from warnings import simplefilter
simplefilter(action='ignore', category=FutureWarning)

from sklearn.tree import export_graphviz
from sklearn.tree import DecisionTreeClassifier
#3：1拆分数据集
from sklearn.model_selection import train_test_split
#乳腺癌数据集
from sklearn.datasets import load_breast_cancer
import pydot
cancer = load_breast_cancer()
#参数random_state是指随机生成器，0表示函数输出是固定不变的
X_train,X_test,y_train,y_test = train_test_split(cancer['data'],cancer['target'],random_state=42)
tree = DecisionTreeClassifier(random_state=0)
tree.fit(X_train,y_train)
print('Train score:{:.3f}'.format(tree.score(X_train,y_train)))
print('Test score:{:.3f}'.format(tree.score(X_test,y_test)))
#生成可视化图
export_graphviz(tree,out_file="tree.dot",class_names=['严重','轻微'],feature_names=cancer.feature_names,impurity=False,filled=True)
#展示可视化图
(graph,) = pydot.graph_from_dot_file('tree.dot')
graph.write_png('tree.png')






import numpy as np
import matplotlib.pyplot as plt

from sklearn import linear_model, decomposition, datasets
from sklearn.pipeline import Pipeline
from  sklearn.model_selection import GridSearchCV

logistic = linear_model.LogisticRegression()

pca = decomposition.PCA()
pipe = Pipeline(steps=[('pca', pca), ('logistic', logistic)])

digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target

###############################################################################
# Plot the PCA spectrum
pca.fit(X_digits)

plt.figure(1, figsize=(4, 3))
plt.clf()
plt.axes([.2, .2, .7, .7])
plt.plot(np.cumsum(pca.explained_variance_ratio_), linewidth=2)
plt.axis('tight')
plt.xlabel('n_components')
plt.ylabel('explained_variance_')

###############################################################################
# Prediction

n_components = [20, 40, 64]
Cs = np.logspace(-4, 4, 3)

#Parameters of pipelines can be set using ‘__’ separated parameter names:

estimator = GridSearchCV(pipe,
                         dict(pca__n_components=n_components,
                              logistic__C=Cs))
estimator.fit(X_digits, y_digits)

plt.axvline(estimator.best_estimator_.named_steps['pca'].n_components,
            linestyle=':', label='n_components chosen')
plt.legend(prop=dict(size=12))
plt.show()