Libraries

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

Data

from sklearn.datasets import load_breast_cancer

cancer = load_breast_cancer()

cancer.keys()

df = pd.DataFrame(cancer['data'], columns=cancer['feature_names'])

df.head()

PCA Visualisatie

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
scaled_data = scaler.fit_transform(df)

scaled_data

from sklearn.decomposition import PCA

pca = PCA(n_components=2)
pca.fit(scaled_data)

pca_data = pca.transform(scaled_data)

scaled_data.shape

pca_data.shape

plt.figure(figsize=(8,6))
plt.scatter(pca_data[:,0], pca_data[:,1], c=cancer['target'], cmap='plasma')
plt.xlabel('Eerste PC')
plt.ylabel('Tweede PC')

pca.explained_variance_ratio_

Interpretatie

pca.components_

df_comp = pd.DataFrame(pca.components_, columns=cancer['feature_names'])

df_comp

plt.figure(figsize=(12,6))
sns.heatmap(df_comp, cmap='plasma')