import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
train=pd.read_csv(r'D:\xunleixiazai\train.csv')
test=pd.read_csv(r'D:\xunleixiazai\test.csv')
train.info()
print('-'*40)
test.info()
train.head(10)
train.describe()

> train['Age']=train['Age'].fillna(train['Age'].mean())
> train['Embarked']=train['Embarked'].fillna(train['Embarked'].max())
> train=train.drop(['Name','Ticket','Cabin'],axis=1)

pmean=train[['Pclass','Survived']].groupby(['Pclass'],as_index=False).mean()
pcount=train[['Pclass','Survived']].groupby(['Pclass'],as_index=False).count()
pd.merge(pmean,pcount,on='Pclass',suffixes=('_mean','_count'))

smean=train[['Sex','Survived']].groupby(['Sex'],as_index=False).mean()
scount=train[['Sex','Survived']].groupby(['Sex'],as_index=False).count()
pd.merge(smean,scount,on='Sex',suffixes=('_mean','_count'))

train['Age']=train['Age'].astype(np.int32)
pd.cut(train['Age'],[0,18,35,60])
train['Age']=np.where(train['Age']<18,0,np.where(train['Age']<35,1,np.where(train['Age']<60,2,3)))
对Sex也进行01划分frmale=0.male=1
train['Sex']=np.where(train['Sex']=='female',0,1)
对 Embarked进行划分s=0,c=1,q=2
train['Embarked']=np.where(train['Embarked']=='S',0,np.where(train['Embarked']=='C',1,2))

train['family']=train['SibSp']+train['Parch']+1
train['isalone']=np.where(train['family']==1,0,1)
train.drop('family',axis=1)

train=train.drop(['SibSp','Parch'],axis=1)
train=train.drop('family',axis=1)
train=train.drop(['Fare','PassengerId'],axis=1)

test['Age']=test['Age'].fillna(test['Age'].mean())
test['Embarked']=test['Embarked'].fillna(test['Age'].max())
test=test.drop(['Name','Ticket','Cabin'],axis=1)
test['Age']=test['Age'].astype(np.int32)
pd.cut(test['Age'],[0,18,35,60])
test['Age']=np.where(test['Age']<18,0,np.where(test['Age']<35,1,np.where(test['Age']<60,2,3)))
test['Sex']=np.where(test['Sex']=='female',0,1)
test['Embarked']=np.where(test['Embarked']=='S',0,np.where(test['Embarked']=='C',1,2))
test['family']=test['SibSp']+test['Parch']+1
test['isalone']=np.where(test['family']==1,0,1)
test.drop('family',axis=1)
test=test.drop(['SibSp','Parch'],axis=1)
test=test.drop('family',axis=1)
test=test.drop('Fare',axis=1)

X_train=train.drop('Survived',axis=1)
y_train=train['Survived']
X_test=test.drop('PassengerId',axis=1).copy()
X_train.shape,y_train.shape,X_test.shape

from sklearn.linear_model import LogisticRegression
clf=LogisticRegression()
clf.fit(X_train,y_train)
clf
x_pred=clf.predict(X_test)
x_pred
result=pd.DataFrame({'PassengerId':test['PassengerId'], 'Survived':x_pred.astype(np.int32)})
result.to_csv(r"D:\xunleixiazai\titanic.csv", index=False)

from sklearn.ensemble import RandomForestClassifier
rf=RandomForestClassifier(n_estimators=100)
rf.fit(X_train,y_train)
x_pred=rf.predict(X_test)
random_forest.score(X_train, y_train)
result=pd.DataFrame({'PassengerId':test['PassengerId'],'Survived':x_pred.astype(np.int32)})
result.to_csv(r"D:\xunleixiazai\titanic1.csv", index=False)