“Matrice de corrélation Python des fonctionnalités” Réponses codées

Matrice de corrélation Python des fonctionnalités

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

file = 'https://aegis4048.github.io/downloads/notebooks/sample_data/unconv_MV_v5.csv'
df = pd.read_csv(file)

df = df.iloc[:, 1:-1]

corr = df.corr(method='spearman')

# Generate a mask for the upper triangle
mask = np.zeros_like(corr, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True

# Set up the matplotlib figure
fig, ax = plt.subplots(figsize=(6, 5))

# Generate a custom diverging colormap
cmap = sns.diverging_palette(220, 10, as_cmap=True, sep=100)

# Draw the heatmap with the mask and correct aspect ratio
sns.heatmap(corr, mask=mask, cmap=cmap, vmin=-1, vmax=1, center=0, linewidths=.5)

fig.suptitle('Correlation matrix of features', fontsize=15)
ax.text(0.77, 0.2, 'aegis4048.github.io', fontsize=13, ha='center', va='center',
         transform=ax.transAxes, color='grey', alpha=0.5)

fig.tight_layout()