{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.005268,
     "end_time": "2021-03-21T01:43:26.398126",
     "exception": false,
     "start_time": "2021-03-21T01:43:26.392858",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Credit of this notebook goes entirely to below public notebook, kindly upvote and appreciate the original author\n",
    "\n",
    "* https://www.kaggle.com/muhammad4hmed/lets-overfit-together"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2021-03-21T01:43:26.411073Z",
     "iopub.status.busy": "2021-03-21T01:43:26.410014Z",
     "iopub.status.idle": "2021-03-21T01:43:26.414755Z",
     "shell.execute_reply": "2021-03-21T01:43:26.415196Z"
    },
    "papermill": {
     "duration": 0.012965,
     "end_time": "2021-03-21T01:43:26.415505",
     "exception": false,
     "start_time": "2021-03-21T01:43:26.402540",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "\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",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-03-21T01:43:26.427333Z",
     "iopub.status.busy": "2021-03-21T01:43:26.426414Z",
     "iopub.status.idle": "2021-03-21T01:43:26.475008Z",
     "shell.execute_reply": "2021-03-21T01:43:26.475504Z"
    },
    "papermill": {
     "duration": 0.055753,
     "end_time": "2021-03-21T01:43:26.475682",
     "exception": false,
     "start_time": "2021-03-21T01:43:26.419929",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>image_id</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>002a34c58c5b758217ed1f584ccbcfe9</td>\n",
       "      <td>0.013326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>004f33259ee4aef671c2b95d54e4be68</td>\n",
       "      <td>0.037235</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>008bdde2af2462e86fd373a445d0f4cd</td>\n",
       "      <td>0.939700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>009bc039326338823ca3aa84381f17f1</td>\n",
       "      <td>0.123799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>00a2145de1886cb9eb88869c85d74080</td>\n",
       "      <td>0.654006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2995</th>\n",
       "      <td>ff91fb82429a27521bbec8569b041f02</td>\n",
       "      <td>0.936325</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2996</th>\n",
       "      <td>ff9fcc4087ed5e941209aa3fa948e364</td>\n",
       "      <td>0.963583</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2997</th>\n",
       "      <td>ffaa288c8abca300974f043b57d81521</td>\n",
       "      <td>0.178720</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2998</th>\n",
       "      <td>ffc441e0c8b7153844047483a577e7c3</td>\n",
       "      <td>0.225196</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2999</th>\n",
       "      <td>ffccf1709d0081d122a1d1f9edbefdf1</td>\n",
       "      <td>0.987406</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                              image_id    target\n",
       "0     002a34c58c5b758217ed1f584ccbcfe9  0.013326\n",
       "1     004f33259ee4aef671c2b95d54e4be68  0.037235\n",
       "2     008bdde2af2462e86fd373a445d0f4cd  0.939700\n",
       "3     009bc039326338823ca3aa84381f17f1  0.123799\n",
       "4     00a2145de1886cb9eb88869c85d74080  0.654006\n",
       "...                                ...       ...\n",
       "2995  ff91fb82429a27521bbec8569b041f02  0.936325\n",
       "2996  ff9fcc4087ed5e941209aa3fa948e364  0.963583\n",
       "2997  ffaa288c8abca300974f043b57d81521  0.178720\n",
       "2998  ffc441e0c8b7153844047483a577e7c3  0.225196\n",
       "2999  ffccf1709d0081d122a1d1f9edbefdf1  0.987406\n",
       "\n",
       "[3000 rows x 2 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred_2class = pd.read_csv(\"../input/vinbigdata-2class-prediction/2-cls test pred.csv\")\n",
    "low_threshold = 0.0\n",
    "high_threshold = 0.90\n",
    "pred_2class"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.004459,
     "end_time": "2021-03-21T01:43:26.485337",
     "exception": false,
     "start_time": "2021-03-21T01:43:26.480878",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Apply 2class filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-03-21T01:43:26.504745Z",
     "iopub.status.busy": "2021-03-21T01:43:26.503972Z",
     "iopub.status.idle": "2021-03-21T01:43:27.617091Z",
     "shell.execute_reply": "2021-03-21T01:43:27.616495Z"
    },
    "papermill": {
     "duration": 1.127304,
     "end_time": "2021-03-21T01:43:27.617254",
     "exception": false,
     "start_time": "2021-03-21T01:43:26.489950",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "n_normal: 1586 -> 1974 with threshold 0.0 & 0.9\n",
      "Keep 0 Add 1026 Replace 1974\n",
      "Saved to submission.csv\n"
     ]
    }
   ],
   "source": [
    "NORMAL = \"14 1 0 0 1 1\"\n",
    "\n",
    "pred_det_df = pd.read_csv(\"../input/vinbigdatastack/submission_postprocessed.csv\")\n",
    "n_normal_before = len(pred_det_df.query(\"PredictionString == @NORMAL\"))\n",
    "merged_df = pd.merge(pred_det_df, pred_2class, on=\"image_id\", how=\"left\")\n",
    "\n",
    "\n",
    "if \"target\" in merged_df.columns:\n",
    "    merged_df[\"class0\"] = 1 - merged_df[\"target\"]\n",
    "\n",
    "c0, c1, c2 = 0, 0, 0\n",
    "for i in range(len(merged_df)):\n",
    "    p0 = merged_df.loc[i, \"class0\"]\n",
    "    if p0 < low_threshold:\n",
    "\n",
    "        c0 += 1\n",
    "    elif low_threshold <= p0 and p0 < high_threshold:\n",
    "\n",
    "        merged_df.loc[i, \"PredictionString\"] += f\" 14 {p0} 0 0 1 1\"\n",
    "        c1 += 1\n",
    "    else:\n",
    "\n",
    "        merged_df.loc[i, \"PredictionString\"] = NORMAL\n",
    "        c2 += 1\n",
    "\n",
    "n_normal_after = len(merged_df.query(\"PredictionString == @NORMAL\"))\n",
    "print(\n",
    "    f\"n_normal: {n_normal_before} -> {n_normal_after} with threshold {low_threshold} & {high_threshold}\"\n",
    ")\n",
    "print(f\"Keep {c0} Add {c1} Replace {c2}\")\n",
    "submission_filepath = str(\"submission.csv\")\n",
    "submission_df = merged_df[[\"image_id\", \"PredictionString\"]]\n",
    "submission_df.to_csv(submission_filepath, index=False)\n",
    "print(f\"Saved to {submission_filepath}\")\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.9"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 7.332473,
   "end_time": "2021-03-21T01:43:28.131726",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2021-03-21T01:43:20.799253",
   "version": "2.2.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}