dimensionality_reduction_pca.md

Note: This is a generated markdown export from the Jupyter notebook file dimensionality_reduction_pca.ipynb. You can also view the notebook with the nbviewer from Jupyter.

Dimensionality Reduction with PCA (SVD)

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

from sklearn import decomposition, datasets
from matplotlib.colors import ListedColormap

iris = datasets.load_iris()
pca = decomposition.PCA(n_components=2)
new_dim = pca.fit_transform(iris.data)

df = pd.DataFrame(new_dim, columns=['X', 'Y'])
df['label'] = iris.target
df.head()

	X	Y	label
0	-2.684126	0.319397	0
1	-2.714142	-0.177001	0
2	-2.888991	-0.144949	0
3	-2.745343	-0.318299	0
4	-2.728717	0.326755	0

fig = plt.figure()
fig.suptitle('PCA (SVD)', fontsize=14, fontweight='bold')
ax = fig.add_subplot(111)

plt.scatter(df[df.label == 0].X, df[df.label == 0].Y, color='red', label=iris.target_names[0])
plt.scatter(df[df.label == 1].X, df[df.label == 1].Y, color='blue', label=iris.target_names[1])
plt.scatter(df[df.label == 2].X, df[df.label == 2].Y, color='green', label=iris.target_names[2])

_ = plt.legend(bbox_to_anchor=(1.25, 1))