def train(data, attributes, labels, k):
trees = []
for i in range(k):
new_data = data
sample = data.raw_data[np.random.choice(data.raw_data.shape[0],
100,
replace=True)]
new_data.raw_data = sample
numbers = np.random.randint(1, data.raw_data.shape[1] - 1, size=50)
features = copy.deepcopy(attributes)
for attr in attributes:
if int(attr) not in numbers:
del features[attr]
new_data.attributes = features
tree = dt.id3(new_data, features, labels)
pruned = dt.pruning_tree(tree, 1)
trees.append(pruned)
err, depth = dt.report_error(new_data, pruned)
transformed_data = np.zeros((data.raw_data.shape[0], k + 1))
labels = []
for row, test in enumerate(data.raw_data):
transformed_data[row, 0] = test[0]
for col, tree in enumerate(trees, 1):
label = dt.predict(data, test, tree)
transformed_data[row, col] = int(label)
labels.append(int(label))
labels.append(1)
lbls = transformed_data[:, 0]
w, a, lab = svm.train(transformed_data, lbls, k)
return a, lab
def train(data, attributes, labels, k):
maj =[]
for i in range(k):
new_data = data
sample = data.raw_data[np.random.choice(data.raw_data.shape[0], 100, replace=True)]
new_data.raw_data = sample
numbers = np.random.randint(1, data.raw_data.shape[1]-1, size=50)
features = copy.deepcopy(attributes)
for attr in attributes:
if int(attr) not in numbers:
del features[attr]
new_data.attributes = features
tree = dt.id3(new_data, features, labels)
pruned = dt.pruning_tree(tree, 1)
err, depth = dt.report_error(new_data, pruned)
maj.append(100-err)
return sum(maj)/k
def train(data, attributes, labels, k):
tree = dt.id3(data, attributes, labels, maxDepth=2)
return tree