Gaussian Fit Case

import pandas as pd
import matplotlib.pyplot as plt
from scipy.stats import norm

# Replace 'B5 segmentSummary (1).csv' with the actual CSV file path
file_path = 'B5 segmentSummary (1).csv'

# Read the CSV file into a Pandas DataFrame
df = pd.read_csv(file_path)

# Calculate summary statistics for the 'cases' column
cases_summary = df['Slide name'].describe()

# Print summary statistics for 'cases' column
print("Summary Statistics for 'Slide name' column:")
print(cases_summary)

# Define the range of column positions you want to analyze (columns 6 through 9)
start_column_position = 6  # Corresponds to column 6
end_column_position = 9   # Corresponds to column 9

# Iterate through each numerical column and create a separate figure for Gaussian distribution
for i in range(start_column_position, end_column_position + 1):
    col = df.columns[i]

    # Skip 'cases' column
    if col == 'Slide name':
        continue

    plt.figure(figsize=(8, 6))

    # Plot Gaussian distribution
    target_column = df.iloc[:, i]
    mean = target_column.mean()
    std_dev = target_column.std()

    # Generate data for the Gaussian distribution
    x_range = target_column.dropna().values
    fitted_data = norm.pdf(x_range, mean, std_dev)

    # Plot the Gaussian distribution
    plt.plot(x_range, fitted_data, 'b-', label='Fitted Gaussian')

    # Plot settings
    plt.hist(target_column.dropna(), bins=30, density=True, alpha=0.7, color='gray', label='Data Histogram')
    plt.axvline(mean, color='red', linestyle='dashed', linewidth=2, label='Mean')
    plt.xlabel('Values')
    plt.ylabel('Density')
    plt.title(f'Gaussian Fit for {col}')
    plt.legend()

    plt.show()