File size: 26,724 Bytes
9a8258d d042c14 9a8258d a84194a 9a8258d 6cac969 a84194a 6cac969 d042c14 6cac969 c717e13 6cac969 c717e13 9a8258d 6cac969 9a8258d c717e13 6cac969 a84194a 6cac969 c717e13 d042c14 6cac969 a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a 9a8258d a84194a d042c14 a84194a 9a8258d d042c14 9a8258d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 |
{
"cells": [
{
"cell_type": "markdown",
"id": "7259c012",
"metadata": {},
"source": [
"# TDCE Learning Model Basic Model Construction\n",
"\n",
"This notebook display the basic construction of Time Driven Cost Estimation Learning Model step by step without using the experiment script (experiment_script.py)"
]
},
{
"cell_type": "markdown",
"id": "050178b5",
"metadata": {},
"source": [
"Import the library"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ae7385ba",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import importlib\n",
"import sys\n",
"import os\n",
"import time\n",
"import numpy as np\n",
"import requests\n",
"import ipywidgets as widgets\n",
"from IPython.display import display\n",
"import git"
]
},
{
"cell_type": "markdown",
"id": "bf7b5cc7",
"metadata": {},
"source": [
"If run from online source or Google Collab please run this code for clone the model file"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4bb874d3",
"metadata": {},
"outputs": [],
"source": [
"run_from_online = True\n",
"ignore_download_dataset = False\n",
"\n",
"\n",
"if run_from_online:\n",
" try:\n",
" repo = git.Repo.clone_from('https://huggingface.co/iaecpsu-1/tdce-basic',\n",
" './tdce-basic',\n",
" branch='main')\n",
" except git.exc.GitCommandError:\n",
" print(\"Repository already exists or cannot be cloned. Continuing with existing files.\")\n",
" pass\n",
"\n",
" # fmt:off\n",
" sys.path.append('./tdce-basic/model')\n",
" sys.path.append('./tdce-basic/functions/matrix_generator')\n",
" sys.path.append('./tdce-basic/functions')\n",
" sys.path.append('./tdce-basic/functions/data_extractor')\n",
"\n",
" try:\n",
" # For online execution, in Google Colab\n",
" !pip install tensor-sensor\n",
" except:\n",
" pass\n",
" \n",
" import tdce_model as tdce\n",
" import material_fc_layer as mfl\n",
" import employee_fc_layer as efl\n",
" import capital_fc_layer as cfl\n",
" import loss\n",
" import cost_matrix_class as cmc\n",
" import display_input_variation as diva\n",
" import viyacrab_augmentation as viya\n",
" import adjust_data as ajd\n",
" import result_display as rd\n",
" import mini_plot as mp\n",
" # fmt:on\n",
" \n",
"\n",
"else :\n",
" # fmt:off\n",
" sys.path.append('../model')\n",
" sys.path.append('../functions/matrix_generator')\n",
" sys.path.append('../functions')\n",
" sys.path.append('../functions/data_extractor')\n",
" \n",
" import tdce_model as tdce\n",
" import material_fc_layer as mfl\n",
" import employee_fc_layer as efl\n",
" import capital_fc_layer as cfl\n",
" import loss\n",
" import cost_matrix_class as cmc\n",
" import display_input_variation as diva\n",
" import viyacrab_augmentation as viya\n",
" import adjust_data as ajd\n",
" import result_display as rd\n",
" import mini_plot as mp\n",
" # fmt:on\n",
"\n",
"importlib.reload(tdce)\n",
"importlib.reload(mfl)\n",
"importlib.reload(efl)\n",
"importlib.reload(cfl)\n",
"importlib.reload(loss)\n",
"importlib.reload(tdce)\n",
"importlib.reload(cmc)\n",
"importlib.reload(diva)\n",
"importlib.reload(viya)\n",
"importlib.reload(ajd)\n",
"importlib.reload(rd)\n",
"importlib.reload(mp)"
]
},
{
"cell_type": "markdown",
"id": "6b7fd72c",
"metadata": {},
"source": [
"## Dataset \n",
"We will use our project dataset for experimental, we pick the [extended-random-dataset](https://huggingface.co/datasets/theethawats98/tdce-example-extended-random) which is the dataset with high dimension but moderate variation to use as case study for out demonstation. We create the dataset in folder `datasets` and then inside it have the folder `extended-random` again. We will create the folder if it is not exist and download the datafile from the our huggingface."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "aa31e7f6",
"metadata": {},
"outputs": [],
"source": [
"try:\n",
" os.mkdir('result')\n",
" os.mkdir(f\"datasets\")\n",
" os.mkdir(f\"datasets/extended-random\")\n",
"except FileExistsError:\n",
" print(\"Folder is Exist\")\n",
" pass"
]
},
{
"cell_type": "markdown",
"id": "ca939290",
"metadata": {},
"source": [
"Download Files"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f98a61ed",
"metadata": {},
"outputs": [],
"source": [
"def download_file():\n",
" capital_cost_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_capital_cost.csv\"\n",
" capital_path = 'datasets/extended-random/generated_capital_cost.csv'\n",
" employee_usage_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_employee_usage.csv\"\n",
" employee_path = 'datasets/extended-random/generated_employee_usage.csv'\n",
" material_usage_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_material_usage.csv\"\n",
" material_path = 'datasets/extended-random/generated_material_usage.csv'\n",
" process_data_link = \"https://huggingface.co/datasets/theethawats98/tdce-example-extended-random/resolve/main/generated_process_data.csv\"\n",
" process_path = 'datasets/extended-random/generated_process_data.csv'\n",
"\n",
"\n",
" for link, path in [\n",
" (capital_cost_link, capital_path),\n",
" (employee_usage_link, employee_path),\n",
" (material_usage_link, material_path),\n",
" (process_data_link, process_path)\n",
" ]:\n",
" if not os.path.exists(path):\n",
" response = requests.get(link)\n",
" if response.status_code == 200:\n",
" with open(path, 'wb') as file:\n",
" file.write(response.content)\n",
" print(f'File {path} downloaded successfully')\n",
" else:\n",
" print(f'Failed to download file {path}')\n",
" # Downloading the datasets\n",
" print(\"Downloading datasets...\")\n",
"\n",
"if (not ignore_download_dataset):\n",
" download_file()"
]
},
{
"cell_type": "markdown",
"id": "8b97d5b2",
"metadata": {},
"source": [
"## Model Setting\n",
"Select the correct setting for your model."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3a387bbe",
"metadata": {},
"outputs": [],
"source": [
"hour_day_employee_widget = widgets.BoundedIntText(\n",
" value=8,\n",
" min=1,\n",
" max=24,\n",
" step=1,\n",
" description='Hours per Day for Employee:',\n",
" disabled=False\n",
")\n",
"\n",
"\n",
"hour_day_capital_cost_widget = widgets.BoundedIntText(\n",
" value=21,\n",
" min=1,\n",
" max=24,\n",
" step=1,\n",
" description='Hours per Day for Utility / Capital Cost:',\n",
" disabled=False\n",
")\n",
"\n",
"use_outlier_removal_widget = widgets.Checkbox(\n",
" value=False,\n",
" description='Enable Outlier Removal',\n",
" disabled=False,\n",
" indent=False\n",
")\n",
"\n",
"\n",
"\n",
"outlier_index_widget = widgets.Dropdown(\n",
" options=['1', '1.5', '2'],\n",
" value='1.5',\n",
" description='Removal Idication Index:',\n",
" disabled=False,\n",
")\n",
"\n",
"use_augmentation_widget = widgets.Checkbox(\n",
" value=False,\n",
" description='Enable Data Augmentation',\n",
" disabled=False,\n",
" indent=False\n",
")\n",
"\n",
"use_early_stopping_widget = widgets.Checkbox(\n",
" value=False,\n",
" description='Enable Early Stopping',\n",
" disabled=False,\n",
" indent=False\n",
")\n",
"\n",
"early_stopping_patience_widget = widgets.BoundedIntText(\n",
" value=10,\n",
" min=1,\n",
" max=100,\n",
" step=1,\n",
" description='Early Stopping Patience Round:',\n",
" disabled=False\n",
")\n",
"\n",
"element_level_lr_widget = widgets.Dropdown(\n",
" options=['0.001','0.05', '0.01','0.1','0.5'],\n",
" value='0.01',\n",
" description='Element Level Learning Rate:',\n",
" disabled=False,\n",
")\n",
"\n",
"model_level_lr_widget = widgets.Dropdown(\n",
" options=['0.0000001','0.00000001','0.000000001'],\n",
" value='0.00000001',\n",
" description='Model Level Learning Rate:',\n",
" disabled=False,\n",
")\n",
"epoch_widget = widgets.BoundedIntText(\n",
" value=100,\n",
" min=10,\n",
" max=1000,\n",
" step=10,\n",
" description='Number of Epochs:',\n",
" disabled=False\n",
")\n",
"\n",
"\n",
"display(hour_day_employee_widget)\n",
"display(hour_day_capital_cost_widget)\n",
"display(use_outlier_removal_widget)\n",
"display(outlier_index_widget)\n",
"display(use_augmentation_widget)\n",
"display(use_early_stopping_widget)\n",
"display(early_stopping_patience_widget)\n",
"display(element_level_lr_widget)\n",
"display(model_level_lr_widget)\n",
"display(epoch_widget)"
]
},
{
"cell_type": "markdown",
"id": "204af1e1",
"metadata": {},
"source": [
"If you config the value on the widget, please reexecute all of these bottom cells for create a model according to your data.\n",
"\n",
"\n",
"Getting Value from Widget"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8e7c42b1",
"metadata": {},
"outputs": [],
"source": [
"hour_day_employee = hour_day_employee_widget.value\n",
"hour_day_capital_cost = hour_day_capital_cost_widget.value\n",
"use_outlier_removal= use_outlier_removal_widget.value\n",
"outlier_index = float(outlier_index_widget.value)\n",
"use_augmentation = use_augmentation_widget.value\n",
"element_level_lr = float(element_level_lr_widget.value)\n",
"model_level_lr = float(model_level_lr_widget.value)\n",
"use_early_stopping =use_early_stopping_widget.value\n",
"early_stopping_patience = early_stopping_patience_widget.value\n",
"epoch_number = epoch_widget.value"
]
},
{
"cell_type": "markdown",
"id": "842aa666",
"metadata": {},
"source": [
"Generated Cost Matrix"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f7ed24d9",
"metadata": {},
"outputs": [],
"source": [
"folder_path = 'datasets/extended-random'\n",
"output_folder_path = f'result/{model_level_lr}'\n",
"\n",
"cost_generator = cmc.CostMatrixGenerator()\n",
"cost_generator.change_data_directory(folder_path)\n",
"cost_generator.load_data()\n",
"input_variation = diva.display_input_variation_by_directory(folder_path)\n",
"input_variation.to_csv(f\"{folder_path}/data_variation.csv\")\n",
"\n",
"(process_df,employee_usage,material_usage,capital_cost_usage) = cost_generator.get_data()"
]
},
{
"cell_type": "markdown",
"id": "4ea56434",
"metadata": {},
"source": [
"If you want to see the raw data, you can display using `process_df`, `process_df.head()`, `employee_df` and so on."
]
},
{
"cell_type": "markdown",
"id": "3bd65eb3",
"metadata": {},
"source": [
"## Pre-Processing\n",
"djust and filter in input datasets (Material, Employee, Capital Cost) to match the output dataset (Process Dataset) and Depend on Outlier Removal Condition"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cec6dcf7",
"metadata": {},
"outputs": [],
"source": [
"if use_outlier_removal:\n",
" cost_generator.remove_outlier_iqr(outlier_index)\n",
" (\n",
" new_process_df,\n",
" new_employee_usage,\n",
" new_material_usage,\n",
" new_capital_cost_usage,\n",
" ) = cost_generator.get_data()\n",
" (new_capital_cost_usage, new_employee_usage, new_material_usage) = (\n",
" ajd.adjust_to_match_process(\n",
" capital_cost_usage=new_capital_cost_usage,\n",
" employee_usage=new_employee_usage,\n",
" material_usage=new_material_usage,\n",
" new_process_df=new_process_df,\n",
" )\n",
" )\n",
" new_variation = diva.display_input_variation(\n",
" new_process_df,\n",
" new_material_usage,\n",
" new_employee_usage,\n",
" new_capital_cost_usage,\n",
" )\n",
" new_variation.to_csv(f\"{folder_path}/data_variation_after_outlier.csv\")\n",
" new_process_df.to_csv(f\"{folder_path}/process_df_after_outlier.csv\")\n",
" try:\n",
" print(\"Data Variation After Outlier Removed\")\n",
" display(new_variation)\n",
" except Exception as e:\n",
" print(\"This is not Jupyter Notebook\", e)\n",
"else:\n",
" display(input_variation)"
]
},
{
"cell_type": "markdown",
"id": "00976358",
"metadata": {},
"source": [
"### Data Splitting\n",
"Split training and validation dataset"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d1904264",
"metadata": {},
"outputs": [],
"source": [
"(\n",
" train_process_df,\n",
" train_employee_usage,\n",
" train_material_usage,\n",
" train_capital_cost,\n",
" validate_process_df,\n",
" validate_employee_usage,\n",
" validate_material_usage,\n",
" validate_capital_cost,\n",
") = cost_generator.train_test_split_without_matrix(0.7)\n",
"\n",
"\n",
"# Generate Cost Matrix for Validation Set\n",
"validation_payload = cost_generator.get_validation_payload(\n",
" validate_process_df\n",
")\n",
"\n",
"\n",
"# Display Variation of Train Data\n",
"train_variation = diva.display_input_variation(\n",
" train_process_df,\n",
" train_material_usage,\n",
" train_employee_usage,\n",
" train_capital_cost,\n",
")\n",
"train_variation.to_csv(\n",
" f\"{folder_path}/train_data_variation.csv\")\n",
"train_process_df.to_csv(\n",
" f\"{folder_path}/train_process_df.csv\")\n",
"# Display Variation of Validation Data\n",
"validate_variation = diva.display_input_variation(\n",
" validate_process_df,\n",
" validate_material_usage,\n",
" validate_employee_usage,\n",
" validate_capital_cost,\n",
")\n",
"validate_variation.to_csv(\n",
" f\"{folder_path}/validate_data_variation.csv\"\n",
")\n",
"if use_augmentation:\n",
" # TODO: Increase the Generalization of the Model\n",
" # Augmented the Imbalance Class of Training Data\n",
" train_process_df.to_csv(\n",
" f\"{folder_path}/train_process_df_before_augmented.csv\"\n",
" )\n",
" train_process_df = viya.vy_training_augmentation(\n",
" train_process_df)\n",
" # Display Variation of Train Data After Augmented\n",
" train_variation = diva.display_input_variation(\n",
" train_process_df,\n",
" train_material_usage,\n",
" train_employee_usage,\n",
" train_capital_cost,\n",
" )\n",
" train_variation.to_csv(\n",
" f\"{folder_path}/train_data_variation_after_augmented.csv\"\n",
" )\n",
" train_process_df.to_csv(\n",
" f\"{folder_path}/train_process_df_after_augmented_{round}.csv\"\n",
" )\n",
" \n",
"# Generate Matrix From Training Set\n",
"(\n",
" material_cost_matrix,\n",
" material_amount_matrix,\n",
" employee_cost_matrix,\n",
" employee_duration_matrix,\n",
" employee_day_amount_matrix,\n",
" capital_cost_matrix,\n",
" day_amount_matrix,\n",
" capital_cost_duration_matrix, # New On Finetune\n",
" result_matrix,\n",
") = cost_generator.generate_data_from_input(\n",
" train_process_df,\n",
" train_material_usage,\n",
" train_employee_usage,\n",
" train_capital_cost,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "d1bdcbbc",
"metadata": {},
"source": [
"## Initial Model\n",
"\n",
"### Initial Layer\n",
"Create function to initial layer from cost matrix, it will automatically find what the input size is need for due to the data"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2fce43cf",
"metadata": {},
"outputs": [],
"source": [
"def inital_layer(\n",
" material_cost_matrix,\n",
" employee_cost_matrix,\n",
" capital_cost_matrix,\n",
"):\n",
" total_col = 0\n",
" # Material FC Layer\n",
" row, high, col = material_cost_matrix.shape\n",
" material_layer_1 = mfl.MaterialFCLayer(col, 1)\n",
" # material_layer_1.annotate(material_cost_matrix, material_amount_matrix)\n",
" total_col += col\n",
"\n",
" # Monthy Employee FC Layer\n",
" row, high, col = employee_cost_matrix.shape\n",
" employee_layer_1 = efl.EmployeeFCLayer(col, 1, 8)\n",
" total_col += col\n",
" # monthy_employee_layer_1.annotate(monthy_employee_cost_matrix, duration_matrix)\n",
"\n",
" # Capital Cost FC Layer\n",
" row, high, col = capital_cost_matrix.shape\n",
" capital_cost_layer1 = cfl.CapitalCostFCLayer(col, 1, 21)\n",
" total_col += col\n",
" # capital_cost_layer1.annotate(\n",
" # capital_cost_matrix, life_time_matrix, machine_hour_matrix, duration_matrix)\n",
"\n",
" return (\n",
" material_layer_1,\n",
" employee_layer_1,\n",
" capital_cost_layer1,\n",
" )\n"
]
},
{
"cell_type": "markdown",
"id": "662b0bd2",
"metadata": {},
"source": [
"### Model Initialization\n",
"Create the model object from its class"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "53684466",
"metadata": {},
"outputs": [],
"source": [
"# Initial Model\n",
"tdce_model = tdce.TDCEModel()\n",
" \n",
"# Create the Layer\n",
"(\n",
" material_layer_1,\n",
" employee_layer_1,\n",
" capital_cost_layer1,\n",
") = inital_layer(\n",
" capital_cost_matrix=capital_cost_matrix,\n",
" employee_cost_matrix=employee_cost_matrix,\n",
" material_cost_matrix=material_cost_matrix,\n",
")\n",
"\n",
"# Add the Layer to the Model\n",
"tdce_model.inital_inside_element(\n",
" material_layer=material_layer_1,\n",
" capital_cost_layer=capital_cost_layer1,\n",
" employee_layer=employee_layer_1,\n",
")\n",
"\n",
"# Install the error calculator\n",
"tdce_model.use(loss=loss.mse, loss_prime=loss.mse_prime,\n",
" loss_percent=loss.rmspe)\n",
"\n",
"# Set Early Stopping\n",
"if use_early_stopping:\n",
" tdce_model.activate_early_stopping()\n",
" tdce_model.edit_patience_round(early_stopping_patience)"
]
},
{
"cell_type": "markdown",
"id": "df6d4796",
"metadata": {},
"source": [
"Setting the learning rate"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b75da97b",
"metadata": {},
"outputs": [],
"source": [
"# Use the same learning rate for all element level\n",
"tdce_model.set_learning_rate(\n",
" element_level_lr,element_level_lr,element_level_lr\n",
")\n",
"\n",
"# activate model weight\n",
"tdce_model.activete_model_weight()"
]
},
{
"cell_type": "markdown",
"id": "38df7ced",
"metadata": {},
"source": [
"## Training\n",
"\n",
"Fit a model with input and output data"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2fe52d20",
"metadata": {},
"outputs": [],
"source": [
"start_time = time.time()\n",
"\n",
"tdce_model.fit_with_validation(\n",
" epoch=epoch_number,\n",
" learning_rate=model_level_lr,\n",
" material_amount_matrix=material_amount_matrix,\n",
" material_cost_matrix=material_cost_matrix,\n",
" employee_cost_matrix=employee_cost_matrix,\n",
" employee_duration_matrix=employee_duration_matrix,\n",
" employee_day_amount_matrix=employee_day_amount_matrix,\n",
" result_matrix=result_matrix,\n",
" capital_cost_matrix=capital_cost_matrix,\n",
" day_amount_matrix=day_amount_matrix,\n",
" validation_payload=validation_payload,\n",
" capital_cost_duration_matrix=capital_cost_duration_matrix,\n",
" )\n",
"\n",
"end_time = time.time()\n",
"time_usage = end_time - start_time\n",
"print(f\"Learning Rate: {model_level_lr} / {element_level_lr}\")\n",
"print(f\"Time Using {time_usage} Second\")\n"
]
},
{
"cell_type": "markdown",
"id": "39b9aa25",
"metadata": {},
"source": [
"Get the Error Listing"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7fa00c92",
"metadata": {},
"outputs": [],
"source": [
"try:\n",
" os.mkdir(f\"{output_folder_path}\")\n",
"except FileExistsError:\n",
" print(\"Folder is Exist\")\n",
" pass"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8861bedb",
"metadata": {},
"outputs": [],
"source": [
"error_list = tdce_model.get_epoch_error()\n",
"sample_error_list = tdce_model.get_sample_error()\n",
"error_df = pd.DataFrame(error_list)\n",
"sample_error_df = pd.DataFrame(sample_error_list)\n",
"\n",
"\n",
"# Get Overall Output\n",
"minimum_error = error_df[\"error\"].min()\n",
"minimum_percent_error = error_df[\"error_percent\"].min()\n",
"minimum_validate_error = error_df[\"validate_error\"].min()\n",
"minimum_validate_percent_error = error_df[\"validate_error_percent\"].min()\n",
"\n",
"# Export the Output Result\n",
"error_df.to_csv(f\"{output_folder_path}/{epoch_number}-{element_level_lr}.csv\")\n",
"sample_error_df.to_csv(\n",
" f\"{output_folder_path}/error-list-{epoch_number}-{element_level_lr}.csv\"\n",
")\n",
"sample_payload = tdce_model.get_sample_payload()\n",
"sample_payload_df = pd.DataFrame(sample_payload)\n",
"\n",
"# Export all the sample / history of all training\n",
"sample_payload_df.to_csv(\n",
" f\"{output_folder_path}/sample-payload-list-{epoch_number}-{element_level_lr}.csv\",\n",
" index=False,\n",
")\n",
"\n",
"print(f\"Minimum Error: {minimum_error}\"\n",
" f\" / Minimum Percent Error (RMSPE): {minimum_percent_error}\"\n",
" f\" / Minimum Validate Error: {minimum_validate_error}\"\n",
" f\" / Minimum Validate Percent Error (RMSEP): {minimum_validate_percent_error}\")\n"
]
},
{
"cell_type": "markdown",
"id": "639b9b91",
"metadata": {},
"source": [
"## Visualization\n",
"\n",
"### Error Behavior\n",
"Display the model training behavior"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dc3bdc9d",
"metadata": {},
"outputs": [],
"source": [
"mp.plotting_learning_curve(epoch_error=error_df,element_learning_rate=element_level_lr,\n",
" model_learning_rate=model_level_lr)"
]
},
{
"cell_type": "markdown",
"id": "0c101da0",
"metadata": {},
"source": [
"### Weight Adjustment Behavior\n",
"Display the Weight of Each Model Element"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bbd09ca5",
"metadata": {},
"outputs": [],
"source": [
"importlib.reload(mp)\n",
"mp.plot_model_level_weight(adjustment_data=sample_payload_df,epoch_error=error_df)"
]
},
{
"cell_type": "markdown",
"id": "3a99ea9c",
"metadata": {},
"source": [
"Display the weight of each material, labor, and utility cost object."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "283c58fe",
"metadata": {},
"outputs": [],
"source": [
"material_columns = [col for col in sample_payload_df.columns if col.startswith('material_weight_')]\n",
"employee_columns = [col for col in sample_payload_df.columns if col.startswith('employee_weight_')]\n",
"capital_columns = [col for col in sample_payload_df.columns if col.startswith('capital_cost_weight_')]\n",
"\n",
"\n",
"importlib.reload(mp)\n",
"mp.plot_element_level_weight(\n",
" adjustment_data=sample_payload_df,\n",
" material_columns=material_columns,labor_columns= employee_columns,\n",
" utility_columns= capital_columns)"
]
},
{
"cell_type": "markdown",
"id": "d6cc2707",
"metadata": {},
"source": [
"## Export Model\n",
"Export Model to keep and use in another place"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "74b2f7e2",
"metadata": {},
"outputs": [],
"source": [
"tdce_model.export_model(\"tdce_model.pkl\")"
]
},
{
"cell_type": "markdown",
"id": "dce151ec",
"metadata": {},
"source": [
"© 2025, Intelligent Automation Engineering Center, Prince of Songkla University"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|