通过直方图进行PCA准备

import graphviz
import mglearn
from mpl_toolkits.mplot3d import Axes3D
from sklearn.datasets import load_breast_cancer, make_blobs
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from IPython.display import display
import matplotlib.pyplot as plt
import numpy as np
import matplotlib as mt
import pandas as pd
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
cancer = load_breast_cancer()

# X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target,
#                                                     random_state=1)
fig, axes = plt.subplots(15, 2, figsize=(10, 20))
malignant = cancer.data[cancer.target == 0]
benign = cancer.data[cancer.target == 1]
ax = axes.ravel()
# 直方图显示了数据值的分布情况
for i in range(30):
    _, bins = np.histogram(cancer.data[:, i], bins=50)
    # 逐列取数
    ax[i].hist(malignant[:, i], bins=bins, color=mglearn.cm3(0), alpha=.5)
    ax[i].hist(benign[:, i], bins=bins, color=mglearn.cm3(2), alpha=.5)
    ax[i].set_title(cancer.feature_names[i])
    ax[i].set_yticks(())
ax[0].set_xlabel("Feature magnitude")
ax[0].set_ylabel("Frequency")
ax[0].legend(["malignant", "benign"], loc="best")
fig.tight_layout()
plt.show()