Prep data
# Get data
import numpy as np
import pandas as pd
df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/'
'machine-learning-databases/wine/wine.data',
header=None)
df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash',
'Alcalinity of ash', 'Magnesium', 'Total phenols',
'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins',
'Color intensity', 'Hue',
'OD280/OD315 of diluted wines', 'Proline']
# Split data
from sklearn.model_selection import train_test_split
X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.3,
stratify=y,
random_state=0)
# Standardize data
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_test_std = sc.transform(X_test)
Feature importance
from sklearn.decomposition import PCA
pca = PCA()
X_train_pca = pca.fit_transform(X_train_std)
pca.explained_variance_ratio_
array([0.36951469, 0.18434927, 0.11815159, 0.07334252, 0.06422108,
0.05051724, 0.03954654, 0.02643918, 0.02389319, 0.01629614,
0.01380021, 0.01172226, 0.00820609])
import matplotlib.pyplot as plt
plt.bar(range(1, 14), pca.explained_variance_ratio_, alpha=0.5, align='center')
plt.step(range(1, 14), np.cumsum(pca.explained_variance_ratio_), where='mid')
plt.ylabel('Explained variance ratio')
plt.xlabel('Principal components')
plt.show()
PCA with k dimensions
pca = PCA(n_components=2)
X_train_pca = pca.fit_transform(X_train_std)
X_test_pca = pca.transform(X_test_std)
plt.scatter(X_train_pca[:, 0], X_train_pca[:, 1])
plt.xlabel('PC 1')
plt.ylabel('PC 2')
plt.show()
Kernel PCA
import matplotlib.pyplot as plt
from sklearn.datasets import make_moons
from sklearn.decomposition import KernelPCA
X, y = make_moons(n_samples=100, random_state=123)
scikit_kpca = KernelPCA(n_components=2, kernel='rbf', gamma=15)
X_skernpca = scikit_kpca.fit_transform(X)
plt.scatter(X_skernpca[y == 0, 0], X_skernpca[y == 0, 1],
color='red', marker='^', alpha=0.5)
plt.scatter(X_skernpca[y == 1, 0], X_skernpca[y == 1, 1],
color='blue', marker='o', alpha=0.5)
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.tight_layout()
plt.show()
