def RRExtra_rf_dis(n_trees, X, Y, train_indices, test_indices, seed):
clf = RRExtraTreesClassifier(n_estimators=500,
random_state=seed,
bootstrap=True,
n_jobs=-1)
clf.fit(X[train_indices], Y[train_indices])
pred = clf.predict(X[test_indices])
weight = clf.score(X[test_indices], Y[test_indices])
#print(1 - clf.oob_score_)
n_samples = X.shape[0]
dis = np.zeros((n_samples, n_samples))
for i in range(n_samples):
dis[i][i] = 1
res = clf.apply(X)
for i in range(n_samples):
for j in range(i + 1, n_samples):
a = np.ravel(res[i])
b = np.ravel(res[j])
score = a == b
d = float(score.sum()) / n_trees
dis[i][j] = dis[j][i] = d
X_features1 = np.transpose(dis)
X_features2 = X_features1[train_indices]
X_features3 = np.transpose(X_features2)
return X_features3[train_indices], X_features3[test_indices], weight, pred
X_features1 = np.transpose(dis)
X_features2 = X_features1[train_indices]
X_features3 = np.transpose(X_features2)
return X_features3[train_indices], X_features3[test_indices], weight, pred
from uci_loader import *
X, y = getdataset('diabetes')
print(X.shape)
clf = RRForestClassifier(n_estimators=20, random_state=1000, n_jobs=-1)
indd = int(len(y) / 2)
clf.fit(X[:indd], y[:indd])
print("Random Rotation Forest Accuracy:",
np.mean(clf.predict(X[indd:]) == y[indd:]))
classifier = RRExtraTreesClassifier(n_estimators=20)
classifier.fit(X[:indd], y[:indd])
print("Random Rotation Extra Trees Accuracy:",
np.mean(classifier.predict(X[indd:]) == y[indd:]))
classifier = RandomForestClassifier(n_estimators=20)
classifier.fit(X[:indd], y[:indd])
print("Random Forest Accuracy:",
np.mean(classifier.predict(X[indd:]) == y[indd:]))
train_indices, test_indices = splitdata(X=X, Y=y, ratio=0.5, seed=1000)
print("Start rest")
# view1
seed = 1000
X_features_train1, X_features_test1, w1, pred1 = RR_rf_dis(
n_trees=10,
from uci_comparison import compare_estimators
from sklearn.ensemble.forest import RandomForestClassifier, ExtraTreesClassifier
from rr_forest import RRForestClassifier
from rr_extra_forest import RRExtraTreesClassifier
estimators = {
'RandomForest': RandomForestClassifier(n_estimators=20),
'RndRotForest': RRForestClassifier(n_estimators=20),
'ExtraTrees': ExtraTreesClassifier(n_estimators=20),
'RndRotETrees': RRExtraTreesClassifier(n_estimators=20),
}
# optionally, pass a list of UCI dataset identifiers as the datasets parameter, e.g. datasets=['iris', 'diabetes']
# optionally, pass a dict of scoring functions as the metric parameter, e.g. metrics={'F1-score': f1_score}
compare_estimators(estimators)
from uci_loader import *
X, y = getdataset('diabetes')
from rr_forest import RRForestClassifier
from rr_extra_forest import RRExtraTreesClassifier
from sklearn.ensemble.forest import RandomForestClassifier
classifier = RRForestClassifier(n_estimators=20)
classifier.fit(X[:len(y) / 2], y[:len(y) / 2])
print "Random Rotation Forest Accuracy:", np.mean(
classifier.predict(X[len(y) / 2:]) == y[len(y) / 2:])
classifier = RRExtraTreesClassifier(n_estimators=20)
classifier.fit(X[:len(y) / 2], y[:len(y) / 2])
print "Random Rotation Extra Trees Accuracy:", np.mean(
classifier.predict(X[len(y) / 2:]) == y[len(y) / 2:])
classifier = RandomForestClassifier(n_estimators=20)
classifier.fit(X[:len(y) / 2], y[:len(y) / 2])
print "Random Forest Accuracy:", np.mean(
classifier.predict(X[len(y) / 2:]) == y[len(y) / 2:])