lda_pca.py

import matplotlib.pyplot as plt

from sklearn.datasets.base import load_data
from sklearn.utils import Bunch
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis


def load_netflix(return_X_y=False):
    data, target, target_names = load_data('/home/comtom/extra/netflix/', 'file1.csv')

    if return_X_y:
        return data, target

    return Bunch(data=data, target=target,
                 target_names=[1, 2, 3, 4, 5],
                 DESCR='',
                 feature_names=['movieId', 'userID', 'ratingDate'])

netflix = load_netflix()

X = netflix.data
y = netflix.target
target_names = netflix.target_names

pca = PCA(n_components=2)
X_r = pca.fit(X).transform(X)

lda = LinearDiscriminantAnalysis(n_components=2)
X_r2 = lda.fit(X, y).transform(X)

print('Explained variance ratio (primeros dos componentes): %s' % str(pca.explained_variance_ratio_))

plt.figure()
colors = ['navy', 'turquoise', 'darkorange', 'red', 'yellow']
lw = 1

for color, i, target_name in zip(colors, [1, 2, 3, 4, 5], target_names):
    plt.scatter(X_r[y == i, 0], X_r[y == i, 1], color=color, alpha=.4, lw=lw,
                label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('PCA del dataset de netflix')

plt.figure()
for color, i, target_name in zip(colors, [1, 2, 3, 4, 5], target_names):
    plt.scatter(X_r2[y == i, 0], X_r2[y == i, 1], alpha=.4, color=color,
                label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('LDA del dataset de netflix')

plt.show()