def MDLPC_criterion(self, data, feature, cut_point):
'''
Determines whether a partition is accepted according to the MDLPC criterion
:param feature: feature of interest
:param cut_point: proposed cut_point
:param partition_index: index of the sample (dataframe partition) in the interval of interest
:return: True/False, whether to accept the partition
'''
#get dataframe only with desired attribute and class columns, and split by cut_point
data_partition = data.copy(deep=True)
data_left = data_partition[data_partition[feature] <= cut_point]
data_right = data_partition[data_partition[feature] > cut_point]
#compute information gain obtained when splitting data at cut_point
cut_point_gain = cut_point_information_gain(dataset=data_partition, cut_point=cut_point,
feature_label=feature, class_label=self._class_name)
#compute delta term in MDLPC criterion
N = len(data_partition) # number of examples in current partition
partition_entropy = entropy(data_partition[self._class_name])
k = len(data_partition[self._class_name].unique())
k_left = len(data_left[self._class_name].unique())
k_right = len(data_right[self._class_name].unique())
entropy_left = entropy(data_left[self._class_name]) # entropy of partition
entropy_right = entropy(data_right[self._class_name])
delta = log(3 ** k, 2) - (k * partition_entropy) + (k_left * entropy_left) + (k_right * entropy_right)
#to split or not to split
gain_threshold = (log(N - 1, 2) + delta) / N
if cut_point_gain > gain_threshold:
return True
else:
return False
def MDLPC_criterion(self, data, feature, cut_point):
'''
Determines whether a partition is accepted according to the MDLPC criterion
:param feature: feature of interest
:param cut_point: proposed cut_point
:param partition_index: index of the sample (dataframe partition) in the interval of interest
:return: True/False, whether to accept the partition
'''
#get dataframe only with desired attribute and class columns, and split by cut_point
data_partition = data.copy(deep=True)
data_left = data_partition[data_partition[feature] <= cut_point]
data_right = data_partition[data_partition[feature] > cut_point]
#compute information gain obtained when splitting data at cut_point
cut_point_gain = cut_point_information_gain(dataset=data_partition, cut_point=cut_point,
feature_label=feature, class_label=self._class_name)
#compute delta term in MDLPC criterion
N = len(data_partition) # number of examples in current partition
partition_entropy = entropy(data_partition[self._class_name])
k = len(data_partition[self._class_name].unique())
k_left = len(data_left[self._class_name].unique())
k_right = len(data_right[self._class_name].unique())
entropy_left = entropy(data_left[self._class_name]) # entropy of partition
entropy_right = entropy(data_right[self._class_name])
delta = log(3 ** k, 2) - (k * partition_entropy) + (k_left * entropy_left) + (k_right * entropy_right)
#to split or not to split
gain_threshold = (log(N - 1, 2) + delta) / N
if cut_point_gain > gain_threshold:
return True
else:
return False
def best_cut_point(self, data, feature):
'''
Selects the best cut point for a feature in a data partition based on information gain
:param data: data partition (pandas dataframe)
:param feature: target attribute
:return: value of cut point with highest information gain (if many, picks first). None if no candidates
'''
candidates = self.boundaries_in_partition(data=data, feature=feature)
# candidates = self.feature_boundary_points(data=data, feature=feature)
if not candidates:
return None
gains = [(cut, cut_point_information_gain(dataset=data, cut_point=cut, feature_label=feature,
class_label=self._class_name)) for cut in candidates]
gains = sorted(gains, key=lambda x: x[1], reverse=True)
return gains[0][0] #return cut point
def best_cut_point(self, data, feature):
'''
Selects the best cut point for a feature in a data partition based on information gain
:param data: data partition (pandas dataframe)
:param feature: target attribute
:return: value of cut point with highest information gain (if many, picks first). None if no candidates
'''
candidates = self.boundaries_in_partition(data=data, feature=feature)
# candidates = self.feature_boundary_points(data=data, feature=feature)
if not candidates:
return None
gains = [(cut, cut_point_information_gain(dataset=data, cut_point=cut, feature_label=feature,
class_label=self._class_name)) for cut in candidates]
gains = sorted(gains, key=lambda x: x[1], reverse=True)
return gains[0][0] #return cut point
