Pythonでのグリッドサーチを行ったときのエラー

Question

forest = RandomForestClassifier(min_samples_leaf=3, random_state=0)
forest.fit(train_features, train_labels)

print('f1 score: {:.3f}'.format(f1_score(test_labels, forest.predict(test_features), average = 'micro')))

# ハイパーパラメータ
forest_grid_param = {
    'n_estimators': [100],
    'max_features': [1, 'auto', None],
    'max_depth': [1, 5, 10, None],
    'min_samples_leaf': [1, 2, 4,]
}

# スコア方法をF1に設定
f1_scoring = make_scorer(f1_score,  pos_label=1)

# グリッドサーチで学習
forest_grid_search = GridSearchCV(RandomForestClassifier(random_state=0, n_jobs=-1), forest_grid_param, scoring=f1_scoring, cv=4)
forest_grid_search.fit(train_features, train_labels)

# 結果
print('Best parameters: {}'.format(forest_grid_search.best_params_))
print('Best score: {:.3f}'.format(forest_grid_search.best_score_))

このようなコードを実行したとき、

forest_grid_search.fit(train_features, train_labels)

以上の部分で、エラーがでました。

Traceback (most recent call last):
  File "zyan05.py", line 120, in <module>
    forest_grid_search.fit(train_features, train_labels)
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 945, in fit
    return self._fit(X, y, groups, ParameterGrid(self.param_grid))
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 564, in _fit
    for parameters in parameter_iterable
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 758, in __call__
    while self.dispatch_one_batch(iterator):
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 608, in dispatch_one_batch
    self._dispatch(tasks)
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 571, in _dispatch
    job = self._backend.apply_async(batch, callback=cb)
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 109, in apply_async
    result = ImmediateResult(func)
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 326, in __init__
    self.results = batch()
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 131, in __call__
    return [func(*args, **kwargs) for func, args, kwargs in self.items]
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 131, in <listcomp>
    return [func(*args, **kwargs) for func, args, kwargs in self.items]
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 260, in _fit_and_score
    test_score = _score(estimator, X_test, y_test, scorer)
  File "/Users/anaconda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 288, in _score
    score = scorer(estimator, X_test, y_test)
  File "/Users//anaconda/lib/python3.6/site-packages/sklearn/metrics/scorer.py", line 98, in __call__
    **self._kwargs)
TypeError: 'numpy.float64' object is not callable

原因が不明です。

どのように改善したら良いでしょうか。
よろしくお願い致します。

#train_featureのひとつ

[[  1.29289835e-04   1.17485219e-04   1.19890843e-04 ...,   9.05183214e-05
    8.27563718e-05   8.78005056e-05]
 [  1.49255279e-04   1.35313449e-04   1.36294066e-04 ...,   8.62639847e-05
    9.09304063e-05   7.84873169e-05]
 [  1.88674124e-04   1.92549213e-04   1.94561864e-04 ...,   1.27251725e-04
    1.32504809e-04   1.19707440e-04]
 ..., 
 [  1.16313098e-05   2.90295617e-05   3.99510497e-05 ...,   1.52137304e-05
    1.43487523e-05   3.92287642e-05]
 [  1.58036700e-05   3.00034379e-05   3.78270972e-05 ...,   1.91663956e-05
    2.44618265e-05   2.47100536e-05]
 [  5.88701713e-05   3.20351268e-05   1.23424729e-05 ...,   2.63503805e-05
    4.25346609e-05   3.44451908e-05]]

# test_label

test_labels = [2,2,2,2,2,2,2,2,2,3,3,3,3,3,3,3,3,3]

以上のようなデータで行っています。

Answer 1

TypeError: 'numpy.float64' object is not callable
の前のトレースバックが必要ですね。
できれば、エラーの全文を追記してください。

---

f1_scoring = make_scorer(f1_score, average='micro',  pos_label=1)

Comments

[gymgym]

申し訳ございません。
エラー全文追加させていただきました。

よろしくお願い致します。

[mkgrei]

http://scikit-learn.org/stable/modules/generated/sklearn.metrics.make_scorer.html
関数を引数にとります。

[gymgym]

回答ありがとうございます。
質問させていただきたいのですが、
forest_grid_search.fit(train_features, train_labels)　の部分でエラーがでているのですが、
f1_scoring = make_scorer(f1_score(test_labels, forest.predict(test_features), average='micro'), pos_label=1)　の部分が原因なのでしょうか。
また、関数はf1_score(test_labels, forest.predict(test_features), average='micro')では不十分なのでしょうか。

よろしくお願い致します。

[mkgrei]

初めてf1_scoringが使用された時にエラーが出ています。

不十分というより、それは関数が実行されて実数が返ってきています。
関数ではありません。

[gymgym]

f1_scoring = make_scorer(f1_score, pos_label=1)
以上のようなことでしょうか。
このようにすると、
Traceback (most recent call last):
File "alpha01_2.py", line 103, in <module>
forest_grid_search.fit(X_train, y_train)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 945, in fit
return self._fit(X, y, groups, ParameterGrid(self.param_grid))
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 564, in _fit
for parameters in parameter_iterable
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 758, in __call__
while self.dispatch_one_batch(iterator):
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 608, in dispatch_one_batch
self._dispatch(tasks)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 571, in _dispatch
job = self._backend.apply_async(batch, callback=cb)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 109, in apply_async
result = ImmediateResult(func)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 326, in __init__
self.results = batch()
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 131, in __call__
return [func(*args, **kwargs) for func, args, kwargs in self.items]
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 131, in <listcomp>
return [func(*args, **kwargs) for func, args, kwargs in self.items]
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 260, in _fit_and_score
test_score = _score(estimator, X_test, y_test, scorer)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 288, in _score
score = scorer(estimator, X_test, y_test)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/metrics/scorer.py", line 98, in __call__
**self._kwargs)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/metrics/classification.py", line 692, in f1_score
sample_weight=sample_weight)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/metrics/classification.py", line 806, in fbeta_score
sample_weight=sample_weight)
File "/Users/anaconda/lib/python3.6/site-packages/sklearn/metrics/classification.py", line 1018, in precision_recall_fscore_support
"choose another average setting." % y_type)
ValueError: Target is multiclass but average='binary'. Please choose another average setting.

以上のようなエラーがでて、averageをどこで指定したらよいかわかりません。
何度も申し訳ないのですが、よろしくお願い致します。

[mkgrei]

sklearn.metrics.make_scorer(score_func, greater_is_better=True, needs_proba=False, needs_threshold=False, **kwargs)
Score function (or loss function) with signature score_func(y, y_pred, **kwargs).
公式ドキュメントを読むと以上のことが書いてあるので、

f1_scoring = make_scorer(f1_score, pos_label=1, average='micro')

とすればよいことがわかります。

[gymgym]

mkgreiさんのおかげでうまく実行することができました。
初歩的な質問ばかりですみませんでした。

本当にありがとうございました。