adding codes

FIFA Moneyball/deliverable/.ipynb_checkpoints/FIFA_Project-checkpoint.ipynb

@@ -0,0 +1,348 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "kQvYkx3jmwdV"
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn import linear_model\n",
+    "from sklearn.preprocessing import StandardScaler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "oF9NZcRpnZG5"
+   },
+   "outputs": [],
+   "source": [
+    "players_fifa = pd.read_csv('Fifa 23 Players Data Final.csv')\n",
+    "\n",
+    "players = players_fifa[['Full Name', 'Overall', 'Potential', 'Value',\n",
+    "       'Positions Played','Best Position', 'Nationality', 'Age','Club Name', 'Wage', 'Release Clause', 'Club Position',\n",
+    "       'Contract Until']]\n",
+    "\n",
+    "#We create a subset with only the players that play for Real Madrid, so we can analize our team\n",
+    "\n",
+    "Real_Madrid = players[players['Club Name'] == 'Real Madrid CF']\n",
+    "Real_Madrid"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 237
+    },
+    "id": "jC7_yA10nyS8",
+    "outputId": "f6aae012-45d0-463c-c612-0128fd402811"
+   },
+   "outputs": [],
+   "source": [
+    "#We decided to sell our oldest players, so we filter our Real_Madrid DataFrame to find the players who are older than 30.\n",
+    "Real_Madrid[Real_Madrid['Age'] > 30]\n",
+    "\n",
+    "#We also take a look at their wages.\n",
+    "Real_Madrid[['Full Name', 'Wage']].sort_values(by='Wage', ascending= False).head(7)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "poJvQLrCMs-x"
+   },
+   "outputs": [],
+   "source": [
+    "#We start the search of our now players, filterting the dataset with the following conditions and we save the result in a new DataFrame.\n",
+    "\n",
+    "possible_transfers = players[players['Positions Played'].isin(['LW', 'LW,CAM','LW,LM','LW,ST']) & (players['Age'] < 25) & (players['Age'] > 20) & (players['Potential'] >= 85)]\n",
+    "\n",
+    "#Since we only want to analize the top 10 players, we update our DataFrame with only the top 10 players.\n",
+    "\n",
+    "possible_transfers = possible_transfers.head(10)\n",
+    "\n",
+    "#We create a new column called 'Transfer Index' where we can see how good the pontential of each player is compare to their Release Clause\n",
+    "\n",
+    "possible_transfers['Transfer Index'] = possible_transfers['Potential'] / possible_transfers['Release Clause']\n",
+    "\n",
+    "#We sort the data by this index and we pick the first player.\n",
+    "\n",
+    "possible_transfers.sort_values(by='Transfer Index', ascending = False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "Lq8bPexqnVlY",
+    "outputId": "57e257b7-0ea4-4a13-b81b-e00779ebaee2"
+   },
+   "outputs": [],
+   "source": [
+    "# Select the feature columns from the 'players' DataFrame\n",
+    "X = players[['Overall', 'Potential', 'Value', 'Age', 'Release Clause']]\n",
+    "\n",
+    "# Create a StandardScaler to standardize the feature data\n",
+    "scaler = StandardScaler()\n",
+    "\n",
+    "# Standardize the feature data using the StandardScaler\n",
+    "X_standardized = scaler.fit_transform(X)\n",
+    "\n",
+    "# Select the data for the player named 'Kvaratskhelia'\n",
+    "Kvaratskhelia = X_standardized[1284]\n",
+    "\n",
+    "# Reshape the 'Kvaratskhelia' data to match the shape of the other data\n",
+    "Kvaratskhelia = pd.DataFrame(Kvaratskhelia).transpose()\n",
+    "\n",
+    "# Remove the 'Kvaratskhelia' data from the standardized feature matrix\n",
+    "X_standardized = np.delete(X_standardized, 1284, axis=0)\n",
+    "\n",
+    "# Select the target column 'Wage' from the 'players' DataFrame\n",
+    "y = players[['Wage']]\n",
+    "\n",
+    "# Remove the 'Kvaratskhelia' row from the target data\n",
+    "y = y.drop(1284)\n",
+    "\n",
+    "# Create a Linear Regression model\n",
+    "model = linear_model.LinearRegression()\n",
+    "\n",
+    "# Fit the Linear Regression model to the standardized features and target\n",
+    "result = model.fit(X_standardized, y)\n",
+    "\n",
+    "#Finally we predict the wage of our player\n",
+    "predicted_wage = model.predict(Kvaratskhelia)\n",
+    "\n",
+    "print(predicted_wage)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Pick players for CM positions according to expected conditions\n",
+    "fifa_data_performance_CM = players_fifa[(players_fifa['Overall' ]>85) & (players_fifa['Age' ]<28) & (players_fifa['Club Name'] !='Real Madrid CF')&(players_fifa['Best Position']=='CM')]\n",
+    "fifa_data_performance_CM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Data with more related columns\n",
+    "CM_selected = fifa_data_performance_CM[['Full Name','CM Rating',\"Passing Total\", \"Dribbling Total\", \"Defending Total\", \"Physicality Total\", \"Short Passing\", \"BallControl\", \"Vision\", \"Stamina\", \"Interceptions\", \"Positioning\"]]\n",
+    "\n",
+    "numeric_data = CM_selected.select_dtypes(include='number').corr()\n",
+    "plt.figure(figsize=(20, 5))\n",
+    "sns.heatmap(numeric_data,annot=True, cmap='viridis', fmt='.2f')\n",
+    "plt.title('Correlation Heatmap')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Data with more refined skills from previous findings above\n",
+    "CM_selected_second = fifa_data_performance_CM[['Full Name','CM Rating',\"Passing Total\", \"Dribbling Total\", \"Short Passing\",'BallControl', \"Vision\", \"Interceptions\"]]\n",
+    "\n",
+    "numeric_data_second = CM_selected_second.select_dtypes(include='number').corr()\n",
+    "plt.figure(figsize=(20, 5))\n",
+    "sns.heatmap(numeric_data_second,annot=True, cmap='viridis', fmt='.2f')\n",
+    "plt.title('Correlation Heatmap')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Display results by ordered price per performance ratio\n",
+    " \n",
+    "CM_selected_second['Total CM skills'] = CM_selected[\"Passing Total\"]+ CM_selected[\"Dribbling Total\"]+ CM_selected [\"Short Passing\"] + CM_selected['BallControl'] + CM_selected[\"Vision\"] + CM_selected[\"Interceptions\"]\n",
+    "CM_selected_second[\"Release Clause\"] = fifa_data_performance_CM[\"Release Clause\"]\n",
+    "CM_selected_second['Release Clause/Total CM skills'] = CM_selected_second['Release Clause']/CM_selected_second['Total CM skills']\n",
+    "sorted_CM = CM_selected_second.sort_values(by='Release Clause/Total CM skills')\n",
+    "display(sorted_CM)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Top three players\n",
+    "sorted_CM.head(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Predicted Wage for our player choice\n",
+    "X = players_fifa[['Overall','Potential','Value','Age','Release Clause']]\n",
+    "scaler = StandardScaler()\n",
+    "X_standardized = scaler.fit_transform(X)\n",
+    "Sergej  = X_standardized[64]\n",
+    "Sergej  = pd.DataFrame(Sergej).transpose()\n",
+    "X_standardized = np.delete(X_standardized, 64, axis=0)\n",
+    "y = players_fifa[['Wage']]\n",
+    "y = y.drop(64)\n",
+    "model = linear_model.LinearRegression()\n",
+    "result = model.fit(X_standardized,y)\n",
+    "# display(result.intercept_)\n",
+    "# display(result.coef_)\n",
+    "print(result.score(X_standardized,y))\n",
+    "predicted_wage = model.predict(Sergej)\n",
+    "print(predicted_wage)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Checking the end of contract day\n",
+    "sorted_CM[\"Contract Until\"] = fifa_data_performance_CM[\"Contract Until\"]\n",
+    "sorted_CM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Pick players for ST position with expected conditions\n",
+    "fifa_data_ST = players_fifa[(players_fifa['Age'] < 25) &\n",
+    "                            (players_fifa['Overall'] > 70) &\n",
+    "                            (players_fifa['Overall'] < 90) &\n",
+    "                            (players_fifa['Positions Played'].isin (['ST','CF,ST','ST,LW','RW,ST']))]\n",
+    "\n",
+    "\n",
+    "fifa_data_ST"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Filter out data with necessary columns for ST position\n",
+    "filter_ST = players_fifa[['Full Name', 'ST Rating', \"Passing Total\", \"Dribbling Total\", \"Shooting Total\", \"Heading Accuracy\", \"Jumping\", \"BallControl\", \"Vision\", \"Acceleration\", \"Positioning\"]]\n",
+    "\n",
+    "numeric_data = filter_ST.select_dtypes(include='number').corr()\n",
+    "plt.figure(figsize=(15, 5))\n",
+    "sns.heatmap(numeric_data,annot=True, cmap='viridis', fmt='.2f')\n",
+    "plt.title('Correlation Heatmap')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Sort players with Release Clause per ST point ratio\n",
+    "total_column = filter_ST.select_dtypes(include='number').sum(axis=1)\n",
+    "filter_ST[\"Total ST Point\"] = total_column\n",
+    "filter_ST[\"Release Clause\"] = players_fifa[\"Release Clause\"]\n",
+    "filter_ST['Ratio Column'] = filter_ST['Release Clause']/filter_ST['Total ST Point']\n",
+    "sorted_ST = filter_ST.sort_values(by='Ratio Column')\n",
+    "display(sorted_ST)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# check first 6 players\n",
+    "sorted_ST.head(6)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fifa_data_ST['fifa_data_ST Index'] = fifa_data_ST['Potential'] / fifa_data_ST['Release Clause']\n",
+    "players_fifa.loc[:, 'fifa_data_23 Index'] = players_fifa['Potential'] / players_fifa['Release Clause']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Predicted wage for ST position\n",
+    "X = players_fifa [['Overall','Potential','Value','Age','Release Clause']]\n",
+    "scaler = StandardScaler()\n",
+    "X_standardized = scaler.fit_transform(X)\n",
+    "Tammya = X_standardized[220]\n",
+    "Tammya = pd.DataFrame(Tammya).transpose()\n",
+    "X_standardized = np.delete(X_standardized, 220, axis=0)\n",
+    "y = players_fifa [['Wage']]\n",
+    "y = y.drop(220)\n",
+    "model = linear_model.LinearRegression()\n",
+    "result = model.fit(X_standardized, y)\n",
+    "predicted_wage = model.predict(Tammya)\n",
+    "print(predicted_wage)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "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": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}