def id3(x, y, feature_list, impurity_measure="entropy", parent_node=None):
"""
Creates a decision tree, with the id3 alogoritm, based on learning data
:param x: dataset of items as list of list
:param y: target values for items as list
:param feature_list: available features for each iteration as list
:param impurity_measure: impurity measure entropy or gini as string
:param parent_node: parent for this node iteration as Tree (node representation), default None
:return: root node for tree as type Tree (node representation)
"""
x = np.array(x)
uniques, counts = np.unique(y, return_counts=True)#Find unique target values
if len(uniques) == 1: # Set is pure, only one target value left in set
return Tree(uniques[0], label=uniques[0])
if len(feature_list) == 0:#No more attributes to split on
if counts[0] > counts[1]:
return Tree(uniques[0], label=uniques[0])
else:
return Tree(uniques[1], label=uniques[1])
best_attribute = max_ig(x, y, feature_list, impurity_measure)
vals, counts = np.unique(x[:, best_attribute], return_counts=True)#Finds unique attribute values
this_node = Tree(best_attribute, parent_node)
n_children = len(vals)
feature_list.remove(best_attribute)
children_labels = []
for child in range(n_children): #Creates each children, based on unique attribute values
x_for_this_child = []
y_for_this_child = []
for item in range(len(x)): #Loops through all items, and passes on all items with correct attribute value
if x[item][best_attribute] == vals[child]: # Items where the attribute value is equal to the decision branch
x_for_this_child.append(x[item])
y_for_this_child.append(y[item])
# Continues to grow this child node
new_child = id3(x_for_this_child, y_for_this_child, feature_list, impurity_measure, parent_node=this_node)
new_child.set_was_split_on(vals[child]) #Saves what attribute value this child was split on
this_node.add_child(new_child)
children_labels.append(new_child.label)
label_list, label_count = np.unique(children_labels, return_counts=True) #Lists of children labels
label = label_list[np.argmax(label_count)]
this_node.set_label(label)#This node get most popular label among children
return this_node
def __fit_without_prune(self, data, features, target):
'''
Built entire decision tree without pruning
'''
continuous_features = list()
discrete_features = list()
for feature in features:
if len(list(data[feature])) > 0:
is_continue = self.is_attr_continue(list(data[feature]))
if is_continue:
continuous_features.append(feature)
else:
discrete_features.append(feature)
if not continuous_features:
return MyID3(self.gain_ratio).fit(data, features, target)
# Continuous attribute
# If only one value exist
entropy_data_target = Calculate.entropy(data[target])
if entropy_data_target == 0:
value_list = Calculate.get_unique_data(data, target)
value_dict = dict()
for key, value in value_list.items():
value_dict[key] = len(value_list[key])
return Tree(
Node(
None,
0.0, # Entropy must be 0 since only one value exist
value_dict,
result=data[target][0],
is_leaf=True))
if (len(features) == 0):
value_list = Calculate.get_unique_data(data, target)
value_dict = dict()
for key, value in value_list.items():
value_dict[key] = len(value_list[key])
return Tree(
Node(None,
entropy_data_target,
value_dict,
result=Calculate.most_label(data[target]),
is_leaf=True))
# Find best attribute and build tree recursively
best_attr = ''
best_point = 0
is_discrete = False
best_splitter = 0
chosen_edge = list(['', ''])
for feature in continuous_features:
best_treshold = self.find_threshold(data[[feature]],
data[[target]])
if best_treshold[1] > best_point:
best_attr = str(feature)
chosen_edge[0] = best_attr + ' > ' + str(best_treshold[0])
chosen_edge[1] = best_attr + ' <= ' + str(best_treshold[0])
best_point = best_treshold[1]
best_splitter = best_treshold[0]
for feature in discrete_features:
point = Calculate.info_gain(data[feature], data[target])
if point > best_point:
best_point = point
best_attr = str(feature)
is_discrete = True
value_list = Calculate.get_unique_data(data, target)
value_dict = dict()
for key, value in value_list.items():
value_dict[key] = len(value_list[key])
dtree = Tree(Node(best_attr, best_point, value_dict))
# Scan all posible value to be generated subtree
if is_discrete:
list_attribute = Calculate.get_unique_data(data, best_attr)
else:
list_attribute = Calculate.split_by_threshold(
data, best_attr, best_splitter)
i = 0
for attribute in list_attribute:
data = pd.DataFrame(data=list_attribute[attribute]).reset_index(
drop=True)
dtree.add_child(self.__fit_without_prune(data, features, target))
if is_discrete:
dtree.children[i].value.edge = attribute
else:
dtree.children[i].value.edge = chosen_edge[i]
i += 1
return dtree
def fit(self, data, attributes, target_name):
'''
Built and return decision tree using ID3 algorithm
'''
data_target = data[target_name]
# Data target contains one label
entropy_data_target = Calculate.entropy(data_target)
if entropy_data_target == 0:
value_list = Calculate.get_unique_data(data, target_name)
value_dict = dict()
for key, value in value_list.items():
value_dict[key] = len(value_list[key])
# Set current_node, info_gain, values
tree = Tree(
Node(None,
entropy_data_target,
value_dict,
result=data_target[0],
is_leaf=True))
return tree
# Nothing attribute shall be chosen
if len(attributes) == 0:
# Set current_node, info_gain, values
value_list = Calculate.get_unique_data(data, target_name)
value_dict = dict()
for key, value in value_list.items():
value_dict[key] = len(value_list[key])
tree = Tree(
Node(None,
entropy_data_target,
value_dict,
result=Calculate.most_label(data_target),
is_leaf=True))
return tree
else:
# Find best attribute to be node using either info gain or gain ratio
best_attr = ''
best_point = 0 # Could be Info gain or Gain ratio
for attr in attributes:
if self.gain_ratio:
point = Calculate.gain_ratio(data[attr], data_target)
if point > best_point:
best_point = point
best_attr = attr
else:
point = Calculate.info_gain(data[attr], data_target)
if point > best_point:
best_point = point
best_attr = attr
value_list = Calculate.get_unique_data(data, target_name)
value_dict = dict()
for key, value in value_list.items():
value_dict[key] = len(value_list[key])
# Build decision tree recursively
dtree = Tree(Node(best_attr, best_point, value_dict))
# Delete usage attribute in attributes
attributes.remove(best_attr)
# Scan all posible value to be generated subtree
list_attribute = Calculate.get_unique_data(data, best_attr)
i = 0
for attribute in list_attribute:
data = pd.DataFrame(
data=list_attribute[attribute]).reset_index(drop=True)
data.drop(best_attr, axis=1, inplace=True)
dtree.add_child(self.fit(data, attributes, target_name))
dtree.children[i].value.edge = attribute
i += 1
return dtree