plot_pca_2d_projection with examples#

An example showing the plot_pca_2d_projection function used by a scikit-learn PCA object.

 9 # Authors: The scikit-plots developers
10 # SPDX-License-Identifier: BSD-3-Clause

Import scikit-plots#

16 from sklearn.datasets import (
17     load_iris as data_3_classes,
18 )
19 from sklearn.decomposition import PCA
20 from sklearn.model_selection import train_test_split
21
22 import numpy as np
23
24 np.random.seed(0)  # reproducibility
25 # importing pylab or pyplot
26 import matplotlib.pyplot as plt
27
28 # Import scikit-plot
29 import scikitplot as sp

Loading the dataset#

35 # Load the data
36 X, y = data_3_classes(return_X_y=True, as_frame=True)
37 X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.5, random_state=0)

PCA#

43 # Create an instance of the PCA
44 pca = PCA(random_state=0).fit(X_train)
45
46 # Create an instance of the LogisticRegression
47 # model = LogisticRegression(max_iter=int(1e5), random_state=0).fit(X_train, y_train)
48
49 # Perform predictions
50 # y_val_prob = model.predict_proba(X_val)

Plot!#

56 # Plot!
57 ax = sp.decomposition.plot_pca_2d_projection(
58     pca,
59     X_train,
60     y_train,
61     biplot=True,
62     feature_labels=X.columns.tolist(),
63     save_fig=True,
64     save_fig_filename="",
65     # overwrite=True,
66     add_timestamp=True,
67     # verbose=True,
68 )
PCA 2-D Projection

Tags: model-type: classification model-workflow: feature engineering plot-type: scatter plot-type: 2D plot-type: principal component plot-type: PCA level: beginner purpose: showcase

Total running time of the script: (0 minutes 0.552 seconds)

Related examples

plot_pca_component_variance with examples

plot_pca_component_variance with examples

plot_cumulative_gain with examples

plot_cumulative_gain with examples

plot_lift with examples

plot_lift with examples

plot_feature_importances with examples

plot_feature_importances with examples

Gallery generated by Sphinx-Gallery