from data_parser import DataParser
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
parser = DataParser('europe.csv')
matrix_non_standarized = np.matrix(parser.get_numerical_csv())
# Create a figure instance
fig = plt.figure(1, figsize=(9, 6))
# Create an axes instance
ax = fig.add_subplot(111)
## Custom x-axis labels
ax.set_xticklabels([
'Area', 'GDP', 'Inflation', 'Life.expect', 'Military', 'Pop.growth',
'Unemployment'
])
## add patch_artist=True option to ax.boxplot()
## to get fill color
bp = ax.boxplot(matrix_non_standarized, patch_artist=True)
## change outline color, fill color and linewidth of the boxes
for box in bp['boxes']:
# change outline color
box.set(color='#7570b3', linewidth=2)
# change fill color
box.set(facecolor='#1b9e77')
'GDP': matrix_for_correlation[1],
'Inflation': matrix_for_correlation[2],
'Life.expect': matrix_for_correlation[3],
'Military': matrix_for_correlation[4],
'Pop.growth': matrix_for_correlation[5],
'Unemployment': matrix_for_correlation[6]
}
df = pd.DataFrame(matrix_for_correlation_with_keys, columns=[
'Area', 'GDP', 'Inflation', 'Life.expect', 'Military', 'Pop.growth', 'Unemployment'])
correlation_matrix = df.corr()
# If you want to show heatmap:
covariance_matrix = np.cov(np.array(parser.get_numerical_csv()).T)
print('COV', covariance_matrix)
autovals_corr, autovecs_corr = np.linalg.eig(correlation_matrix)
print('AUTOVALS | AUTOVECS, COR')
print(autovals_corr, autovecs_corr)
autovals_cov, autovecs_cov = np.linalg.eig(covariance_matrix)
print('AUTOVALS | AUTOVECS, COV')
print(autovals_cov, autovecs_cov)
# PCA
n_components = 7
pca = PCA(n_components=n_components)
