第二章:数据清洗及特征处理
2.1 缺失值观察与处理
2.1.1 :缺失值观察
df.info()
df.isnull().sum()
df[['Age','Cabin','Embarked']].head()
2.1.2 :对缺失值进行处理
df[df['Age']==None]=0
df.head()
df[df['Age'].isnull()] = 0
df.head()
df[df['Age'] == np.nan] = 0
df.head()
df.dropna().head()
df.fillna(0).head()
2.2 重复值观察与处理
2.2.1 :请查看数据中的重复值
df[df.duplicated()]
2.2.2 :对重复值进行处理
#删除重复行
df = df.drop_duplicates()
df.head()
2.2.3 :将前面清洗的数据保存为csv格式
df.to_csv('test_clear.csv')
2.3 特征观察与处理
2.3.1 :对年龄进行分箱(离散化)处理
df['AgeBand'] = pd.cut(df['Age'], 5,labels = [1,2,3,4,5])
df.head()
df.to_csv('test_ave.csv')
df['AgeBand'] = pd.cut(df['Age'],[0,5,15,30,50,80],labels = [1,2,3,4,5])
df.head()
df.to_csv('test_cut.csv'
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()
df.to_csv('test_pr.csv')
2.3.2 :对文本变量进行转换
df['Sex'].value_counts()
df['Cabin'].value_counts()
df['Embarked'].value_counts()
df['Sex'].unique()
df['Sex'].nunique()
df['Sex_num'] = df['Sex'].replace(['male','female'],[1,2])
df.head()
df['Sex_num'] = df['Sex'].map({'male': 1, 'female': 2})
df.head()
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))
df.head()
for feat in ["Age", "Embarked"]:
x = pd.get_dummies(df[feat], prefix=feat)
df = pd.concat([df, x], axis=1)
df.head()
2.3.3 :从纯文本Name特征里提取出Titles的特征(所谓的Titles就是Mr,Miss,Mrs等)
df['Title'] = df.Name.str.extract('([A-Za-z]+)\.', expand=False)
df.head()
df.to_csv('test_fin.csv')