model.py

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.preprocessing import StandardScaler
import numpy as np

# Load the data
trips_full_data_df = pd.read_csv('Trips_Full Data.csv')
trips_by_distance_df = pd.read_csv('Trips_by_Distance.csv')

# Convert 'Date' to datetime if it's not already and set as index
trips_full_data_df['Date'] = pd.to_datetime(trips_full_data_df['Date'])
trips_by_distance_df['Date'] = pd.to_datetime(trips_by_distance_df['Date'])

# Set 'Date' as index to prepare for merge
trips_full_data_df.set_index('Date', inplace=True)
trips_by_distance_df.set_index('Date', inplace=True)

# Filter the data for Week 32 of 2019 for the predictor variables
week_32_full = trips_full_data_df[trips_full_data_df['Week of Date'] == 'Week 32']

# Prepare the Week 31 data for the target variable and group by 'Date'
week_31_distance = trips_by_distance_df[trips_by_distance_df['Week'] == 31]
week_31_distance_grouped = week_31_distance.groupby('Date').agg({'Number of Trips 5-10': 'sum'})

# Merge the Week 32 and Week 31 data on 'Date'
merged_data = week_32_full.join(week_31_distance_grouped)


if merged_data.isnull().values.any():
    print("Warning: NaN values found after merging. Check alignment of 'Date' columns.")
    merged_data.dropna(inplace=True)  


X = merged_data[['Trips 1-25 Miles', 'Trips 25-100 Miles']]
y = merged_data['Number of Trips 5-10']

X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_val_scaled = scaler.transform(X_val)

model = LinearRegression()
model.fit(X_train_scaled, y_train)

from sklearn.metrics import r2_score, mean_squared_error

# Predict on the validation set
y_pred = model.predict(X_val_scaled)

# Calculate R² on the validation set
r2 = r2_score(y_val, y_pred)

# Calculate RMSE on the validation set
mse = mean_squared_error(y_val, y_pred)
rmse = np.sqrt(mse)  # Calculating the square root of the MSE to get RMSE
print(f"Coefficients: {model.coef_}")
print(f"Intercept: {model.intercept_}")


print(f"Linear Regression - Coefficient of determination (R^2) on validation set: {r2}")
print(f"Linear Regression - Root Mean Square Error (RMSE) on validation set: {rmse}")