sklearn速度复习-决策树

//例子
from sklearn.feature_extraction import DictVectorizer
from sklearn import tree
from sklearn import preprocessing
import csv
Dtree = open(r'AllElectronics.csv', 'r')# 读入数据
reader = csv.reader(Dtree)
headers = reader.__next__()# 获取第一行数据
print(headers)
featureList = []# 定义两个列表
labelList = []
for row in reader: # 把label存入list
    labelList.append(row[-1])
    rowDict = {}
    for i in range(1, len(row)-1):
        rowDict[headers[i]] = row[i]#建立一个数据字典
    featureList.append(rowDict)# 把数据字典存入list
print(featureList)
vec = DictVectorizer()# 把数据转换成01表示
x_data = vec.fit_transform(featureList).toarray()
print("x_data: " + str(x_data))
print(vec.get_feature_names())# 打印属性名称
print("labelList: " + str(labelList))# 打印标签
lb = preprocessing.LabelBinarizer()# 把标签转换成01表示
y_data = lb.fit_transform(labelList)
print("y_data: " + str(y_data))
model = tree.DecisionTreeClassifier(criterion='entropy')# 创建决策树模型
model.fit(x_data, y_data)# 输入数据建立模型
x_test = x_data[0]# 测试
print("x_test: " + str(x_test))
predict = model.predict(x_test.reshape(1,-1))
print("predict: " + str(predict))
import graphviz # http://www.graphviz.org/# 导出决策树
dot_data = tree.export_graphviz(model, 
                                out_file = None, 
                                feature_names = vec.get_feature_names(),
                                class_names = lb.classes_,
                                filled = True,
                                rounded = True,
                                special_characters = True)
graph = graphviz.Source(dot_data)
graph.render('computer')
#graph
vec.get_feature_names()
print(lb.classes_)

//决策树-线性二分
import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import classification_report
from sklearn import tree
data = np.genfromtxt("LR-testSet.csv", delimiter=",")# 载入数据
x_data = data[:,:-1]
y_data = data[:,-1]
plt.scatter(x_data[:,0],x_data[:,1],c=y_data) 
plt.show()
model = tree.DecisionTreeClassifier()# 创建决策树模型
model.fit(x_data, y_data)# 输入数据建立模型
import graphviz # http://www.graphviz.org/# 导出决策树
dot_data = tree.export_graphviz(model, 
                                out_file = None, 
                                feature_names = ['x','y'],
                                class_names = ['label0','label1'],
                                filled = True,
                                rounded = True,
                                special_characters = True)
graph = graphviz.Source(dot_data)
#graph
x_min, x_max = x_data[:, 0].min() - 1, x_data[:, 0].max() + 1# 获取数据值所在的范围
y_min, y_max = x_data[:, 1].min() - 1, x_data[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),# 生成网格矩阵
                     np.arange(y_min, y_max, 0.02))
z = model.predict(np.c_[xx.ravel(), yy.ravel()])# ravel与flatten类似，多维数据转一维。flatten不会改变原始数据，ravel会改变原始数据
z = z.reshape(xx.shape)
cs = plt.contourf(xx, yy, z)# 等高线图
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)# 样本散点图
plt.show()
predictions = model.predict(x_data)
print(classification_report(predictions,y_data))

#非线性二分
import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import classification_report
from sklearn import tree
from sklearn.model_selection import train_test_split
data = np.genfromtxt("LR-testSet2.txt", delimiter=",")# 载入数据
x_data = data[:,:-1]
y_data = data[:,-1]
plt.scatter(x_data[:,0],x_data[:,1],c=y_data) 
plt.show()
x_train,x_test,y_train,y_test = train_test_split(x_data, y_data) #分割数据
#创建决策树模型,max_depth，树的深度,min_samples_split 内部节点再划分所需最小样本数
model = tree.DecisionTreeClassifier(max_depth=7,min_samples_split=4)
model.fit(x_train, y_train)# 输入数据建立模型
import graphviz # http://www.graphviz.org/# 导出决策树
dot_data = tree.export_graphviz(model, 
                                out_file = None, 
                                feature_names = ['x','y'],
                                class_names = ['label0','label1'],
                                filled = True,
                                rounded = True,
                                special_characters = True)
graph = graphviz.Source(dot_data)
#graph
x_min, x_max = x_data[:, 0].min() - 1, x_data[:, 0].max() + 1# 获取数据值所在的范围
y_min, y_max = x_data[:, 1].min() - 1, x_data[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),# 生成网格矩阵
                     np.arange(y_min, y_max, 0.02))
z = model.predict(np.c_[xx.ravel(), yy.ravel()])# ravel与flatten类似，多维数据转一维。flatten不会改变原始数据，ravel会改变原始数据
z = z.reshape(xx.shape)
cs = plt.contourf(xx, yy, z)# 等高线图
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)# 样本散点图
plt.show()
predictions = model.predict(x_train)
print(classification_report(predictions,y_train))
predictions = model.predict(x_test)
print(classification_report(predictions,y_test))

cart
from sklearn import tree
import numpy as np
data = np.genfromtxt("cart.csv", delimiter=",")# 载入数据
x_data = data[1:,1:-1]
y_data = data[1:,-1]
model = tree.DecisionTreeClassifier()# 创建决策树模型
model.fit(x_data, y_data)# 输入数据建立模型
#graph