4-Titanic船员生存实战

数据预处理

import pandas as pd
titanic = pd.read_csv('./data/titanic_train.csv')
titanic.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

titanic.describe()

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	891.000000	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

缺失项填充和字符数据映射成数字数据

titanic['Age'] = titanic['Age'].fillna(titanic['Age'].median())
titanic.describe()

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	891.000000	891.000000	891.000000	891.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	29.361582	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	13.019697	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	22.000000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	35.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

print(titanic['Sex'].unique())

['male' 'female']

titanic.loc[titanic['Sex']=='male', 'Sex'] = 0
titanic.loc[titanic['Sex']=='female', 'Sex'] = 1
titanic.describe()

	PassengerId	Survived	Pclass	Sex	Age	SibSp	Parch	Fare
count	891.000000	891.000000	891.000000	891.000000	891.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	0.352413	29.361582	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	0.477990	13.019697	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.000000	0.420000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	0.000000	22.000000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	0.000000	28.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	1.000000	35.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	1.000000	80.000000	8.000000	6.000000	512.329200

print(titanic['Embarked'].unique())
titanic['Embarked'] = titanic['Embarked'].fillna('S')
titanic.loc[titanic['Embarked']=='S', 'Embarked'] = 0
titanic.loc[titanic['Embarked']=='C', 'Embarked'] = 1
titanic.loc[titanic['Embarked']=='Q', 'Embarked'] = 2
print(titanic['Embarked'].unique())

['S' 'C' 'Q' nan]
[0 1 2]

使用线性回归算法实现

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import KFold

predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
alg = LinearRegression()
fold = KFold(n_splits=3, shuffle=False).split(titanic[predictors])

predictions = []
for train, test in fold:
    train_predictors = (titanic[predictors].iloc[train,:])
    train_target = titanic['Survived'].iloc[train]
    alg.fit(train_predictors, train_target)
    test_predictions = alg.predict(titanic[predictors].iloc[test,:])
    predictions.append(test_predictions)

import numpy as np

predictions = np.concatenate(predictions, axis=0)
predictions[predictions > .5] = 1
predictions[predictions <= .5] = 0
accuracy = len(predictions[predictions == titanic['Survived']]) / len(predictions)
print(len(predictions[predictions == titanic['Survived']]))
print(len(predictions))
print(accuracy)

698
891
0.7833894500561167

逻辑回归算法实现

from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression

alg = LogisticRegression()
scores = cross_val_score(alg, titanic[predictors], titanic['Survived'], cv=3)
print(scores.mean())

0.7878787878787877


C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)

使用随机森林算法

titanic_test = pd.read_csv('./data/test.csv')
titanic_test['Age'] = titanic_test['Age'].fillna(titanic['Age'].median())
titanic_test['Fare'] = titanic_test['Fare'].fillna(titanic_test['Fare'].median())

titanic_test.loc[titanic_test['Sex'] == 'male', 'Sex'] = 0 
titanic_test.loc[titanic_test['Sex'] == 'female', 'Sex'] = 1

titanic_test['Embarked'] = titanic_test['Embarked'].fillna('S')
titanic_test.loc[titanic_test['Embarked'] == 'S', 'Embarked'] = 0
titanic_test.loc[titanic_test['Embarked'] == 'C', 'Embarked'] = 1
titanic_test.loc[titanic_test['Embarked'] == 'Q', 'Embarked'] = 2

from sklearn import model_selection
from sklearn.ensemble import RandomForestClassifier

predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
alg = RandomForestClassifier(random_state=1, n_estimators=10, min_samples_split=2, min_samples_leaf=1)
kf = KFold(n_splits=3, shuffle=False).split(titanic[predictors])
scores = model_selection.cross_val_score(alg, titanic[predictors], titanic['Survived'], cv=kf)
print(scores.mean())

0.7856341189674523

alg = RandomForestClassifier(random_state=1, n_estimators=50, min_samples_split=4, min_samples_leaf=2)
kf = KFold(n_splits=3, shuffle=False).split(titanic[predictors])
scores = model_selection.cross_val_score(alg, titanic[predictors], titanic['Survived'], cv=kf)
print(scores.mean())

0.8159371492704826

再次进行特征处理

titanic['FamilySize'] = titanic['SibSp'] + titanic['Parch']
# .apply方法生成一个新的series
titanic['NameLength'] = titanic['Name'].apply(lambda x: len(x))

import re

def get_title(name):
    title_search = re.search(' ([A-Za-z]+)\.', name)
    if title_search:
        return title_search.group(1)
    return ''

titles = titanic['Name'].apply(get_title)
print(pd.value_counts(titles))

title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Dr": 5, "Rev": 6, "Major": 7, "Col": 7, "Mlle": 8, "Mme": 8, "Don": 9, "Lady": 10, "Countess": 10, "Jonkheer": 10, "Sir": 9, "Capt": 7, "Ms": 2}
for k,v in title_mapping.items():
    titles[titles == k] = v

print(pd.value_counts(titles))
titanic['Title'] = titles

Mr          517
Miss        182
Mrs         125
Master       40
Dr            7
Rev           6
Col           2
Major         2
Mlle          2
Lady          1
Mme           1
Countess      1
Jonkheer      1
Sir           1
Don           1
Ms            1
Capt          1
Name: Name, dtype: int64
1     517
2     183
3     125
4      40
5       7
6       6
7       5
10      3
8       3
9       2
Name: Name, dtype: int64

import numpy as np
from sklearn.feature_selection import SelectKBest, f_classif
import matplotlib.pyplot as plt

predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked', 'FamilySize', 'Title', 'NameLength']
selector = SelectKBest(f_classif, k=5)
selector.fit(titanic[predictors], titanic['Survived'])
#得到原始的pvalues并转换
scores = -np.log10(selector.pvalues_)

plt.bar(range(len(predictors)), scores)
plt.xticks(range(len(predictors)), predictors, rotation = 'vertical')
plt.show()

选出最佳的四个特征

predictors = ['Pclass', 'Sex', 'Title', 'NameLength']
alg = RandomForestClassifier(random_state=1, n_estimators=100, min_samples_split=8, min_samples_leaf=4)
kf = KFold(n_splits=5, shuffle=False).split(titanic[predictors])
scores = model_selection.cross_val_score(alg, titanic[predictors], titanic['Survived'], cv=kf)
print(scores.mean())

0.7946331052664617

使用集成算法

from sklearn.ensemble import GradientBoostingClassifier
import numpy as np

algorithms = [
    [GradientBoostingClassifier(random_state=1, n_estimators=25, max_depth=3), ["Pclass", "Sex", "Age", "Fare", "Embarked", "FamilySize", "Title",]],
    [LogisticRegression(random_state=1), ["Pclass", "Sex", "Fare", "FamilySize", "Title", "Age", "Embarked"]]
]

predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
kf = KFold(n_splits=5, shuffle=False).split(titanic[predictors])
    
predictions = []
for train, test in kf:
    train_target = titanic['Survived'].iloc[train]
    full_test_predictions = []
    for alg, predictors in algorithms:
        alg.fit(titanic[predictors].iloc[train,:], train_target)
        # The .astype(float) is necessary to convert the dataframe to all floats and avoid an sklearn error.
        test_predictions = alg.predict_proba(titanic[predictors].iloc[test,:].astype(float))[:,1]
        full_test_predictions.append(test_predictions)
    
    test_predictions = (full_test_predictions[0] + full_test_predictions[1]) / 2
    
    test_predictions[test_predictions <= .5] = 0
    test_predictions[test_predictions > .5] = 1
    predictions.append(test_predictions)
    
predictions = np.concatenate(predictions, axis=0)
accuracy = len(predictions[predictions == titanic["Survived"]]) / len(predictions)
print(accuracy)

0.8226711560044894


C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)