python - 如何防止标签编码器将 y 列添加到 X numpy.array

Question

我在下面有以下代码，但是标签编码器的最后一行

X = MultiColumnLabelEncoder(columns = ['newlyConst','balcony', 'cellar', 'lift', 'garden', ]).fit_transform(df)

将 y 列（租）添加到 X numpy.array 中。

我不确定如何以另一种方式指定要编码的列以防止此问题，例如，通过指定 X np 数组和特定列而不是通过 df ，因为当我收到索引错误时。

任何帮助都会很棒，谢谢！

更新 我用长标签编码器代替了一个更优雅的解决方案，正如我的@Corralien所说的那样——在这里找到了深入的信息Converting Pandas Types

替换：

df = df.astype({"newlyConst" :int, "balcony" : int, "cellar" : int, "lift" : int, "garden":int})

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn import linear_model


df = pd.read_csv('immo_data.csv')


df.drop(columns=['telekomTvOffer', 'telekomHybridUploadSpeed', 'pricetrend',
        'telekomUploadSpeed', 'scoutId', 'noParkSpaces', 'yearConstructedRange',
        'houseNumber', 'interiorQual', 'petsAllowed', 'street', 'streetPlain', 'baseRentRange',
        'geo_plz','geo_bln', 'geo_krs','thermalChar', 'floor','numberOfFloors', 'noRoomsRange', 'livingSpaceRange',
        'regio3', 'description', 'facilities', 'hasKitchen','heatingCosts', 'energyEfficiencyClass',
        'lastRefurbish', 'electricityBasePrice', 'electricityKwhPrice','date','condition', 'typeOfFlat','serviceCharge'
        ,'heatingType','firingTypes', 'yearConstructed'], axis=1, inplace = True)

df_head=df.head(250)

df_nan_count=df.isna().sum()
#With 'firingTypes', 'yearConstructed', 'condition', 'typeOfFlat' number of NaN values exceeding 40-50%, those will be dropped 

df.dropna(inplace=True)

df3=df.count()

df=df[['regio1', 'newlyConst', 'balcony', 'picturecount', 'cellar', 'livingSpace', 
       'lift','noRooms', 'garden', 'baseRent', 'totalRent']]


dfcount = df.nunique()


##Regression
X = df.iloc[:, :-1].values
y = df.iloc[:, -1].values



#Encoding Categorical Data
from sklearn.preprocessing import LabelEncoder
from sklearn.pipeline import Pipeline
le = LabelEncoder()



class MultiColumnLabelEncoder:
    def __init__(self,columns = None):
        self.columns = columns # array of column names to encode

    def fit(self,X,y=None):
        return self # not relevant here
   
        '''
        Transforms columns of X specified in self.columns using
        LabelEncoder(). If no columns specified, transforms all
        columns in X.
       '''

    def transform(self,X):
      
        output = X.copy()
        if self.columns is not None:
            for col in self.columns:
                output[col] = LabelEncoder().fit_transform(output[col])
        else:
            for colname,col in output.iteritems():
                output[colname] = LabelEncoder().fit_transform(col)
        return output

    def fit_transform(self,X,y=None):
        return self.fit(X,y).transform(X)

X = MultiColumnLabelEncoder(columns = ['newlyConst','balcony', 'cellar', 'lift', 'garden', ]).fit_transform(df)



# Encoding categorical data
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [0])], remainder='passthrough')
X = np.array(ct.fit_transform(X))

df

                 regio1  newlyConst  balcony  picturecount  cellar  livingSpace  lift  noRooms  garden  totalRent
0   Nordrhein_Westfalen           0        0             6       1        86.00     0      4.0       1     840.00
2               Sachsen           1        1             8       1        83.80     1      3.0       0    1300.00
4                Bremen           0        1            19       0        84.97     0      3.0       0     903.00
6               Sachsen           0        0             9       1        62.00     0      2.0       1     380.00
7                Bremen           0        1             5       1        60.30     0      3.0       0     584.25
8     Baden_Württemberg           0        0             5       1        53.00     0      2.0       0     690.00
10              Sachsen           0        1            11       1        40.20     0      2.0       0     307.00
11              Sachsen           0        0             9       1        80.00     0      3.0       1     555.00
12      Rheinland_Pfalz           0        0             4       0       100.00     0      4.0       1     920.00
13  Nordrhein_Westfalen           0        0             3       0       123.44     0      4.0       0    1150.00

标签： pythonpandas

Answer 1

答案是删除标签编码器，而是使用下面的代码将真/假值更改为整数。更多信息可以在这里找到改变 Pandas 数据类型

df = df.astype({"newlyConst" :int, "balcony" : int, "cellar" : int, "lift" : int, "garden":int})