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

curdir = os.getcwd()
path_delim = '/'
df = pd.read_excel(curdir + path_delim + "data/tests_28_10_2023_19_16.xlsx", sheet_name="data")

# Generating a sample dataset
np.random.seed(0)  # For reproducibility
sample_data = np.random.normal(loc=0, scale=1, size=100)  # Generating 100 samples from a normal distribution

# Performing the Shapiro-Wilk test
statistic, p_value = stats.shapiro(df['calculatedRatio'])

# Printing the results
print(f"Shapiro-Wilk test statistic: {statistic}")
print(f"P-value: {p_value}")

alpha = 0.05  # Set the significance level
if p_value > alpha:
    print("Sample looks Gaussian (fail to reject H0 - null hypothesis)")
else:
    print("Sample does not look Gaussian (reject H0 - null hypothesis)")