In [ ]:
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
import numpy as np
np.set_printoptions(suppress=True)
digits = load_digits()
X, y = digits.data, digits.target
X_train, X_test, y_train, y_test = train_test_split(X, y)
0) Import the model
In [ ]:
from sklearn.decomposition import PCA
1) Instantiate the model
In [ ]:
pca = PCA(n_components=2)
2) Fit to training data
In [ ]:
pca.fit(X)
3) Transform to lower-dimensional representation
In [ ]:
print(X.shape)
X_pca = pca.transform(X)
X_pca.shape
In [ ]:
import matplotlib.pyplot as plt
%matplotlib inline
plt.scatter(X_pca[:, 0], X_pca[:, 1], c=plt.cm.tab10(y))
In [ ]:
from sklearn.manifold import Isomap
isomap = Isomap()
In [ ]:
X_isomap = isomap.fit_transform(X)
In [ ]:
plt.figure()
plt.scatter(X_isomap[:, 0], X_isomap[:, 1], c=plt.cm.tab10(y))
In [ ]:
# %load solutions/digits_tsne.py