我试图使用Python 3.4中的scikit-learn
包进行网格搜索。
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model.logistic import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.grid_search import GridSearchCV
import pandas as pd
from sklearn.cross_validation import train_test_split
from sklearn.metrics import precision_score, recall_score, accuracy_score
from sklearn.preprocessing import LabelBinarizer
import numpy as np
pipeline = Pipeline([
('vect', TfidfVectorizer(stop_words='english')),
('clf', LogisticRegression)
])
parameters = {
'vect__max_df': (0.25, 0.5, 0.75),
'vect__stop_words': ('english', None),
'vect__max_features': (2500, 5000, 10000, None),
'vect__ngram_range': ((1, 1), (1, 2)),
'vect__use_idf': (True, False),
'vect__norm': ('l1', 'l2'),
'clf__penalty': ('l1', 'l2'),
'clf__C': (0.01, 0.1, 1, 10)
}
if __name__ == '__main__':
grid_search = GridSearchCV(pipeline, parameters, n_jobs=-1, verbose=1, scoring='accuracy', cv = 3)
df = pd.read_csv('SMS Spam Collection/SMSSpamCollection', delimiter='\t', header=None)
lb = LabelBinarizer()
X, y = df[1], np.array([number[0] for number in lb.fit_transform(df[0])])
X_train, X_test, y_train, y_test = train_test_split(X, y)
grid_search.fit(X_train, y_train)
print('Best score: ', grid_search.best_score_)
print('Best parameter set:')
best_parameters = grid_search.best_estimator_.get_params()
for param_name in sorted(best_parameters):
print(param_name, best_parameters[param_name])
然而,它并没有成功运行,错误信息看起来像这样:
Fitting 3 folds for each of 1536 candidates, totalling 4608 fits
Traceback (most recent call last):
File "/home/xiangru/PycharmProjects/machine_learning_note_with_sklearn/grid search.py", line 36, in <module>
grid_search.fit(X_train, y_train)
File "/usr/local/lib/python3.4/dist-packages/sklearn/grid_search.py", line 732, in fit
return self._fit(X, y, ParameterGrid(self.param_grid))
File "/usr/local/lib/python3.4/dist-packages/sklearn/grid_search.py", line 493, in _fit
base_estimator = clone(self.estimator)
File "/usr/local/lib/python3.4/dist-packages/sklearn/base.py", line 47, in clone
new_object_params[name] = clone(param, safe=False)
File "/usr/local/lib/python3.4/dist-packages/sklearn/base.py", line 35, in clone
return estimator_type([clone(e, safe=safe) for e in estimator])
File "/usr/local/lib/python3.4/dist-packages/sklearn/base.py", line 35, in <listcomp>
return estimator_type([clone(e, safe=safe) for e in estimator])
File "/usr/local/lib/python3.4/dist-packages/sklearn/base.py", line 35, in clone
return estimator_type([clone(e, safe=safe) for e in estimator])
File "/usr/local/lib/python3.4/dist-packages/sklearn/base.py", line 35, in <listcomp>
return estimator_type([clone(e, safe=safe) for e in estimator])
File "/usr/local/lib/python3.4/dist-packages/sklearn/base.py", line 45, in clone
new_object_params = estimator.get_params(deep=False)
TypeError: get_params() missing 1 required positional argument: 'self'
我也尝试只使用了。
if __name__ == '__main__':
pipeline.get_params()
它会给出相同的错误信息。 谁知道该如何解决?
d
的dict
上调用dict.keys()
而不是d.keys()
)。best_estimator_
是否给出了一个估计器类型而不是估计器类型的实例?如果是这样,那么问题就出在这里;你必须通过调用该类型(使用适当的参数)来构造一个估计。 - abarnert