def testTree():
best = ('A', 5)
data = {'A': [1,2,6,7,8,9,3,4,5], 'C': [1,0,1,0,1,0,1,0,1], 'B': [1,1,0,0,0,0,1,1,1]}
df = pd.DataFrame(data)
print tree.find_best_label_new(df, 'A', 'B')
print 'best feature and label'
print tree.find_best_feature_and_label_for_split(df, 'B', regression=True)
def branch_node(node, df, threshold, Y, regression=False):
"""
:param node: Node object defined in Stats
:param df: The dataframe being used by the tree
:param threshold: max branching depth
:param Y: Feature to predict
:return: void
"""
print 'Branching Level : ' + str(node.level)
data = node.get_node_data(df)
print 'Length of data ' + str(len(data)) + ' len df: ' + str(len(df))
feature, label = mytree.find_best_feature_and_label_for_split(data, Y, regression)
print 'feature: {} label: {}'.format(feature, label)
if feature is not None and node.level < threshold:
A_array, B_array = node.split(feature, df[feature], label)
print ' A : {} B: {}'.format(sum(A_array), sum(B_array))
node.add_left(A_array)
node.add_right(B_array)
branch_node(node.left, df, threshold, Y, regression)
branch_node(node.right, df, threshold, Y, regression)
else:
if not regression:
predict = 0
prob = mystats.binary_probability(data, Y)
print 'PROBABILITY ' + str(prob)
if prob >= .5:
predict = 1
error = mystats.binary_error(data, Y, predict)
else:
print str(feature) +'is fueaturea ' + str(label) + str(node.presence)
predict = float(sum(data[Y]))/len(data[Y])
error = mystats.compute_MSE(predict, list(data[Y]))
node.leaf(predict, error)