Question

我尝试从两个变量'date_birth'和'date_survey'创建一个新变量'age'

import numpy as np
import pandas as pd
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn import linear_model, pipeline
from sklearn.pipeline import FeatureUnion
from sklearn.pipeline import Pipeline

我的数据框

df = pd.DataFrame({'a':[1,2,3], 
                   'date_survey': ['10.01.2013', '20.02.2014', '30.03.2015'],
                   'birth': ['1985', '1984', '1986'] })

管道代码

X = df[['date_survey', 'birth']]
y = df['a']
class MultiColumn:
    def __init__(self,columns = None):
        self.columns = columns # array of column names to encode

    def fit(self,X,y=None):
        return self
    def transform(self, X):                                                           
        return X[self.columns]
class Age(TransformerMixin):

    def transform(self, X, y=None, **fit_params): 
        X['date_survey'] = pd.to_datetime(X['date_survey'])
        year = pd.DataFrame(X['date_survey'].apply(lambda x: x.year))
        age = X['birth'].convert_objects(convert_numeric=True) - year
        return age

    def fit(self, X, y=None, **fit_params):
        return self
regressor = linear_model.SGDRegressor()
pipeline = Pipeline([
          ('union', FeatureUnion(
        transformer_list=[    
             # age
            ('age', Pipeline([
                ('selector', MultiColumn(columns=['date_survey', 'birth'])),
                ('date', Age())

            ])),
        ])),
    # Use a regression
    ('model_fitting', regressor),
])
pipeline.fit(X, y)

我收到错误

ValueError: Input contains NaN, infinity or a value too large for dtype('float64').

我猜是Age类中的错误，但我无法理解如何改进它

Answer 1

  date_survey birth date_survey_in_transform  year
0  10.01.2013  1985               2013-10-01  2013
1  20.02.2014  1984               2014-02-20  2014
2  30.03.2015  1986               2015-03-30  2015

birth - year是否定的。

age = X['birth'].convert_objects(convert_numeric=True) - year

我修改了一些代码，让它运行没有错误。

import numpy as np
import pandas as pd
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn import linear_model, pipeline
from sklearn.pipeline import FeatureUnion
from sklearn.pipeline import Pipeline
from sklearn.linear_model import SGDRegressor

df = pd.DataFrame({'a':[1,2,3], 
                   'date_survey': ['10.01.2013', '20.02.2014', '30.03.2015'],
                   'birth': ['1985', '1984', '1986'] })

X = df[['date_survey', 'birth']]
y = df['a']
class MultiColumn:
    def __init__(self,columns=None):
        self.columns = columns # array of column names to encode

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

    def transform(self, X):                                                           
        return X[self.columns]

class Age(TransformerMixin):

    def transform(self, X, y=None, **fit_params): 
        X['date'] = pd.to_datetime(X['date_survey'])
        X['year'] = X['date'].dt.year
        X['age'] = X['year'] - X['birth'].astype('int64')
        return X['age'].reshape(-1, 1)

    def fit(self, X, y=None, **fit_params):
        return self

pipeline = Pipeline([
    ('union', FeatureUnion(
        transformer_list=[
            # age
            ('age', Pipeline([
                ('selector', MultiColumn(columns=['date_survey', 'birth'])),
                ('date', Age())
                ])
             ),
            ]
        )
     ),
    # Use a regression
    ('model_fitting', SGDRegressor())
    ])

pipeline.fit(X, y)

创建管道的类中的错误

1 个答案: