Linear Regression

import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from scipy import stats

# Load data
data = pd.read_csv('', encoding='latin1')
# Display the columns
print("Columns:", data.columns.tolist())

# Set up the matplotlib figure
fig, axes = plt.subplots(4, 4, figsize=(18, 16))  # Increased grid size to 3x3
fig.tight_layout(pad=5.0)
axes = axes.flatten()

# Mapping dictionary: dataframe column -> pretty name
rename_dict = {
    
}

# Variables to plot
variables = [] # Corrected variable name to Windspeed

# Plot each variable
for i, var in enumerate(variables):
    ax = axes[i]
    plot_data = data[['Fire', var]].dropna()

    if len(plot_data) > 1:
        x = plot_data['Fire']
        y = plot_data[var]

        # Perform linear regression
        slope, intercept, r_value, p_value, std_err = stats.linregress(x, y)
        r2 = r_value ** 2

        # Plot regression line
        sns.regplot(x=x, y=y, ax=ax,
                    scatter_kws={'s': 70, 'color': 'grey'},
                    line_kws={'color': 'red'})

        # Labels
        ax.set_xlabel(rename_dict['Fire'], fontsize=12)
        ax.set_ylabel(rename_dict[var], fontsize=12)

        # Add R² and p-value annotation
        ax.text(0.05, 0.95, f"$R^2$ = {r2:.2f}\n$p$ = {p_value:.3e}",
                transform=ax.transAxes,
                fontsize=11,
                verticalalignment='top',
                bbox=dict(boxstyle="round,pad=0.3", facecolor='white', alpha=0.6))

    else:
        ax.text(0.5, 0.5, "Insufficient data to plot",
                horizontalalignment='center', verticalalignment='center',
                transform=ax.transAxes, fontsize=12)

# Hide any unused subplots (if grid larger than number of variables)
for j in range(len(variables), len(axes)):
    fig.delaxes(axes[j])

plt.show()