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 41.2/41.2 kB 5.8 MB/s eta 0:00:00\n", " Preparing metadata (setup.py): started\n", " Preparing metadata (setup.py): finished with status 'done'\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->malaya) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->malaya) (2022.12.7)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->malaya) (2.0.12)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->malaya) (3.4)\n", "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->malaya) (1.2.0)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->malaya) (3.1.0)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers->malaya) (3.12.0)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers->malaya) (23.1)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers->malaya) (6.0)\n", "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers->malaya) (0.13.3)\n", "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->malaya-boilerplate>=0.0.23->malaya) (2023.4.0)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->malaya-boilerplate>=0.0.23->malaya) (4.5.0)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil->dateparser->malaya) (1.16.0)\n", "Requirement already satisfied: pytz-deprecation-shim in /usr/local/lib/python3.10/dist-packages (from tzlocal->dateparser->malaya) (0.1.0.post0)\n", "Requirement already satisfied: tzdata in /usr/local/lib/python3.10/dist-packages (from pytz-deprecation-shim->tzlocal->dateparser->malaya) (2023.3)\n", "Building wheels for collected packages: memoization\n", " Building wheel for memoization (setup.py): started\n", " Building wheel for memoization (setup.py): finished with status 'done'\n", " Created wheel for memoization: filename=memoization-0.4.0-py3-none-any.whl size=50451 sha256=141a590c0d0e96c0d2722fc813159226b0ffd782397d6039d2cd512d00b6260d\n", " Stored in directory: /root/.cache/pip/wheels/3e/b8/c5/b553d5e8b0249bd2859b3b6d7bb2a1849e7b01c6e8b64f6e87\n", "Successfully built memoization\n", "Installing collected packages: unidecode, networkx, memoization, ftfy, herpetologist, malaya-boilerplate, dateparser, malaya\n", " Attempting uninstall: networkx\n", " Found existing installation: networkx 3.1\n", " Uninstalling networkx-3.1:\n", " Successfully uninstalled networkx-3.1\n", "Successfully installed dateparser-1.1.8 ftfy-6.1.1 herpetologist-0.0.9 malaya-5.0 malaya-boilerplate-0.0.24 memoization-0.4.0 networkx-2.5.1 unidecode-1.3.6\n" ] } ] }, { "cell_type": "markdown", "source": [ "Step 2" ], "metadata": { "id": "_Jc-KhA88u_L" } }, { "cell_type": "code", "source": [ "from haystack.telemetry import tutorial_running\n", "\n", "tutorial_running(1)\n", "import logging\n", "\n", "logging.basicConfig(format=\"%(levelname)s - %(name)s - %(message)s\", level=logging.WARNING)\n", "logging.getLogger(\"haystack\").setLevel(logging.INFO)" ], "metadata": { "id": "uAsxEs2p6vDh" }, "execution_count": 9, "outputs": [] }, { "cell_type": "code", "source": [ "from haystack.nodes import PreProcessor\n", "from haystack.utils import convert_files_to_docs\n", "\n", "all_docs = convert_files_to_docs(dir_path='/content/drive/MyDrive/data/malaysia/')\n", "preprocessor = PreProcessor(\n", " clean_empty_lines=True,\n", " clean_whitespace=True,\n", " clean_header_footer=False,\n", " split_by=\"word\",\n", " split_length=100,\n", " split_respect_sentence_boundary=True,\n", ")\n", "docs = preprocessor.process(all_docs)\n", "\n", "print(f\"n_files_input: {len(all_docs)}\\nn_docs_output: {len(docs)}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000, "referenced_widgets": [ "4a10768a2d2e480b98141b0e126361ac", "57203d98432240beb78408ae427f3bf0", "7cefcf4f54eb41438f34690c61bb1c38", "c6994d8d9a644b7f9a63ace7d95ab9ee", "515d0e82e8304e4a998b251e2acc255b", "0b0dd05193024ed5bd34ebd6802e3b2d", "a6566d3fd8ff4de698a9b5ed36a249f9", "0a8fdc1f3f1f4af0afe8f4e652053c96", "d41f2b1276ca4fa2a923e60dfdbe76f8", "447a657e01cd417889f4e40e262ab1cf", "d5458bc789c449c78b448193b0df4784" ] }, "id": "UEpwb3PbYgrK", "outputId": "340ecb9c-4ff9-473c-e62a-8242a9e6a962" }, "execution_count": 10, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "WARNING:haystack.utils.preprocessing:Skipped file /content/drive/MyDrive/data/malaysia/ms-train-2.0.json as type .json is not supported here. See haystack.file_converter for support of more file types\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/+60.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/.my.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/1911 Encyclopædia Britannica.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/1980-an.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/1990-an.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/8 Negara Membangun.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/APEC Australia 2007.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/APEC Malaysia 2020.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/APEC Singapura 2009.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/ASEAN Campur Tiga.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/A Famosa.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Abad ke-20.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Abkhazia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Afghanistan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Afrika Selatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Agama.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Agama Buddha.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Agama di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Agama rakyat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Agama rakyat Cina.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Agensi Angkasa Negara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Akrotiri dan Dhekelia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Al-Sultan Abdullah Ri’ayatuddin Al-Mustafa Billah Shah ibni Almarhum Sultan Haji Ahmad Shah Al-Musta’in Billah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Alam Sekitar Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Albania.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Algeria.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Amerika Syarikat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Amiriah Arab Bersatu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Angkatan Tentera Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Anguilla.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Animisme.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Antigua dan Barbuda.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Anugerah dan Festival Filem Antarabangsa ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Anwar Ibrahim.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Arab Saudi.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Argentina.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Armenia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Asia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Asia Barat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Asia Selatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Asia Tengah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Asia Tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Asia Timur.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Asia Utara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Asia tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Australia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Azerbaijan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/BERSIH.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Baba dan Nyonya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Badan perundangan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Badminton.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahagian di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahagian pentadbiran di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahamas.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa Dusun.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa Iban.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa Jawa.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa Melayu Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa Tamil.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa Zamboangueño.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa kriol.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahasa rojak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bahrain.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bangladesh.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bangunan Sultan Abdul Samad.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Banjaran Crocker.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bank Negara Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Barbados.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Barisan Nasional.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Batu Caves.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bekalan air dan sanitasi di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Belanjawan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Belarus.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Belize.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bendera ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bendera Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Benin.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bermuda.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bhutan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bibliografi Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bidayuh.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bijih timah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bola sepak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Boling sepuluh pin.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bolivia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Borneo.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Borneo British.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Borneo Utara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Botswana.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Brazil.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Brunei.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Brunei Darussalam.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Budaya Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Budaya di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Buddhisme di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bumiputera.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bumiputera (Malaysia).txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Burkina Faso.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bursa Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Burundi.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cameroon.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cape Verde.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Central Intelligence Agency.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cerita rakyat Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Chad.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Chile.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cina Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cip komputer.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cogan kata.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Colombia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Comoros.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Costa Rica.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Croatia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cuba.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cuti umum di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Cyprus.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Côte d'Ivoire.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Daerah di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah Kebesaran Persekutuan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran Wilayah Persekutuan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Johor.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Kedah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Kelantan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Melaka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Negeri Sembilan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Pahang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Perak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Perlis.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Pulau Pinang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Sabah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Sarawak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Selangor.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Terengganu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darurat Tanah Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Darurat di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dasar Ekonomi Baru.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dasar tenaga Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dasar visa ahli-ahli ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dataran Merdeka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Deepavali.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Deklarasi ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Demografi Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Demografi di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Demonim.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dewan Bahasa dan Pustaka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dewan Negara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dewan Pertuanan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dewan Rakyat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dewan Undangan Negeri Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dikir barat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Djibouti.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Doi.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Domain peringkat tinggi kod negara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dominica.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Dominika.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ecuador.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ekonomi Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ekonomi di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/El Salvador.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Elektronik.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Emiriah Arab Bersatu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Empangan hidroelektrik Bakun.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Empayar British.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Empayar Jepun.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Equatorial Guinea.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Eritrea.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Eropah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Eswatini.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ethiopia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Etnonim.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Eurasia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Fail Kewibawaan Antarabangsa Maya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Fiji.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Filipina.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Formula Satu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Forum Serantau ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Gabon.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Gambia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Garis kasar Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Gawai Dayak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Geografi (Ptolemy).txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Geografi Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Geografi di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/George Samuel Windsor Earl.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Georgia (negara).txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Georgia Selatan dan Kepulauan Sandwich Selatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Getah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ghana.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Gibraltar.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Gigawatt.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Go Asean.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Grand Prix Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Grenada.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Guatemala.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Guernsey.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Guinea.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Guinea-Bissau.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Gunung Kinabalu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Guyana.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hak asasi manusia di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hari Buruh.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hari Kebangsaan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hari Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hari Merdeka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hari Pemerintahan Sendiri Borneo Utara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hari Pemerintahan Sendiri Sarawak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hari Raya Aidiladha.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hari Raya Aidilfitri.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Harimau Malaya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hibiscus rosa-sinensis.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hindu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hinduisme di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hoki.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hoki Piala Dunia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Honduras.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hong Kong.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hubungan Parti Tindakan Rakyat-Pertubuhan Kebangsaan Melayu Bersatu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Hubungan luar Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/ISBN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/ISO 3166.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/ISO 3166-2:MY.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/ISO 4217.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Iban.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ibu negara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Iklim khatulistiwa.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Indeks Pembangunan Manusia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Indeks rencana berkaitan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Indeks rencana berkenaan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/India.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/India Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Indonesia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Infrastruktur di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Inisiatif Chiang Mai.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Iran.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Iraq.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Islam.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Islam di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Israel.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Abu Bakar.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Alam Shah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Anak Bukit.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Arau.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Balai Besar.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Besar Seri Menanti.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Bukit Serene.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Iskandariah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Melawati.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Negara, Jalan Duta.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Syarqiyyah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Istana Telipot.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/JSTOR.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jain.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jajahan Mahkota Borneo Utara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jajahan Mahkota Labuan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jajahan Mahkota Sarawak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jamaica.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jamaika.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/James Brooke.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jata Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jenayah di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jepun.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jersey.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Johann Friedrich Blumenbach.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Johor.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jomo Kwame Sundaram.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jordan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jules Dumont d'Urville.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Jurang pendapatan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kaamatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kabinet Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kadazan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kanada.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kaum.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kaum Kaukasia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kawasan Pentadbiran Khas Republik Rakyat China.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kawasan Perdagangan Bebas ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kawasan Perdagangan Bebas ASEAN–China.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kawasan Perdagangan Bebas ASEAN–India.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kazakhstan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kebebasan beragama.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kedah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kejohanan Bola Sepak ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kelantan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Keluaran dalam negara kasar.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kemboja.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kementerian Pendidikan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kemerdekaan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kemiskinan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kenya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepadatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepadatan penduduk.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepemerintahan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Ashmore dan Cartier.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Cayman.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Cocos (Keeling).txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Cook.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Falkland.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Laut Karang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Pitcairn.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Solomon.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Turks dan Caicos.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kepulauan Virgin British.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kerajaan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kerajaan Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kerajaan Melayu Jambi.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kerajaan Sarawak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kerajaan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kerjasama Ekonomi Asia-Pasifik.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kesatuan-kesatuan sekerja di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kesatuan Afrika.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kesultanan Johor.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kesultanan Melaka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kesultanan Melayu Melaka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kesusasteraan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ketenteraan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ketuanan Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Khoo Kay Kim.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kiribati.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kod panggilanMalaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Koloni Singapura.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Konfrontasi Indonesia-Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Konfusianisme.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Korea Selatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Korea Utara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Koridor Raya Multimedia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Krisis Kewangan Asia 1997.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Krisis Perlembagaan Malaysia 1988.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Krisis pencerobohan Lahad Datu 2013.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kristang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kristian.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kristian di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kuala Lumpur.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kumpulan 15.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kumpulan etnik.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kuwait.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kyrgyzstan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Labuan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Lagu ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Lagu kebangsaan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Lambang ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Langkasuka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Laos.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Lapangan Terbang Antarabangsa Kuala Lumpur.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Laut China Selatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Lebuhraya Utara-Selatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Lesotho.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Liberia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Libya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Liga Arab.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Litar Antarabangsa Sepang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Lubnan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Maal Hijrah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Macau.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Madagascar.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Maghribi.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mahathir bin Mohamad.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mahkamah Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mahkamah Syariah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mahkamah Syariah di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Majapahit.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Majlis Industri Pertahanan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Majlis Raja-Raja.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Malawi.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Malayan Union.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Malaysia Timur.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Maldives.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mali.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Malta.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Manglish.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Masakan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Masjid Kampung Laut.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mata wang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Maulidur Rasul.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mauritania.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mauritius.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mazhab.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Media Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Melaka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Melaka Belanda.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Melaka Portugis.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Melanesia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Melayu Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Menara Berkembar Petronas.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mesir.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mesyuarat Asia–Eropah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mexico.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mike Pompeo.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mikronesia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Milton Osborne.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Monarki Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mongolia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Monsun.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Montenegro.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Montserrat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Mozambique.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Murtabak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/MusicBrainz.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Muzik Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Myanmar.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Nagorno-Karabakh.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Najib Razak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Nama-nama Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Namibia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Nauru.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negara-Negara Komanwel.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negara-negara Komanwel.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negara Palestin.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negara anggota Persatuan Negara-negara Asia Tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negaraku.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negeri-Negeri Selat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negeri-negeri Melayu Bersekutu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negeri-negeri Melayu Tidak Bersekutu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negeri-negeri Selat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negeri Sembilan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negeri dan Wilayah Persekutuan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Negeri dan wilayah persekutuan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Nepal.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/New Zealand.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Nicaragua.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Niger.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Nigeria.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Niue.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Oceania.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Oman.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Orang Asli.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Orang Cina Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Orang Cina di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Orang Hui.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Orang Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Orang Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Orang Negrito.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ossetia Selatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pahang Darul Makmur.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pakistan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Palembang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pamalayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pameran Aeroangkasa dan Maritim Antarabangsa Langkawi.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Panama.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pantai Timur, Semenanjung Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Papua Barat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Papua New Guinea.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Parameswara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pariti kuasa beli.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Parlimen Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Parti Komunis Malaya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Parti Rakyat Bersatu Sarawak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pekali Gini.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pelancongan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pemanduan di sebelah kanan atau kiri.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pemburu-pengumpul.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pemerintahan sendiri.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pemerintahan sendiri Singapura.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pendidikan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pendidikan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pendudukan Jepun di Borneo British.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pendudukan Jepun di Tanah Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pengangkutan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pengecam Nama Piawaian Antarabangsa.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pengislaman.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Penguatkuasaan undang-undang di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Penjagaan kesihatan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Penjagaan kesihatan sejagat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Penjajahan Jepun di Tanah Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pentadbiran Tentera British (Borneo).txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pentadbiran Tentera British (Tanah Melayu).txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Penyimpan Mohor Besar Raja-Raja.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Per kapita.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perairan wilayah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perak Darul Ridzuan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perang Dunia Kedua.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Peratusan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perayaan Islam.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perdana Menteri Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perfileman Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pergerakan Negara-Negara Berkecuali.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perhimpunan Agung Pertubuhan Bangsa-Bangsa Bersatu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perhimpunan Bersih 2007.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perhimpunan Hindraf 2007.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Peristiwa 13 Mei.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perisytiharan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perjanjian 18 perkara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perjanjian 20 Perkara Sabah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perjanjian ASEAN Mengenai Pencemaran Jerebu Rentas Sempadan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perjanjian Inggeris-Belanda 1824.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perjanjian Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perjanjian Persahabatan dan Kerjasama di Asia Tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perkara 160 Perlembagaan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perkongsian Ekonomi Komprehensif Serantau.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perkongsian Ekonomi Komprehensif untuk Asia Timur.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perlembagaan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perlis.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perluasan Persatuan Negara-negara Asia Tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Persatuan Negara-negara Asia Tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Persekutuan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Persekutuan Bola Sepak ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Persekutuan Tanah Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pertanian di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pertemuan Raifal Tentera ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pertubuhan Bangsa-Bangsa Bersatu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pertubuhan Kerjasama Islam.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pertubuhan Persidangan Islam.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pertubuhan berkaitan dengan Persatuan Negara-negara Asia Tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Peru.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Petaling Jaya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Piagam ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Piala Thomas.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pilihan raya di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Polinesia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Politik Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Politik di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Prasejarah Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Projek Lebuhraya Utara Selatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Proton Prevé.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pulau Heard dan Kepulauan McDonald.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pulau Krismas.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pulau Man.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pulau Norfolk.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pulau Pinang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Pungutan suara penyatuan Singapura 1962.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Putrajaya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Qatar.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Raja-raja Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Raja Perlis.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Raja Putih.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Raja berperlembagaan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Raja elektif.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Rakyat Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Rangkaian Bandar Pintar ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Republik Afrika Tengah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Republik China di Taiwan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Republik Congo.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Republik Demokratik Congo.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Republik Rakyat China.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Republik Turki Cyprus Utara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ringgit.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ringgit Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Rosmah Mansor.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Rukunegara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Rusia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Russia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Rusuhan kaum Singapura 1964.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Rwanda.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/S2CID.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sabah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sains dan teknologi di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Saint Helena, Ascension dan Tristan da Cunha.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Saint Kitts dan Nevis.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Saint Lucia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Saint Vincent dan Grenadines.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Saint Vincent dan the Grenadines.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Samoa.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sanskrit.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sarawak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sejarah ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sejarah Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sejarah di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Selangor.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Semenanjung Emas.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Semenanjung Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Semenanjung Tanah Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai Tapak Warisan Dunia di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai anggota Negara-negara Komanwel.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai bank di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai gunung di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai negara ASEAN mengikut KDNK.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai negara berdaulat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai negara dan wilayah tanggungan di Asia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai negara mengikut Indeks Pembangunan Manusia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai negara mengikut KDNK (PPP).txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai negara mengikut keluasan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai negara yang merentasi melebihi satu benua.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai negeri Malaysia mengikut KDNK.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai parti politik di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai pulau di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai sungai di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai taman negara di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai tasik di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senarai universiti di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Senegal.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Serbia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Setiausaha Agung Persatuan Negara-negara Asia Tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Setiausaha Negara Amerika Syarikat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Seychelles.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sidang Kemuncak ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sidang Kemuncak Asia Timur.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sierra Leone.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sijil Tinggi Persekolahan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sikh.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sikhisme.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Silat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Simbol Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Simbol kebangsaan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Singapura.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Singapura dalam Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sistem Pendokumenan Universiti.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sistem berparlimen.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Skandal 1Malaysia Development Berhad.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Skuasy.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Société de Géographie.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Soekarno.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Somalia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sri Lanka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Srivijaya.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sudan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sukan Asia Tenggara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sukan Komanwel.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sukan Para ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sukan Sekolah ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sukan Universiti ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sukan di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sukhoi Su-30.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Abdul Halim Mu’adzam Shah ibni Almarhum Sultan Badlishah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Abdullah Ri'ayatuddin Al-Mustafa Billah Shah ibni Almarhum Sultan Haji Ahmad Shah Al-Musta'in Billah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Azlan Muhibbuddin Shah ibni Almarhum Sultan Yussuff Izzuddin Shah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Haji Ahmad Shah Al-Musta’in Billah ibni Almarhum Sultan Abu Bakar Ri’ayatuddin Al-Mu’azzam Shah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Hisamuddin Alam Shah ibni al-Marhum Sultan Alauddin Sulaiman Shah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Iskandar ibni Almarhum Sultan Ismail.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Ismail Nasiruddin Shah ibni al-Marhum Sultan Haji Zainal Abidin III Mu’azzam Shah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Johor.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Kedah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Kelantan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Mizan Zainal Abidin ibni Almarhum Sultan Mahmud Al-Muktafi Billah Shah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Muhammad V.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Pahang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Perak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Salahuddin Abdul Aziz Shah ibni Almarhum Sultan Hisamuddin Alam Shah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Selangor.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Terengganu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sultan Yahya Petra ibni al-Marhum Sultan Ibrahim.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sulu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Sumatera.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Suriname.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Suruhanjaya Cobbold.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Suruhanjaya Tenaga Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Syafii.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Syarikat Hindia Timur British.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Syria.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/São Tomé dan Príncipe.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Taiwan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tajikistan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Taman Negara Kinabalu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tanah Jajahan Mahkota British Borneo Utara.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tanah Jajahan Mahkota Sarawak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tanah Melayu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tanah Melayu British.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tanjung Piai.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tanzania.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Taoisme.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tapak Warisan Dunia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Telekesihatan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Telekomunikasi di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Teluk Sepanggar.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tenaga boleh baharu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tentera Darat Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tentera Laut Diraja Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tentera Udara Diraja Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Terengganu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Thailand.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Thaipusam.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/The ASEAN Way.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/The Malay Mail.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/The National Archives (United Kingdom).txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Time Asia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Timor Leste.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Timor Timur.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Togo.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tokelau.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tonga.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Toponim.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tourism Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Transit aliran ringan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Trinidad dan Tobago.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Trove.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tuanku Abdul Rahman ibni al-Marhum Tuanku Muhammad.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tuanku Ja’afar ibni Almarhum Tuanku Abdul Rahman.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tuanku Syed Putra ibni al-Marhum Syed Hassan Jamalullail.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tuanku Syed Sirajuddin ibni Almarhum Tuanku Syed Putra Jamalullail.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tulisan Jawi.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tumpat.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tun Abdul Razak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tunisia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Turki.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Turkmenistan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Tuvalu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Uganda.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ujian Pencapaian Sekolah Rendah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Ukraine.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Undang-undang Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Unit Kewangan Asia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/United Kingdom.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/United Nations Research Institute For Social Development.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Uruguay.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Utusan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Uzbekistan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Vanuatu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Vayu Purana.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Venezuela.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Vietnam.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Waktu Musim Panas.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Waktu Piawai Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Waktu Umum ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Waktu Universal Selaras.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wanita di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wayang kulit.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wayback Machine.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wilayah Antartik Australia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wilayah Antartik British.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wilayah Lautan Hindi British.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wilayah Persekutuan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wilayah Tanggungan Ross.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wilayah tanggungan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yaman.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri Melaka.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri Pulau Pinang.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri Sabah.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri Sarawak.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yang di-Pertuan Agong.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yang di-Pertuan Besar Negeri Sembilan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yemen.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Yijing.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Zambia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Zimbabwe.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Zon waktu.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wikipedia:Pautan reput.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wikipedia:Polisi perlindungan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Wikipedia:Rencana pilihan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Fail:Independence Square, Kuala Lumpur (6758524547).jpg.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Fail:KotaKinabalu Sabah TelukSapanggar-RoyalNavy-01.jpg.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:APEC.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:Asia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:G15.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:Komanwel.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:Kumpulan etnik di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:Malay-speaking.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:Negeri dan Wilayah Persekutuan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:OIC.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:Pergerakan Negara-Negara Berkecuali dan sukan makan ikan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:Sistem beraja di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Templat:Topik Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:APEC.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:ASEAN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:Asia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:G15.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:Komanwel.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:Malay-speaking.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:Negeri dan Wilayah Persekutuan Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:OIC.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:Pergerakan Negara-Negara Berkecuali dan sukan makan ikan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:Sistem beraja di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Perbincangan templat:Topik Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Bantuan:Kawalan kewibawaan.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:APEC.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:CS1 maint: date and year.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:CS1 maint: date format.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:CS1 maint: multiple names: authors list.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Fauna di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Flora di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Guna tarikh dmy dari Januari 2023.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Harv and Sfn template errors.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Istana di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Masyarakat Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Mitologi Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pautan luar mati dari Oktober 2021.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan BIBSYS.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan BNE.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan BNF.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan CANTICN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan CINII.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan EMU.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan FAST.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan GND.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan HDS.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan ISNI.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan J9U.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan LCCN.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NARA.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NDL.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NKC.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NLA.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NLK.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan SELIBR.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan SUDOC.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan TDVİA.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan Trove.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan VIAF.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan kawasan MusicBrainz.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan multiple.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Seni bina Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Kategori:Tempat-tempat berpenduduk di Malaysia.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Portal:50.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Portal:Flag of Malaysia.svg.txt\n", "INFO:haystack.utils.preprocessing:Converting /content/drive/MyDrive/data/malaysia/Portal:Malaysia.txt\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "Preprocessing: 0%| | 0/801 [00:00,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ,\n", " ...],\n", " 'root_node': 'File',\n", " 'params': {},\n", " 'file_paths': ['/content/drive/MyDrive/data/malaysia/Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/+60.txt',\n", " '/content/drive/MyDrive/data/malaysia/.my.txt',\n", " '/content/drive/MyDrive/data/malaysia/1911 Encyclopædia Britannica.txt',\n", " '/content/drive/MyDrive/data/malaysia/1980-an.txt',\n", " '/content/drive/MyDrive/data/malaysia/1990-an.txt',\n", " '/content/drive/MyDrive/data/malaysia/8 Negara Membangun.txt',\n", " '/content/drive/MyDrive/data/malaysia/APEC Australia 2007.txt',\n", " '/content/drive/MyDrive/data/malaysia/APEC Malaysia 2020.txt',\n", " '/content/drive/MyDrive/data/malaysia/APEC Singapura 2009.txt',\n", " '/content/drive/MyDrive/data/malaysia/ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/ASEAN Campur Tiga.txt',\n", " '/content/drive/MyDrive/data/malaysia/A Famosa.txt',\n", " '/content/drive/MyDrive/data/malaysia/Abad ke-20.txt',\n", " '/content/drive/MyDrive/data/malaysia/Abkhazia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Afghanistan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Afrika Selatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Agama.txt',\n", " '/content/drive/MyDrive/data/malaysia/Agama Buddha.txt',\n", " '/content/drive/MyDrive/data/malaysia/Agama di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Agama rakyat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Agama rakyat Cina.txt',\n", " '/content/drive/MyDrive/data/malaysia/Agensi Angkasa Negara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Akrotiri dan Dhekelia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Al-Sultan Abdullah Ri’ayatuddin Al-Mustafa Billah Shah ibni Almarhum Sultan Haji Ahmad Shah Al-Musta’in Billah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Alam Sekitar Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Albania.txt',\n", " '/content/drive/MyDrive/data/malaysia/Algeria.txt',\n", " '/content/drive/MyDrive/data/malaysia/Amerika Syarikat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Amiriah Arab Bersatu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Angkatan Tentera Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Anguilla.txt',\n", " '/content/drive/MyDrive/data/malaysia/Animisme.txt',\n", " '/content/drive/MyDrive/data/malaysia/Antigua dan Barbuda.txt',\n", " '/content/drive/MyDrive/data/malaysia/Anugerah dan Festival Filem Antarabangsa ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Anwar Ibrahim.txt',\n", " '/content/drive/MyDrive/data/malaysia/Arab Saudi.txt',\n", " '/content/drive/MyDrive/data/malaysia/Argentina.txt',\n", " '/content/drive/MyDrive/data/malaysia/Armenia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Asia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Asia Barat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Asia Selatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Asia Tengah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Asia Tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Asia Timur.txt',\n", " '/content/drive/MyDrive/data/malaysia/Asia Utara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Asia tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Australia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Azerbaijan.txt',\n", " '/content/drive/MyDrive/data/malaysia/BERSIH.txt',\n", " '/content/drive/MyDrive/data/malaysia/Baba dan Nyonya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Badan perundangan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Badminton.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahagian di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahagian pentadbiran di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahamas.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa Dusun.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa Iban.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa Jawa.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa Melayu Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa Tamil.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa Zamboangueño.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa kriol.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahasa rojak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bahrain.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bangladesh.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bangunan Sultan Abdul Samad.txt',\n", " '/content/drive/MyDrive/data/malaysia/Banjaran Crocker.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bank Negara Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Barbados.txt',\n", " '/content/drive/MyDrive/data/malaysia/Barisan Nasional.txt',\n", " '/content/drive/MyDrive/data/malaysia/Batu Caves.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bekalan air dan sanitasi di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Belanjawan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Belarus.txt',\n", " '/content/drive/MyDrive/data/malaysia/Belize.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bendera ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bendera Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Benin.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bermuda.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bhutan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bibliografi Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bidayuh.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bijih timah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bola sepak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Boling sepuluh pin.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bolivia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Borneo.txt',\n", " '/content/drive/MyDrive/data/malaysia/Borneo British.txt',\n", " '/content/drive/MyDrive/data/malaysia/Borneo Utara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Botswana.txt',\n", " '/content/drive/MyDrive/data/malaysia/Brazil.txt',\n", " '/content/drive/MyDrive/data/malaysia/Brunei.txt',\n", " '/content/drive/MyDrive/data/malaysia/Brunei Darussalam.txt',\n", " '/content/drive/MyDrive/data/malaysia/Budaya Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Budaya di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Buddhisme di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bumiputera.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bumiputera (Malaysia).txt',\n", " '/content/drive/MyDrive/data/malaysia/Burkina Faso.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bursa Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Burundi.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cameroon.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cape Verde.txt',\n", " '/content/drive/MyDrive/data/malaysia/Central Intelligence Agency.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cerita rakyat Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Chad.txt',\n", " '/content/drive/MyDrive/data/malaysia/Chile.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cina Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cip komputer.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cogan kata.txt',\n", " '/content/drive/MyDrive/data/malaysia/Colombia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Comoros.txt',\n", " '/content/drive/MyDrive/data/malaysia/Costa Rica.txt',\n", " '/content/drive/MyDrive/data/malaysia/Croatia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cuba.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cuti umum di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Cyprus.txt',\n", " \"/content/drive/MyDrive/data/malaysia/Côte d'Ivoire.txt\",\n", " '/content/drive/MyDrive/data/malaysia/Daerah di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah Kebesaran Persekutuan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran Wilayah Persekutuan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Johor.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Kedah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Kelantan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Melaka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Negeri Sembilan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Pahang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Perak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Perlis.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Pulau Pinang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Sabah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Sarawak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Selangor.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darjah kebesaran negeri Terengganu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darurat Tanah Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Darurat di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dasar Ekonomi Baru.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dasar tenaga Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dasar visa ahli-ahli ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dataran Merdeka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Deepavali.txt',\n", " '/content/drive/MyDrive/data/malaysia/Deklarasi ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Demografi Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Demografi di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Demonim.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dewan Bahasa dan Pustaka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dewan Negara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dewan Pertuanan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dewan Rakyat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dewan Undangan Negeri Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dikir barat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Djibouti.txt',\n", " '/content/drive/MyDrive/data/malaysia/Doi.txt',\n", " '/content/drive/MyDrive/data/malaysia/Domain peringkat tinggi kod negara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dominica.txt',\n", " '/content/drive/MyDrive/data/malaysia/Dominika.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ecuador.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ekonomi Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ekonomi di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/El Salvador.txt',\n", " '/content/drive/MyDrive/data/malaysia/Elektronik.txt',\n", " '/content/drive/MyDrive/data/malaysia/Emiriah Arab Bersatu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Empangan hidroelektrik Bakun.txt',\n", " '/content/drive/MyDrive/data/malaysia/Empayar British.txt',\n", " '/content/drive/MyDrive/data/malaysia/Empayar Jepun.txt',\n", " '/content/drive/MyDrive/data/malaysia/Equatorial Guinea.txt',\n", " '/content/drive/MyDrive/data/malaysia/Eritrea.txt',\n", " '/content/drive/MyDrive/data/malaysia/Eropah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Eswatini.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ethiopia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Etnonim.txt',\n", " '/content/drive/MyDrive/data/malaysia/Eurasia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Fail Kewibawaan Antarabangsa Maya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Fiji.txt',\n", " '/content/drive/MyDrive/data/malaysia/Filipina.txt',\n", " '/content/drive/MyDrive/data/malaysia/Formula Satu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Forum Serantau ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Gabon.txt',\n", " '/content/drive/MyDrive/data/malaysia/Gambia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Garis kasar Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Gawai Dayak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Geografi (Ptolemy).txt',\n", " '/content/drive/MyDrive/data/malaysia/Geografi Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Geografi di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/George Samuel Windsor Earl.txt',\n", " '/content/drive/MyDrive/data/malaysia/Georgia (negara).txt',\n", " '/content/drive/MyDrive/data/malaysia/Georgia Selatan dan Kepulauan Sandwich Selatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Getah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ghana.txt',\n", " '/content/drive/MyDrive/data/malaysia/Gibraltar.txt',\n", " '/content/drive/MyDrive/data/malaysia/Gigawatt.txt',\n", " '/content/drive/MyDrive/data/malaysia/Go Asean.txt',\n", " '/content/drive/MyDrive/data/malaysia/Grand Prix Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Grenada.txt',\n", " '/content/drive/MyDrive/data/malaysia/Guatemala.txt',\n", " '/content/drive/MyDrive/data/malaysia/Guernsey.txt',\n", " '/content/drive/MyDrive/data/malaysia/Guinea.txt',\n", " '/content/drive/MyDrive/data/malaysia/Guinea-Bissau.txt',\n", " '/content/drive/MyDrive/data/malaysia/Gunung Kinabalu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Guyana.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hak asasi manusia di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hari Buruh.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hari Kebangsaan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hari Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hari Merdeka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hari Pemerintahan Sendiri Borneo Utara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hari Pemerintahan Sendiri Sarawak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hari Raya Aidiladha.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hari Raya Aidilfitri.txt',\n", " '/content/drive/MyDrive/data/malaysia/Harimau Malaya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hibiscus rosa-sinensis.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hindu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hinduisme di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hoki.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hoki Piala Dunia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Honduras.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hong Kong.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hubungan Parti Tindakan Rakyat-Pertubuhan Kebangsaan Melayu Bersatu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Hubungan luar Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/ISBN.txt',\n", " '/content/drive/MyDrive/data/malaysia/ISO 3166.txt',\n", " '/content/drive/MyDrive/data/malaysia/ISO 3166-2:MY.txt',\n", " '/content/drive/MyDrive/data/malaysia/ISO 4217.txt',\n", " '/content/drive/MyDrive/data/malaysia/Iban.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ibu negara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Iklim khatulistiwa.txt',\n", " '/content/drive/MyDrive/data/malaysia/Indeks Pembangunan Manusia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Indeks rencana berkaitan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Indeks rencana berkenaan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/India.txt',\n", " '/content/drive/MyDrive/data/malaysia/India Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Indonesia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Infrastruktur di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Inisiatif Chiang Mai.txt',\n", " '/content/drive/MyDrive/data/malaysia/Iran.txt',\n", " '/content/drive/MyDrive/data/malaysia/Iraq.txt',\n", " '/content/drive/MyDrive/data/malaysia/Islam.txt',\n", " '/content/drive/MyDrive/data/malaysia/Islam di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Israel.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Abu Bakar.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Alam Shah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Anak Bukit.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Arau.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Balai Besar.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Besar Seri Menanti.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Bukit Serene.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Iskandariah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Melawati.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Negara, Jalan Duta.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Syarqiyyah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Istana Telipot.txt',\n", " '/content/drive/MyDrive/data/malaysia/JSTOR.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jain.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jajahan Mahkota Borneo Utara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jajahan Mahkota Labuan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jajahan Mahkota Sarawak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jamaica.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jamaika.txt',\n", " '/content/drive/MyDrive/data/malaysia/James Brooke.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jata Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jenayah di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jepun.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jersey.txt',\n", " '/content/drive/MyDrive/data/malaysia/Johann Friedrich Blumenbach.txt',\n", " '/content/drive/MyDrive/data/malaysia/Johor.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jomo Kwame Sundaram.txt',\n", " '/content/drive/MyDrive/data/malaysia/Jordan.txt',\n", " \"/content/drive/MyDrive/data/malaysia/Jules Dumont d'Urville.txt\",\n", " '/content/drive/MyDrive/data/malaysia/Jurang pendapatan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kaamatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kabinet Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kadazan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kanada.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kaum.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kaum Kaukasia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kawasan Pentadbiran Khas Republik Rakyat China.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kawasan Perdagangan Bebas ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kawasan Perdagangan Bebas ASEAN–China.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kawasan Perdagangan Bebas ASEAN–India.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kazakhstan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kebebasan beragama.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kedah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kejohanan Bola Sepak ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kelantan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Keluaran dalam negara kasar.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kemboja.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kementerian Pendidikan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kemerdekaan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kemiskinan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kenya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepadatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepadatan penduduk.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepemerintahan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Ashmore dan Cartier.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Cayman.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Cocos (Keeling).txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Cook.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Falkland.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Laut Karang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Pitcairn.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Solomon.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Turks dan Caicos.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kepulauan Virgin British.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kerajaan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kerajaan Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kerajaan Melayu Jambi.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kerajaan Sarawak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kerajaan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kerjasama Ekonomi Asia-Pasifik.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kesatuan-kesatuan sekerja di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kesatuan Afrika.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kesultanan Johor.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kesultanan Melaka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kesultanan Melayu Melaka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kesusasteraan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ketenteraan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ketuanan Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Khoo Kay Kim.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kiribati.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kod panggilanMalaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Koloni Singapura.txt',\n", " '/content/drive/MyDrive/data/malaysia/Konfrontasi Indonesia-Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Konfusianisme.txt',\n", " '/content/drive/MyDrive/data/malaysia/Korea Selatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Korea Utara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Koridor Raya Multimedia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Krisis Kewangan Asia 1997.txt',\n", " '/content/drive/MyDrive/data/malaysia/Krisis Perlembagaan Malaysia 1988.txt',\n", " '/content/drive/MyDrive/data/malaysia/Krisis pencerobohan Lahad Datu 2013.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kristang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kristian.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kristian di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kuala Lumpur.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kumpulan 15.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kumpulan etnik.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kuwait.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kyrgyzstan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Labuan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Lagu ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Lagu kebangsaan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Lambang ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Langkasuka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Laos.txt',\n", " '/content/drive/MyDrive/data/malaysia/Lapangan Terbang Antarabangsa Kuala Lumpur.txt',\n", " '/content/drive/MyDrive/data/malaysia/Laut China Selatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Lebuhraya Utara-Selatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Lesotho.txt',\n", " '/content/drive/MyDrive/data/malaysia/Liberia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Libya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Liga Arab.txt',\n", " '/content/drive/MyDrive/data/malaysia/Litar Antarabangsa Sepang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Lubnan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Maal Hijrah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Macau.txt',\n", " '/content/drive/MyDrive/data/malaysia/Madagascar.txt',\n", " '/content/drive/MyDrive/data/malaysia/Maghribi.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mahathir bin Mohamad.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mahkamah Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mahkamah Syariah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mahkamah Syariah di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Majapahit.txt',\n", " '/content/drive/MyDrive/data/malaysia/Majlis Industri Pertahanan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Majlis Raja-Raja.txt',\n", " '/content/drive/MyDrive/data/malaysia/Malawi.txt',\n", " '/content/drive/MyDrive/data/malaysia/Malayan Union.txt',\n", " '/content/drive/MyDrive/data/malaysia/Malaysia Timur.txt',\n", " '/content/drive/MyDrive/data/malaysia/Maldives.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mali.txt',\n", " '/content/drive/MyDrive/data/malaysia/Malta.txt',\n", " '/content/drive/MyDrive/data/malaysia/Manglish.txt',\n", " '/content/drive/MyDrive/data/malaysia/Masakan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Masjid Kampung Laut.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mata wang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Maulidur Rasul.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mauritania.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mauritius.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mazhab.txt',\n", " '/content/drive/MyDrive/data/malaysia/Media Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Melaka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Melaka Belanda.txt',\n", " '/content/drive/MyDrive/data/malaysia/Melaka Portugis.txt',\n", " '/content/drive/MyDrive/data/malaysia/Melanesia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Melayu Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Menara Berkembar Petronas.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mesir.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mesyuarat Asia–Eropah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mexico.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mike Pompeo.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mikronesia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Milton Osborne.txt',\n", " '/content/drive/MyDrive/data/malaysia/Monarki Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mongolia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Monsun.txt',\n", " '/content/drive/MyDrive/data/malaysia/Montenegro.txt',\n", " '/content/drive/MyDrive/data/malaysia/Montserrat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Mozambique.txt',\n", " '/content/drive/MyDrive/data/malaysia/Murtabak.txt',\n", " '/content/drive/MyDrive/data/malaysia/MusicBrainz.txt',\n", " '/content/drive/MyDrive/data/malaysia/Muzik Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Myanmar.txt',\n", " '/content/drive/MyDrive/data/malaysia/Nagorno-Karabakh.txt',\n", " '/content/drive/MyDrive/data/malaysia/Najib Razak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Nama-nama Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Namibia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Nauru.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negara-Negara Komanwel.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negara-negara Komanwel.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negara Palestin.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negara anggota Persatuan Negara-negara Asia Tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negaraku.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negeri-Negeri Selat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negeri-negeri Melayu Bersekutu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negeri-negeri Melayu Tidak Bersekutu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negeri-negeri Selat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negeri Sembilan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negeri dan Wilayah Persekutuan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Negeri dan wilayah persekutuan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Nepal.txt',\n", " '/content/drive/MyDrive/data/malaysia/New Zealand.txt',\n", " '/content/drive/MyDrive/data/malaysia/Nicaragua.txt',\n", " '/content/drive/MyDrive/data/malaysia/Niger.txt',\n", " '/content/drive/MyDrive/data/malaysia/Nigeria.txt',\n", " '/content/drive/MyDrive/data/malaysia/Niue.txt',\n", " '/content/drive/MyDrive/data/malaysia/Oceania.txt',\n", " '/content/drive/MyDrive/data/malaysia/Oman.txt',\n", " '/content/drive/MyDrive/data/malaysia/Orang Asli.txt',\n", " '/content/drive/MyDrive/data/malaysia/Orang Cina Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Orang Cina di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Orang Hui.txt',\n", " '/content/drive/MyDrive/data/malaysia/Orang Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Orang Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Orang Negrito.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ossetia Selatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pahang Darul Makmur.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pakistan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Palembang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pamalayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pameran Aeroangkasa dan Maritim Antarabangsa Langkawi.txt',\n", " '/content/drive/MyDrive/data/malaysia/Panama.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pantai Timur, Semenanjung Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Papua Barat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Papua New Guinea.txt',\n", " '/content/drive/MyDrive/data/malaysia/Parameswara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pariti kuasa beli.txt',\n", " '/content/drive/MyDrive/data/malaysia/Parlimen Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Parti Komunis Malaya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Parti Rakyat Bersatu Sarawak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pekali Gini.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pelancongan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pemanduan di sebelah kanan atau kiri.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pemburu-pengumpul.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pemerintahan sendiri.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pemerintahan sendiri Singapura.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pendidikan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pendidikan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pendudukan Jepun di Borneo British.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pendudukan Jepun di Tanah Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pengangkutan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pengecam Nama Piawaian Antarabangsa.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pengislaman.txt',\n", " '/content/drive/MyDrive/data/malaysia/Penguatkuasaan undang-undang di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Penjagaan kesihatan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Penjagaan kesihatan sejagat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Penjajahan Jepun di Tanah Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pentadbiran Tentera British (Borneo).txt',\n", " '/content/drive/MyDrive/data/malaysia/Pentadbiran Tentera British (Tanah Melayu).txt',\n", " '/content/drive/MyDrive/data/malaysia/Penyimpan Mohor Besar Raja-Raja.txt',\n", " '/content/drive/MyDrive/data/malaysia/Per kapita.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perairan wilayah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perak Darul Ridzuan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perang Dunia Kedua.txt',\n", " '/content/drive/MyDrive/data/malaysia/Peratusan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perayaan Islam.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perdana Menteri Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perfileman Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pergerakan Negara-Negara Berkecuali.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perhimpunan Agung Pertubuhan Bangsa-Bangsa Bersatu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perhimpunan Bersih 2007.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perhimpunan Hindraf 2007.txt',\n", " '/content/drive/MyDrive/data/malaysia/Peristiwa 13 Mei.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perisytiharan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perjanjian 18 perkara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perjanjian 20 Perkara Sabah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perjanjian ASEAN Mengenai Pencemaran Jerebu Rentas Sempadan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perjanjian Inggeris-Belanda 1824.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perjanjian Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perjanjian Persahabatan dan Kerjasama di Asia Tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perkara 160 Perlembagaan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perkongsian Ekonomi Komprehensif Serantau.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perkongsian Ekonomi Komprehensif untuk Asia Timur.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perlembagaan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perlis.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perluasan Persatuan Negara-negara Asia Tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Persatuan Negara-negara Asia Tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Persekutuan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Persekutuan Bola Sepak ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Persekutuan Tanah Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pertanian di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pertemuan Raifal Tentera ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pertubuhan Bangsa-Bangsa Bersatu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pertubuhan Kerjasama Islam.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pertubuhan Persidangan Islam.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pertubuhan berkaitan dengan Persatuan Negara-negara Asia Tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Peru.txt',\n", " '/content/drive/MyDrive/data/malaysia/Petaling Jaya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Piagam ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Piala Thomas.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pilihan raya di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Polinesia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Politik Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Politik di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Prasejarah Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Projek Lebuhraya Utara Selatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Proton Prevé.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pulau Heard dan Kepulauan McDonald.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pulau Krismas.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pulau Man.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pulau Norfolk.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pulau Pinang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Pungutan suara penyatuan Singapura 1962.txt',\n", " '/content/drive/MyDrive/data/malaysia/Putrajaya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Qatar.txt',\n", " '/content/drive/MyDrive/data/malaysia/Raja-raja Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Raja Perlis.txt',\n", " '/content/drive/MyDrive/data/malaysia/Raja Putih.txt',\n", " '/content/drive/MyDrive/data/malaysia/Raja berperlembagaan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Raja elektif.txt',\n", " '/content/drive/MyDrive/data/malaysia/Rakyat Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Rangkaian Bandar Pintar ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Republik Afrika Tengah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Republik China di Taiwan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Republik Congo.txt',\n", " '/content/drive/MyDrive/data/malaysia/Republik Demokratik Congo.txt',\n", " '/content/drive/MyDrive/data/malaysia/Republik Rakyat China.txt',\n", " '/content/drive/MyDrive/data/malaysia/Republik Turki Cyprus Utara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ringgit.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ringgit Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Rosmah Mansor.txt',\n", " '/content/drive/MyDrive/data/malaysia/Rukunegara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Rusia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Russia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Rusuhan kaum Singapura 1964.txt',\n", " '/content/drive/MyDrive/data/malaysia/Rwanda.txt',\n", " '/content/drive/MyDrive/data/malaysia/S2CID.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sabah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sains dan teknologi di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Saint Helena, Ascension dan Tristan da Cunha.txt',\n", " '/content/drive/MyDrive/data/malaysia/Saint Kitts dan Nevis.txt',\n", " '/content/drive/MyDrive/data/malaysia/Saint Lucia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Saint Vincent dan Grenadines.txt',\n", " '/content/drive/MyDrive/data/malaysia/Saint Vincent dan the Grenadines.txt',\n", " '/content/drive/MyDrive/data/malaysia/Samoa.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sanskrit.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sarawak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sejarah ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sejarah Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sejarah di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Selangor.txt',\n", " '/content/drive/MyDrive/data/malaysia/Semenanjung Emas.txt',\n", " '/content/drive/MyDrive/data/malaysia/Semenanjung Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Semenanjung Tanah Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai Tapak Warisan Dunia di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai anggota Negara-negara Komanwel.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai bank di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai gunung di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai negara ASEAN mengikut KDNK.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai negara berdaulat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai negara dan wilayah tanggungan di Asia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai negara mengikut Indeks Pembangunan Manusia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai negara mengikut KDNK (PPP).txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai negara mengikut keluasan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai negara yang merentasi melebihi satu benua.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai negeri Malaysia mengikut KDNK.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai parti politik di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai pulau di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai sungai di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai taman negara di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai tasik di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senarai universiti di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Senegal.txt',\n", " '/content/drive/MyDrive/data/malaysia/Serbia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Setiausaha Agung Persatuan Negara-negara Asia Tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Setiausaha Negara Amerika Syarikat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Seychelles.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sidang Kemuncak ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sidang Kemuncak Asia Timur.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sierra Leone.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sijil Tinggi Persekolahan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sikh.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sikhisme.txt',\n", " '/content/drive/MyDrive/data/malaysia/Silat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Simbol Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Simbol kebangsaan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Singapura.txt',\n", " '/content/drive/MyDrive/data/malaysia/Singapura dalam Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sistem Pendokumenan Universiti.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sistem berparlimen.txt',\n", " '/content/drive/MyDrive/data/malaysia/Skandal 1Malaysia Development Berhad.txt',\n", " '/content/drive/MyDrive/data/malaysia/Skuasy.txt',\n", " '/content/drive/MyDrive/data/malaysia/Société de Géographie.txt',\n", " '/content/drive/MyDrive/data/malaysia/Soekarno.txt',\n", " '/content/drive/MyDrive/data/malaysia/Somalia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sri Lanka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Srivijaya.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sudan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sukan Asia Tenggara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sukan Komanwel.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sukan Para ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sukan Sekolah ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sukan Universiti ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sukan di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sukhoi Su-30.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Abdul Halim Mu’adzam Shah ibni Almarhum Sultan Badlishah.txt',\n", " \"/content/drive/MyDrive/data/malaysia/Sultan Abdullah Ri'ayatuddin Al-Mustafa Billah Shah ibni Almarhum Sultan Haji Ahmad Shah Al-Musta'in Billah.txt\",\n", " '/content/drive/MyDrive/data/malaysia/Sultan Azlan Muhibbuddin Shah ibni Almarhum Sultan Yussuff Izzuddin Shah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Haji Ahmad Shah Al-Musta’in Billah ibni Almarhum Sultan Abu Bakar Ri’ayatuddin Al-Mu’azzam Shah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Hisamuddin Alam Shah ibni al-Marhum Sultan Alauddin Sulaiman Shah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Iskandar ibni Almarhum Sultan Ismail.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Ismail Nasiruddin Shah ibni al-Marhum Sultan Haji Zainal Abidin III Mu’azzam Shah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Johor.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Kedah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Kelantan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Mizan Zainal Abidin ibni Almarhum Sultan Mahmud Al-Muktafi Billah Shah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Muhammad V.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Pahang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Perak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Salahuddin Abdul Aziz Shah ibni Almarhum Sultan Hisamuddin Alam Shah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Selangor.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Terengganu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sultan Yahya Petra ibni al-Marhum Sultan Ibrahim.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sulu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Sumatera.txt',\n", " '/content/drive/MyDrive/data/malaysia/Suriname.txt',\n", " '/content/drive/MyDrive/data/malaysia/Suruhanjaya Cobbold.txt',\n", " '/content/drive/MyDrive/data/malaysia/Suruhanjaya Tenaga Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Syafii.txt',\n", " '/content/drive/MyDrive/data/malaysia/Syarikat Hindia Timur British.txt',\n", " '/content/drive/MyDrive/data/malaysia/Syria.txt',\n", " '/content/drive/MyDrive/data/malaysia/São Tomé dan Príncipe.txt',\n", " '/content/drive/MyDrive/data/malaysia/Taiwan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tajikistan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Taman Negara Kinabalu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tanah Jajahan Mahkota British Borneo Utara.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tanah Jajahan Mahkota Sarawak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tanah Melayu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tanah Melayu British.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tanjung Piai.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tanzania.txt',\n", " '/content/drive/MyDrive/data/malaysia/Taoisme.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tapak Warisan Dunia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Telekesihatan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Telekomunikasi di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Teluk Sepanggar.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tenaga boleh baharu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tentera Darat Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tentera Laut Diraja Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tentera Udara Diraja Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Terengganu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Thailand.txt',\n", " '/content/drive/MyDrive/data/malaysia/Thaipusam.txt',\n", " '/content/drive/MyDrive/data/malaysia/The ASEAN Way.txt',\n", " '/content/drive/MyDrive/data/malaysia/The Malay Mail.txt',\n", " '/content/drive/MyDrive/data/malaysia/The National Archives (United Kingdom).txt',\n", " '/content/drive/MyDrive/data/malaysia/Time Asia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Timor Leste.txt',\n", " '/content/drive/MyDrive/data/malaysia/Timor Timur.txt',\n", " '/content/drive/MyDrive/data/malaysia/Togo.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tokelau.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tonga.txt',\n", " '/content/drive/MyDrive/data/malaysia/Toponim.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tourism Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Transit aliran ringan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Trinidad dan Tobago.txt',\n", " '/content/drive/MyDrive/data/malaysia/Trove.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tuanku Abdul Rahman ibni al-Marhum Tuanku Muhammad.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tuanku Ja’afar ibni Almarhum Tuanku Abdul Rahman.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tuanku Syed Putra ibni al-Marhum Syed Hassan Jamalullail.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tuanku Syed Sirajuddin ibni Almarhum Tuanku Syed Putra Jamalullail.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tulisan Jawi.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tumpat.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tun Abdul Razak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tunisia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Turki.txt',\n", " '/content/drive/MyDrive/data/malaysia/Turkmenistan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Tuvalu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Uganda.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ujian Pencapaian Sekolah Rendah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Ukraine.txt',\n", " '/content/drive/MyDrive/data/malaysia/Undang-undang Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Unit Kewangan Asia.txt',\n", " '/content/drive/MyDrive/data/malaysia/United Kingdom.txt',\n", " '/content/drive/MyDrive/data/malaysia/United Nations Research Institute For Social Development.txt',\n", " '/content/drive/MyDrive/data/malaysia/Uruguay.txt',\n", " '/content/drive/MyDrive/data/malaysia/Utusan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Uzbekistan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Vanuatu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Vayu Purana.txt',\n", " '/content/drive/MyDrive/data/malaysia/Venezuela.txt',\n", " '/content/drive/MyDrive/data/malaysia/Vietnam.txt',\n", " '/content/drive/MyDrive/data/malaysia/Waktu Musim Panas.txt',\n", " '/content/drive/MyDrive/data/malaysia/Waktu Piawai Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Waktu Umum ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Waktu Universal Selaras.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wanita di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wayang kulit.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wayback Machine.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wilayah Antartik Australia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wilayah Antartik British.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wilayah Lautan Hindi British.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wilayah Persekutuan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wilayah Tanggungan Ross.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wilayah tanggungan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yaman.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri Melaka.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri Pulau Pinang.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri Sabah.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yang di-Pertua Negeri Sarawak.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yang di-Pertuan Agong.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yang di-Pertuan Besar Negeri Sembilan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yemen.txt',\n", " '/content/drive/MyDrive/data/malaysia/Yijing.txt',\n", " '/content/drive/MyDrive/data/malaysia/Zambia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Zimbabwe.txt',\n", " '/content/drive/MyDrive/data/malaysia/Zon waktu.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wikipedia:Pautan reput.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wikipedia:Polisi perlindungan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Wikipedia:Rencana pilihan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Fail:Independence Square, Kuala Lumpur (6758524547).jpg.txt',\n", " '/content/drive/MyDrive/data/malaysia/Fail:KotaKinabalu Sabah TelukSapanggar-RoyalNavy-01.jpg.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:APEC.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:Asia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:G15.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:Komanwel.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:Kumpulan etnik di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:Malay-speaking.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:Negeri dan Wilayah Persekutuan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:OIC.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:Pergerakan Negara-Negara Berkecuali dan sukan makan ikan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:Sistem beraja di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Templat:Topik Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:APEC.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:ASEAN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:Asia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:G15.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:Komanwel.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:Malay-speaking.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:Negeri dan Wilayah Persekutuan Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:OIC.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:Pergerakan Negara-Negara Berkecuali dan sukan makan ikan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:Sistem beraja di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Perbincangan templat:Topik Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Bantuan:Kawalan kewibawaan.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:APEC.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:CS1 maint: date and year.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:CS1 maint: date format.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:CS1 maint: multiple names: authors list.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Fauna di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Flora di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Guna tarikh dmy dari Januari 2023.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Harv and Sfn template errors.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Istana di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Masyarakat Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Mitologi Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pautan luar mati dari Oktober 2021.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan BIBSYS.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan BNE.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan BNF.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan CANTICN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan CINII.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan EMU.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan FAST.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan GND.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan HDS.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan ISNI.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan J9U.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan LCCN.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NARA.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NDL.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NKC.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NLA.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan NLK.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan SELIBR.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan SUDOC.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan TDVİA.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan Trove.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan VIAF.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan kawasan MusicBrainz.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Rencana dengan pengenalan multiple.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Seni bina Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Kategori:Tempat-tempat berpenduduk di Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/Portal:50.txt',\n", " '/content/drive/MyDrive/data/malaysia/Portal:Flag of Malaysia.svg.txt',\n", " '/content/drive/MyDrive/data/malaysia/Portal:Malaysia.txt',\n", " '/content/drive/MyDrive/data/malaysia/ms-train-2.0.json'],\n", " 'node_id': 'DocumentStore'}" ] }, "metadata": {}, "execution_count": 12 } ] }, { "cell_type": "code", "source": [ "from haystack.nodes import FARMReader\n", "from haystack.utils import fetch_archive_from_http\n", "\n", "reader = FARMReader(model_name_or_path=\"distilbert-base-uncased-distilled-squad\", use_gpu=True)\n", "data_dir = \"data/squad20\"\n", "# data_dir = \"PATH/TO_YOUR/TRAIN_DATA\"\n", "reader.train(data_dir='/content/drive/MyDrive/data/malaysia', train_filename='ms-train-2.0.json', use_gpu=True, n_epochs=1, save_dir=\"MyCustomReader\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 810, "referenced_widgets": [ "51c5432770f746499d39eabe90ea3b22", "eab6be491a2b4626bce29cb25dd69996", "799f93ec6e56423a8517c33221de66a8", "b7d6dc1b527843e4ae253bff6d09042c", "41dd5492e6504ef7aec30aec1aa0fac1", "e248351c67e24939b879e51bb1acf8b1", "be735c6903954cdc9598ae9503c9b687", "fd15a5f5fd0b486f942c996d2ab14142", "893457340de84d4c8f34153bb7a8a951", "8ae517ce456f4967b46e1c8efcf98309", "c155cde688d04bdca473ce9fb2df4677", "7e3445e1f55d4755b99dc3f38cb3739d", "849eaa2172ac4b87b99b243d6f14ac73", "e4f3fa94ab334d5cb17d1f400aa467af", "d4d8f8701be743e59274545a8a0b01d4", "20ed4923120c477eb64e79d528505dc1", "0147700d0964475db0583ca6001af643", "de89adfba1cc47a2b55d274d6ff7934d", "e37e7144dfe54a4ea966dfba155d196a", "625da93559c64880bed38efec2addf54", "33724b8fe0524ee194a73cf3d48ae8c6", "f243166fd8a94baba327fe072980ba60" ] }, "id": "nzLo2C8ree2e", "outputId": "55076548-e7eb-4d44-f7ba-6dd9f6edff1e" }, "execution_count": 14, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "INFO:haystack.modeling.utils:Using devices: CUDA:0 - Number of GPUs: 1\n", "INFO:haystack.modeling.utils:Using devices: CUDA:0 - Number of GPUs: 1\n", "INFO:haystack.modeling.model.language_model: * LOADING MODEL: 'distilbert-base-uncased-distilled-squad' (DistilBert)\n", "INFO:haystack.modeling.model.language_model:Auto-detected model language: english\n", "INFO:haystack.modeling.model.language_model:Loaded 'distilbert-base-uncased-distilled-squad' (DistilBert model) from model hub.\n", "INFO:haystack.modeling.utils:Using devices: CUDA:0 - Number of GPUs: 1\n", "INFO:haystack.modeling.utils:Using devices: CUDA:0 - Number of GPUs: 1\n", "INFO:haystack.modeling.data_handler.data_silo:\n", "Loading data into the data silo ... \n", " ______\n", " |o | !\n", " __ |:`_|---'-.\n", " |__|______.-/ _ \\-----.|\n", " (o)(o)------'\\ _ / ( )\n", " \n", "INFO:haystack.modeling.data_handler.data_silo:LOADING TRAIN DATA\n", "INFO:haystack.modeling.data_handler.data_silo:==================\n", "INFO:haystack.modeling.data_handler.data_silo:Loading train set from: /content/drive/MyDrive/data/malaysia/ms-train-2.0.json \n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "Preprocessing dataset: 0%| | 0/38 [00:00,\n", " ,\n", " ,\n", " ,\n", " ]" ] }, "metadata": {}, "execution_count": 21 } ] }, { "cell_type": "code", "source": [ "from getpass import getpass\n", "\n", "model_api_key = getpass(\"Enter model provider API key:\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "jXTBW7DLDgS3", "outputId": "e3f2e61d-5793-4c74-92db-71bcebf27f3b" }, "execution_count": 28, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Enter model provider API key:··········\n" ] } ] }, { "cell_type": "code", "source": [ "import requests\n", "\n", "API_URL = \"https://api-inference.huggingface.co/models/yewsam1277/question-answering-bahasa-malaysia\"\n", "headers = {\"Authorization\": \"Bearer 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\"}\n", "\n", "def query(payload):\n", "\tresponse = requests.post(API_URL, headers=headers, json=payload)\n", "\treturn response.json()\n", "\n", "output = query({\n", "\t\"inputs\": {\n", "\t\t\"question\": \"What's my name?\",\n", "\t\t\"context\": \"My name is Clara and I live in Berkeley.\"\n", "\t},\n", "})" ], "metadata": { "id": "khjTEfPYRSZY" }, "execution_count": 31, "outputs": [] }, { "cell_type": "code", "source": [ "print(output)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yeg66fIFRdz0", "outputId": "021f4727-a2b5-48a5-c286-a68d64305a73" }, "execution_count": 32, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "{'error': \"Can't load config for 'None'. Make sure that:\\n\\n- 'None' is a correct model identifier listed on 'https://huggingface.co/models'\\n\\n- or 'None' is the correct path to a directory containing a config.json file\\n\\n\"}\n" ] } ] }, { "cell_type": "code", "source": [ "from haystack.nodes import PromptNode\n", "\n", "model_name = \"yewsam1277/question-answering-bahasa-malaysia\"\n", "prompt_node = PromptNode(model_name, api_key=model_api_key, max_length=256)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "rW04CMhXDpih", "outputId": "1804d27b-320f-4b90-badc-4c9bb5381d92" }, "execution_count": 30, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "\u001b[31m╭─\u001b[0m\u001b[31m──────────────────────────────\u001b[0m\u001b[31m \u001b[0m\u001b[1;31mTraceback \u001b[0m\u001b[1;2;31m(most recent call last)\u001b[0m\u001b[31m \u001b[0m\u001b[31m───────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n", "\u001b[31m│\u001b[0m in \u001b[92m\u001b[0m:\u001b[94m4\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/haystack/nodes/\u001b[0m\u001b[1;33mbase.py\u001b[0m:\u001b[94m46\u001b[0m in \u001b[92mwrapper_exportable_to_yaml\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 43 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[96mself\u001b[0m._component_config[\u001b[33m\"\u001b[0m\u001b[33mparams\u001b[0m\u001b[33m\"\u001b[0m][k] = v \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 44 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 45 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Call the actuall __init__ function with all the arguments\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 46 \u001b[2m│ │ \u001b[0minit_func(\u001b[96mself\u001b[0m, *args, **kwargs) \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 47 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 48 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mreturn\u001b[0m wrapper_exportable_to_yaml \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 49 \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/haystack/nodes/prompt/\u001b[0m\u001b[1;33mprompt_node.py\u001b[0m:\u001b[94m119\u001b[0m in \u001b[92m__init__\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m116 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m117 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m118 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96misinstance\u001b[0m(model_name_or_path, \u001b[96mstr\u001b[0m): \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m119 \u001b[2m│ │ │ \u001b[0m\u001b[96mself\u001b[0m.prompt_model = PromptModel( \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m120 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mmodel_name_or_path=model_name_or_path, \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m121 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mmax_length=max_length, \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m122 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mapi_key=api_key, \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/haystack/nodes/\u001b[0m\u001b[1;33mbase.py\u001b[0m:\u001b[94m46\u001b[0m in \u001b[92mwrapper_exportable_to_yaml\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 43 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[96mself\u001b[0m._component_config[\u001b[33m\"\u001b[0m\u001b[33mparams\u001b[0m\u001b[33m\"\u001b[0m][k] = v \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 44 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 45 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Call the actuall __init__ function with all the arguments\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 46 \u001b[2m│ │ \u001b[0minit_func(\u001b[96mself\u001b[0m, *args, **kwargs) \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 47 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 48 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mreturn\u001b[0m wrapper_exportable_to_yaml \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 49 \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/haystack/nodes/prompt/\u001b[0m\u001b[1;33mprompt_model.py\u001b[0m:\u001b[94m67\u001b[0m in \u001b[92m__init__\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 64 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[96mself\u001b[0m.devices = devices \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 65 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 66 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[96mself\u001b[0m.model_kwargs = model_kwargs \u001b[94mif\u001b[0m model_kwargs \u001b[94melse\u001b[0m {} \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 67 \u001b[2m│ │ \u001b[0m\u001b[96mself\u001b[0m.model_invocation_layer = \u001b[96mself\u001b[0m.create_invocation_layer(invocation_layer_clas \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 68 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 69 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92mcreate_invocation_layer\u001b[0m( \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 70 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[96mself\u001b[0m, invocation_layer_class: Optional[Type[PromptModelInvocationLayer]] \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/haystack/nodes/prompt/\u001b[0m\u001b[1;33mprompt_model.py\u001b[0m:\u001b[94m91\u001b[0m in \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[92mcreate_invocation_layer\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 88 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94mreturn\u001b[0m invocation_layer( \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 89 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0mmodel_name_or_path=\u001b[96mself\u001b[0m.model_name_or_path, max_length=\u001b[96mself\u001b[0m.max_leng \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 90 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 91 \u001b[2m│ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mValueError\u001b[0m( \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 92 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[33mf\u001b[0m\u001b[33m\"\u001b[0m\u001b[33mModel \u001b[0m\u001b[33m{\u001b[0m\u001b[96mself\u001b[0m.model_name_or_path\u001b[33m}\u001b[0m\u001b[33m is not supported - no matching invocation \u001b[0m \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 93 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[33mf\u001b[0m\u001b[33m\"\u001b[0m\u001b[33m Currently supported invocation layers are: \u001b[0m\u001b[33m{\u001b[0mPromptModelInvocationLayer.in \u001b[31m│\u001b[0m\n", "\u001b[31m│\u001b[0m \u001b[2m 94 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[33mf\u001b[0m\u001b[33m\"\u001b[0m\u001b[33m You can implement and provide custom invocation layer for \u001b[0m\u001b[33m{\u001b[0m\u001b[96mself\u001b[0m.model_nam \u001b[31m│\u001b[0m\n", "\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n", "\u001b[1;91mValueError: \u001b[0mModel yewsam1277/question-answering-bahasa-malaysia is not supported - no matching invocation layer \n", "found. Currently supported invocation layers are: \u001b[1m[\u001b[0m\u001b[1m<\u001b[0m\u001b[1;95mclass\u001b[0m\u001b[39m \u001b[0m\n", "\u001b[32m'haystack.nodes.prompt.invocation_layer.open_ai.OpenAIInvocationLayer'\u001b[0m\u001b[39m>, , , , , , , \u001b[0m\u001b[1m]\u001b[0m You can implement and provide custom \n", "invocation layer for yewsam1277/question-answering-bahasa-malaysia by subclassing PromptModelInvocationLayer.\n" ], "text/html": [ "
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮\n",
              " in <cell line: 4>:4                                                                              \n",
              "                                                                                                  \n",
              " /usr/local/lib/python3.10/dist-packages/haystack/nodes/base.py:46 in wrapper_exportable_to_yaml  \n",
              "                                                                                                  \n",
              "    43 │   │   │   │   self._component_config[\"params\"][k] = v                                    \n",
              "    44 │   │                                                                                      \n",
              "    45 │   │   # Call the actuall __init__ function with all the arguments                        \n",
              "  46 │   │   init_func(self, *args, **kwargs)                                                   \n",
              "    47 │                                                                                          \n",
              "    48 │   return wrapper_exportable_to_yaml                                                      \n",
              "    49                                                                                            \n",
              "                                                                                                  \n",
              " /usr/local/lib/python3.10/dist-packages/haystack/nodes/prompt/prompt_node.py:119 in __init__     \n",
              "                                                                                                  \n",
              "   116 │   │   │   )                                                                              \n",
              "   117 │   │                                                                                      \n",
              "   118 │   │   if isinstance(model_name_or_path, str):                                            \n",
              " 119 │   │   │   self.prompt_model = PromptModel(                                               \n",
              "   120 │   │   │   │   model_name_or_path=model_name_or_path,                                     \n",
              "   121 │   │   │   │   max_length=max_length,                                                     \n",
              "   122 │   │   │   │   api_key=api_key,                                                           \n",
              "                                                                                                  \n",
              " /usr/local/lib/python3.10/dist-packages/haystack/nodes/base.py:46 in wrapper_exportable_to_yaml  \n",
              "                                                                                                  \n",
              "    43 │   │   │   │   self._component_config[\"params\"][k] = v                                    \n",
              "    44 │   │                                                                                      \n",
              "    45 │   │   # Call the actuall __init__ function with all the arguments                        \n",
              "  46 │   │   init_func(self, *args, **kwargs)                                                   \n",
              "    47 │                                                                                          \n",
              "    48 │   return wrapper_exportable_to_yaml                                                      \n",
              "    49                                                                                            \n",
              "                                                                                                  \n",
              " /usr/local/lib/python3.10/dist-packages/haystack/nodes/prompt/prompt_model.py:67 in __init__     \n",
              "                                                                                                  \n",
              "    64 │   │   self.devices = devices                                                             \n",
              "    65 │   │                                                                                      \n",
              "    66 │   │   self.model_kwargs = model_kwargs if model_kwargs else {}                           \n",
              "  67 │   │   self.model_invocation_layer = self.create_invocation_layer(invocation_layer_clas   \n",
              "    68 │                                                                                          \n",
              "    69 │   def create_invocation_layer(                                                           \n",
              "    70 │   │   self, invocation_layer_class: Optional[Type[PromptModelInvocationLayer]]           \n",
              "                                                                                                  \n",
              " /usr/local/lib/python3.10/dist-packages/haystack/nodes/prompt/prompt_model.py:91 in              \n",
              " create_invocation_layer                                                                          \n",
              "                                                                                                  \n",
              "    88 │   │   │   │   return invocation_layer(                                                   \n",
              "    89 │   │   │   │   │   model_name_or_path=self.model_name_or_path, max_length=self.max_leng   \n",
              "    90 │   │   │   │   )                                                                          \n",
              "  91 │   │   raise ValueError(                                                                  \n",
              "    92 │   │   │   f\"Model {self.model_name_or_path} is not supported - no matching invocation    \n",
              "    93 │   │   │   f\" Currently supported invocation layers are: {PromptModelInvocationLayer.in   \n",
              "    94 │   │   │   f\" You can implement and provide custom invocation layer for {self.model_nam   \n",
              "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\n",
              "ValueError: Model yewsam1277/question-answering-bahasa-malaysia is not supported - no matching invocation layer \n",
              "found. Currently supported invocation layers are: [<class \n",
              "'haystack.nodes.prompt.invocation_layer.open_ai.OpenAIInvocationLayer'>, <class \n",
              "'haystack.nodes.prompt.invocation_layer.azure_open_ai.AzureOpenAIInvocationLayer'>, <class \n",
              "'haystack.nodes.prompt.invocation_layer.chatgpt.ChatGPTInvocationLayer'>, <class \n",
              "'haystack.nodes.prompt.invocation_layer.azure_chatgpt.AzureChatGPTInvocationLayer'>, <class \n",
              "'haystack.nodes.prompt.invocation_layer.hugging_face.HFLocalInvocationLayer'>, <class \n",
              "'haystack.nodes.prompt.invocation_layer.hugging_face_inference.HFInferenceEndpointInvocationLayer'>, <class \n",
              "'haystack.nodes.prompt.invocation_layer.anthropic_claude.AnthropicClaudeInvocationLayer'>, <class \n",
              "'haystack.nodes.prompt.invocation_layer.cohere.CohereInvocationLayer'>] You can implement and provide custom \n",
              "invocation layer for yewsam1277/question-answering-bahasa-malaysia by subclassing PromptModelInvocationLayer.\n",
              "
\n" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "from haystack.agents.memory import ConversationSummaryMemory\n", "\n", "summary_memory = ConversationSummaryMemory(prompt_node)" ], "metadata": { "id": "DyEHMGNzF8O2" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "from haystack.agents.conversational import ConversationalAgent\n", "\n", "conversational_agent = ConversationalAgent(prompt_node=prompt_node, memory=summary_memory)" ], "metadata": { "id": "AoAp5qkyF8xQ" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [], "metadata": { "id": "zGZycy11GBFi" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "%%bash\n", "\n", "pip install wikipedia-api" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "_wamqY3c8IxU", "outputId": "6f3de92c-b603-46a2-fdad-510f19e7f363" }, "execution_count": 2, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting wikipedia-api\n", " Downloading Wikipedia_API-0.5.8-py3-none-any.whl (13 kB)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from wikipedia-api) (2.27.1)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->wikipedia-api) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->wikipedia-api) (2022.12.7)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->wikipedia-api) (2.0.12)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->wikipedia-api) (3.4)\n", "Installing collected packages: wikipedia-api\n", "Successfully installed wikipedia-api-0.5.8\n" ] } ] }, { "cell_type": "markdown", "source": [ "Step 1" ], "metadata": { "id": "sIiGJFfp8pS5" } }, { "cell_type": "code", "source": [ "import wikipediaapi" ], "metadata": { "id": "GgrT-AR6_c3k" }, "execution_count": 1, "outputs": [] }, { "cell_type": "code", "source": [ "wiki = wikipediaapi.Wikipedia('ms')\n", "page = wiki.page('Malaysia')" ], "metadata": { "id": "pT6Uv174_gC1" }, "execution_count": 2, "outputs": [] }, { "cell_type": "code", "source": [ "pages = {'Malaysia': page}" ], "metadata": { "id": "3GRhr9usBOP_" }, "execution_count": 3, "outputs": [] }, { "cell_type": "code", "source": [ "pages.update(page.links)" ], "metadata": { "id": "R1vTyWDF_4xz" }, "execution_count": 4, "outputs": [] }, { "cell_type": "code", "source": [ "len(pages)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "9YDqQc-D_5Qm", "outputId": "c6d66de0-37e3-422a-c6f5-f11121a6e44b" }, "execution_count": 5, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "801" ] }, "metadata": {}, "execution_count": 5 } ] }, { "cell_type": "code", "source": [ "from google.colab import drive\n", "drive.mount('/content/drive')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "34xBK3UjSlgm", "outputId": "9464e6fc-12c9-487d-900e-fa2a8e337477" }, "execution_count": 6, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n" ] } ] }, { "cell_type": "code", "source": [ "done = 0\n", "for key in pages:\n", " try:\n", " with open(f'/content/drive/MyDrive/data/malaysia/{pages[key].title}.txt', 'w') as f:\n", " get_text = pages[key].text\n", " get_text = get_text.lower().replace('\\n', ' ')\n", " f.write(get_text)\n", " except Exception as e:\n", " pass\n", " done += 1\n", " print(f\"Written: {pages[key].title}\\t(done {done})\", end='\\r')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "hSIkmyCUEHPO", "outputId": "61c13232-2597-428d-ea36-c8412fcb31b6" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [] } ] }, { "cell_type": "code", "source": [ "len(pages)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "6zZqHxFKEVlp", "outputId": "7e3b21e7-f379-4920-cff2-fe3ff3e4ff49" }, "execution_count": 8, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "801" ] }, "metadata": {}, "execution_count": 8 } ] }, { "cell_type": "markdown", "source": [ "Training" ], "metadata": { "id": "EPW-wv5Y4Srg" } }, { "cell_type": "code", "source": [], "metadata": { "id": "JzB8xJiS4UJe" }, "execution_count": null, "outputs": [] } ] }