def fit(self, X, y):
n_features = np.shape(X)[1]
# If max_features have not been defined => select it as
# sqrt(n_features)
if not self.max_features:
self.max_features = int(math.sqrt(n_features))
if self.debug:
print("Training (%s estimators):" % (self.n_estimators))
# Choose one random subset of the data for each tree
subsets = get_random_subsets(X, y, self.n_estimators)
for i in self.bar(range(self.n_estimators)):
X_subset, y_subset = subsets[i]
# Feature bagging (select random subsets of the features)
idx = np.random.choice(range(n_features),
size=self.max_features,
replace=True)
# Save the indices of the features for prediction
self.feature_indices.append(idx)
# Choose the features corresponding to the indices
X_subset = X_subset[:, idx]
# Fit the tree to the data
self.trees[i].fit(X_subset, y_subset)
if self.debug:
progress = 100 * (i / self.n_estimators)
print("Progress: %.2f%%" % progress)
def fit(self, X, y):
with pyRAPL.Measurement('Fit_3', output=csv_output):
n_features = np.shape(X)[1]
# If max_features have not been defined => select it as
# sqrt(n_features)
if not self.max_features:
self.max_features = int(math.sqrt(n_features))
# Choose one random subset of the data for each tree
subsets = get_random_subsets(X, y, self.n_estimators)
for i in self.progressbar(range(self.n_estimators)):
X_subset, y_subset = subsets[i]
# Feature bagging (select random subsets of the features)
idx = np.random.choice(range(n_features),
size=self.max_features,
replace=True)
# Save the indices of the features for prediction
self.trees[i].feature_indices = idx
# Choose the features corresponding to the indices
X_subset = X_subset[:, idx]
# Fit the tree to the data
self.trees[i].fit(X_subset, y_subset)
csv_output.save()