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")

df = df[["calculatedRatio", "deviceRatio", "led1Average", "led1Buffer", "led1Sample", "led2Average", "led2Buffer", "led2Sample"]]
# print(df.to_numpy())

# # Contingency table
# observed = [
#     [25, 15, 10],
#     [10, 20, 15],
#     [15, 10, 20]
# ]

observed = df
# # Perform the chi-square test for independence
chi2, p, dof, expected = scipy.stats.chi2_contingency(observed)

print(f"Chi-square statistic: {chi2}")
print(f"P-value: {p}")
print(f"Degrees of freedom: {dof}")
print("Expected frequencies:")
print(expected)

df['calculatedRatio'].plot.kde()
df['deviceRatio'].plot.kde()
# plt.legend(['calculatedRatio'])
plt.legend(["calculatedRatio", "deviceRatio"], loc ="upper right") 
plt.show()

# Observed frequencies
observed = np.array(df['led1Buffer'].to_numpy())

# Expected frequencies
expected = np.array(df['led2Buffer'].to_numpy())  # Assuming equal expected frequencies

# Perform the chi-square goodness-of-fit test
chi2, p = scipy.stats.chisquare(observed, f_exp=expected)

print(f"Chi-square statistic: {chi2}")
print(f"P-value: {p}")