第二章第一节数据清洗
第一部分数据处理
第二部分 特征观察与处理
#将连续变量Age平均分箱成5个年龄段,并分别用类别变量12345表示
df['AgeBand'] = pd.cut(df['Age'], 5,labels = ['1','2','3','4','5'])
df.head()
#将连续变量Age划分为[0,5) [5,15) [15,30) [30,50) [50,80)五个年龄段,并分别用类别变量12345表示
df['AgeBand'] = pd.cut(df['Age'],[0,5,15,30,50,80],labels = ['1','2','3','4','5'])
df.head(3)
#将连续变量Age按10% 30% 50 70% 90%五个年龄段,并用分类变量12345表示
df['AgeBand'] = pd.qcut(df['Age'],[0,0.1,0.3,0.5,0.7,0.9],labels = ['1','2','3','4','5'])
df.head()
#对文本变量进行转换
#(1) 查看文本变量名及种类
#【方法一】:value_counts
df['Sex'].value_counts()
df['Cabin'].value_counts()
df['Embarked'].value_counts()
#【方法二】unique
df['Sex'].unique()
df['Sex'].nunique()
(2) 将文本变量Sex, Cabin ,Embarked用数值变量12345表示
#[方法一]replace
df['Sex_num'] = df['Sex'].replace(['male','female'],[1,2])
df.head()
#【方法二】map
df['Sex_num'] = df['Sex'].map({'male': 1, 'female': 2})
df.head()
#【方法三】使用sklearn.preprocessing的LabelEncoder
from sklearn.preprocessing import LabelEncoder
for feat in ['Cabin', 'Ticket']:
lbl = LabelEncoder()
label_dict = dict(zip(df[feat].unique(), range(df[feat].nunique())))
df[feat + "_labelEncode"] = df[feat].map(label_dict)
df[feat + "_labelEncode"] = lbl.fit_transform(df[feat].astype(str))
(3) 将文本变量Sex, Cabin, Embarked用one-hot编码表示
#将类别文本转换为one-hot编码
#方法一: OneHotEncoder
for feat in ["Age", "Embarked"]:
# x = pd.get_dummies(df["Age"] // 6)
# x = pd.get_dummies(pd.cut(df['Age'],5))
x = pd.get_dummies(df[feat], prefix=feat)
df = pd.concat([df, x], axis=1)
#df[feat] = pd.get_dummies(df[feat], prefix=feat)
df.head
#保存一下
df.to_csv('test_fina.csv')