kaggle_泰坦尼克幸存者可视化

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier   # 决策树的类
from sklearn.model_selection import GridSearchCV, train_test_split, cross_val_score  # 网格搜索，TTS， 交叉验证

data = pd.read_csv(r"D:/Python/datalearning/sklearn/day08_data.csv")
data.head()

# 将缺失值严重的数据进行删除
# axis=1：表示对列进行操作，inplace=True表示用生成的数据代替原来的数据
data.drop(["Cabin","Name","Ticket"], inplace=True, axis=1)

# 缺失值处理
data["Age"] = data["Age"].fillna(data["Age"].mean())   # 用均值进行填充
# 将存在缺失值数据的行进行删除，dropna默认对行进行操作
data = data.dropna()

# 查看属性中有多少类：通过unique()函数进行显示，结果只有3类
data["Embarked"].unique()

[OUT]:array(['S', 'C', 'Q'], dtype=object)

# 重点：如何将输出标签中的分类转成数字
labels = data["Embarked"].unique().tolist()
data["Embarked"] = data["Embarked"].apply(lambda x: labels.index(x))

# data["sex"] = (data["Sex"] == "male").astype("int")
data.loc[:,"Sex"] = (data["Sex"] == "male").astype("int")   # 将生成的布尔值转成0-1， 
data.head()

# 取出属性不是Survied的所有行的数据
X = data.iloc[:,data.columns != "Survived"]  
y = data.iloc[:,data.columns == "Survived"]    作为最终的输出结果

Xtrain, Xtest, ytrain, ytest = train_test_split(X,y,test_size=0.3)

# Xtrain.index = range(Xtrain.shape[0])
for i in [Xtrain, Xtest, ytrain, ytest]:
    i.index = range(i.shape[0])  # 将range函数的结果赋值给索引

# 普通模型
clf = DecisionTreeClassifier(random_state=25)
clf = clf.fit(Xtrain, ytrain)
score = clf.score(Xtest,ytest)
score

# 交叉验证：结果未必会比上面的好
clf = DecisionTreeClassifier(random_state=25)
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     # max_depth不同
                                 ,criterion="entropy"  # 欠拟合使用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()

# 基尼系数0-0.5；信息熵的范围是0-1；gini_threholds = np.linspace(0,0.5,50)
# [*range(1,10)]：转成列表形式
parameters = {
    "criterion":("gini","entropy")
    ,"splitter":("best","random")
    ,"max_depth":[*range(1,10)]
    ,"min_samples_leaf":[*range(1,50,5)]
    ,"min_impurity_decrease":[*np.linspace(0,0.5,50)]
}

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

GS.best_params_   # 返回参数和参数取值列表中的最佳组合
GS.best_score_    # 网格搜索模型后的评判标准