def train_extra_Randomized_forest_classifer(training_data, n_est=10):
randomized = ExtraTreesClassifier(n_estimators=n_est,
max_depth=None,
min_samples_split=2,
class_weight="balanced")
randomized.classes_ = [0, 1]
scores = cross_val_score(randomized,
training_data[:,
selected_features].astype('float'),
training_data[:, -1].astype('float'),
cv=10,
scoring='roc_auc')
print("Scores gotten using Extra Randomized Forests (# of estimators=" +
str(n_est) + ")")
print(scores)
print(np.mean(scores))
return randomized, np.mean(scores)
def run_on_feature_union():
load_word_embeddings()
(training_data, _) = read_lines_from_file('data/filtered_features.csv')
training_data = np.array(training_data)
#training_data = generate_normalized_data(training_data)
clf = RandomForestClassifier(n_estimators=100, class_weight="balanced")
clf.classes_ = [0, 1]
adaboost = AdaBoostClassifier(n_estimators=100)
adaboost.classes_ = [0, 1]
svm_clf = svm.SVC(probability=True)
svm_clf.classes_ = [0, 1]
randomized = ExtraTreesClassifier(n_estimators=45,
max_depth=None,
min_samples_split=2,
class_weight="balanced")
randomized.classes_ = [0, 1]
pipeline = Pipeline([
('features',
FeatureUnion(
[('numeric_features', NumericFeaturesExtractor()),
('bag_of_words_features', BagOfWordsExtractor()),
('w2v_features', Word2VecExtractor())],
transformer_weights={
'numeric_features': 0.5,
'bag_of_words_features': 0.9,
'w2v_features': 1.0,
})), ('clf', clf)
])
pipeline.fit(training_data, training_data[:, -1].astype('float'))
scores = cross_val_score(pipeline,
training_data,
training_data[:, -1].astype('float'),
cv=10,
scoring='roc_auc')
print(scores)
print(np.mean(scores))