机器学习——多方法简单分类（含有 决策树、朴素贝叶斯、随机森林、svm向量机）含源码 自学指南

直接给代码：

# -- coding: gbk --
from sklearn.datasets import load_breast_cancer
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import  train_test_split
from sklearn.tree import export_graphviz
import pandas as pd
import graphviz
import mglearn
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_moons
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.svm import SVC
from pylab import *
def 决策树():
    cancer = load_breast_cancer()
    X_train, X_test, y_train, y_test = train_test_split(
        cancer.data, cancer.target, stratify=cancer.target, random_state=42)
    tree = DecisionTreeClassifier(random_state=0)
    print(X_train)
    print(y_train.shape)
    tree.fit(X_train, y_train)
    y_predict=tree.predict(X_test)
    print("Accuracy on training set: {:.3f}".format(tree.score(X_train, y_train)))
    print("Accuracy on test set: {:.3f}".format(tree.score(X_test, y_test)))
    '''
    export_graphviz(tree, out_file="tree.dot", class_names=["malignant", "benign"], feature_names=cancer.feature_names,
                    impurity=False, filled=True)

    with open("tree.dot") as f:
        dot_graph = f.read()
    graphviz.Source(dot_graph)
    '''
    print("特征的重要：
{}".format(tree.feature_importances_))

def 随机森林():
    X, y = make_moons(n_samples=100, noise=0.25, random_state=3)
    X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y,random_state=42)
    '''五颗随机森林'''
    forest = RandomForestClassifier(n_estimators=5, random_state=2)
    forest.fit(X_train, y_train)
    y_pred=forest.predict(X_test)
    print(y_pred)
    print(y_test)
    print(np.mean(y_test==y_pred ))
    fig, axes = plt.subplots(2, 3, figsize=(20, 10))
    for i, (ax, tree) in enumerate(zip(axes.ravel(), forest.estimators_)):    ax.set_title("Tree {}".format(i))
    mglearn.plots.plot_tree_partition(X_train, y_train, tree, ax=ax)
    mglearn.plots.plot_2d_separator(forest, X_train, fill=True, ax=axes[-1, -1], alpha=.4)
    axes[-1, -1].set_title("Random Forest")
    mglearn.discrete_scatter(X_train[:, 0], X_train[:, 1], y_train)

def 梯度提升树():
    cancer = load_breast_cancer()
    X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, random_state=0)
    #gbrt = GradientBoostingClassifier(random_state=0, max_depth=1)
    gbrt = GradientBoostingClassifier(random_state=0,  learning_rate=0.01)
    gbrt.fit(X_train, y_train)
    y_pred=gbrt.predict(X_test)
    print(y_pred)
    print(np.mean(y_pred==y_test))

def SVM向量机简易():
    X, y = mglearn.tools.make_handcrafted_dataset()
    '''
    gamma参数是上一节给出的公式中的参数，用于控制高斯核的宽度。它决定了点与点之间“靠近”是指多大的距离。
    C参数是正则化参数，与线性模型中用到的类似。它限制每个点的重要性（或者更确切地说，每个点的dual_coef_）。

    '''
    svm = SVC(kernel='rbf', C=10, gamma=0.1).fit(X, y)
    mglearn.plots.plot_2d_separator(svm, X, eps=.5)
    mglearn.discrete_scatter(X[:, 0], X[:, 1], y)
    # 画出支持向量
    sv = svm.support_vectors_
    sv_labels = svm.dual_coef_.ravel() > 0
    mglearn.discrete_scatter(sv[:, 0], sv[:, 1], sv_labels, s=15, markeredgewidth=3)
    plt.xlabel("Feature 0")
    plt.ylabel("Feature 1")
    plt.show()

def 预处理向量机数据():
    cancer = load_breast_cancer()
    X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, random_state=0)
    svc = SVC()
    svc.fit(X_train, y_train)
    y_pred=svc.predict(X_test)
    print(np.mean(y_pred==y_test))

    '''预处理——缩放'''
    min_on_training = X_train.min(axis=0)
    range_on_training = (X_train - min_on_training).max(axis=0)

    X_train_scaled = (X_train - min_on_training) / range_on_training
    X_test_scaled = (X_test - min_on_training) / range_on_training
    print("Minimum for each feature
{}".format(X_train_scaled.min(axis=0)))
    print("Maximum for each feature
 {}".format(X_train_scaled.max(axis=0)))

    '''变换'''
    X_test_scaled = (X_test - min_on_training) / range_on_training
    svc = SVC()
    svc.fit(X_train_scaled, y_train)
    y_pred=svc.predict(X_test_scaled)
    print(np.mean(y_pred==y_test))
if __name__ =='__main__':
    预处理向量机数据()