Do not know if this problem is posted somewhere else, please direct me to it if that is the case, thanks

I have some data that looks like this

I want to calculate the area under the curve, however as the initial and end point do not go to zero I would like to make a linear regression based on the start and end data and then calculate the area under the data but confined within the linear regressions in something like this

I want to choose the the data for the linear regression and then calculate the area under the data based on the last point in the regression for the pre-baseline and the first point in the regression for the post-baseline that is confined within the linear regression.

I have played a bit with chatGPT to provide me some code that than do what I want but it does not seem to understand that I only want the area between the linear regressions and data

def baseline_correction(data, indices):
# Calculate a unified baseline using linear regression on selected indices
slope, intercept, _, _, _ = linregress(data[indices, 0], data[indices, 1])
return slope, intercept

def calculate_area(data, start_index, end_index, slope, intercept):
# Correct the current by subtracting the baseline
corrected_current = data[start_index:end_index, 1] – (data[start_index:end_index, 0] * slope + intercept)
# Calculate the area (charge) under the corrected current curve
charge = trapz(corrected_current, x=data[start_index:end_index, 0])
return charge, corrected_current

def process_cycles(data, cycle_starts):
charges = []
for i in range(len(cycle_starts) – 1):
start_index = cycle_starts[i]
end_index = cycle_starts[i + 1]

    # Selecting only the increasing potential part of the cycle
    increasing_potential_indices = np.where(np.diff(data[start_index:end_index, 0]) > 0)[0] + start_index
    
    # Combine pre-peak and post-peak data points for baseline
    pre_peak_indices = increasing_potential_indices[np.where((data[increasing_potential_indices, 0] >= 0.35) & (data[increasing_potential_indices, 0] <= 0.4))]
    post_peak_indices = increasing_potential_indices[np.where((data[increasing_potential_indices, 0] >= 0.525) & (data[increasing_potential_indices, 0] <= 0.55))]
    combined_indices = np.concatenate((pre_peak_indices, post_peak_indices))
    
    # Calculate unified baseline
    slope, intercept = baseline_correction(data, combined_indices)
    
    # Define peak region (between 0.35V to 0.4V)
    peak_start_idx = np.min(np.where(data[:, 0] >= 0.4)[0])
    peak_end_idx = np.max(np.where(data[:, 0] <= 0.525)[0])
    
    # Calculate the charge
    charge, corrected_current = calculate_area(data, peak_start_idx, peak_end_idx, slope, intercept)
    charges.append(charge)
    
    # Visualization
    plt.figure(figsize=(10, 6))
    plt.plot(data[start_index:end_index, 0], data[start_index:end_index, 1], label='Original Data', color='gray')
    plt.plot(data[combined_indices, 0], data[combined_indices, 1], 'o', label='Baseline Points', color='red')
    baseline_curve = data[peak_start_idx:peak_end_idx, 0] * slope + intercept
    plt.plot(data[peak_start_idx:peak_end_idx, 0], baseline_curve, label='Baseline', color='green')
    plt.plot(data[peak_start_idx:peak_end_idx, 0], corrected_current, label='Corrected Current', color='purple')
    plt.fill_between(data[peak_start_idx:peak_end_idx, 0], 0, corrected_current, color='purple', alpha=0.3, label='Area Under Curve')
    plt.xlabel('Potential (V)')
    plt.ylabel('Current (A)')
    plt.title(f'Cycle {i+1} Charge Calculation')
    plt.legend()
    plt.grid(True)
    plt.show()

return charges