def clear(key_params=[]): X, y = ReadingFile.read_csv('TRAIN_CORPUS.csv') X = PreprocessData.prepare_data(X, mode='save', key_features=key_params) return X, y
return metrics.accuracy_score(y, predicted) # In[2]: X, y = clear() svm_clf = SVC(kernel='linear') svm_clf.fit(X, y) # In[3]: # test feature transformation scores = [] X, y = ReadingFile.read_csv('TRAIN_CORPUS.csv') scores.append(check_score(X, y, svm_clf)) X, y = ReadingFile.read_csv('TRAIN_CORPUS.csv') scores.append(check_score(PreprocessData.prepare_features(X), y, svm_clf)) X, y = ReadingFile.read_csv('TRAIN_CORPUS.csv') scores.append( check_score(PreprocessData.prepare_data(X, mode='save'), y, svm_clf)) scores # In[6]: # test feature importances