class VotingEnsemble(BaseClassifier):
def __init__(self, feature_length, num_classes, x=10):
super().__init__(feature_length, num_classes)
self.model = VotingClassifier(estimators=[
('gba',
GradientBoostingClassifier(n_estimators=100,
learning_rate=1.0,
max_depth=1,
random_state=0)),
('knn',
KNeighborsClassifier(metric='manhattan',
weights='distance',
n_neighbors=3)),
('Nc', NearestCentroid(metric='manhattan')), ('nvb', GaussianNB()),
('rf', RandomForestClassifier(n_estimators=10,
criterion='entropy')),
('svmlin', svm.SVC(kernel='linear')),
('svmpol', svm.SVC(kernel='poly')),
('svmrbf', svm.SVC(kernel='rbf'))
],
voting='hard')
self.num_classes = num_classes
def train(self, features, labels):
"""
Using a set of features and labels, trains the classifier and returns the training accuracy.
:param features: An MxN matrix of features to use in prediction
:param labels: An M row list of labels to train to predict
:return: Prediction accuracy, as a float between 0 and 1
"""
labels = self.labels_to_categorical(labels)
self.model.fit(features, labels)
accuracy = self.model.score(features, labels)
return accuracy
# make sure you save model using the same library as we used in machine learning price-predictor
def predict(self, features, labels):
"""
Using a set of features and labels, predicts the labels from the features,
and returns the accuracy of predicted vs actual labels.
:param features: An MxN matrix of features to use in prediction
:param labels: An M row list of labels to test prediction accuracy on
:return: Prediction accuracy, as a float between 0 and 1
"""
label_train = self.labels_to_categorical(labels)
labels = self.model.predict(features)
accuracy = self.model.score(features, label_train)
return accuracy
def get_prediction(self, features):
return self.model.predict(features)
def reset(self):
"""
Resets the trained weights / parameters to initial state
:return:
"""
pass
def labels_to_categorical(self, labels):
_, IDs = unique(labels, return_inverse=True)
return IDs
max_depth=4,
random_state=2018)
rf = RandomForestClassifier(1000,
criterion='gini',
n_jobs=-1,
random_state=2018)
lor = LogisticRegression(solver='newton-cg',
multi_class='multinomial',
max_iter=1000)
clf = VotingClassifier([('gbt', gbt), ('rf', rf), ('lor', lor)],
voting='soft',
weights=[3, 2, 1],
n_jobs=-1)
if args.s:
clf.fit(X_train, y_train)
joblib.dump(clf, 'checkpoint/voting.pkl')
X_test = pd.read_csv("data/test_python.csv", encoding='utf-8')
pred = clf.predict_proba(X_test)
np.savetxt('submission/submission.csv',
np.c_[X_test['listing_id'], pred[:, [2, 1, 0]]],
delimiter=',',
header='listing_id,high,medium,low',
fmt='%d,%.16f,%.16f,%.16f',
comments='')
else:
cv = StratifiedKFold(n_splits=3, shuffle=True, random_state=2018)
scores = cross_val_score(clf,
X_train,
y_train,
scoring='neg_log_loss',
pipe1 = make_pipeline(ColumnSelector(cols=split1), LinearSVC())
pipe2 = make_pipeline(ColumnSelector(cols=split2), LinearSVC())
pipe3 = make_pipeline(ColumnSelector(cols=split3), LinearSVC())
pipe4 = make_pipeline(ColumnSelector(cols=split4), LinearSVC())
pipe5 = make_pipeline(ColumnSelector(cols=split5), LinearSVC())
# create the ensemble with the votingclassifier
cls = VotingClassifier([
('l1', pipe1),
('l2', pipe2),
('l3', pipe3),
('l4', pipe4),
('l5', pipe5),
],
n_jobs=4)
cls.fit(cars_train_X, cars_train_y)
# uncomment the 3 lines below if needed to see the accuracy and std-dev of the training set
# scores = cross_val_score(cls, cars_train_X, cars_train_y, cv=5, verbose=True)
# print(scores)
# print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
# this reaches about 30% acc
# create the predictions and dump to a file for plotting the heatmap
y_pred = cls.predict(cars_test_X)
with open('5subset_linearsvm_voting.sav', 'wb') as f:
pkl.dump((y_pred, cars_test_y), f)
y_true = cars_test_y
preds = {}