python 决策树建立 泰坦尼克号

概述### 泰坦尼克号海难生存人员预测# 导入需要的库import pandas as pd from sklearn.tree import DecisionTreeClassifierfrom sklearn.model_selection import train_test_splitfrom sklearn.model_selection import GridS

### 泰坦尼克号海难生存人员预测# 导入需要的库import pandas as pd from sklearn.tree import  DecisionTreeClassifIErfrom sklearn.model_selection import train_test_splitfrom sklearn.model_selection import gridsearchcvfrom sklearn.model_selection import cross_val_predictimport matplotlib.pyplot as pltdata = pd.read_csv(r‘file:///E:/学习/python/机器学习课件 9.20-9.21/titanic/train.csv‘,index_col = 0)# 查看数据集的基本特征data.head()data.infodata.shape#不涉及到训练集和测试集之间相互影响的#删除缺失值过多的列，和观察判断来说和预测的y没有关系的列data.drop(["Cabin","name","Ticket"],inplace=True,axis=1)data.infodata.head()# 对数据集中的缺失值进行处理  年龄中缺失值  这里用均值进行填补data.loc[:,‘Age‘] = data.loc[:,‘Age‘].fillna(data.loc[:,‘Age‘].mean())# 对缺失数据少的数据直接删除data = data.dropna()data.info# =============================================================================# #将分类变量转换为数值变量# # 将二分类变量转化为0，1变量# # astype能够轻松的将pandas中文本变量转换为数值型变量# data[‘Sex‘] = (data[‘Sex‘] == ‘male‘).astype("int")# data.head()# =============================================================================labels=data[‘Sex‘].unique().toList()# 得到去重之后的数据 将其转换为列表 其各个数值所对应的数据的索引分别为0，1 # 我们用函数将其索引赋值给对应的数据 ， 即实现了对其的离散化和数值化data[‘Sex‘]=[*map(lambda x:labels.index(x),data[‘Sex‘])]# 将三分类的问题转化为数值变量labels = data[‘Embarked‘].unique().toList()  # 对数据列进行去重 并将其转换为列表格式data["Embarked"] = data["Embarked"].apply(lambda x: labels.index(x))# 提取标签和特征矩阵  分裂数据集 -- 测试集合训练集X = data.iloc[:,1:]       Y = data.iloc[:,1]             # 导入数据划分的包from sklearn.model_selection import train_test_split# 注意 这里的X_train,X_test,y_train,y_test的顺序不能颠倒X_train,y_test = train_test_split(X,Y,test_size = 0.3,random_state = 420)# 首先修正分割后的索引for i in [X_train,y_test]:    i.index = range(i.shape[0])# =============================================================================# # 对数据集进行数据预处理 处理缺失值和异常值# X_train.info   # 发现年龄这一列中有缺失值  这里用均值进行填补# X_train.loc[:,‘Age‘] = X_train.Age.fillna(X_train.loc[:,‘Age‘].mean())# # X_test.loc[:,‘Age‘] = X_test.Age.fillna(X_test.loc[:,‘Age‘].mean())# =============================================================================# 建立预测模型# 实例化模型clf = DecisionTreeClassifIEr(random_state=25)# 利用训练数据集对实例化后的数据进行训练clf = clf.fit(X_train,y_train)# 查看训练后的模型分别在训练集和测试集上面的得分clf.score(X_train,y_train)clf.score(X_test,y_test)clf.feature_importances_# 显示出各个特征属性所对应的名称以及重要性[*zip(data.columns,clf.feature_importances_)]from sklearn.model_selection import cross_val_scorevar = cross_val_score(clf,Xtrain,Ytrain,cv=10).var()var# 调整树的深度观察模型的拟合程度tr = []te = []test = []# 设置树的深度在0到10之间for i in range(1,10):    clf = DecisionTreeClassifIEr(max_depth = i,random_state= 666)    clf = clf.fit(X_train,y_train)    score_train = clf.score(X_train,y_train)    score_te = cross_val_score(clf,cv=10).mean()    tr.append(score_train)    te.append(score_te)    # 模型在测试集上面的准确率    score_test = clf.score(X_test,y_test)    test.append(score_test)print(len(test))print(max(te))len(tr)# 切换绘图风格plt.style.use("ggplot")plt.plot(range(1,10),tr,color="red",label="train")plt.plot(range(1,te,color="blue",label="cross_val_score")plt.plot(range(1,test,color="green",label="test")plt.xticks(range(1,10))plt.legend()plt.show()# 用网格搜索调整参数from sklearn.model_selection import gridsearchcvimport numpy as npgini_thresholds = np.linspace(0,0.5,20)gini_thresholds# 首先构造一个所有搜索参数的字典parameters = {‘splitter‘:(‘best‘,‘random‘),‘criterion‘:("gini","entropy"),"max_depth":range(1,‘min_samples_leaf‘:range(1,50,5),‘min_impurity_decrease‘:np.linspace(0,20)}# 实例化模型,先不传参clf = DecisionTreeClassifIEr(random_state=25)# 实例化网格搜索APIGS = gridsearchcv(clf,parameters,cv = 5,verbose=1 )# 对数据进行网格搜索GS.fit(Xtrain,Ytrain)#属性best_params_查看调整出来的最佳参数GS.best_params_#属性best_score_查看最佳分数GS.best_score_

总结

以上是内存溢出为你收集整理的python 决策树建立 泰坦尼克号全部内容，希望文章能够帮你解决python 决策树建立 泰坦尼克号所遇到的程序开发问题。

如果觉得内存溢出网站内容还不错，欢迎将内存溢出网站推荐给程序员好友。