import numpy as np
from sklearn.metrics import r2_score
import matplotlib.pyplot as plt

# Load data from the CSV file, skipping the first row (header) and handling missing or bad values
data = np.genfromtxt('data.csv', delimiter=',', skip_header=1, invalid_raise=False, missing_values='NaN')

# Remove rows containing missing values
data = data[~np.isnan(data).any(axis=1)]

# Extract columns
wavegen_output = data[:, 0]
diff_amplifier_measured = data[:, 2]
wavegen_measured = data[:, 1]

# Define polynomial degree
degree = 1

# Calculate polynomial fits
coefficients_output = np.polyfit(wavegen_output, diff_amplifier_measured, degree)
coefficients_measured = np.polyfit(wavegen_measured, diff_amplifier_measured, degree)

# Generate polynomial functions using the coefficients
poly_func_output = np.poly1d(coefficients_output)
poly_func_measured = np.poly1d(coefficients_measured)

# Calculate R^2 value
r_squared_output = r2_score(diff_amplifier_measured, poly_func_output(wavegen_output))
r_squared_measured = r2_score(diff_amplifier_measured, poly_func_measured(wavegen_measured))