[sklearn数据科学浅尝]kaggle泰坦尼克号幸存预测问题（入全球前10%）

import os
import pandas as pd
import numpy as np
import warnings
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
import seaborn as sns
from sklearn import preprocessing
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn.ensemble import GradientBoostingClassifier
from sklearn import model_selection
excl = lambda x: os.popen(x).readlines()
%matplotlib inline
warnings.filterwarnings('ignore')

train = pd.read_csv('./titanic_datas/train.csv')
train.head()

test = pd.read_csv('./titanic_datas/test.csv')
test.head()

train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId    891 non-null int64
Survived       891 non-null int64
Pclass         891 non-null int64
Name           891 non-null object
Sex            891 non-null object
Age            714 non-null float64
SibSp          891 non-null int64
Parch          891 non-null int64
Ticket         891 non-null object
Fare           891 non-null float64
Cabin          204 non-null object
Embarked       889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB

test.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 418 entries, 0 to 417
Data columns (total 11 columns):
PassengerId    418 non-null int64
Pclass         418 non-null int64
Name           418 non-null object
Sex            418 non-null object
Age            418 non-null float64
SibSp          418 non-null int64
Parch          418 non-null int64
Ticket         418 non-null object
Fare           418 non-null float64
Cabin          91 non-null object
Embarked       418 non-null object
dtypes: float64(2), int64(4), object(5)
memory usage: 36.0+ KB

train.describe()

test.describe()

fare_mean = train["Fare"].mean()
test.loc[pd.isnull(test.Fare),'Fare'] = fare_mean 
embarked_mode = train['Embarked'].mode()
train.loc[pd.isnull(train.Embarked),['Embarked']] = embarked_mode[0]
age_mean = train['Age'].mean()
train.loc[pd.isnull(train.Age),['Age']] = age_mean
test.loc[pd.isnull(test.Age),['Age']] = age_mean

label = train['Survived']
train.drop('Survived',axis=1,inplace=True)

X_train,X_test,Y_train,Y_test = train_test_split(train,label,test_size = 0.3,random_state = 1)

X_train['Survived'] = Y_train
X_test['Survived'] = Y_test 

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5))
sns.barplot('Sex', 'Survived', data=X_train, ax=axis1) 
sns.barplot('Sex', 'Survived', data=X_test, ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a23a577f0>

train['Sex'] = train['Sex'].apply(lambda x: 1 if x == 'male' else 0)
test['Sex'] = test['Sex'].apply(lambda x: 1 if x == 'male' else 0)

train = pd.get_dummies(data= train,columns=['Sex'])
test = pd.get_dummies(data= test,columns=['Sex'])

def Name_Title_Code(x):
    if x == 'Mr.':
        return 1
    if (x == 'Mrs.') or (x=='Ms.') or (x=='Lady.') or (x == 'Mlle.') or (x =='Mme'):
        return 2
    if x == 'Miss':
        return 3
    if x == 'Rev.':
        return 4
    return 5

X_train['Name_Title'] = X_train['Name'].apply(lambda x: x.split(',')[1]).apply(lambda x: x.split()[0])
X_test['Name_Title'] = X_test['Name'].apply(lambda x: x.split(',')[1]).apply(lambda x: x.split()[0])

X_train.groupby('Name_Title')['Survived'].count()

Name_Title
Capt.        1
Col.         2
Don.         1
Dr.          4
Lady.        1
Major.       1
Master.     27
Miss.      126
Mlle.        1
Mme.         1
Mr.        365
Mrs.        87
Rev.         5
the          1
Name: Survived, dtype: int64

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5))
sns.barplot('Name_Title', 'Survived', data=X_train.sort_values('Name_Title'), ax=axis1) 
sns.barplot('Name_Title', 'Survived', data=X_test.sort_values('Name_Title'), ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a23e730f0>

def Name_Title_Code(x):
    if x == 'Mr.':
        return 1
    if (x == 'Mrs.') or (x=='Ms.') or (x=='Lady.') or (x == 'Mlle.') or (x =='Mme'):
        return 2
    if x == 'Miss':
        return 3
    if x == 'Rev.':
        return 4
    return 5

train['Name_Title'] = train['Name'].apply(lambda x: x.split(',')[1]).apply(lambda x: x.split()[0])
test['Name_Title'] = test['Name'].apply(lambda x: x.split(',')[1]).apply(lambda x: x.split()[0])

train['Name_Title'] = train['Name_Title'].apply(Name_Title_Code)
test['Name_Title'] = test['Name_Title'].apply(Name_Title_Code)

train = pd.get_dummies(columns = ['Name_Title'], data = train)
test = pd.get_dummies(columns = ['Name_Title'], data = test)

train.head()

X_train['Name_len'] = X_train['Name'].apply(lambda x: len(x))
X_test['Name_len'] = X_test['Name'].apply(lambda x: len(x))

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(20,10))
sns.barplot('Name_len', 'Survived', data=X_train.sort_values(['Name_len']), ax=axis1) 
sns.barplot('Name_len', 'Survived', data=X_test.sort_values(['Name_len']), ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a24bdc4e0>

train['Name_len'] = train['Name'].apply(lambda x: len(x))
test['Name_len'] = test['Name'].apply(lambda x: len(x))

def Ticket_First_Let(x):
    return x[0]

X_train['Ticket_First_Letter'] = X_train['Ticket'].apply(Ticket_First_Let)
X_test['Ticket_First_Letter'] = X_test['Ticket'].apply(Ticket_First_Let)

X_train.groupby('Ticket_First_Letter')['Survived'].count()

Ticket_First_Letter
1     87
2    129
3    225
4     10
5      2
6      6
7      6
8      1
9      1
A     20
C     32
F      3
L      3
P     49
S     40
W      9
Name: Survived, dtype: int64

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5))
sns.barplot('Ticket_First_Letter', 'Survived', data=X_train.sort_values('Ticket_First_Letter'), ax=axis1) 
sns.barplot('Ticket_First_Letter', 'Survived', data=X_test.sort_values('Ticket_First_Letter'), ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a24dc7358>

def Ticket_First_Letter_Code(x):
    if (x == '1'):
        return 1
    if x == '3':
        return 2
    if x == '4':
        return 3
    if x == 'C':
        return 4
    if x == 'S':
        return 5
    if x == 'P':
        return 6
    if x == '6':
        return 7
    if x == '7':
        return 8
    if x == 'A':
        return 9
    if x == 'W':
        return 10
    return 11

train['Ticket_First_Letter'] = train['Ticket'].apply(Ticket_First_Let)
test['Ticket_First_Letter'] = test['Ticket'].apply(Ticket_First_Let)

train['Ticket_First_Letter'].unique()

array(['A', 'P', 'S', '1', '3', '2', 'C', '7', 'W', '4', 'F', 'L', '9',
       '6', '5', '8'], dtype=object)

test['Ticket_First_Letter'].unique()

array(['3', '2', '7', 'A', '6', 'W', 'S', 'P', 'C', '1', 'F', '4', '9',
       'L'], dtype=object)

train['Ticket_First_Letter'] = train['Ticket_First_Letter'].apply(Ticket_First_Letter_Code)
test['Ticket_First_Letter'] = test['Ticket_First_Letter'].apply(Ticket_First_Letter_Code)

X_train['Cabin'] = X_train['Cabin'].fillna('Missing')
X_test['Cabin'] = X_test['Cabin'].fillna('Missing')

def Cabin_First_Letter(x):
    if x == 'Missing':
        return 'XX'
    return x[0]

X_train['Cabin_First_Letter'] = X_train['Cabin'].apply(Cabin_First_Letter)
X_test['Cabin_First_Letter'] = X_test['Cabin'].apply(Cabin_First_Letter) 

X_train.groupby('Cabin_First_Letter')['Survived'].count()

Cabin_First_Letter
A      12
B      28
C      41
D      21
E      22
F       8
G       3
XX    488
Name: Survived, dtype: int64

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5))
sns.barplot('Cabin_First_Letter', 'Survived', data=X_train.sort_values('Cabin_First_Letter'), ax=axis1) 
sns.barplot('Cabin_First_Letter', 'Survived', data=X_test.sort_values('Cabin_First_Letter'), ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a24ba4208>

def Cabin_First_Letter_Code(x):
    if x == 'XX':
        return 1
    if x == 'B':
        return 2
    if x == 'C':
        return 3
    if x == 'D':
        return 4     
    return 5

train['Cabin'] = train['Cabin'].fillna('Missing')
test['Cabin'] = test['Cabin'].fillna('Missing')

train['Cabin_First_Letter'] = train['Cabin'].apply(Cabin_First_Letter)
test['Cabin_First_Letter'] = test['Cabin'].apply(Cabin_First_Letter) 

train['Cabin_First_Letter'] = train['Cabin_First_Letter'].apply(Cabin_First_Letter_Code)
test['Cabin_First_Letter'] = test['Cabin_First_Letter'].apply(Cabin_First_Letter_Code)

train = pd.get_dummies(columns = ['Cabin_First_Letter'], data = train) 
test = pd.get_dummies(columns = ['Cabin_First_Letter'], data = test) 

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5))
sns.barplot('Embarked', 'Survived', data=X_train.sort_values('Embarked'), ax=axis1) 
sns.barplot('Embarked', 'Survived', data=X_test.sort_values('Embarked'), ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a259bc6d8>

train = pd.get_dummies(train,columns = ['Embarked'])
test = pd.get_dummies(test,columns = ['Embarked'])

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5))
sns.barplot('SibSp', 'Survived', data=X_train.sort_values('SibSp'), ax=axis1) 
sns.barplot('SibSp', 'Survived', data=X_test.sort_values('SibSp'), ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a25b7ea90>

X_train['Fam_Size'] = X_train['SibSp']  + X_train['Parch'] 
X_test['Fam_Size'] = X_test['SibSp']  + X_test['Parch'] 

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5))
sns.barplot('Fam_Size', 'Survived', data=X_train.sort_values('Parch'), ax=axis1) 
sns.barplot('Fam_Size', 'Survived', data=X_test.sort_values('Parch'), ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a25c67fd0>

def Family_feature(train, test):
    for i in [train, test]:
        i['Fam_Size'] = np.where((i['SibSp']+i['Parch']) == 0 , 'Solo',
                           np.where((i['SibSp']+i['Parch']) <= 3,'Nuclear', 'Big'))
        del i['SibSp']
        del i['Parch']
    return train, test 
train, test  = Family_feature(train, test)

train = pd.get_dummies(train,columns = ['Fam_Size']) 
test =  pd.get_dummies(test,columns = ['Fam_Size']) 

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5))
sns.barplot('Pclass', 'Survived', data=X_train.sort_values('Pclass'), ax=axis1) 
sns.barplot('Pclass', 'Survived', data=X_test.sort_values('Pclass'), ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a25e84c50>

train['Pclass_1']  = np.int32(train['Pclass'] == 1)  
train['Pclass_2']  = np.int32(train['Pclass'] == 2)  
train['Pclass_3']  = np.int32(train['Pclass'] == 3)  

test['Pclass_1']  = np.int32(test['Pclass'] == 1)  
test['Pclass_2']  = np.int32(test['Pclass'] == 2)  
test['Pclass_3']  = np.int32(test['Pclass'] == 3)  

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5)) 
sns.distplot(X_train[X_train.Survived==1]['Age'].dropna().values, bins=range(0, 81, 6),color='red', ax=axis1) 
sns.distplot(X_train[X_train.Survived==0]['Age'].dropna().values, bins=range(0, 81, 6),color = 'blue', ax=axis1) 

sns.distplot(X_test[X_test.Survived==1]['Age'].dropna().values, bins=range(0, 81, 6),color='red', ax=axis2) 
sns.distplot(X_test[X_test.Survived==0]['Age'].dropna().values, bins=range(0, 81, 6),color = 'blue', ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a2614dd30>

train['Small_Age'] = np.int32(train['Age'] <= 5)  
train['Old_Age'] = np.int32(train['Age'] >= 65)  
train['Middle_Age'] = np.int32((train['Age'] >= 15) & (train['Age'] <= 25))  
 
test['Small_Age'] = np.int32(test['Age'] <= 5)  
test['Old_Age'] = np.int32(test['Age'] >= 65)  
test['Middle_Age'] = np.int32((test['Age'] >= 15) & (test['Age'] <= 25))  

X_train['Fare'] = X_train['Fare'] + 1
X_test['Fare'] = X_test['Fare'] + 1

X_train['Fare'] = X_train['Fare'].apply(np.log)
X_test['Fare'] = X_test['Fare'].apply(np.log)

fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,5)) 
sns.distplot(X_train[X_train.Survived==1]['Fare'].dropna().values, bins=range(0, 10, 1),color='red', ax=axis1) 
sns.distplot(X_train[X_train.Survived==0]['Fare'].dropna().values, bins=range(0, 10, 1),color = 'blue', ax=axis1) 

sns.distplot(X_test[X_test.Survived==1]['Fare'].dropna().values, bins=range(0, 10, 1),color='red', ax=axis2) 
sns.distplot(X_test[X_test.Survived==0]['Fare'].dropna().values, bins=range(0, 10, 1),color = 'blue', ax=axis2) 

<matplotlib.axes._subplots.AxesSubplot at 0x1a2627ac50>

train['Fare'] = train['Fare'] + 1
test['Fare'] = test['Fare'] + 1

train['Fare'] = train['Fare'].apply(np.log)
test['Fare'] = test['Fare'].apply(np.log) 

train['Fare_0_2'] = np.int32(train['Fare'] <= 2)
train['Fare_2_3'] = np.int32((train['Fare'] > 2) & (train['Fare'] <= 3) )
train['Fare_3_4'] = np.int32((train['Fare'] > 3) & (train['Fare'] <= 4) )
train['Fare_4_5'] = np.int32((train['Fare'] > 4) & (train['Fare'] <= 5)) 
train['Fare_5_'] = np.int32(train['Fare'] > 5)


test['Fare_0_2'] = np.int32(test['Fare'] <= 2)
test['Fare_2_3'] = np.int32((test['Fare'] > 2) & (test['Fare'] <= 3) )
test['Fare_3_4'] = np.int32((test['Fare'] > 3) & (test['Fare'] <= 4) )
test['Fare_4_5'] = np.int32((test['Fare'] > 4) & (test['Fare'] <= 5)) 
test['Fare_5_'] = np.int32(test['Fare'] > 5)

train.drop(['Ticket','PassengerId','Name','Age','Cabin','Pclass'],axis = 1, inplace=True)
test.drop( ['PassengerId','Ticket','Name','Age','Cabin','Pclass'],axis =1, inplace=True)     

X_train_ = train.loc[X_train.index]
X_test_ = train.loc[X_test.index]

Y_train_ = label.loc[X_train.index]
Y_test_ = label.loc[X_test.index]

X_test_ = X_test_[X_train_.columns]

pd.set_option('display.max_columns',50)
train.head()

test = test[train.columns]

rf_ = RandomForestClassifier(criterion='gini', 
                             n_estimators=700,
#                              max_depth=5,
                             min_samples_split=16,
                             min_samples_leaf=1,
                             max_features='auto',  
                             random_state=10,
                             n_jobs=-1) 
rf_.fit(X_train_,Y_train_) 
rf_.score(X_test_,Y_test_)

0.7910447761194029

rf_.fit(train,label) 

RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=16,
            min_weight_fraction_leaf=0.0, n_estimators=700, n_jobs=-1,
            oob_score=False, random_state=10, verbose=0, warm_start=False)

pd.concat((pd.DataFrame(train.columns, columns = ['variable']), 
           pd.DataFrame(rf_.feature_importances_, columns = ['importance'])), 
          axis = 1).sort_values(by='importance', ascending = False)[:20]

excl("ls titanic_datas")

['gender_submission.csv\n', 'test.csv\n', 'train.csv\n']

submit = pd.read_csv('./titanic_datas/gender_submission.csv')
submit.set_index('PassengerId',inplace=True)

res_rf = rf_.predict(test)
submit['Survived'] = res_rf
submit['Survived'] = submit['Survived'].apply(int)
submit.to_csv('./titanic_datas/submit.csv')

excl("ls titanic_datas")

['gender_submission.csv\n', 'submit.csv\n', 'test.csv\n', 'train.csv\n']

Your Best Entry 
Your submission scored 0.81339