python数据预处理之将类别数据转换为数值的方法

import pandas as pdfrom io import StringIOcsv_data = '''A,B,C,D1,2,3,45,6,,80,11,12,'''df = pd.read_csv(StringIO(csv_data))print(df)#统计为空的数目print(df.isnull().sum())print(df.values)#丢弃空的print(df.dropna())print('after', df)from sklearn.preprocessing import Imputer# axis=0 列  axis = 1 行imr = Imputer(missing_values='NaN', strategy='mean', axis=0)imr.fit(df) # fit 构建得到数据imputed_data = imr.transform(df.values) #transform 将数据进行填充print(imputed_data)df = pd.DataFrame([['green', 'M', 10.1, 'class1'],          ['red', 'L', 13.5, 'class2'],          ['blue', 'XL', 15.3, 'class1']])df.columns =['color', 'size', 'price', 'classlabel']print(df)size_mapping = {'XL':3, 'L':2, 'M':1}df['size'] = df['size'].map(size_mapping)print(df)## 遍历Seriesfor idx, label in enumerate(df['classlabel']):  print(idx, label)#1, 利用LabelEncoder类快速编码,但此时对color并不适合,#看起来,好像是有大小的from sklearn.preprocessing import LabelEncoderclass_le = LabelEncoder()color_le = LabelEncoder()df['classlabel'] = class_le.fit_transform(df['classlabel'].values)#df['color'] = color_le.fit_transform(df['color'].values)print(df)#2, 映射字典将类标转换为整数import numpy as npclass_mapping = {label: idx for idx, label in enumerate(np.unique(df['classlabel']))}df['classlabel'] = df['classlabel'].map(class_mapping)print('2,', df)#3,处理1不适用的#利用创建一个新的虚拟特征from sklearn.preprocessing import OneHotEncoderpf = pd.get_dummies(df[['color']])df = pd.concat([df, pf], axis=1)df.drop(['color'], axis=1, inplace=True)print(df)