头哥教学平台-泰坦尼克号生还预测_泰坦尼克号生还预测头歌

第2关 填充缺失值

import pandas as pd
import numpy as np

def process_nan_value(data):
    '''
    处理data中缺失值，有缺失值的特征为`Age`，`Cabin`，`Embarked`。
    :param data: 训练集的特征，类型为DataFrame
    :return:处理好缺失值后的训练集特征，类型为DataFrame
    '''

    #********* Begin *********#
    data['Age'].replace(np.nan,np.nanmedian(data['Age']),
       inplace=True)
    #data['Age'].replace(np.nan,np.nanmedian(data['Age']),inplace=True)
    data.drop(labels='Cabin',axis=1,inplace=True)
    data['Embarked'].replace(np.nan,'S',inplace=True)

    return data
    #********* End *********#
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19

第3关 特征工程与生还预测

import pandas as pd
import numpy as np
import sklearn
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import RandomForestRegressor

#********* Begin *********#
titanic = pd.read_csv('./train.csv')
def set_missing_ages(df):

    # 把已有的数值型特征取出来丢进Random Forest Regressor中

    age_df = df[['Age', 'Fare', 'Parch', 'SibSp', 'Pclass']]

    # 乘客分成已知年龄和未知年龄两部分

    known_age = age_df[age_df.Age.notnull()].values

    unknown_age = age_df[age_df.Age.isnull()].values

    # y即目标年龄

    y = known_age[:, 0]

    # X即特征属性值

    X = known_age[:, 1:]

    # fit到RandomForestRegressor之中

    rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1)

    rfr.fit(X, y)

    # 用得到的模型进行未知年龄结果预测

    predictedAges = rfr.predict(unknown_age[:, 1::])

    # 用得到的预测结果填补原缺失数据

    df.loc[(df.Age.isnull()), 'Age'] = predictedAges

    return df

titanic = set_missing_ages(titanic)

dummies_Embarked = pd.get_dummies(titanic['Embarked'], prefix= 'Embarked')

dummies_Sex = pd.get_dummies(titanic['Sex'], prefix= 'Sex')

dummies_Pclass = pd.get_dummies(titanic['Pclass'], prefix= 'Pclass')

df = pd.concat([titanic, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)

df.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)

# print(df)

train_label = df['Survived']

train_titanic = df.drop('Survived', 1)

titanic_test = pd.read_csv('./test.csv')
titanic_test = set_missing_ages(titanic_test)

dummies_Embarked = pd.get_dummies(titanic_test['Embarked'], prefix= 'Embarked')

dummies_Sex = pd.get_dummies(titanic_test['Sex'], prefix= 'Sex')

dummies_Pclass = pd.get_dummies(titanic_test['Pclass'], prefix= 'Pclass')

df_test = pd.concat([titanic_test,dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)

df_test.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)
#model = RandomForestClassifier(random_state=1, n_estimators=10, min_samples_split=2, min_samples_leaf=1)
model = RandomForestClassifier(n_estimators=10)
model.fit(train_titanic, train_label)

predictions = model.predict(df_test)

result = pd.DataFrame({'Survived':predictions.astype(np.int32)})

result.to_csv("./predict.csv", index=False)


#********* End *********#
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86

结果不是很稳定，多运行几次，准确率能到80以上