1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
|
"""
=========================================================
Pipelining: chaining a PCA and a logistic regression
=========================================================
The PCA does an unsupervised dimensionality reduction, while the logistic
regression does the prediction.
We use a GridSearchCV to set the dimensionality of the PCA
"""
# Code source: Gaël Varoquaux
# Modified for documentation by Jaques Grobler
# License: BSD 3 clause
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn import datasets
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
# Define a pipeline to search for the best combination of PCA truncation
# and classifier regularization.
pca = PCA()
# Define a Standard Scaler to normalize inputs
scaler = StandardScaler()
# set the tolerance to a large value to make the example faster
logistic = LogisticRegression(max_iter=10000, tol=0.1)
pipe = Pipeline(steps=[("scaler", scaler), ("pca", pca), ("logistic", logistic)])
X_digits, y_digits = datasets.load_digits(return_X_y=True)
# Parameters of pipelines can be set using '__' separated parameter names:
param_grid = {
"pca__n_components": [5, 15, 30, 45, 60],
"logistic__C": np.logspace(-4, 4, 4),
}
search = GridSearchCV(pipe, param_grid, n_jobs=2)
search.fit(X_digits, y_digits)
print("Best parameter (CV score=%0.3f):" % search.best_score_)
print(search.best_params_)
# Plot the PCA spectrum
pca.fit(X_digits)
fig, (ax0, ax1) = plt.subplots(nrows=2, sharex=True, figsize=(6, 6))
ax0.plot(
np.arange(1, pca.n_components_ + 1), pca.explained_variance_ratio_, "+", linewidth=2
)
ax0.set_ylabel("PCA explained variance ratio")
ax0.axvline(
search.best_estimator_.named_steps["pca"].n_components,
linestyle=":",
label="n_components chosen",
)
ax0.legend(prop=dict(size=12))
# For each number of components, find the best classifier results
results = pd.DataFrame(search.cv_results_)
components_col = "param_pca__n_components"
best_clfs = results.groupby(components_col)[
[components_col, "mean_test_score", "std_test_score"]
].apply(lambda g: g.nlargest(1, "mean_test_score"))
ax1.errorbar(
best_clfs[components_col],
best_clfs["mean_test_score"],
yerr=best_clfs["std_test_score"],
)
ax1.set_ylabel("Classification accuracy (val)")
ax1.set_xlabel("n_components")
plt.xlim(-1, 70)
plt.tight_layout()
plt.show()
|
