# Why is my Tableau correlation coefficient different from what I calculated using Python?

I'm required to create a correlation matrix table using Tableau so I've created a version using Python to check if I did everything right.

The numbers are coming out different for both calculations. For example, correlation coefficient of Hotel 3 and 34 cross shows as 0.62 using python, but is 0.639 using Tableau.

Am I doing either calculation wrong? Please see this link for raw data, tableau workbook and pdf of plot created using python.

The code I used to create the correlation matrix is as follows:

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

%matplotlib inline

pivot = data.pivot_table(index=['Period','Slice'], columns='Hotel', values='Net Score Change', aggfunc=np.sum, fill_value=0)
pivot.reset_index(inplace=True)

sns.set(font_scale=0.5)
plt.figure(figsize=(20,16))
sns.heatmap(pivot.corr(), cmap='coolwarm', annot=True)


Both are using the Pearson algorithm to calculate correlations: https://en.m.wikipedia.org/wiki/Pearson_correlation_coefficient

However, the floating values operations are slightly different and this slight difference becomes taller when you make several operations like Pearson.

You can try by calculating the Pearson algorithm manually for both cases.