Data preprocessing (2)--one-hot Coding single Heat code # uses pandans.dummies and sklearn.feature_extraction respectively. Dictvectorizer for processing __color

discrete feature encoding are divided into two situations:

1, the value of discrete feature is not the size of the meaning, such as color:[red,blue], then the use of One-hot encoding

2, the value of discrete feature has the meaning of size, such as SIZE:[X,XL,XXL], then use the mapping of the value of {x:1,xl:2,xxl:3} in [90]:

Import NumPy as NP

Import Pandas as PD

From pandas import Series, dataframe

Np.set_printoptions (precision=4)

X ... In [91]:

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

XOUT[91]:

	Color	size	Prize	class Label
0	Green	M	10.1	Class1
1	Red	L	13.5	Class2
2	Blue	Xl	15.3	Class1

... In [92]:

Size_mapping = {  

           ' XL ': 3,  

           ' L ': 2,  

           ' M ': 1}  

Df

XOUT[92]:

	Color	size	Prize	class Label
0	Green	1	10.1	Class1
1	Red	2	13.5	Class2
2	Blue	3	15.3	Class1

... In [93]:

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

# use Pd.get_dummies () for processing

Pd.get_dummies (DF)

XOUT[93]:

	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

... In [94]:

Df

XOUT[94]:

	Color	size	Prize	class Label
0	Green	1	10.1	Class1
1	Red	2	13.5	Class2
2	Blue	3	15.3	Class1

... In [95]:

X

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

# Use  sklearn.feature_extraction. Dictvectorizer for processing

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

XOUT[95]:

[{' Color ': ' Green ', ' Prize ': 10.1, ' Size ': 1},
 {' Color ': ' Red ', ' prize ': 13.5, ' Size ': 2},
 {' Color ': ' Blue ', ' Prize ': 15.300000000000001, ' Size ': 3}]

... In [96]:

Label_list

XOUT[96]:

[' Class1 ', ' class2 ', ' Class1 ']

... In [97]:

From sklearn.feature_extraction import Dictvectorizer

VEC = Dictvectorizer ()

# Dictvectorizer.fit_transform () accept a list made up of dict

dummy_x = Vec.fit_transform (feature_list). ToArray ()

Dummy_x

XOUT[97]:

Array ([[  0.,   1.,   0,  10.1,   1.],
       [0.  ,   0.,   1.,  13.5,   2.],
       [ C12/>1. ,   0.,   0.,  15.3,   3.]]

... In [98]:

From Sklearn Import preprocessing

Label_bin = preprocessing. Labelbinarizer ()

# preprocessing. Labelbinarizer.fit_transform () accepts a list

dummy_y = Label_bin.fit_transform (label_list)

Dummy_y

XOUT[98]:

Array ([[0],
       [1],
       [0]])

... In [99]: