机器学习——决策树
决策树是一种用于分类和回归的非参数监督学习方法。目标是创建一个模型，通过从数据特性中推导出简单的决策规则来预测目标变量的值
导入类库
1 import numpy as np 2 import pandas as pd 3 from sklearn.feature_extraction import DictVectorizer 4 from sklearn.tree import DecisionTreeClassifier 5 from sklearn.model_selection import train_test_split
简单版
1 def decide_play1(): 2 df = pd.read_csv('dtree.csv') 3 dict_train = df.to_dict(orient='record') 4 5 dv = DictVectorizer(sparse=False) 6 dv_train = dv.fit_transform(dict_train) 7 # print(dv_train) 8 # dv_train1 = np.append(dv_train, dv_train[:, 5].reshape(-1, 1), axis=1) 9 # dv_train2 = np.delete(dv_train1, 5, axis=1) 10 # print('*' * 50) 11 # print(dv_train2) 12 13 # print(dv_train[:,:5]) 14 # print(dv_train[:,6:]) 15 # print(dv_train[:,5]) 16 y = dv_train[:, 5] 17 x = np.delete(dv_train, 5, axis=1) 18 print(x) 19 print(y) 20 dtc = DecisionTreeClassifier() 21 dtc.fit(x, y.reshape(-1, 1)) 22 print(dtc.predict(np.array([x[3]])))
正式版
1 def decide_play(): 2 # ID3 3 df = pd.read_csv('dtree.csv') 4 # 将数据转换为字典格式，orient='record'参数指定数据格式为{column:value,column:value}的形式 5 dict_train = df.loc[:, ['Outlook', 'Temperatur', 'Humidity', 'Windy']].to_dict(orient='record') 6 dict_target = pd.DataFrame(df['PlayGolf'], columns=['PlayGolf']).to_dict(orient='record') 7 8 9 # 训练数据字典向量化 10 dv_train = DictVectorizer(sparse=False) 11 x_train = dv_train.fit_transform(dict_train) 12 13 # 目标数据字典向量化 14 dv_target = DictVectorizer(sparse=False) 15 y_target = dv_target.fit_transform(dict_target) 16 17 # 创建训练模型并训练 18 d_tree = DecisionTreeClassifier() 19 d_tree.fit(x_train, y_target) 20 21 data_predict = { 22 'Humidity': 85, 23 'Outlook': 'sunny', 24 'Temperatur': 85, 25 'Windy': False 26 } 27 28 x_data = dv_train.transform(data_predict) 29 print(dv_target.inverse_transform(d_tree.predict(x_data))) 30 31 32 if __name__ == '__main__': 33 decide_play()
泰坦尼克生存率决策
1 import numpy as np 2 import pandas as pd 3 from sklearn.feature_extraction import DictVectorizer 4 from sklearn.model_selection import train_test_split 5 from sklearn.tree import DecisionTreeClassifier 6 from sklearn.metrics import r2_score 7 8 9 def titanic_tree(): 10 # 获取数据 11 df = pd.read_csv('Titanic.csv') 12 # df = df.fillna(0) 13 # dict_train = df.loc[:, ['Pclass', 'Age', 'Sex']].to_dict(orient='record') 14 # dict_target = pd.DataFrame(df['Survived'], columns=['Survived']).to_dict(orient='record') 15 # x_train, x_test, y_train, y_test = train_test_split(dict_train, dict_target, test_size=0.25) 16 17 # 处理数据，找出特征值和目标值 18 x = df.loc[:, ['Pclass', 'Age', 'Sex']] 19 y = df.loc[:, ['Survived']] 20 # 缺失值处理 21 x['Age'].fillna(x['Age'].mean(), inplace=True) 22 # 分割数据集到训练集和测试集 23 x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25) 24 # print(y_test) 25 dv_train = DictVectorizer(sparse=False) 26 x_train = dv_train.fit_transform(x_train.to_dict(orient='record')) 27 x_test = dv_train.transform(x_test.to_dict(orient='record')) 28 29 dv_target = DictVectorizer(sparse=False) 30 y_target = dv_target.fit_transform(y_train.to_dict(orient='record')) 31 y_test = dv_target.transform(y_test.to_dict(orient='record')) 32 # print(y_test) 33 # 用决策树进行预测 34 d_tree = DecisionTreeClassifier() 35 d_tree.fit(x_train, y_train) 36 37 data_predict = { 38 'Pclass': 1, 39 'Age': 38, 40 'Sex': 'female' 41 42 } 43 44 x_data = dv_train.transform(data_predict) 45 print(dv_target.inverse_transform(d_tree.predict(x_data).reshape(-1,1))) 46 # print(d_tree.predict(x_test)) 47 # print(y_test) 48 # 预测准确率 49 # print(d_tree.score(x_test, y_test)) 50 51 52 if __name__ == '__main__': 53 titanic_tree()
(Decision Tree)及其变种是另一类将输入空间分成不同的区域，每个区域有独立参数的算法。
决策树分类算法是一种基于实例的归纳学习方法，它能从给定的无序的训练样本中，提炼出树型的分类模型。树中的每个非叶子节点记录了使用哪个特征来进行类别的判断，每个叶子节点则代表了最后判断的类别。根节点到每个叶子节点均形成一条分类的路径规则。而对新的样本进行测试时，只需要从根节点开始，在每个分支节点进行测试，沿着相应的分支递归地进入子树再测试，一直到达叶子节点，该叶子节点所代表的类别即是当前测试样本的预测类别
