Kaggle练习——Titanic

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline

inputData = pd.read_csv('./train.csv')
trainData = inputData.copy(deep = True)

拷贝一份trainData用于数据处理，不动原数据。（其实好像没啥用）

del trainData['PassengerId']
del trainData['Cabin']
del trainData['Ticket']

删除机舱和乘客id

trainData.describe()

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

trainData['Age'].mode(1)

0    24.0
dtype: float64

pandas中mode可以用来求众数，试一试.
不给具体列的时候，每一列都是众数。
axis = 1是统计每一行的众数
axis = 0是我对于一行，抽取每一列的众数

# print(trainData['Name'])
trainData['Name'] = trainData['Name'].str.extract(r", (.*?)\.", expand=False)
print(trainData["Name"])
trainData.rename(columns={
   'Name':'Title'}, inplace=True)

0        Mr
1       Mrs
2      Miss
3       Mrs
4        Mr
       ... 
886     Rev
887    Miss
888    Miss
889      Mr
890      Mr
Name: Name, Length: 891, dtype: object

#将title合并为几个组
trainData["Title"]=trainData["Title"].replace(['Mr','Don'],'Mr')
trainData["Title"]=trainData["Title"].replace(['Mrs','Miss','Mme','Ms','Lady','Dona','Mlle'],'Ms')
trainData["Title"]=trainData["Title"].replace(['Sir','Major','Col','Capt'],'Major')
trainData["Title"]=trainData["Title"].replace(['Master','Jonkheer','the Countess'],'Jonkheer')
trainData["Title"]=trainData["Title"].replace(['Rev','Dr'],'Rev')

把title分类

from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import LabelEncoder

a = LabelEncoder().fit_transform(trainData['Sex'])
OneHotEncoder( sparse=False ).fit_transform(a.reshape(-1,1)) # 注意: 这里把 a 用 reshape 转换成 2-D array

listUniq = trainData['Title'].unique().reshape(-1,1)
print(listUniq)
enc = OneHotEncoder()
enc.fit(listUniq)
enc.transform(trainData[['Title']]).toarray()
# b = LabelEncoder().fit_transform(trainData['Title'])
# trainData['Title'] = OneHotEncoder( sparse=False ).fit_transform(b.reshape(-1,1))

[['Mr']
 ['Ms']
 ['Jonkheer']
 ['Rev']
 ['Major']]





array([[0., 0., 1., 0., 0.],
       [0., 0., 0., 1., 0.],
       [0., 0., 0., 1., 0.],
       ...,
       [0., 0., 0., 1., 0.],
       [0., 0., 1., 0., 0.],
       [0., 0., 1., 0., 0.]])

对性别和类别进行onehot编码。成功是成功了，发现不会用……无语子，不知道怎么放进模型）

trainData[trainData['Title'] == 'Mr']['Age'].mode(1)

0    19.0
1    25.0
dtype: float64

trainData[trainData['Title'] == 'Ms']['Age'].mode(1)

0    24.0
dtype: float64

trainData[trainData['Title'] == 'Major