classifier_cross_val.py

folds = RepeatedStratifiedKFold(n_splits=10, n_repeats=10)
vectorizer = TomotopyLDAVectorizer(num_of_topics=15, workers=workers, min_df=min_df,
                                   rm_top=rm_top)
clf = SVC()
pca = PCA(n_components=0.95)
pipe = Pipeline([("vectorizer", vectorizer), ("scalar", StandardScaler()),
                 ("classifier", clf)])


results = cross_val_score(pipe, docs, y_true, cv=folds, n_jobs=2, verbose=1,
                          scoring="accuracy")
                          
                          
print("Accuracy -> mean: {}\t std: {}".format(results.mean(), results.std()))