def addEpochAlpha(epoch, alpha):
file = "outputs/rules/alphas.py"
content = " if epoch == " + str(epoch) + ":\n"
content += " return " + str(alpha)
functions.storeRule(file, content)
def buildDecisionTree(df,root,file, config, dataset_features):
if root == 1:
if config['enableRandomForest'] != True and config['enableGBM'] != True and config['enableAdaboost'] != True:
raw_df = df.copy()
algorithm = config['algorithm']
enableAdaboost = config['enableAdaboost']
#--------------------------------------
#print(df.shape)
charForResp = "'"
if algorithm == 'Regression':
charForResp = ""
tmp_root = root * 1
df_copy = df.copy()
winner_name = findDecision(df, config)
#find winner index, this cannot be returned by find decision because columns dropped in previous steps
j = 0
for i in dataset_features:
if i == winner_name:
winner_index = j
j = j + 1
numericColumn = False
if dataset_features[winner_name] != 'object':
numericColumn = True
#restoration
columns = df.shape[1]
for i in range(0, columns-1):
column_name = df.columns[i]; column_type = df[column_name].dtypes
if column_type != 'object' and column_name != winner_name:
df[column_name] = df_copy[column_name]
classes = df[winner_name].value_counts().keys().tolist()
for i in range(0,len(classes)):
current_class = classes[i]
subdataset = df[df[winner_name] == current_class]
subdataset = subdataset.drop(columns=[winner_name])
if numericColumn == True:
compareTo = current_class #current class might be <=x or >x in this case
else:
compareTo = " == '"+str(current_class)+"'"
#print(subdataset)
terminateBuilding = False
#-----------------------------------------------
#can decision be made?
if enableAdaboost == True:
#final_decision = subdataset['Decision'].value_counts().idxmax()
final_decision = subdataset['Decision'].mean() #get average
terminateBuilding = True
elif len(subdataset['Decision'].value_counts().tolist()) == 1:
final_decision = subdataset['Decision'].value_counts().keys().tolist()[0] #all items are equal in this case
terminateBuilding = True
elif subdataset.shape[1] == 1: #if decision cannot be made even though all columns dropped
final_decision = subdataset['Decision'].value_counts().idxmax() #get the most frequent one
terminateBuilding = True
elif algorithm == 'Regression' and subdataset.shape[0] < 5: #pruning condition
#elif algorithm == 'Regression' and subdataset['Decision'].std(ddof=0)/global_stdev < 0.4: #pruning condition
final_decision = subdataset['Decision'].mean() #get average
terminateBuilding = True
#-----------------------------------------------
if i == 0:
check_condition = "if"
else:
check_condition = "elif"
functions.storeRule(file,(functions.formatRule(root),"",check_condition," obj[",str(winner_index),"]",compareTo,":"))
#-----------------------------------------------
if terminateBuilding == True: #check decision is made
functions.storeRule(file,(functions.formatRule(root+1),"return ",charForResp+str(final_decision)+charForResp))
else: #decision is not made, continue to create branch and leafs
root = root + 1 #the following rule will be included by this rule. increase root
buildDecisionTree(subdataset, root, file, config, dataset_features)
root = tmp_root * 1
#---------------------------------------------
#calculate accuracy metrics
if root == 1:
if config['enableRandomForest'] != True and config['enableGBM'] != True and config['enableAdaboost'] != True:
#this is reguler decision tree. find accuracy here.
moduleName = "outputs/rules/rules"
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description) #rules0
num_of_features = df.shape[1] - 1
instances = df.shape[0]
classified = 0; mae = 0; mse = 0
#instead of for loops, pandas functions perform well
raw_df['Prediction'] = raw_df.apply(findPrediction, axis=1)
if algorithm != 'Regression':
idx = raw_df[raw_df['Prediction'] == raw_df['Decision']].index
#raw_df['Classified'] = 0
#raw_df.loc[idx, 'Classified'] = 1
#print(raw_df)
accuracy = 100*len(idx)/instances
print("Accuracy: ", accuracy,"% on ",instances," instances")
else:
raw_df['Absolute_Error'] = abs(raw_df['Prediction'] - raw_df['Decision'])
raw_df['Absolute_Error_Squared'] = raw_df['Absolute_Error'] * raw_df['Absolute_Error']
#print(raw_df)
mae = raw_df['Absolute_Error'].sum()/instances
print("MAE: ",mae)
mse = raw_df['Absolute_Error_Squared'].sum()/instances
rmse = math.sqrt(mse)
print("RMSE: ",rmse)
mean = raw_df['Decision'].mean()
print("Mean: ", mean)
if mean > 0:
print("MAE / Mean: ",100*mae/mean,"%")
print("RMSE / Mean: ",100*rmse/mean,"%")
def buildDecisionTree(df,root,file, config, dataset_features): algorithm = config['algorithm'] enableAdaboost = config['enableAdaboost'] debug = config['debug'] #-------------------------------------- #print(df.shape) charForResp = "'" if algorithm == 'Regression': charForResp = "" tmp_root = root * 1 df_copy = df.copy() winner_name = findDecision(df, config) #find winner index, this cannot be returned by find decision because columns dropped in previous steps j = 0 for i in dataset_features: if i == winner_name: winner_index = j j = j + 1 numericColumn = False if dataset_features[winner_name] != 'object': numericColumn = True #restoration columns = df.shape[1] for i in range(0, columns-1): column_name = df.columns[i]; column_type = df[column_name].dtypes if column_type != 'object' and column_name != winner_name: df[column_name] = df_copy[column_name] classes = df[winner_name].value_counts().keys().tolist() for i in range(0,len(classes)): current_class = classes[i] subdataset = df[df[winner_name] == current_class] subdataset = subdataset.drop(columns=[winner_name]) if numericColumn == True: compareTo = current_class #current class might be <=x or >x in this case else: compareTo = " == '"+str(current_class)+"'" #print(subdataset) terminateBuilding = False #----------------------------------------------- #can decision be made? if enableAdaboost == True: #final_decision = subdataset['Decision'].value_counts().idxmax() final_decision = subdataset['Decision'].mean() #get average terminateBuilding = True elif len(subdataset['Decision'].value_counts().tolist()) == 1: final_decision = subdataset['Decision'].value_counts().keys().tolist()[0] #all items are equal in this case terminateBuilding = True elif subdataset.shape[1] == 1: #if decision cannot be made even though all columns dropped final_decision = subdataset['Decision'].value_counts().idxmax() #get the most frequent one terminateBuilding = True elif algorithm == 'Regression' and subdataset.shape[0] < 5: #pruning condition #elif algorithm == 'Regression' and subdataset['Decision'].std(ddof=0)/global_stdev < 0.4: #pruning condition final_decision = subdataset['Decision'].mean() #get average terminateBuilding = True #----------------------------------------------- if debug == True: print(functions.formatRule(root),"if ",winner_name,compareTo,":") else: functions.storeRule(file,(functions.formatRule(root),"if obj[",str(winner_index),"]",compareTo,":")) #----------------------------------------------- if terminateBuilding == True: #check decision is made if debug == True: print(functions.formatRule(root+1),"return ",charForResp+str(final_decision)+charForResp) else: functions.storeRule(file,(functions.formatRule(root+1),"return ",charForResp+str(final_decision)+charForResp)) else: #decision is not made, continue to create branch and leafs root = root + 1 #the following rule will be included by this rule. increase root buildDecisionTree(subdataset, root, file, config, dataset_features) root = tmp_root * 1
def buildDecisionTree(df, root, file, config, dataset_features):
models = []
if root == 1:
if config['RandomForest'] != True:
raw_df = df.copy()
algorithm = config['algorithm']
#--------------------------------------
#print(df.shape)
charForResp = "'"
if algorithm == 'Regression':
charForResp = ""
tmp_root = root * 1
df_copy = df.copy()
winner_name = findDecision(df, config)
j = 0
for i in dataset_features:
if i == winner_name:
winner_index = j
j = j + 1
numericColumn = False
if dataset_features[winner_name] != 'object':
numericColumn = True
#restoration
columns = df.shape[1]
for i in range(0, columns - 1):
column_name = df.columns[i]
column_type = df[column_name].dtypes
if column_type != 'object' and column_name != winner_name:
df[column_name] = df_copy[column_name]
classes = df[winner_name].value_counts().keys().tolist()
for i in range(0, len(classes)):
current_class = classes[i]
subdataset = df[df[winner_name] == current_class]
subdataset = subdataset.drop(columns=[winner_name])
if numericColumn == True:
compareTo = current_class
else:
compareTo = " == '" + str(current_class) + "'"
#print(subdataset)
terminateBuilding = False
#-----------------------------------------------
if len(subdataset['Decision'].value_counts().tolist()) == 1:
final_decision = subdataset['Decision'].value_counts().keys(
).tolist()[0]
terminateBuilding = True
elif subdataset.shape[1] == 1:
final_decision = subdataset['Decision'].value_counts().idxmax()
terminateBuilding = True
elif algorithm == 'Regression' and subdataset.shape[0] < 5:
final_decision = subdataset['Decision'].mean()
terminateBuilding = True
#-----------------------------------------------
if i == 0:
check_condition = "if"
else:
check_condition = "elif"
functions.storeRule(file,
(functions.formatRule(root), "", check_condition,
" obj[", str(winner_index), "]", compareTo, ":"))
#-----------------------------------------------
if terminateBuilding == True:
functions.storeRule(
file, (functions.formatRule(root + 1), "return ",
charForResp + str(final_decision) + charForResp))
else:
root = root + 1
buildDecisionTree(subdataset, root, file, config, dataset_features)
root = tmp_root * 1
#---------------------------------------------
#calculate accuracy metrics
if root == 1:
if config['RandomForest'] != True:
moduleName = "outputs/rules/rules"
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description)
models.append(myrules)
num_of_features = df.shape[1] - 1
instances = df.shape[0]
classified = 0
mae = 0
mse = 0
raw_df['Prediction'] = raw_df.apply(findPrediction, axis=1)
#print(raw_df['Prediction'])
#exit()
if algorithm != 'Regression':
True_positive = 0
True_negative = 0
False_positive = 0
False_negative = 0
for i in range(instances):
if (raw_df['Prediction'][i] == raw_df['Decision'][i]
and raw_df['Prediction'][i] == 'Yes'):
True_positive = True_positive + 1
if ((raw_df['Prediction'][i] != raw_df['Decision'][i]
and raw_df['Prediction'][i] == 'No')):
False_negative = False_negative + 1
if ((raw_df['Prediction'][i] != raw_df['Decision'][i]
and raw_df['Prediction'][i] == 'Yes')):
False_positive = False_positive + 1
idx = raw_df[raw_df['Prediction'] == raw_df['Decision']].index
accuracy = 100 * len(idx) / instances
precision = 100 * True_positive / (True_positive +
False_positive)
recall = 100 * True_positive / (True_positive + False_negative)
F1_score = 2 * (precision * recall) / (precision + recall)
print("accuracy: ", accuracy, "% trên tổng số ", instances,
"phép thử")
print("precision: ", precision, "% ")
print("recall: ", recall, "% ")
print("F1 score: ", F1_score)
else:
raw_df['Absolute_Error'] = abs(raw_df['Prediction'] -
raw_df['Decision'])
raw_df['Absolute_Error_Squared'] = raw_df[
'Absolute_Error'] * raw_df['Absolute_Error']
#print(raw_df)
mae = raw_df['Absolute_Error'].sum() / instances
print("MAE: ", mae)
mse = raw_df['Absolute_Error_Squared'].sum() / instances
rmse = math.sqrt(mse)
print("RMSE: ", rmse)
mean = raw_df['Decision'].mean()
print("Mean: ", mean)
if mean > 0:
print("MAE / Mean: ", 100 * mae / mean, "%")
print("RMSE / Mean: ", 100 * rmse / mean, "%")
return models