{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "62252039-37f7-467f-bde2-0a576770d4be",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e9f9088b-aab7-4faf-a158-5b6e51d1b1bc",
   "metadata": {},
   "outputs": [],
   "source": [
    "features = [\n",
    "    # \"batting_team\",\n",
    "    # \"bowling_team\",\n",
    "    # \"balls\",\n",
    "    # \"runs\",\n",
    "    # \"wickets\",\n",
    "    \"wkt_last_5_overs\",\n",
    "    # \"runrate_last_5_overs\",\n",
    "    \"current_RR\",\n",
    "    # \"average\",\n",
    "    \"balls_left\",\n",
    "    \"wkts_left\",\n",
    "    # \"required_RR\",\n",
    "    # \"projected_score_more\",\n",
    "    # \"min_score_more\",\n",
    "    # \"max_score_more\",\n",
    "    # \"projected_avg_score_more\",\n",
    "    \"runrate_last_5_overs-current_RR\",\n",
    "    \"deviation_from_projected\",\n",
    "]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7694e380-b6d3-4d56-af94-66f5233e6c49",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/media/instantinopaul/data/Code/ML/github.com/scorepredictor/env/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from ydata_profiling import ProfileReport"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4845035c-3501-4eb0-a67b-0bbc5e289a8b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/media/instantinopaul/data/Code/ML/github.com/scorepredictor/env/lib/python3.10/site-packages/ydata_profiling/utils/dataframe.py:137: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  df.rename(columns={\"index\": \"df_index\"}, inplace=True)\n",
      "Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]/media/instantinopaul/data/Code/ML/github.com/scorepredictor/env/lib/python3.10/site-packages/ydata_profiling/model/typeset.py:125: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
      "  not pdt.is_categorical_dtype(series)\n",
      "Summarize dataset: 100%|██████████| 51/51 [00:11<00:00,  4.50it/s, Completed]                                                               \n",
      "Generate report structure: 100%|██████████| 1/1 [00:02<00:00,  2.68s/it]\n",
      "Render HTML: 100%|██████████| 1/1 [00:01<00:00,  1.43s/it]\n",
      "Export report to file: 100%|██████████| 1/1 [00:00<00:00, 210.06it/s]\n"
     ]
    }
   ],
   "source": [
    "df=pd.read_feather('data/t20features.feather')\n",
    "r=ProfileReport(df[features])\n",
    "r.to_file('result/profilereportT20.html')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1272e5c3-2a60-4966-b70a-43f49101a5a9",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/media/instantinopaul/data/Code/ML/github.com/scorepredictor/env/lib/python3.10/site-packages/ydata_profiling/utils/dataframe.py:137: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  df.rename(columns={\"index\": \"df_index\"}, inplace=True)\n",
      "Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]/media/instantinopaul/data/Code/ML/github.com/scorepredictor/env/lib/python3.10/site-packages/ydata_profiling/model/typeset.py:208: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
      "  is_valid_dtype = pdt.is_categorical_dtype(series) and not pdt.is_bool_dtype(\n",
      "Summarize dataset: 100%|██████████| 51/51 [00:07<00:00,  7.05it/s, Completed]                                                               \n",
      "Generate report structure: 100%|██████████| 1/1 [00:02<00:00,  2.76s/it]\n",
      "Render HTML: 100%|██████████| 1/1 [00:01<00:00,  1.32s/it]\n",
      "Export report to file: 100%|██████████| 1/1 [00:00<00:00, 121.46it/s]\n"
     ]
    }
   ],
   "source": [
    "df=pd.read_feather('data/odifeatures.feather')\n",
    "r=ProfileReport(df[features])\n",
    "r.to_file('result/profilereportODI.html')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e55fd847-05c8-47dc-aedc-9b96c23b4aa6",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "cricpred",
   "language": "python",
   "name": "cricpred"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}