Question

这是我的代码。

import pandas as pd 
import numpy as np
import json
import seaborn as sb 
from sklearn.metrics import log_loss
from sklearn import linear_model 
from sklearn.model_selection import StratifiedKFold
from sklearn.svm import SVC
from scipy.stats import zscore
from Transformers import TextTransformer
from sklearn.metrics import confusion_matrix, accuracy_score
from sklearn.model_selection import GridSearchCV
%matplotlib inline
df = pd.read_json('data/train.json', encoding = 'utf-8', dtype = {'description': str})
from sklearn.pipeline import Pipeline, FeatureUnion
a = TextTransformer('description', max_features=50)
b = TextTransformer('features', max_features=10)
pipeline = Pipeline([
    ('feats', FeatureUnion([
        ('description',a ), # can pass in either a pipeline
        ('features',b ) # or a transformer
    ])),
    ('clf', SVC())  # classifier
])
pipeline.fit(df)

我很好奇的是，我试图预测目标变量df [＆＃39; interest_level＆＃39;]。但是，pipeline.fit只接受2个参数，其中一个参数是self。我如何传递目标变量呢？

另一点需要注意的是，我尝试使用pipeline.fit（df，y = df [＆＃39; interest_level＆＃39;]），它也会抛出相同的异常。我正在使用最新版本的pandas / numpy / sklearn。

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-17-0a34f1c24eca> in <module>()
      7     ('clf', SVC())  # classifier
      8 ])
----> 9 pipeline.fit(df,df['interest_level'])
     10 # pg = {'clf__C': [0.1,1]}
     11 # grid = GridSearchCV(pipeline, param_grid= pg ,cv = 2)

/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/pipeline.pyc in fit(self, X, y, **fit_params)
    266             This estimator
    267         """
--> 268         Xt, fit_params = self._fit(X, y, **fit_params)
    269         if self._final_estimator is not None:
    270             self._final_estimator.fit(Xt, y, **fit_params)

/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/pipeline.pyc in _fit(self, X, y, **fit_params)
    232                 pass
    233             elif hasattr(transform, "fit_transform"):
--> 234                 Xt = transform.fit_transform(Xt, y, **fit_params_steps[name])
    235             else:
    236                 Xt = transform.fit(Xt, y, **fit_params_steps[name]) \

/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/base.pyc in fit_transform(self, X, y, **fit_params)
    495         else:
    496             # fit method of arity 2 (supervised transformation)
--> 497             return self.fit(X, y, **fit_params).transform(X)
    498 
    499 

TypeError: fit() takes exactly 2 arguments (3 given)

Answer 1

根据文件你是对的：

pipeline: fit()

您还可以查看此示例：

pipeline / featureunion example

你得到的错误是什么？我会运行以下内容：

pipeline.fit(df[:, -1], df[:, len(df.columns)]-1)

管道配合仅包含2个参数

1 个答案: