import numpy as np
from sklearn.linear_model import LinearRegression

# Load data from the CSV file
data = np.genfromtxt('data2.csv', delimiter=',', skip_header=1, invalid_raise=False, missing_values='NaN')

# Number of data points in each set
set_size = 80

# List to store slopes of individual fitting functions
slopes = []

# Iterate through the data sets
for i in range(len(data) // set_size):
    # Extract data for the current set
    set_data = data[i * set_size: (i + 1) * set_size]

    # Extract x and y values
    x_values = set_data[:, 1]
    y_values = set_data[:, 2]

    # Fit linear regression model
    model = LinearRegression().fit(x_values.reshape(-1, 1), y_values)

    # Get slope of the linear fitting function
    slope = model.coef_[0]
    
    # Append slope to the list
    slopes.append(slope)
    
    # Print the slope for the current set
    print("Slope of linear fitting function for set", i+1, ":", slope)

# Calculate the average slope
average_slope = np.mean(slopes)

# Print the average slope
print("\nAverage slope (V / V):", average_slope*1000)
print("STDEV slope :", np.std(slopes)*1000)