超级会员免费看
该博客详细探讨了泰坦尼克号数据集中的生还者与船舱等级、头衔、性别、家庭成员数量、船票共享和价格等因素的关系。通过数据预处理、特征工程和模型建立，对乘客的生存情况进行了预测。处理缺失值时，填充了Cabin、Embarked和Age字段，并创建了新的特征。
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.ensemble import RandomForestClassifier
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import re
from sklearn import preprocessing
from sklearn.feature_extraction import DictVectorizer
from sklearn.linear_model import LogisticRegression
plt.rcParams['font.sans-serif']=['SimHei'] #显示中文标签
plt.rcParams['axes.unicode_minus']=False
导入数据：
data_train = pd.read_csv("F:/kaggle数据/titanic/train.csv")
data_test = pd.read_csv("F:/kaggle数据/titanic/test.csv")
查看缺失信息：
"""
训练集中"Age"、"Cabin"、"Embarked"缺失
测试集中"Age"、"Fare"、"Cabin"缺失
测试集中无"Survived"标签值
"""
缺失值处理方法：
"""
1.直接删除此特征（缺损数据太多的情况，防止引入噪声）
2.直接删除缺损数据的样本（~土豪操作~只用于训练数据集，且样本量较大，缺损数据样本较少的情况）
3.直接将有无数值作为新的特征（数据缺失较多，且数据有无本身是对预测是一个有用的特征）
4.中值或均值回补（缺失数据较多，不想损失此较多训练数据，特征又比较重要的情况，是比较常用的方法）
5.参考其他特征，利用与此特征的相关性编写算法回补数据（~大神级操作~回补的准确性可能会比较高一些，但实现过程复杂）
"""
data_train.isnull().any()
结果：
PassengerId False
Survived False
Pclass False
Name False
Sex False
Age True
SibSp False
Parch False
Ticket False
Fare False
Cabin True
Embarked True
dtype: bool
data_test.isnull().any()
结果：
PassengerId False
Pclass False
Name False
Sex False
Age True
SibSp False
Parch False
Ticket False
Fare True
Cabin True
Embarked False
dtype: bool
data_train.info(null_counts=True)
结果：
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 PassengerId 891 non-null int64
1 Survived 891 non-null int64
2 Pclass 891 non-null int64
3 Name 891 non-null object
4 Sex 891 non-null object
5 Age 714 non-null float64
6 SibSp 891 non-null int64
7 Parch 891 non-null int64
8 Ticket 891 non-null object
9 Fare 891 non-null float64
10 Cabin 204 non-null object
11 Embarked 889 non-null object
dtypes: float64(2), int64
data_test.info(null_counts=True)
结果：
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 418 entries, 0 to 417
Data columns (total 11 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 PassengerId 418 non-null int64
1 Pclass 418 non-null int64
2 Name 418 non-null object
3 Sex 418 non-null object
4 Age 332 non-null float64
5 SibSp 418 non-null int64
6 Parch 418 non-null int64
7 Ticket 418 non-null object
8 Fare 417 non-null float64
9 Cabin 91 non-null object
10 Embarked 418 non-null object
dtypes: float64(2), int64(4), object(5)
memory usage: 36.0+ KB
一、查看数据信息
1、船舱等级与生还者的关系
1） 使用不同分类下的value_counts()
bottom = np.zeros(3)
x = np.sort(data_train["Pclass"].unique())
for i in range(2):
y = data_train[data_train["Survived"]==i].groupby(["Pclass"])["Survived"].value_counts()
plt.bar(x,y,bottom=bottom,width=0.5,label="{}".format(i))
for xi,yi,zi in zip(x,bottom,y):
plt.text(xi,((yi+zi)+yi)/2,zi,ha="center",va="center")
bottom += y.values
plt.legend()
plt.title("船舱等级与生还的关系")
plt.show()
2）直接挑选不同Pclass类别下的Survived分类数,并统计频数合并
h1 = data_train[data_train["Pclass"]==1]["Survived"].value_counts().reindex(index=(0,1))
h2 = data_train[data_train["Pclass"]==2]["Survived"].value_counts()
h3 = data_train[data_train["Pclass"]==3]["Survived"].value_counts()
pd.DataFrame([list(h1),list(h2),list(h3)],index=(1,2,3),columns=(0,1))
pd.DataFrame([np.array(h1),np.array(h2),np.array(h3)],index=(1,2,3),columns=(1,2))
merge = pd.DataFrame({0:data_train[data_train['Survived'] == 0]["Pclass"].value_counts(),1:data_train[data_train['Survived'] == 1]["Pclass"].value_counts()})
merge
3）使用 pd.crosstab直接进行频数统计
Pclass_Survived = pd.crosstab(index=data_train["Pclass"], columns=data_train["Survived"])
Pclass_Survived.plot(kind="bar",stacked=True)
X = np.arange(3)
bottom= np.zeros(3)
for i in range(2):
Z= Pclass_Survived[i]
for x,y,z in zip(X,bottom,Z):
plt.text(x,((y+z)+y)/2,z,ha="center",va="center")
bottom += Z
plt.title("船舱等级与生还的关系")
plt.show()
2、头衔与生还的关系
data_train['Appellation'] = data_train["Name"].apply(lambda x : re.search("\w+\.",x).group()).str.replace(".","")
data_train['Appellation'].replace(['Capt','Col','Countess','Don','Dr','Jonkheer','Lady','Major','Rev','Sir'], 'Rare',inplace=True)
data_train['Appellation'].replace(['Mlle','Ms'], 'Miss',inplace=True)
data_train['Appellation'].replace('Mme', 'Mrs',inplace=True)
data_train.Appellation.unique()
Appellation_Survived = pd.crosstab(index = data_train["Appellation"], columns = data_train["Survived"])
Appellation_Survived.plot(kind="bar")
plt.xticks(ticks=np.arange(5),labels=Appellation_Survived.index,rotation=360)
plt.title("头衔与生还的关系")
plt.show()
3、性别和生还的关系
Sex_Survived = pd.crosstab(data_train["Sex"],data_train["Survived"])
Sex_Survived.plot(kind="bar")
plt.xticks(ticks=np.arange(2),labels=(Sex_Survived.index),rotation=360)
plt.title("性别与生还者的关系")
plt.show()
4、兄弟姐妹配偶数量和生还的关系
Sibsp_Survived = pd.crosstab(data_train["SibSp"],data_train["Survived"])
Sibsp_Survived.plot(kind="bar")
plt.xticks(ticks=np.arange(7),labels=Sibsp_Survived.index,rotation=360)
plt.title("兄弟姐妹配偶数量和生还的关系")
plt.show()
Sibsp_Survived.iloc[1:,:].plot(kind="bar")
plt.xticks(ticks=np.arange(5),labels=Sibsp_Survived.iloc[1:,:].index,rotation=360)
plt.title("兄弟姐妹配偶数量和生还的关系")
plt.show()
5、同船家人数和生还的关系
Parch_Survived = pd.crosstab(index=data_train["Parch"],columns=data_train["Survived"])
Parch_Survived.plot(kind="bar")
plt.xticks(np.arange(7),Parch_Survived.index,rotation=360)
plt.title("同船家人数和生还的关系")
plt.show()
Parch_Survived.iloc[3:,:].plot(kind="bar")
plt.xticks(np.arange(4),Parch_Survived.iloc[3:,:].index,rotation=360)
plt.title("同船家人数和生还的关系")
plt.show()
6、船票是否共有与生还的关系
data_train["Ticket"].unique().size
681,小于船客总数，说明有共用票，新建特征，将共用票的置为1，反正，为0
不将分组类别作为索引（as_index = False）
统计不同Ticket使用者数量
Ticket_Count = data_train.groupby("Ticket",as_index = False)["PassengerId"].count()
结果：
Ticket PassengerId
0 110152 3
1 110413 3
2 110465 2
3 110564 1
4 110813 1
... ... ...
676 W./C. 6608 4
677 W./C. 6609 1
678 W.E.P. 5734 1
679 W/C 14208 1
680 WE/P 5735 2
681 rows × 2 columns
提取使用者为1的Ticket id，将data_train中满足Ticket使用者为1的置成0，其余的置成1
Ticket_Count_0 = Ticket_Count[Ticket_Count.PassengerId == 1]['Ticket']
data_train['GroupTicket'] = np.where(data_train.Ticket.isin(Ticket_Count_0), 0, 1)
GroupTicket_Survived = pd.crosstab(data_train["GroupTicket"],data_train["Survived"])
GroupTicket_Survived.plot(kind="bar")
plt.xticks(np.arange(2),GroupTicket_Survived.index,rotation=360)
plt.show()
7、船票价格和生还的关系
bins = np.arange(-50,600,50)
data_train["Fare_range"] = pd.cut(data_train["Fare"],bins=bins)
Fare_range_Survived = pd.crosstab(data_train["Fare_range"],data_train["Survived"])
Fare_range_Survived.plot(kind="bar")
plt.xticks(np.arange(8),Fare_range_Survived.index)
plt.show()
Fare_range_Survived.iloc[2:,:].plot(kind="bar")
plt.xticks(np.arange(6),Fare_range_Survived.iloc[2:,:].index,rotation=360)
plt.show()
二、 处理缺失值之前保证数据完整性，copy一份
train = data_train.copy()
1、"Cabin"使用No填充,表示没座位
train["Cabin"].fillna("No",inplace=True)
Cabin_Survived = pd.crosstab(train["Cabin"],train["Survived"])
train["Group_Cabin"] = np.where(train["Cabin"]=="No",0,1)
Group_Cabin_Survived = pd.crosstab(train["Group_Cabin"],train["Survived"])
Group_Cabin_Survived.plot(kind="bar")
plt.xticks(np.arange(2),Group_Cabin_Survived.index,rotation=360)
plt.show()
2、"Embarked"缺失两个使用众数填充
train["Embarked"].fillna(train["Embarked"].mode()[0],inplace=True)
train["Embarked_New"] = train["Embarked"].map({"S":0,"C":1,"Q":2})
Embarked_New_Survived = pd.crosstab(train["Embarked_New"],train["Survived"])
Embarked_New_Survived.plot(kind="bar")
plt.xticks(np.arange(3),Embarked_New_Survived.index)
plt.show()
3、"Age"采用头衔对应的中位数填充
Age_Appellation_median = train.groupby('Appellation')['Age'].median()
train.set_index(keys=train["Appellation"],inplace=True)
train["Age"].fillna(Age_Appellation_median,inplace=True)
Age缺失值填充完成后，使用reset_index，其中，drop表示不保留以前的索引，也就是"Appellation"，该特征在训练集后边仍有，可不保存，否则因为冲突报错
train = train.reset_index(drop=True)
bins = np.arange(0,90,10)
train["Age_Group"] = pd.cut(train["Age"], bins=bins)
Age_Group_Survived = pd.crosstab(train["Age_Group"],train["Survived"])
Age_Group_Survived.plot(kind="bar")
plt.xticks(np.arange(8),Age_Group_Survived.index,rotation=360)
plt.show()
三、新特征创建
train["Sex"] = train["Sex"].map({"male":0,"female":1})
dict = DictVectorizer(sparse=False)
Appellation_new = dict.fit_transform(pd.DataFrame(train["Appellation"]).to_dict(orient="records"))
Appellation_new = pd.DataFrame(Appellation_new)
train = pd.merge(train,Appellation_new,left_index=True,right_index=True)
train["Age_reserved"] = train["Age"]
train.loc[(train["Age"]>0)&(train["Age"]<=10),"Age"] =0
train.loc[(train["Age"]>10)&(train["Age"]<=20),"Age"] =1
train.loc[(train["Age"]>20)&(train["Age"]<=30),"Age"] =2
train.loc[(train["Age"]>30)&(train["Age"]<=40),"Age"] =3
train.loc[(train["Age"]>40)&(train["Age"]<=50),"Age"] =4
train.loc[(train["Age"]>50)&(train["Age"]<=60),"Age"] =5
train.loc[(train["Age"]>60)&(train["Age"]<=70),"Age"] =6
train.loc[(train["Age"]>70)&(train["Age"]<=80),"Age"] =7
train["Fare_reserved"] = train["Fare"]
train.loc[(train["Fare"]>-50)&(train["Fare"]<=0),"Fare"] = 0
train.loc[(train["Fare"]>0)&(train["Fare"]<=50),"Fare"] = 1
train.loc[(train["Fare"]>50)&(train["Fare"]<=100),"Fare"] = 2
train.loc[(train["Fare"]>100)&(train["Fare"]<=150),"Fare"] = 3
train.loc[(train["Fare"]>150)&(train["Fare"]<=200),"Fare"] = 4
train.loc[(train["Fare"]>200)&(train["Fare"]<=250),"Fare"] = 5
train.loc[(train["Fare"]>250)&(train["Fare"]<=300),"Fare"] = 6
train.loc[(train["Fare"]>300)&(train["Fare"]<=350),"Fare"] = 7
train.loc[(train["Fare"]>350)&(train["Fare"]<=400),"Fare"] = 8
train.loc[(train["Fare"]>400)&(train["Fare"]<=450),"Fare"] = 9
train.loc[(train["Fare"]>450)&(train["Fare"]<=500),"Fare"] = 10
train.loc[(train["Fare"]>500)&(train["Fare"]<=550),"Fare"] = 11
train["Family"] = train["SibSp"] + train["Parch"] + 1
train.drop(["PassengerId","Name","Ticket","Cabin","Embarked","Appellation","Fare_range","Age_Group"],axis=1,inplace=True)
四、模型搭建
x = train.drop("Survived",axis=1).values
y = train["Survived"].values
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.25,random_state=0)
print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(y_test.shape)
结果：
(668, 17)
(668,)
(223, 17)
(223,)
knn = KNeighborsClassifier()
dec = DecisionTreeClassifier()
rf = RandomForestClassifier()
param = {"n_neighbors":[2,3,4,5,6,7,8,9,10]}
grid = GridSearchCV(estimator=knn,param_grid=param,cv=5)
grid.fit(x_train,y_train)
print(grid.best_params_)
print(grid.score(x_test,y_test))
结果：
{'n_neighbors': 5}
0.7399103139013453
param = {"max_depth":[2,3,4,5,6]}
grid = GridSearchCV(estimator=dec,param_grid=param,cv=5)
grid.fit(x_train,y_train)
print(grid.best_params_)
print(grid.score(x_test,y_test))
结果：
{'max_depth': 3}
0.7982062780269058
param = {"max_depth":[2,3,4,5,6], "n_estimators":[10,30,50,70,100,120,150,170,200]}
grid = GridSearchCV(estimator=rf,param_grid=param,cv=5)
grid.fit(x_train,y_train)
print(grid.best_params_)
print(grid.score(x_test,y_test))
结果：
{'max_depth': 6, 'n_estimators': 120}
0.820627802690583
logis = LogisticRegression()
logis.get_params
param = {"C":[0.01,0.03,0.1,0.3,1,2],
"penalty":["l1","l2"]}
grid = GridSearchCV(estimator=logis,param_grid=param,cv=5)
grid.fit(x_train,y_train)
print(grid.best_params_)
print(grid.score(x_test,y_test))
结果：
{'C': 1, 'penalty': 'l1'}
0.8295964125560538
data_test["Appellation"] = data_test["Name"].apply(lambda x : re.search("\w+\.",x).group()).str.replace(".","")
data_test['Appellation'].replace(['Capt','Col','Countess','Don','Dr','Jonkheer','Lady','Major','Rev','Sir'], 'Rare',inplace=True)
data_test['Appellation'].replace(['Mlle','Ms'], 'Miss',inplace=True)
data_test['Appellation'].replace('Mme', 'Mrs',inplace=True)
五、对测试集进行同样特征处理操作
data_test["Appellation"] = data_test["Name"].apply(lambda x : re.search("\w+\.",x).group()).str.replace(".","")
data_test['Appellation'].replace(['Capt','Col','Countess','Don','Dr','Jonkheer','Lady','Major','Rev','Sir'], 'Rare',inplace=True)
data_test['Appellation'].replace(['Mlle','Ms'], 'Miss',inplace=True)
data_test['Appellation'].replace('Mme', 'Mrs',inplace=True)
test = data_test.copy()
Appellation_new_test = pd.DataFrame(dict.transform(pd.DataFrame(test["Appellation"]).to_dict(orient="records")))
test = pd.merge(test,Appellation_new_test,left_index=True,right_index=True)
test["Cabin"].fillna("No",inplace=True)
test["Group_Cabin"] = np.where(test["Cabin"]=="No",0,1)
test["Embarked_New"] = test["Embarked"].map({"S":0,"C":1,"Q":2})
test["Sex"] = test["Sex"].map({"male":0,"female":1})
test_median = test.groupby("Appellation")["Age"].median()
test.set_index("Appellation",inplace=True)
test["Age"].fillna(test_median ,inplace=True)
test.reset_index(drop=False,inplace=True)
bins = np.arange(0,90,10)
test["Age_range"] = pd.cut(test["Age"],bins=bins)
test["Age_range"].value_counts(dropna=False)
test["Age_reserved"] = test["Age"]
test.loc[(test["Age"]>0)&(test["Age"]<=10),"Age"] =0
test.loc[(test["Age"]>10)&(test["Age"]<=20),"Age"] =1
test.loc[(test["Age"]>20)&(test["Age"]<=30),"Age"] =2
test.loc[(test["Age"]>30)&(test["Age"]<=40),"Age"] =3
test.loc[(test["Age"]>40)&(test["Age"]<=50),"Age"] =4
test.loc[(test["Age"]>50)&(test["Age"]<=60),"Age"] =5
test.loc[(test["Age"]>60)&(test["Age"]<=70),"Age"] =6
test.loc[(test["Age"]>70)&(test["Age"]<=80),"Age"] =7
test["Fare"].fillna(test["Fare"].mean(),inplace=True)
test["Fare_reserved"] = test["Fare"]
test.loc[(test["Fare"]>-50)&(test["Fare"]<=0),"Fare"] = 0
test.loc[(test["Fare"]>0)&(test["Fare"]<=50),"Fare"] = 1
test.loc[(test["Fare"]>50)&(test["Fare"]<=100),"Fare"] = 2
test.loc[(test["Fare"]>100)&(test["Fare"]<=150),"Fare"] = 3
test.loc[(test["Fare"]>150)&(test["Fare"]<=200),"Fare"] = 4
test.loc[(test["Fare"]>200)&(test["Fare"]<=250),"Fare"] = 5
test.loc[(test["Fare"]>250)&(test["Fare"]<=300),"Fare"] = 6
test.loc[(test["Fare"]>300)&(test["Fare"]<=350),"Fare"] = 7
test.loc[(test["Fare"]>350)&(test["Fare"]<=400),"Fare"] = 8
test.loc[(test["Fare"]>400)&(test["Fare"]<=450),"Fare"] = 9
test.loc[(test["Fare"]>450)&(test["Fare"]<=500),"Fare"] = 10
test.loc[(test["Fare"]>500)&(test["Fare"]<=550),"Fare"] = 11
test["Family"] = test["SibSp"] + test["Parch"] + 1
test["Ticket"].value_counts()
test_count0 = test.groupby("Ticket",as_index=False)["PassengerId"].count()
test_count0 = test_count0[test_count0["PassengerId"]==1]["Ticket"]
test['GroupTicket'] = np.where(test["Ticket"].isin(test_count0), 0, 1)
test.drop(["PassengerId","Name","Ticket","Cabin","Embarked","Appellation","Age_range"],axis=1,inplace=True)
order_train = train.drop("Survived",axis=1)
order = list(order_train.columns)
test = test[order]
x_pre = test.values
param = {"max_depth":[2,3,4,5,6], "n_estimators":[10,30,50,70,100,120,150,170,200]}
grid = GridSearchCV(estimator=rf,param_grid=param,cv=5)
grid.fit(x_train,y_train)
print(grid.score(x_test,y_test))
y_pre = grid.predict(x_pre)
print(grid.best_params_)
pd.DataFrame(y_pre).to_csv("pre123.csv",index=False,header=False)
扫一扫
564
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
