import os
import pandas as pd
import numpy as np

# location will help to open files in the same directory as the py-script
__location__ = os.path.realpath(
    os.path.join(os.getcwd(), os.path.dirname(__file__)))

df = pd.read_csv(os.path.join(__location__, 'vl2-varianz-v1.csv'))

# Dataframe
print(df)
#    x  freq
# 0  1  9
# 1  2  7
# 2  3  5
# 3  4  4
# 4  5  2
print(df.sum())
# x    15
# freq    27
sums = df.sum()
print(sums['freq'])
# 27

# Calculate Mean, respecting frequencies
rowSum = 0
for index, row in df.iterrows():
    rowSum = rowSum + row.x * row.freq
mean = rowSum / sums.freq
print("mean: ", mean)

# Calculate Variance, respecting frequencies
# Sample Variance: ^σ² = (1 / n - 1) * Σ(freq*(x - mean)²)
variancePart1 = (1 / (sums.freq - 1))
variancePart2 = 0
for index, row in df.iterrows():    
    variancePart2 = variancePart2 + (row.freq * (row.x - mean)**2)
    print(row['x'], row['freq'], variancePart2)
variance = variancePart1 * variancePart2
print("variance: ", variance)
# variance:  1.703703703703704