diff --git a/project/Final_Report.ipynb b/project/Final_Report.ipynb
index afec465..09071c6 100644
--- a/project/Final_Report.ipynb
+++ b/project/Final_Report.ipynb
@@ -48,11 +48,811 @@
"8. **Conclusions**\n",
" - Write a short summary of your project goes here."
]
+ },
+ {
+ "metadata": {
+ "ExecuteTime": {
+ "end_time": "2024-12-09T15:24:16.987194Z",
+ "start_time": "2024-12-09T15:24:16.974515Z"
+ }
+ },
+ "cell_type": "code",
+ "source": [
+ "# Importing Libraries\n",
+ "import sys\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import os\n",
+ "\n",
+ "import fastf1\n",
+ "import fastf1.plotting\n",
+ "from fastf1.ergast.structure import FastestLap\n",
+ "\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.preprocessing import StandardScaler\n",
+ "from sklearn.linear_model import LinearRegression\n",
+ "from sklearn.ensemble import RandomForestRegressor\n",
+ "from sklearn.metrics import mean_squared_error, r2_score\n",
+ "from sklearn.tree import DecisionTreeRegressor\n",
+ "from sklearn.ensemble import GradientBoostingRegressor\n",
+ "from sklearn.svm import SVR\n",
+ "import xgboost as xgb\n",
+ "from sklearn.model_selection import cross_val_score\n",
+ "from sklearn.model_selection import train_test_split, GridSearchCV\n",
+ "#print versions of libraries\n",
+ "print(f'Python version: {sys.version}')\n",
+ "print(f'Pandas version: {pd.__version__}')\n",
+ "print(f'Numpy version: {np.__version__}')\n",
+ "print(f'Matplotlib version: {plt.matplotlib.__version__}')\n",
+ "print(f'Seaborn version: {sns.__version__}')\n",
+ "print(f'FastF1 version: {fastf1.__version__}')\n",
+ "print(f'Scikit-learn version: {sys.modules[\"sklearn\"].__version__}')\n",
+ "print(f'XGBoost version: {xgb.__version__}')"
+ ],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Python version: 3.10.13 (main, Sep 11 2023, 08:24:56) [Clang 14.0.6 ]\n",
+ "Pandas version: 2.2.2\n",
+ "Numpy version: 1.23.5\n",
+ "Matplotlib version: 3.8.4\n",
+ "Seaborn version: 0.13.2\n",
+ "FastF1 version: 3.4.4\n",
+ "Scikit-learn version: 1.5.1\n",
+ "XGBoost version: 2.1.1\n"
+ ]
+ }
+ ],
+ "execution_count": 7
+ },
+ {
+ "metadata": {},
+ "cell_type": "markdown",
+ "source": [
+ "## Problem Statement\n",
+ "We are analyzing Formula One driver performance to understand and predict race outcomes based on various conditions. Specifically, we aim to:\n",
+ "1. Predict lap times based on weather and track conditions\n",
+ "2. Understand how different variables affect driver performance\n",
+ "3. Create models that can forecast race performance\n",
+ "\n",
+ "This is primarily a regression problem, as we're predicting continuous values (lap times) based on multiple features."
+ ]
+ },
+ {
+ "metadata": {
+ "ExecuteTime": {
+ "end_time": "2024-12-09T15:24:17.026610Z",
+ "start_time": "2024-12-09T15:24:17.013465Z"
+ }
+ },
+ "cell_type": "code",
+ "source": [
+ "# Set up FastF1 plotting and caching\n",
+ "cache_dir = '../data/cache'\n",
+ "if not os.path.exists(cache_dir):\n",
+ " os.makedirs(cache_dir)\n",
+ "\n",
+ "fastf1.Cache.enable_cache(cache_dir)\n",
+ "fastf1.plotting.setup_mpl(misc_mpl_mods=False, color_scheme=None)"
+ ],
+ "outputs": [],
+ "execution_count": 8
+ },
+ {
+ "metadata": {
+ "ExecuteTime": {
+ "end_time": "2024-12-09T15:24:17.053839Z",
+ "start_time": "2024-12-09T15:24:17.050836Z"
+ }
+ },
+ "cell_type": "code",
+ "source": [
+ "# Define years, sessions, and events of interest\n",
+ "years = [2021, 2022, 2023, 2024]\n",
+ "sessions = ['Race']\n",
+ "events = ['Bahrain Grand Prix', 'British Grand Prix', 'United States Grand Prix', 'Mexico City Grand Prix', 'São Paulo Grand Prix'] "
+ ],
+ "outputs": [],
+ "execution_count": 9
+ },
+ {
+ "metadata": {},
+ "cell_type": "markdown",
+ "source": [
+ "## Why these events, sessions, and years?\n",
+ "\n",
+ "These events were chosen because they are all currently scheduled for the 2024 season, as well as having occurred in previous years. \n",
+ "\n",
+ "Each event has a specific set of conditions that may affect driver performance:\n",
+ "- Bahrain: Hot and humid, with high track temperatures\n",
+ "- British: Cool and changeable, with frequent rain\n",
+ "- United States: Very hot, with high track temperatures\n",
+ "- Mexico City: Cool and changeable, with frequent rain\n",
+ "- São Paulo: Hot and humid, with high track temperatures and heavy rain\n",
+ "\n",
+ "As for years, we chose 2021 to 2024 because they are the most recent years for which data is available. In 2021, the regulations changed to allow for more overtaking, so the lap times became incomparable to that of previous years.\n",
+ "\n",
+ "We chose to only use the 'Race' session because it is the most representative of a race condition, as opposed to qualifying, which can be very sporadic."
+ ]
+ },
+ {
+ "metadata": {
+ "ExecuteTime": {
+ "end_time": "2024-12-09T15:24:20.703407Z",
+ "start_time": "2024-12-09T15:24:17.065829Z"
+ }
+ },
+ "cell_type": "code",
+ "source": [
+ "# Get data from FastF1 API\n",
+ "\n",
+ "# Data containers\n",
+ "weather_data_list = []\n",
+ "lap_data_list = []\n",
+ "\n",
+ "#Quick Test\n",
+ "years = [2021]\n",
+ "events = ['Bahrain Grand Prix']\n",
+ "\n",
+ "\n",
+ "# Loop through years and sessions\n",
+ "for year in years:\n",
+ " for event_name in events: \n",
+ " for session_name in sessions:\n",
+ " try:\n",
+ " print(f\"Processing {year} {event_name} - {session_name}\")\n",
+ " \n",
+ " # Load the session\n",
+ " session = fastf1.get_session(year, event_name, session_name, backend='fastf1')\n",
+ " session.load()\n",
+ " \n",
+ " # Process weather data\n",
+ " weather_data = session.weather_data\n",
+ " if weather_data is not None:\n",
+ " weather_df = pd.DataFrame(weather_data)\n",
+ " # Add context columns\n",
+ " weather_df['Year'] = year\n",
+ " weather_df['Event'] = event_name\n",
+ " weather_df['Session'] = session_name\n",
+ " weather_data_list.append(weather_df)\n",
+ "\n",
+ " # Process lap data\n",
+ " lap_data = session.laps\n",
+ " if lap_data is not None:\n",
+ " lap_df = pd.DataFrame(lap_data)\n",
+ " # Add context columns\n",
+ " lap_df['Year'] = year\n",
+ " lap_df['Event'] = event_name\n",
+ " lap_df['Session'] = session_name\n",
+ " # Ensure driver information is included\n",
+ " if 'Driver' not in lap_df.columns:\n",
+ " lap_df['Driver'] = lap_df['DriverNumber'].map(session.drivers)\n",
+ " # Add team information if available\n",
+ " if 'Team' not in lap_df.columns:\n",
+ " lap_df['Team'] = lap_df['Driver'].map(session.drivers_info['TeamName'])\n",
+ " lap_data_list.append(lap_df)\n",
+ " \n",
+ " except Exception as e:\n",
+ " print(f\"Error with {event_name} {session_name} ({year}): {e}\")\n",
+ "\n",
+ "# Combine data into DataFrames\n",
+ "if weather_data_list:\n",
+ " weather_data_combined = pd.concat(weather_data_list, ignore_index=True)\n",
+ " # Ensure consistent column ordering\n",
+ " weather_cols = ['Time', 'Year', 'Event', 'Session', \n",
+ " 'AirTemp', 'Humidity', 'Pressure', 'Rainfall', \n",
+ " 'TrackTemp', 'WindDirection', 'WindSpeed']\n",
+ " weather_data_combined = weather_data_combined[weather_cols]\n",
+ " \n",
+ "if lap_data_list:\n",
+ " lap_data_combined = pd.concat(lap_data_list, ignore_index=True)\n",
+ " # Ensure consistent column ordering\n",
+ " lap_cols = ['Time', 'Year', 'Event', 'Session', \n",
+ " 'Driver', 'Team', 'LapNumber', 'LapTime',\n",
+ " 'Sector1Time', 'Sector2Time', 'Sector3Time',\n",
+ " 'Compound', 'TyreLife', 'FreshTyre',\n",
+ " 'SpeedI1', 'SpeedI2', 'SpeedFL', 'SpeedST']\n",
+ " # Only include columns that exist\n",
+ " existing_cols = [col for col in lap_cols if col in lap_data_combined.columns]\n",
+ " lap_data_combined = lap_data_combined[existing_cols]\n",
+ " \n",
+ "# Time conversion\n",
+ "# Function to convert timedelta to datetime\n",
+ "def convert_timedelta_to_datetime(df, base_date='2021-01-01'):\n",
+ " if 'Time' in df.columns:\n",
+ " # Create a base datetime and add the timedelta\n",
+ " base = pd.Timestamp(base_date)\n",
+ " if df['Time'].dtype == 'timedelta64[ns]':\n",
+ " df['Time'] = base + df['Time']\n",
+ " return df\n",
+ "\n",
+ "# Apply conversion to both dataframes\n",
+ "weather_data_combined = convert_timedelta_to_datetime(weather_data_combined)\n",
+ "lap_data_combined = convert_timedelta_to_datetime(lap_data_combined)\n",
+ "\n",
+ "# Remove missing values\n",
+ "weather_data_combined = weather_data_combined.dropna()\n",
+ "lap_data_combined = lap_data_combined.dropna()\n",
+ "\n",
+ "# Create a new column for lap time in seconds\n",
+ "lap_data_combined['LapTime_seconds'] = lap_data_combined['LapTime'].dt.total_seconds()\n",
+ "\n",
+ "# Merge the data\n",
+ "merged_data = pd.merge_asof(\n",
+ " lap_data_combined.sort_values('Time'),\n",
+ " weather_data_combined.sort_values('Time'),\n",
+ " on='Time',\n",
+ " by=['Event', 'Year'], # Match within same event and year\n",
+ " direction='nearest',\n",
+ " tolerance=pd.Timedelta('1 min') # Allow matching within 1 minute\n",
+ ")"
+ ],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Processing 2021 Bahrain Grand Prix - Race\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "core INFO \tLoading data for Bahrain Grand Prix - Race [v3.4.4]\n",
+ "req INFO \tUsing cached data for session_info\n",
+ "req INFO \tUsing cached data for driver_info\n",
+ "req INFO \tUsing cached data for session_status_data\n",
+ "req INFO \tUsing cached data for lap_count\n",
+ "req INFO \tUsing cached data for track_status_data\n",
+ "req INFO \tUsing cached data for _extended_timing_data\n",
+ "req INFO \tUsing cached data for timing_app_data\n",
+ "core INFO \tProcessing timing data...\n",
+ "req INFO \tUsing cached data for car_data\n",
+ "req INFO \tUsing cached data for position_data\n",
+ "req INFO \tUsing cached data for weather_data\n",
+ "req INFO \tUsing cached data for race_control_messages\n",
+ "core INFO \tFinished loading data for 20 drivers: ['44', '33', '77', '4', '11', '16', '3', '55', '22', '18', '7', '99', '31', '63', '5', '47', '10', '6', '14', '9']\n"
+ ]
+ }
+ ],
+ "execution_count": 10
+ },
+ {
+ "metadata": {},
+ "cell_type": "markdown",
+ "source": [
+ "## Data Description\n",
+ "Our data comes from the FastF1 API, which provides detailed Formula One racing data. Each observation represents a single lap during a race or qualifying session, including:\n",
+ "\n",
+ "Key Variables:\n",
+ "- **Time**: Timestamp of the lap\n",
+ "- **Driver**: Driver identifier\n",
+ "- **LapTime**: Time taken to complete the lap\n",
+ "- **Weather Conditions**:\n",
+ " - TrackTemp: Track temperature in Celsius\n",
+ " - AirTemp: Air temperature in Celsius\n",
+ " - Humidity: Percentage\n",
+ " - Rainfall: Boolean indicating presence of rain\n",
+ "- **Performance Metrics**:\n",
+ " - Sector times (1,2,3)\n",
+ " - Speed measurements at various points\n",
+ " - Compound: Tire compound used\n",
+ " - TyreLife: Age of tires in laps\n",
+ "\n",
+ "Each lap is represented as a fixed-length vector containing these attributes, making it suitable for machine learning algorithms."
+ ]
+ },
+ {
+ "metadata": {
+ "ExecuteTime": {
+ "end_time": "2024-12-09T15:25:18.878045Z",
+ "start_time": "2024-12-09T15:25:18.858848Z"
+ }
+ },
+ "cell_type": "code",
+ "source": [
+ "# Display a sample of the raw data\n",
+ "lap_data_combined.head()"
+ ],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ " Time Year Event Session Driver \\\n",
+ "1 2021-01-01 00:41:37.134 2021 Bahrain Grand Prix Race GAS \n",
+ "4 2021-01-01 00:48:28.044 2021 Bahrain Grand Prix Race GAS \n",
+ "5 2021-01-01 00:50:04.721 2021 Bahrain Grand Prix Race GAS \n",
+ "6 2021-01-01 00:51:41.675 2021 Bahrain Grand Prix Race GAS \n",
+ "8 2021-01-01 00:54:56.129 2021 Bahrain Grand Prix Race GAS \n",
+ "\n",
+ " Team LapNumber LapTime Sector1Time \\\n",
+ "1 AlphaTauri 2.0 0 days 00:02:22.263000 0 days 00:00:45.220000 \n",
+ "4 AlphaTauri 5.0 0 days 00:02:11.534000 0 days 00:01:05.748000 \n",
+ "5 AlphaTauri 6.0 0 days 00:01:36.677000 0 days 00:00:30.990000 \n",
+ "6 AlphaTauri 7.0 0 days 00:01:36.954000 0 days 00:00:31.176000 \n",
+ "8 AlphaTauri 9.0 0 days 00:01:37.030000 0 days 00:00:31.256000 \n",
+ "\n",
+ " Sector2Time Sector3Time Compound TyreLife FreshTyre \\\n",
+ "1 0 days 00:01:00.086000 0 days 00:00:36.957000 MEDIUM 5.0 False \n",
+ "4 0 days 00:00:41.956000 0 days 00:00:23.830000 HARD 1.0 True \n",
+ "5 0 days 00:00:41.802000 0 days 00:00:23.885000 HARD 2.0 True \n",
+ "6 0 days 00:00:41.678000 0 days 00:00:24.100000 HARD 3.0 True \n",
+ "8 0 days 00:00:41.911000 0 days 00:00:23.863000 HARD 5.0 True \n",
+ "\n",
+ " SpeedI1 SpeedI2 SpeedFL SpeedST LapTime_seconds \n",
+ "1 120.0 134.0 182.0 236.0 142.263 \n",
+ "4 231.0 251.0 275.0 213.0 131.534 \n",
+ "5 233.0 254.0 275.0 280.0 96.677 \n",
+ "6 232.0 252.0 274.0 282.0 96.954 \n",
+ "8 234.0 248.0 276.0 286.0 97.030 "
+ ],
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Time | \n",
+ " Year | \n",
+ " Event | \n",
+ " Session | \n",
+ " Driver | \n",
+ " Team | \n",
+ " LapNumber | \n",
+ " LapTime | \n",
+ " Sector1Time | \n",
+ " Sector2Time | \n",
+ " Sector3Time | \n",
+ " Compound | \n",
+ " TyreLife | \n",
+ " FreshTyre | \n",
+ " SpeedI1 | \n",
+ " SpeedI2 | \n",
+ " SpeedFL | \n",
+ " SpeedST | \n",
+ " LapTime_seconds | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 1 | \n",
+ " 2021-01-01 00:41:37.134 | \n",
+ " 2021 | \n",
+ " Bahrain Grand Prix | \n",
+ " Race | \n",
+ " GAS | \n",
+ " AlphaTauri | \n",
+ " 2.0 | \n",
+ " 0 days 00:02:22.263000 | \n",
+ " 0 days 00:00:45.220000 | \n",
+ " 0 days 00:01:00.086000 | \n",
+ " 0 days 00:00:36.957000 | \n",
+ " MEDIUM | \n",
+ " 5.0 | \n",
+ " False | \n",
+ " 120.0 | \n",
+ " 134.0 | \n",
+ " 182.0 | \n",
+ " 236.0 | \n",
+ " 142.263 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 2021-01-01 00:48:28.044 | \n",
+ " 2021 | \n",
+ " Bahrain Grand Prix | \n",
+ " Race | \n",
+ " GAS | \n",
+ " AlphaTauri | \n",
+ " 5.0 | \n",
+ " 0 days 00:02:11.534000 | \n",
+ " 0 days 00:01:05.748000 | \n",
+ " 0 days 00:00:41.956000 | \n",
+ " 0 days 00:00:23.830000 | \n",
+ " HARD | \n",
+ " 1.0 | \n",
+ " True | \n",
+ " 231.0 | \n",
+ " 251.0 | \n",
+ " 275.0 | \n",
+ " 213.0 | \n",
+ " 131.534 | \n",
+ "
\n",
+ " \n",
+ " | 5 | \n",
+ " 2021-01-01 00:50:04.721 | \n",
+ " 2021 | \n",
+ " Bahrain Grand Prix | \n",
+ " Race | \n",
+ " GAS | \n",
+ " AlphaTauri | \n",
+ " 6.0 | \n",
+ " 0 days 00:01:36.677000 | \n",
+ " 0 days 00:00:30.990000 | \n",
+ " 0 days 00:00:41.802000 | \n",
+ " 0 days 00:00:23.885000 | \n",
+ " HARD | \n",
+ " 2.0 | \n",
+ " True | \n",
+ " 233.0 | \n",
+ " 254.0 | \n",
+ " 275.0 | \n",
+ " 280.0 | \n",
+ " 96.677 | \n",
+ "
\n",
+ " \n",
+ " | 6 | \n",
+ " 2021-01-01 00:51:41.675 | \n",
+ " 2021 | \n",
+ " Bahrain Grand Prix | \n",
+ " Race | \n",
+ " GAS | \n",
+ " AlphaTauri | \n",
+ " 7.0 | \n",
+ " 0 days 00:01:36.954000 | \n",
+ " 0 days 00:00:31.176000 | \n",
+ " 0 days 00:00:41.678000 | \n",
+ " 0 days 00:00:24.100000 | \n",
+ " HARD | \n",
+ " 3.0 | \n",
+ " True | \n",
+ " 232.0 | \n",
+ " 252.0 | \n",
+ " 274.0 | \n",
+ " 282.0 | \n",
+ " 96.954 | \n",
+ "
\n",
+ " \n",
+ " | 8 | \n",
+ " 2021-01-01 00:54:56.129 | \n",
+ " 2021 | \n",
+ " Bahrain Grand Prix | \n",
+ " Race | \n",
+ " GAS | \n",
+ " AlphaTauri | \n",
+ " 9.0 | \n",
+ " 0 days 00:01:37.030000 | \n",
+ " 0 days 00:00:31.256000 | \n",
+ " 0 days 00:00:41.911000 | \n",
+ " 0 days 00:00:23.863000 | \n",
+ " HARD | \n",
+ " 5.0 | \n",
+ " True | \n",
+ " 234.0 | \n",
+ " 248.0 | \n",
+ " 276.0 | \n",
+ " 286.0 | \n",
+ " 97.030 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "