def read_tree(self, parent_line, token_line):
parents = list(map(lambda x: int(x) - 1,parent_line.split()))
tokens = token_line.strip().split()
tree_nodes = dict()
root = None
for i in range(len(parents)):
crnt_node_id = i
if crnt_node_id not in tree_nodes.keys():
prev_node = None
while True:
if crnt_node_id == -1:
break
parent_node_id = parents[crnt_node_id]
crnt_node = TreeNode()
if prev_node is not None:
crnt_node.add_child(prev_node)
tree_nodes[crnt_node_id] = crnt_node
crnt_node.idx = crnt_node_id
crnt_node.token = tokens[crnt_node_id]
#if trees[parent-1] is not None:
if parent_node_id in tree_nodes.keys():
tree_nodes[parent_node_id].add_child(crnt_node)
break
elif parent_node_id == -1:
root = crnt_node
break
else:
prev_node = crnt_node
crnt_node_id = parent_node_id
return root
def __decision_tree(self, X, Y, features, level, metric, classes):
# returns the root of the Decision Tree(which consists of TreeNodes) built after fitting the training data
# Here Nodes are printed as in PREORDER traversl
# classes represents the different classes present in the classification problem
# metric can take value gain_ratio or gini_index
# level represents depth of the tree
# We split a node on a particular feature only once (in a given root to leaf node path)
# If the node consists of only 1 class
if len(set(Y)) == 1:
print("Level", level)
output = None
for i in classes:
if i in Y:
output = i
print("Count of", i, "=", len(Y))
else:
print("Count of", i, "=", 0)
if metric == "gain_ratio":
print("Current Entropy is = 0.0")
elif metric == "gini_index":
print("Current Gini Index is = 0.0")
print("Reached leaf Node")
print()
return TreeNode(None, output)
# If we have run out of features to split upon
# In this case we will output the class with maximum count
if len(features) == 0:
print("Level", level)
freq_map = self.__count_unique(Y)
output = None
max_count = -math.inf
for i in classes:
if i not in freq_map:
print("Count of", i, "=", 0)
else:
if freq_map[i] > max_count:
output = i
max_count = freq_map[i]
print("Count of", i, "=", freq_map[i])
if metric == "gain_ratio":
print("Current Entropy is =", self.__entropy(Y))
elif metric == "gini_index":
print("Current Gini Index is =", self.__gini_index(Y))
print("Reached leaf Node")
print()
return TreeNode(None, output)
# Finding the best feature to split upon
max_gain = -math.inf
final_feature = None
for f in features:
if metric == "gain_ratio":
current_gain = self.__gain_ratio(X, Y, f)
elif metric == "gini_index":
current_gain = self.__gini_gain(X, Y, f)
if current_gain > max_gain:
max_gain = current_gain
final_feature = f
print("Level", level)
freq_map = self.__count_unique(Y)
output = None
max_count = -math.inf
for i in classes:
if i not in freq_map:
print("Count of", i, "=", 0)
else:
if freq_map[i] > max_count:
output = i
max_count = freq_map[i]
print("Count of", i, "=", freq_map[i])
if metric == "gain_ratio":
print("Current Entropy is =", self.__entropy(Y))
print("Splitting on feature X[",
final_feature,
"] with gain ratio ",
max_gain,
sep="")
print()
elif metric == "gini_index":
print("Current Gini Index is =", self.__gini_index(Y))
print("Splitting on feature X[",
final_feature,
"] with gini gain ",
max_gain,
sep="")
print()
unique_values = set(
X[:, final_feature]
) # unique_values represents the unique values of the feature selected
df = pd.DataFrame(X)
# Adding Y values as the last column in the dataframe
df[df.shape[1]] = Y
current_node = TreeNode(final_feature, output)
# Now removing the selected feature from the list as we do not want to split on one feature more than once(in a given root to leaf node path)
index = features.index(final_feature)
features.remove(final_feature)
for i in unique_values:
# Creating a new dataframe with value of selected feature = i
df1 = df[df[final_feature] == i]
# Segregating the X and Y values and recursively calling on the splits
node = self.__decision_tree(df1.iloc[:, 0:df1.shape[1] - 1].values,
df1.iloc[:, df1.shape[1] - 1].values,
features, level + 1, metric, classes)
current_node.add_child(i, node)
# Add the removed feature
features.insert(index, final_feature)
return current_node
def __decision_tree(self,X,Y,features,level,metric,classes):
# returns the root of the Decision Tree(which consists of TreeNodes) built after fitting the training data
# Here Nodes are printed as in PREORDER traversl
# classes represents the different classes present in the classification problem
# metric can take value gain_ratio or gini_index
# level represents depth of the tree
# We split a node on a particular feature only once (in a given root to leaf node path)
# If the node consists of only 1 class
if len(set(Y)) == 1:
print("Level",level)
output = None
for i in classes:
if i in Y:
output = i
print("Count of",i,"=",len(Y))
else :
print("Count of",i,"=",0)
if metric == "gain_ratio":
print("Current Entropy is = 0.0")
elif metric == "gini_index":
print("Current Gini Index is = 0.0")
print("Reached leaf Node")
print()
return TreeNode(None,output)
# If we have run out of features to split upon
# In this case we will output the class with maximum count
if len(features) == 0:
print("Level",level)
freq_map = self.__count_unique(Y)
output = None
max_count = -math.inf
for i in classes:
if i not in freq_map:
print("Count of",i,"=",0)
else :
if freq_map[i] > max_count :
output = i
max_count = freq_map[i]
print("Count of",i,"=",freq_map[i])
if metric == "gain_ratio":
print("Current Entropy is =",self.__entropy(Y))
elif metric == "gini_index":
print("Current Gini Index is =",self.__gini_index(Y))
print("Reached leaf Node")
print()
return TreeNode(None,output)
# Finding the best feature to split upon
max_gain = -math.inf
final_feature = None
for f in features :
if metric == "gain_ratio":
current_gain = self.__gain_ratio(X,Y,f)
elif metric =="gini_index":
current_gain = self.__gini_gain(X,Y,f)
if current_gain > max_gain:
max_gain = current_gain
final_feature = f
print("Level",level)
freq_map = self.__count_unique(Y)
output = None
max_count = -math.inf
for i in classes:
if i not in freq_map:
print("Count of",i,"=",0)
else :
if freq_map[i] > max_count :
output = i
max_count = freq_map[i]
print("Count of",i,"=",freq_map[i])
if metric == "gain_ratio" :
print("Current Entropy is =",self.__entropy(Y))
print("Splitting on feature X[",final_feature,"] with gain ratio ",max_gain,sep="")
print()
elif metric == "gini_index":
print("Current Gini Index is =",self.__gini_index(Y))
print("Splitting on feature X[",final_feature,"] with gini gain ",max_gain,sep="")
print()
unique_values = set(X[:,final_feature]) # unique_values represents the unique values of the feature selected
df = pd.DataFrame(X)
# Adding Y values as the last column in the dataframe
df[df.shape[1]] = Y
current_node = TreeNode(final_feature,output)
# Now removing the selected feature from the list as we do not want to split on one feature more than once(in a given root to leaf node path)
index = features.index(final_feature)
features.remove(final_feature)
for i in unique_values:
# Creating a new dataframe with value of selected feature = i
df1 = df[df[final_feature] == i]
# Segregating the X and Y values and recursively calling on the splits
node = self.__decision_tree(df1.iloc[:,0:df1.shape[1]-1].values,df1.iloc[:,df1.shape[1]-1].values,features,level+1,metric,classes)
current_node.add_child(i,node)
# Add the removed feature
features.insert(index,final_feature)
return current_node
from treenode import TreeNode
#TEST 1
dile = TreeNode("Dile")
edo = TreeNode("Edo")
raffo = TreeNode("Raffo", [dile, edo])
cami = TreeNode("Cami")
stella = TreeNode("Stella", [TreeNode("Jess")])
gabry = TreeNode("Gabry", [TreeNode("Saba"), TreeNode("Luca"), stella])
ale = TreeNode("Ale", [TreeNode("Dave"), gabry, TreeNode("Greg")])
enzo = TreeNode("Enzo", [TreeNode("Diodato")])
fra = TreeNode("Fra", [enzo])
fede = TreeNode("Fede", [ale, fra])
cami.add_child(raffo)
cami.add_child(fede)
peppe = TreeNode(
"Peppe",
[TreeNode("Marco"), TreeNode("Gio"),
TreeNode("Marghe")])
cami.add_child(peppe)
print(cami)
print("\n")
print(cami.give_software())
#TEST 2
tredici = TreeNode("13", [TreeNode("16"), TreeNode("17")])
otto = TreeNode("8", [TreeNode("12"), tredici, TreeNode("14")])
quattro = TreeNode("4", [TreeNode("9"), TreeNode("10")])
sette = TreeNode("7", [TreeNode("11", [TreeNode("15")])])
