#泰坦尼克号幸存者预测

泰坦尼克号幸存者预测

泰坦尼克号训练数据见百度网盘：
链接：https://pan.baidu.com/s/1yHvYb2usyW24LqacHk9-Dw
提取码：p1do

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import cross_val_score
import matplotlib.pyplot as plt

data = pd.read_csv(r"./taitan_data.csv")

data.head()

data.info()

#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)

#处理缺失值，对缺失值较多的列进行填补，有一些特征只确实一两个值，可以采取直接删除记录的方法
data["Age"] = data["Age"].fillna(data["Age"].mean())
data = data.dropna()

#将分类变量转换为数值型变量

#将二分类变量转换为数值型变量
#astype能够将一个pandas对象转换为某种类型，和apply(int(x))不同，astype可以将文本类转换为数字，用这个方式可以很便捷地将二分类特征转换为0~1
data["Sex"] = (data["Sex"]== "male").astype("int")

#将三分类变量转换为数值型变量
labels = data["Embarked"].unique().tolist()
data["Embarked"] = data["Embarked"].apply(lambda x: labels.index(x))

#查看处理后的数据集
data.head()

data.head()

X = data.iloc[:,data.columns != "Survived"]
y = data.iloc[:,data.columns == "Survived"]

from sklearn.model_selection import train_test_split
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,y,test_size=0.3)

#修正测试集和训练集的索引
for i in [Xtrain, Xtest, Ytrain, Ytest]:
    i.index = range(i.shape[0])
    
#查看分好的训练集和测试集
Xtrain.head()

clf = DecisionTreeClassifier(random_state=25)
clf = clf.fit(Xtrain, Ytrain)
score_ = clf.score(Xtest, Ytest)

score_

score = cross_val_score(clf,X,y,cv=10).mean()

score

tr = []
te = []
for i in range(10):
    clf = DecisionTreeClassifier(random_state=25
                                 ,max_depth=i+1
                                 ,criterion="entropy"
                                )
    clf = clf.fit(Xtrain, Ytrain)
    score_tr = clf.score(Xtrain,Ytrain)
    score_te = cross_val_score(clf,X,y,cv=10).mean()
    tr.append(score_tr)
    te.append(score_te)
print(max(te))
plt.plot(range(1,11),tr,color="red",label="train")
plt.plot(range(1,11),te,color="blue",label="test")
plt.xticks(range(1,11))
plt.legend()
plt.show()

import numpy as np
gini_thresholds = np.linspace(0,0.5,20)

parameters = {'splitter':('best','random')
              ,'criterion':("gini","entropy")
              ,"max_depth":[*range(1,10)]
              ,'min_samples_leaf':[*range(1,50,5)]
              ,'min_impurity_decrease':[*np.linspace(0,0.5,20)]
             }

clf = DecisionTreeClassifier(random_state=25)
GS = GridSearchCV(clf, parameters, cv=10)
GS.fit(Xtrain,Ytrain)

GS.best_params_

GS.best_score_

GS.best_estimator_

GS.best_params_