{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2023-06-06T16:12:56.482001Z",
     "iopub.status.busy": "2023-06-06T16:12:56.481629Z",
     "iopub.status.idle": "2023-06-06T16:12:56.511919Z",
     "shell.execute_reply": "2023-06-06T16:12:56.510864Z",
     "shell.execute_reply.started": "2023-06-06T16:12:56.481922Z"
    },
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
    "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
    "# For example, here's several helpful packages to load\n",
    "\n",
    "#import numpy as np # linear algebra\n",
    "#import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "\n",
    "# Input data files are available in the read-only \"../input/\" directory\n",
    "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
    "\n",
    "#import os\n",
    "#for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "#    for filename in filenames:\n",
    "#        print(os.path.join(dirname, filename))\n",
    "\n",
    "# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
    "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#|default_exp app"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "\n",
    "import pathlib\n",
    "temp = pathlib.PosixPath\n",
    "pathlib.PosixPath = pathlib.WindowsPath"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:12:56.515330Z",
     "iopub.status.busy": "2023-06-06T16:12:56.514653Z",
     "iopub.status.idle": "2023-06-06T16:13:17.032978Z",
     "shell.execute_reply": "2023-06-06T16:13:17.031623Z",
     "shell.execute_reply.started": "2023-06-06T16:12:56.515291Z"
    },
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "#|export\n",
    "\n",
    "import fastbook\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import os \n",
    "\n",
    "from fastbook import *\n",
    "from fastai.vision.widgets import *\n",
    "import gradio as gr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "im = PILImage.create('plume1.png')\n",
    "im.thumbnail((182,192))\n",
    "im"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:13:17.047225Z",
     "iopub.status.busy": "2023-06-06T16:13:17.046261Z",
     "iopub.status.idle": "2023-06-06T16:13:17.053274Z",
     "shell.execute_reply": "2023-06-06T16:13:17.052116Z",
     "shell.execute_reply.started": "2023-06-06T16:13:17.047171Z"
    }
   },
   "outputs": [],
   "source": [
    "path = Path('/kaggle/input/speuntapped/train')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:13:17.058708Z",
     "iopub.status.busy": "2023-06-06T16:13:17.057847Z",
     "iopub.status.idle": "2023-06-06T16:13:20.265898Z",
     "shell.execute_reply": "2023-06-06T16:13:20.264895Z",
     "shell.execute_reply.started": "2023-06-06T16:13:17.058670Z"
    }
   },
   "outputs": [],
   "source": [
    "fns = get_image_files(path)\n",
    "fns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:13:20.269200Z",
     "iopub.status.busy": "2023-06-06T16:13:20.267211Z",
     "iopub.status.idle": "2023-06-06T16:13:20.276861Z",
     "shell.execute_reply": "2023-06-06T16:13:20.275708Z",
     "shell.execute_reply.started": "2023-06-06T16:13:20.269168Z"
    }
   },
   "outputs": [],
   "source": [
    "plume = DataBlock(\n",
    "    blocks=(ImageBlock, CategoryBlock),\n",
    "    get_items=get_image_files,\n",
    "    splitter=RandomSplitter(valid_pct=0.2,seed=42),\n",
    "    get_y=parent_label\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:13:20.279400Z",
     "iopub.status.busy": "2023-06-06T16:13:20.279013Z",
     "iopub.status.idle": "2023-06-06T16:13:20.294720Z",
     "shell.execute_reply": "2023-06-06T16:13:20.293498Z",
     "shell.execute_reply.started": "2023-06-06T16:13:20.279361Z"
    }
   },
   "outputs": [],
   "source": [
    "plume = plume.new(\n",
    "    item_tfms=RandomResizedCrop(152, min_scale=0.5),\n",
    "    batch_tfms=aug_transforms()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:13:20.296793Z",
     "iopub.status.busy": "2023-06-06T16:13:20.296142Z",
     "iopub.status.idle": "2023-06-06T16:13:29.647446Z",
     "shell.execute_reply": "2023-06-06T16:13:29.646201Z",
     "shell.execute_reply.started": "2023-06-06T16:13:20.296747Z"
    }
   },
   "outputs": [],
   "source": [
    "dls = plume.dataloaders(path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:13:29.649289Z",
     "iopub.status.busy": "2023-06-06T16:13:29.648894Z",
     "iopub.status.idle": "2023-06-06T16:13:30.941482Z",
     "shell.execute_reply": "2023-06-06T16:13:30.940546Z",
     "shell.execute_reply.started": "2023-06-06T16:13:29.649249Z"
    }
   },
   "outputs": [],
   "source": [
    "dls.valid.show_batch(max_n=12, nrows=4) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:13:30.942995Z",
     "iopub.status.busy": "2023-06-06T16:13:30.942633Z",
     "iopub.status.idle": "2023-06-06T16:16:55.896473Z",
     "shell.execute_reply": "2023-06-06T16:16:55.895239Z",
     "shell.execute_reply.started": "2023-06-06T16:13:30.942955Z"
    }
   },
   "outputs": [],
   "source": [
    "learn = vision_learner(dls, resnet50, metrics=error_rate)\n",
    "learn.fine_tune(epochs=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:16:55.899023Z",
     "iopub.status.busy": "2023-06-06T16:16:55.898611Z",
     "iopub.status.idle": "2023-06-06T16:17:12.173908Z",
     "shell.execute_reply": "2023-06-06T16:17:12.172400Z",
     "shell.execute_reply.started": "2023-06-06T16:16:55.898975Z"
    }
   },
   "outputs": [],
   "source": [
    "from IPython.core.pylabtools import figsize \n",
    "interp = ClassificationInterpretation.from_learner(learn)\n",
    "interp.plot_confusion_matrix(figsize=(10,10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:17:12.177922Z",
     "iopub.status.busy": "2023-06-06T16:17:12.177508Z",
     "iopub.status.idle": "2023-06-06T16:17:13.734058Z",
     "shell.execute_reply": "2023-06-06T16:17:13.732857Z",
     "shell.execute_reply.started": "2023-06-06T16:17:12.177864Z"
    }
   },
   "outputs": [],
   "source": [
    "interp.plot_top_losses(20, nrows=10, figsize=(20,20))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:17:13.739200Z",
     "iopub.status.busy": "2023-06-06T16:17:13.735848Z",
     "iopub.status.idle": "2023-06-06T16:17:13.744700Z",
     "shell.execute_reply": "2023-06-06T16:17:13.743507Z",
     "shell.execute_reply.started": "2023-06-06T16:17:13.739151Z"
    }
   },
   "outputs": [],
   "source": [
    "test_image = '/kaggle/input/speuntapped/test/test/ang20190922t192642-4_r4928_c373-plume.png'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:17:13.750250Z",
     "iopub.status.busy": "2023-06-06T16:17:13.749605Z",
     "iopub.status.idle": "2023-06-06T16:17:13.883090Z",
     "shell.execute_reply": "2023-06-06T16:17:13.881894Z",
     "shell.execute_reply.started": "2023-06-06T16:17:13.750206Z"
    }
   },
   "outputs": [],
   "source": [
    "is_plume,_,probs = learn.predict(PILImage.create(test_image))\n",
    "print(f\"This is a: {is_plume}.\")\n",
    "print(f\"Probability it's a plume: {probs[1]:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-06T16:22:39.764768Z",
     "iopub.status.busy": "2023-06-06T16:22:39.764285Z",
     "iopub.status.idle": "2023-06-06T16:22:40.137875Z",
     "shell.execute_reply": "2023-06-06T16:22:40.136697Z",
     "shell.execute_reply.started": "2023-06-06T16:22:39.764726Z"
    }
   },
   "outputs": [],
   "source": [
    "learn.export('methane plume detect.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "learn = load_learner('methane plume detect.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn.predict(im)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "\n",
    "categories = ('No Plume', 'Plume')\n",
    "\n",
    "def classify_image(img):\n",
    "    pred, idx, probs = learn.predict(img)\n",
    "    return dict(zip(categories, map(float, probs)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "classify_image(im)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "\n",
    "image = gr.inputs.Image(shape = (152, 152))\n",
    "label = gr.outputs.Label()\n",
    "examples = ['plume1.png', 'plume2.png', 'noplume1.png', 'noplume2.png']\n",
    "\n",
    "intf = gr.Interface(fn = classify_image, inputs = image, outputs = label, examples = examples)\n",
    "intf.launch(inline = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import nbdev\n",
    "nbdev.export.nb_export('methane-plume-classification-yes-or-no.ipynb')\n",
    "print('Export successful')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}