In the rasa_nlu function , they call GridSearchCV.fit() with clf.fit() . It triggers some warnings, and I would like to catch and change to find out what causes them:
Fitting 2 folds for each of 6 candidates, totalling 12 fits /home/mike/Programming/Rasa/myflaskapp/rasaenv/lib/python3.5/site-packages/sklearn/metrics/classification.py:1135: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples. 'precision', 'predicted', average, warn_for) /home/mike/Programming/Rasa/myflaskapp/rasaenv/lib/python3.5/site-packages/sklearn/metrics/classification.py:1135: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples. 'precision', 'predicted', average, warn_for) /home/mike/Programming/Rasa/myflaskapp/rasaenv/lib/python3.5/site-packages/sklearn/metrics/classification.py:1135: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples. 'precision', 'predicted', average, warn_for) /home/mike/Programming/Rasa/myflaskapp/rasaenv/lib/python3.5/site-packages/sklearn/metrics/classification.py:1135: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples. 'precision', 'predicted', average, warn_for) /home/mike/Programming/Rasa/myflaskapp/rasaenv/lib/python3.5/site-packages/sklearn/metrics/classification.py:1135: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples. 'precision', 'predicted', average, warn_for) /home/mike/Programming/Rasa/myflaskapp/rasaenv/lib/python3.5/site-packages/sklearn/metrics/classification.py:1135: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples. 'precision', 'predicted', average, warn_for) [Parallel(n_jobs=1)]: Done 12 out of 12 | elapsed: 0.1s finished Here is how GridSearchCV is built:
cv_splits = self._num_cv_splits(y) #когда я распечатал его, он дал мне «2», мне ожидалось, что что-то более связанное с ярлыками GridSearchCV(SVC(C=1, probability=True, class_weight='balanced'), param_grid=tuned_parameters, n_jobs=num_threads, cv=cv_splits, scoring='f1_weighted', verbose=1) Where y is labels that have been converted to numbers.
y: [1 0 2 1 1 1 1 1 1 0 0 0 0 0 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3] labels: ['greet', 'goodbye', 'inform', 'greet', 'greet', 'greet', 'greet', 'greet', 'greet', 'goodbye', 'goodbye', 'goodbye', 'goodbye', 'goodbye', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'inform', 'laughing', 'laughing'] Ideally, I would like to find out which warnings were triggered.
Update
At the moment I just tried to get the origin, I still have not found a way to capture the warning:
y = self.transform_labels_str2num(labels) X = np.stack([example.get("text_features") for example in training_data.intent_examples]) self.clf = self._create_classifier(num_threads, y) try: fit_result = self.clf.fit(X, y) y_pred = self.clf.predict(X) print("set(y)-set(y_pred):\n",set(y)-set(y_pred)) But he just gives me an empty set()
Also need to use .predict(X) ? Does it clf.fit() from the clf.fit() results?
