Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import numpy as np
- import pandas as pd
- from sklearn.model_selection import cross_val_score
- from sklearn.cross_validation import train_test_split
- from sklearn.ensemble import AdaBoostClassifier
- data = pd.read_csv(r'D:downloadENB2012.csv', ';')
- data.head()
- kfold = 5 #количество подвыборок для валидации
- itog_val = {} #список для записи результатов кросс валидации разных алгоритмов
- X = data.drop('Y1', axis=1).values[:, :7] # [y] столбец не должен попадать в [X]
- y = data['Y1'].values
- X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
- print ('обучающая выборка:n', X_train[:9])
- print ('n')
- print ('тестовая выборка:n', X_test[:7])
- clf = AdaBoostClassifier(n_estimators=70)
- scores = cross_val_score(clf, X_train, y_train, cv=kfold)
- itog_val['AdaBoostClassifier'] = scores.mean()
- print ('итог', itog_val)
- clf.fit(X_train, y_train)
- clf.score(X_test, y_test)
- y_test_predicted = clf.predict(X_test)
- print ('AdaBoostClassifier first 9 predicted values:n', y_test_predicted[:9])
Add Comment
Please, Sign In to add comment