数据挖掘目标(Kaggle Titanic 生存测试)

复制代码

import numpy as np 
import pandas as pd
import matplotlib.pyplot as plt 
import seaborn as sns

1.数据导入

In [2]:

复制代码

train_data = pd.read_csv(r'../老师文件/train.csv') 
test_data = pd.read_csv(r'../老师文件/test.csv')
labels = pd.read_csv(r'../老师文件/label.csv')['Survived'].tolist()

In [3]:

复制代码

train_data.head()

Out[3]:

| | 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

2.数据预处理

In [4]:

复制代码

train_data.info()

复制代码

<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(5), object(5)
memory usage: 83.7+ KB

In [5]:

复制代码

test_data['Survived'] = 0
concat_data = train_data.append(test_data)

复制代码

C:\Users\Administrator\AppData\Local\Temp\ipykernel_5876\2851212731.py:2: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  concat_data = train_data.append(test_data)

In [6]:

复制代码

#1) replace the missing value with 'U0'
train_data['Cabin'] = train_data.Cabin.fillna('U0')
#2) replace the missing value with '0' and the existing value with '1' 
train_data.loc[train_data.Cabin.notnull(),'Cabin'] =  '1' 
train_data.loc[train_data.Cabin.isnull(),'Cabin'] =  '0'

In [7]:

复制代码

grid = sns.FacetGrid(train_data[['Age','Survived']],'Survived' ) 
grid.map(plt.hist, 'Age', bins = 20) 
plt.show( )

复制代码

C:\Users\Administrator\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: row. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

In [8]:

复制代码

from sklearn.ensemble import RandomForestRegressor

concat_data['Fare'] = concat_data.Fare.fillna(50)
concat_df = concat_data[['Age', 'Fare', 'Pclass','Survived']] 
train_df_age = concat_df.loc[concat_data['Age'].notnull()] 
predict_df_age = concat_df.loc[concat_data['Age'].isnull()] 
X=train_df_age.values[:,1:] 
Y= train_df_age.values[:,0]
RFR = RandomForestRegressor(n_estimators=1000,n_jobs=-1) 
RFR.fit(X,Y)
predict_ages = RFR.predict(predict_df_age.values[:,1:])
concat_data.loc[concat_data.Age.isnull(),'Age'] = predict_ages

In [9]:

复制代码

sex_dummies = pd.get_dummies(concat_data.Sex)

concat_data.drop('Sex',axis=1,inplace=True) 
concat_data = concat_data.join(sex_dummies)

In [10]:

复制代码

from sklearn.preprocessing import StandardScaler

concat_data['Age'] = StandardScaler().fit_transform(concat_data.Age.values.reshape(-1,1))

In [11]:

复制代码

concat_data['Fare'] = pd.qcut(concat_data.Fare,5)
concat_data['Fare'] = pd.factorize(concat_data.Fare)[0]

In [12]:

复制代码

concat_data.drop(['PassengerId'],axis = 1,inplace = True)