import numpy as np

import pandas as pd

from pandas import Series, DataFrame

np.set_printoptions(precision=4)

…

 

df = pd.DataFrame([  

            ['green', 'M', 10.1, 'class1'],   

            ['red', 'L', 13.5, 'class2'],   

            ['blue', 'XL', 15.3, 'class1']])  

df.columns = ['color', 'size', 'prize', 'class label']  

df

color size prize class label 0 green M 10.1 class1 1 red L 13.5 class2 2 blue XL 15.3 class1

…

 

size_mapping = {  

           'XL': 3,  

           'L': 2,  

           'M': 1}  

df['size'] = df['size'].map(size_mapping) 

df

color size prize class label 0 green 1 10.1 class1 1 red 2 13.5 class2 2 blue 3 15.3 class1

…

 

# -----------------------------------------------

# 使用 pd.get_dummies() 进行处理

pd.get_dummies(df)

size prize color_blue color_green color_red class label_class1 class label_class2 0 1 10.1 0 1 0 1 0 1 2 13.5 0 0 1 0 1 2 3 15.3 1 0 0 1 0

…

 

df

color size prize class label 0 green 1 10.1 class1 1 red 2 13.5 class2 2 blue 3 15.3 class1

…

x

# -----------------------------------------------

# 使用  sklearn.feature_extraction.DictVectorizer 进行处理

feature_list = []

label_list = []

for row in df.index[:]:

    label_list.append(df.ix[row][-1])

    rowDict = {}

    for i in range(0, len(df.ix[row])-1):

        rowDict[df.columns[i]] = df.ix[row][i]

    feature_list.append(rowDict)

feature_list

[{'color': 'green', 'prize': 10.1, 'size': 1}, {'color': 'red', 'prize': 13.5, 'size': 2}, {'color': 'blue', 'prize': 15.300000000000001, 'size': 3}]

…

 

label_list

['class1', 'class2', 'class1']

…

 

from sklearn.feature_extraction import DictVectorizer

vec = DictVectorizer()

# DictVectorizer.fit_transform() 接受一个由 dict 组成的 list

dummy_x = vec.fit_transform(feature_list).toarray()

dummy_x

array([[  0. ,   1. ,   0. ,  10.1,   1. ],       [  0. ,   0. ,   1. ,  13.5,   2. ],       [  1. ,   0. ,   0. ,  15.3,   3. ]])

…

 

from sklearn import preprocessing

label_bin = preprocessing.LabelBinarizer()

# preprocessing.LabelBinarizer.fit_transform() 接受一个 list

dummy_y = label_bin.fit_transform(label_list)

dummy_y

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

…

 

# 测试 当 label 种类大于 2 的时候的效果

df['class label'][2] = 'class3'

df

C:\Users\rHotD\Anaconda3\lib\site-packages\ipykernel\__main__.py:2: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrameSee the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy  from ipykernel import kernelapp as app

color size prize class label 0 green 1 10.1 class1 1 red 2 13.5 class2 2 blue 3 15.3 class3

…

 

feature_list = []

label_list = []

for row in df.index[:]:

    label_list.append(df.ix[row][-1])

    rowDict = {}

    for i in range(0, len(df.ix[row])-1):

        rowDict[df.columns[i]] = df.ix[row][i]

    feature_list.append(rowDict)

dummy_y = label_bin.fit_transform(label_list)

dummy_y

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

…

 

# 结论，两者效果差不多一样，但是 pd.get_dummies 更好用一些

…