2.py

import numpy as np
from sklearn.linear_model import LinearRegression

# Load data using NumPy arrays
data_file1 = "/Users/thecreator/Downloads/Trips_Full Data.csv"
data_file2 = "/Users/thecreator/Downloads/Trips_by_Distance.csv"

# Load data from the first file
data1 = np.genfromtxt(data_file1, delimiter=",", skip_header=1, usecols=(10,), dtype=float)
x = data1[~np.isnan(data1)]  # Filter out NaN values in x

# Load data from the second file
data2 = np.genfromtxt(data_file2, delimiter=",", skip_header=1, usecols=(19,), dtype=float)
y = data2[~np.isnan(data2)]  # Filter out NaN values in y

# Check how many valid samples are remaining
print(f"Number of valid samples in x: {len(x)}")
print(f"Number of valid samples in y: {len(y)}")

# Check if there are still samples left after filtering NaN values
if len(x) == 0 or len(y) == 0:
    print("No valid samples remaining after filtering NaN values.")
else:
    # Create and fit the model
    x = x.reshape(-1, 1)  # Reshape x to be a 2D array (required by scikit-learn)
    model = LinearRegression()
    model.fit(x, y)

    # Print the model coefficients
    print(f"Coefficient of determination (R^2): {model.score(x, y):.2f}")
    print(f"Intercept: {model.intercept_:.2f}")
    print(f"Coefficient(slope): {model.coef_[0]:.2f}")

    # Make predictions
    y_pred = model.predict(x)
    print("Predicted responses:")
    print(y_pred)