python数据预处理之将类别数据转换为数值的方法
通过get_dummies方法来转换。
import pandas as pd
from io import StringIO
csv_data = '''A,B,C,D
1,2,3,4
5,6,,8
0,11,12,'''
df = pd.read_csv(StringIO(csv_data))
print(df)
print(df.isnull().sum())
print(df.values)
print(df.dropna())
print('after', df)
from sklearn.preprocessing import Imputer
imr = Imputer(missing_values='NaN', strategy='mean', axis=0)
imr.fit(df)
imputed_data = imr.transform(df.values)
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)
for idx, label in enumerate(df['classlabel']):
print(idx, label)
from sklearn.preprocessing import LabelEncoder
class_le = LabelEncoder()
color_le = LabelEncoder()
df['classlabel'] = class_le.fit_transform(df['classlabel'].values)
print(df)
import numpy as np
class_mapping = {label: idx for idx, label in enumerate(np.unique(df['classlabel']))}
df['classlabel'] = df['classlabel'].map(class_mapping)
print('2,', df)
from sklearn.preprocessing import OneHotEncoder
pf = pd.get_dummies(df[['color']])
df = pd.concat([df, pf], axis=1)
df.drop(['color'], axis=1, inplace=True)
print(df)