print(len(data)) # print(vals) # print(len(data[999])) data = check_array(data, accept_sparse=True) # print("d1: ",data[0]) svd.fit(data) d = svd.fit_transform(data) # print("d1: ",data[0]) #DummyClassifier(strategy='most_frequent').fit(d,[styledict[s] for s in style]) # classifier1 = MLPClassifier(random_state=1,max_iter=1000).fit(d,[styledict[s] for s in style]) classifier = GradientBoostingClassifier( n_estimators=100, init=MLPClassifier(max_iter=1000)).fit(d, [styledict[s] for s in style]) if type(classifier) == type(GaussianNB()): classifier.partial_fit(d, [styledict[s] for s in style], classes=vals) for i in range(3): data, style = grab_rand_data(cur, length) data = svd.fit_transform(data) classifier.partial_fit(data, [styledict[s] for s in style]) elif type(classifier) == type(MLPClassifier()): pass test_size = 50000 # print(cur.fetchone()) data, style = grab_rand_data(cur, test_size) print( classifier.score(svd.fit_transform(data), [styledict[s] for s in style])) # print(classifier1.score(svd.fit_transform(data),[styledict[s] for s in style])) # print(test_clf(classifier,classifier1,svd.fit_transform(data),[styledict[s] for s in style]))