def __init__(self, training_set):
"""
Constructs a new decision tree.
Args:
training_set: model.DataSet
The training data to use when building the decision tree.
"""
self.training_set = training_set
self._tree = id3.build_tree(training_set)
self._plotter = MatplotlibAnnotationTreePlotter(self._tree)
def __init__(self, training_set):
"""
Constructs a new decision tree.
Args:
training_set: model.DataSet
The training data to use when building the decision tree.
"""
self.training_set = training_set
self._tree = id3.build_tree(training_set)
self._plotter = MatplotlibAnnotationTreePlotter(self._tree)
else:
ret += bprint_aux(child_node, index + 2)
return ret
import pandas as pd
has_ids = True
has_header = True
has_labels = True
delimiter = ","
header = 0 if has_header else None
id_col = 0 if has_ids else None
# dataframe = pd.read_csv("./test/datasets/play_tennis.data", index_col=id_col, header=header,delimiter=delimiter)
dataframe = pd.read_csv("hope.csv", index_col=id_col, header=header, delimiter=delimiter)
labels = dataframe.pop(dataframe.columns[-1]) if has_labels else None
dataset = model.DataSet(dataframe, labels=labels)
tree = id3.build_tree(dataset)
printbonito = bprint(tree)
print(printbonito)
txt = open("output.txt", mode="w", encoding="UTF-8")
txt.write(printbonito)
txt.close()
tp = MatplotlibAnnotationTreePlotter(tree)
tp.plot()
class DecisionTree(AbstractClassifier):
"""
Decision tree classifier.
Builds a tree which is like a flow chart. It allows a decision to be
reached by checking the values for various features and following the
appropriate branches until a destination is reached.
In addition to being useful as a classifier, the structure of the
decision tree can lend insight into the data.
"""
def __init__(self, training_set):
"""
Constructs a new decision tree.
Args:
training_set: model.DataSet
The training data to use when building the decision tree.
"""
self.training_set = training_set
self._tree = id3.build_tree(training_set)
self._plotter = MatplotlibAnnotationTreePlotter(self._tree)
def _classify(self, sample):
"""
Predicts a sample's classification based on the decision tree that
was built from the training data.
Args:
sample:
The sample or observation to be classified.
Returns:
The sample's classification.
"""
node = self._tree.get_root_node()
while not node.is_leaf():
feature = node.get_value()
branch = sample[feature]
try:
node = node.get_child(branch)
except KeyError:
return self._handle_value_not_trained_for()
return node.get_value()
def _handle_value_not_trained_for(self):
"""
Handles the case where a sample has a value for a feature which was
not seen in the training set and therefore is not accounted for in
the tree.
Current strategy is to just return the most common label in the
training data set. It might be better to narrow this down to the
most common among samples that would reach the node at which the
unrecognized value was found.
Returns:
label:
The best guess at the label.
"""
return collection_utils.get_most_common(
self.training_set.get_labels())
def plot(self):
"""
Generates a plot of the decision tree to visualize its structure.
Returns:
void
"""
self._plotter.plot()
class DecisionTree(AbstractClassifier):
"""
Decision tree classifier.
Builds a tree which is like a flow chart. It allows a decision to be
reached by checking the values for various features and following the
appropriate branches until a destination is reached.
In addition to being useful as a classifier, the structure of the
decision tree can lend insight into the data.
"""
def __init__(self, training_set):
"""
Constructs a new decision tree.
Args:
training_set: model.DataSet
The training data to use when building the decision tree.
"""
self.training_set = training_set
self._tree = id3.build_tree(training_set)
self._plotter = MatplotlibAnnotationTreePlotter(self._tree)
def _classify(self, sample):
"""
Predicts a sample's classification based on the decision tree that
was built from the training data.
Args:
sample:
The sample or observation to be classified.
Returns:
The sample's classification.
"""
node = self._tree.get_root_node()
while not node.is_leaf():
feature = node.get_value()
branch = sample[feature]
try:
node = node.get_child(branch)
except KeyError:
return self._handle_value_not_trained_for()
return node.get_value()
def _handle_value_not_trained_for(self):
"""
Handles the case where a sample has a value for a feature which was
not seen in the training set and therefore is not accounted for in
the tree.
Current strategy is to just return the most common label in the
training data set. It might be better to narrow this down to the
most common among samples that would reach the node at which the
unrecognized value was found.
Returns:
label:
The best guess at the label.
"""
return collection_utils.get_most_common(self.training_set.get_labels())
def plot(self):
"""
Generates a plot of the decision tree to visualize its structure.
Returns:
void
"""
self._plotter.plot()
