GW_Performance.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert_minutes(val):\n",
    "    if val > 10:\n",
    "        return 1\n",
    "    else:\n",
    "        return 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from Feature_engineering import convert_minutes\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score, mean_squared_error, f1_score\n",
    "\n",
    "def load_and_prepare_results(gameweek):\n",
    "    \"\"\"\n",
    "    Load results for a specific gameweek, converting minutes using the convert_minutes function.\n",
    "    \"\"\"\n",
    "    results_path = f\"C:\\\\Users\\\\prane\\\\Downloads\\\\FPL\\\\GW_PointsPredictor\\\\Default_data\\\\2023-24\\\\results\\\\GW{gameweek}.csv\"\n",
    "    results = pd.read_csv(results_path)\n",
    "    results[\"minutes_actual\"] = results[\"minutes\"].apply(convert_minutes)\n",
    "    return results\n",
    "\n",
    "def load_predicted_data(position, gameweek, data_type):\n",
    "    \"\"\"\n",
    "    Load predicted minutes or points data for a given position and gameweek.\n",
    "    \"\"\"\n",
    "    file_path = f\"C:\\\\Users\\\\prane\\\\Downloads\\\\FPL\\\\GW_PointsPredictor\\\\Predicted_outcomes\\\\GW{gameweek}\\\\{position}_{data_type}.csv\"\n",
    "    return pd.read_csv(file_path)\n",
    "\n",
    "def merge_and_clean_data(predicted_df, results_df):\n",
    "    \"\"\"\n",
    "    Merge predicted data with actual results and remove rows with missing values.\n",
    "    \"\"\"\n",
    "    merged_df = pd.merge(predicted_df, results_df, on=\"name\", how=\"left\").dropna()\n",
    "    return merged_df\n",
    "\n",
    "def evaluate_predictions(predictions_df, actual_column, predicted_column):\n",
    "    \"\"\"\n",
    "    Calculate and print evaluation metrics for the predictions.\n",
    "    \"\"\"\n",
    "    print(confusion_matrix(predictions_df[actual_column], predictions_df[predicted_column]))\n",
    "    print(\"Accuracy score:\", accuracy_score(predictions_df[actual_column], predictions_df[predicted_column]))\n",
    "    print(\"F1 SCORE:\", f1_score(predictions_df[actual_column], predictions_df[predicted_column]))\n",
    "    rmse = np.sqrt(mean_squared_error(predictions_df[actual_column], predictions_df[predicted_column]))\n",
    "    print(f\"Root Mean Square Error: {rmse}\")\n",
    "\n",
    "def process_position(position, gameweek, results):\n",
    "    \"\"\"\n",
    "    Process and evaluate predictions for a given position (goalkeepers, defenders, midfielders, fowards).\n",
    "    \"\"\"\n",
    "    print(f\"\\n{position.upper()}\")\n",
    "    for data_type in [\"minutes\", \"points\"]:\n",
    "        predicted_data = load_predicted_data(position, gameweek, data_type)\n",
    "        if data_type == \"minutes\":\n",
    "            merged_data = merge_and_clean_data(predicted_data, results[[\"name\", \"minutes_actual\"]])\n",
    "        else:\n",
    "            merged_data = merge_and_clean_data(predicted_data, results[[\"name\", \"minutes_actual\", \"total_points\"]])\n",
    "        \n",
    "        evaluate_predictions(merged_data, \"minutes_actual\" if data_type == \"minutes\" else \"total_points\", data_type)\n",
    "\n",
    "gameweek = 26\n",
    "for i in range(1, gameweek + 1):\n",
    "    results = load_and_prepare_results(i)\n",
    "    \n",
    "    print(f\"\\n\\nGAMEWEEK {i}\")\n",
    "    for position in [\"goalkeepers\", \"defenders\", \"midfielders\", \"fowards\"]:\n",
    "        process_position(position, i, results)\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": "3.10.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}