Submission for DSC Tasks 1 & 2 by K Dheeraj

Project_1_Sports_Transport_ML/README.md

@@ -0,0 +1 @@
+# DSC-Tasks-Submission

Project_1_Sports_Transport_ML/Task 1/nba_scoring_leaders.csv

@@ -0,0 +1,34 @@
+Season,Player,Team,Year,Games Played,Total Points,Points per Game
+1992–93,Michael Jordan* (7),Chicago Bulls,1992,78,2541,32.6
+1993–94,David Robinson*,San Antonio Spurs,1993,80,2383,29.8
+1994–95,Shaquille O'Neal*,Orlando Magic,1994,79,2315,29.3
+1995–96 ‡,Michael Jordan* (8),Chicago Bulls,1995,82,2491,30.4
+1996–97,Michael Jordan* (9),Chicago Bulls,1996,82,2431,29.6
+1997–98 ‡,Michael Jordan* (10),Chicago Bulls,1997,82,2357,28.7
+1998–99[o],Allen Iverson*,Philadelphia 76ers,1998,48,1284,26.8
+1999–00 ‡,Shaquille O'Neal* (2),Los Angeles Lakers,1999,79,2344,29.7
+2000–01 ‡,Allen Iverson* (2),Philadelphia 76ers,2000,71,2207,31.1
+2001–02,Allen Iverson* (3),Philadelphia 76ers,2001,60,1883,31.4
+2002–03,Tracy McGrady*,Orlando Magic,2002,75,2407,32.1
+2003–04,Tracy McGrady* (2),Orlando Magic,2003,67,1878,28.0
+2004–05,Allen Iverson* (4),Philadelphia 76ers,2004,75,2302,30.7
+2005–06,Kobe Bryant*,Los Angeles Lakers,2005,80,2832,35.4
+2006–07,Kobe Bryant* (2),Los Angeles Lakers,2006,77,2430,31.6
+2007–08,LeBron James,Cleveland Cavaliers,2007,75,2250,30.0
+2008–09,Dwyane Wade*,Miami Heat,2008,79,2386,30.2
+2009–10,Kevin Durant,Oklahoma City Thunder,2009,82,2472,30.1
+2010–11,Kevin Durant (2),Oklahoma City Thunder,2010,78,2161,27.7
+2011–12[w],Kevin Durant (3),Oklahoma City Thunder,2011,66,1850,28.0
+2012–13,Carmelo Anthony*,New York Knicks,2012,67,1920,28.7
+2013–14 ‡,Kevin Durant (4),Oklahoma City Thunder,2013,81,2593,32.0
+2014–15,Russell Westbrook,Oklahoma City Thunder,2014,67,1886,28.1
+2015–16 ‡,Stephen Curry,Golden State Warriors,2015,79,2375,30.1
+2016–17 ‡,Russell Westbrook (2),Oklahoma City Thunder,2016,81,2558,31.6
+2017–18 ‡,James Harden,Houston Rockets,2017,72,2191,30.4
+2018–19,James Harden (2),Houston Rockets,2018,78,2818,36.1
+2019–20,James Harden (3),Houston Rockets,2019,68,2335,34.3
+2020–21,Stephen Curry (2),Golden State Warriors,2020,63,2015,32.0
+2021–22,Joel Embiid,Philadelphia 76ers,2021,68,2079,30.6
+2022–23 ‡,Joel Embiid (2),Philadelphia 76ers,2022,66,2183,33.1
+2023–24,Luka Dončić,Dallas Mavericks,2023,70,2370,33.9
+2024–25 ‡,Shai Gilgeous-Alexander,Oklahoma City Thunder,2024,76,2484,32.7

Project_1_Sports_Transport_ML/Task 2/Task II.ipynb

@@ -0,0 +1,158 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "efbe15f9-8cd2-4a2f-b034-8f8649d5703f",
+   "metadata": {},
+   "source": [
+    "# 1. Define the Real-World Problem &\n",
+    "# 2. Build a Scikit-Learn Pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "cc8d44ac-52be-4c1b-8785-7b9b74d98358",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pipeline built successfully.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.compose import ColumnTransformer\n",
+    "from sklearn.preprocessing import StandardScaler, OneHotEncoder, FunctionTransformer\n",
+    "from sklearn.ensemble import RandomForestRegressor\n",
+    "from sklearn.impute import SimpleImputer\n",
+    "\n",
+    "# Load the dataset \n",
+    "df = pd.read_csv('hour.csv')\n",
+    "\n",
+    "# Drop unnecessary columns\n",
+    "df = df.drop(columns=['instant', 'dteday', 'casual', 'registered'])\n",
+    "\n",
+    "# Target: 'cnt' (bike rental count)\n",
+    "X = df.drop(columns=['cnt'])\n",
+    "y = df['cnt']\n",
+    "\n",
+    "# Numerical and categorical columns\n",
+    "numerical_features = ['temp', 'atemp', 'hum', 'windspeed']\n",
+    "categorical_features = ['season', 'yr', 'mnth', 'hr', 'holiday', 'weekday', 'workingday', 'weathersit']\n",
+    "\n",
+    "# Feature engineering function (create new feature: temp * hum interaction)\n",
+    "def feature_engineering(X):\n",
+    "    X = X.copy()\n",
+    "    X['temp_hum_interaction'] = X['temp'] * X['hum']\n",
+    "    return X\n",
+    "\n",
+    "# Preprocessing for numerical features\n",
+    "numerical_transformer = Pipeline(steps=[\n",
+    "    ('imputer', SimpleImputer(strategy='mean')), \n",
+    "    ('scaler', StandardScaler())\n",
+    "])\n",
+    "\n",
+    "# Preprocessing for categorical features\n",
+    "categorical_transformer = Pipeline(steps=[\n",
+    "    ('imputer', SimpleImputer(strategy='most_frequent')),\n",
+    "    ('onehot', OneHotEncoder(handle_unknown='ignore'))\n",
+    "])\n",
+    "\n",
+    "# Combined preprocessor\n",
+    "preprocessor = ColumnTransformer(\n",
+    "    transformers=[\n",
+    "        ('num', numerical_transformer, numerical_features),\n",
+    "        ('cat', categorical_transformer, categorical_features)\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "# Full pipeline: Preprocessing + Feature Engineering + Model\n",
+    "pipeline = Pipeline(steps=[\n",
+    "    ('feature_eng', FunctionTransformer(feature_engineering)),  # Add new feature before preprocessing\n",
+    "    ('preprocessor', preprocessor),\n",
+    "    ('model', RandomForestRegressor(n_estimators=100, random_state=42))\n",
+    "])\n",
+    "\n",
+    "print(\"Pipeline built successfully.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e71a24b0-ddbd-4306-b3fd-78dedf4d4965",
+   "metadata": {},
+   "source": [
+    "# 3. Train, Test, and Evaluate the Pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "bc265be7-eb70-4711-be2b-636f63e4189f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean Squared Error (MSE): 2275.59\n",
+      "R² Score: 0.93\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import mean_squared_error, r2_score\n",
+    "\n",
+    "# Split data into train/test sets\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "# Train the pipeline\n",
+    "pipeline.fit(X_train, y_train)\n",
+    "\n",
+    "# Predict on test set\n",
+    "y_pred = pipeline.predict(X_test)\n",
+    "\n",
+    "# Evaluate\n",
+    "mse = mean_squared_error(y_test, y_pred)\n",
+    "r2 = r2_score(y_test, y_pred)\n",
+    "\n",
+    "print(f\"Mean Squared Error (MSE): {mse:.2f}\")\n",
+    "print(f\"R² Score: {r2:.2f}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "feea924f-21c9-4bff-854e-866d3cbccf84",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:base] *",
+   "language": "python",
+   "name": "conda-base-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}