Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import time
- import sys
- from sklearn import ensemble, datasets, model_selection, metrics
- import numpy as np
- n_estimators = int(sys.argv[1])
- rs = np.random.RandomState(12345)
- X, y = datasets.make_classification(n_samples=10000, n_features=12,
- n_informative=12, n_redundant=0,
- n_repeated=0, random_state=rs)
- X = X.astype(np.float32)
- X_train, X_test, y_train, y_test = \
- model_selection.train_test_split(X, y, test_size=0.8,
- random_state=rs)
- rfc = ensemble.RandomForestClassifier(n_estimators=n_estimators,
- n_jobs=-1, random_state=rs)
- time1 = time.perf_counter()
- rfc.fit(X_train, y_train)
- time2 = time.perf_counter()
- proba = rfc.predict_proba(X_test)
- time3 = time.perf_counter()
- print("{:5.3f} sec to fit".format(time2-time1))
- print("{:5.3f} sec to predict".format(time3-time2))
- print("{:5.3f} brier score".format(metrics.brier_score_loss(y_test, proba[:, 1])))
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement