def apply(df, config, header, dataset_features, validation_df = None):
models = []
num_of_trees = config['num_of_trees']
parallelism_on = config["enableParallelism"]
#TODO: is this logical for 48x2 cores?
#config["enableParallelism"] = False #run each tree in parallel but each branch in serial
#TODO: reconstruct for parallel run is problematic. you should reconstruct based on tree id.
input_params = []
pbar = tqdm(range(0, num_of_trees), desc='Bagging')
for i in pbar:
pbar.set_description("Sub decision tree %d is processing" % (i+1))
subset = df.sample(frac=1/num_of_trees)
root = 1
moduleName = "outputs/rules/rule_"+str(i)
file = moduleName+".py"
functions.createFile(file, header)
if parallelism_on: #parallel run
input_params.append((subset, root, file, config, dataset_features, 0, 0, 'root', i))
else: #serial run
Training.buildDecisionTree(subset,root, file, config, dataset_features, parent_level = 0, leaf_id = 0, parents = 'root', tree_id = i)
#-------------------------------
if parallelism_on:
num_cores = config["num_cores"]
pool = Training.MyPool(num_cores)
results = pool.starmap(buildDecisionTree, input_params)
pool.close()
pool.join()
#-------------------------------
#collect models for both serial and parallel here
for i in range(0, num_of_trees):
moduleName = "outputs/rules/rule_"+str(i)
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description)
models.append(myrules)
#-------------------------------
return models
def apply(df, config, header, dataset_features, validation_df=None):
models = []
num_of_trees = config['num_of_trees']
pbar = tqdm(range(0, num_of_trees), desc='Bagging')
for i in pbar:
#for i in range(0, num_of_trees):
pbar.set_description("Sub decision tree %d is processing" % (i + 1))
subset = df.sample(frac=1 / num_of_trees)
root = 1
moduleName = "outputs/rules/rule_" + str(i)
file = moduleName + ".py"
json_file = moduleName + ".json"
functions.createFile(file, header)
functions.createFile(json_file, "[\n")
Training.buildDecisionTree(subset,
root,
file,
config,
dataset_features,
parent_level=0,
leaf_id=0,
parents='root')
functions.storeRule(json_file, "{}]")
#--------------------------------
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description)
models.append(myrules)
#-------------------------------
return models
def buildDecisionTree(df,
root,
file,
config,
dataset_features,
parent_level,
leaf_id,
parents,
tree_id,
validation_df=None,
process_id=None):
Training.buildDecisionTree(df,
root,
file,
config,
dataset_features,
parent_level=parent_level,
leaf_id=leaf_id,
parents=parents,
tree_id=tree_id,
main_process_id=process_id)
def processContinuousFeatures(algorithm, df, column_name, entropy, config):
#if True:
if df[column_name].nunique() <= 20:
unique_values = sorted(df[column_name].unique())
else:
unique_values = []
df_mean = df[column_name].mean()
df_std = df[column_name].std(ddof=0)
df_min = df[column_name].min()
df_max = df[column_name].max()
unique_values.append(df[column_name].min())
unique_values.append(df[column_name].max())
unique_values.append(df[column_name].mean())
scales = list(range(-3, +4, 1))
for scale in scales:
if df_mean + scale * df_std > df_min and df_mean + scale * df_std < df_max:
unique_values.append(df_mean + scale * df_std)
unique_values.sort()
#print(column_name,"->",unique_values)
subset_gainratios = []
subset_gains = []
subset_ginis = []
subset_red_stdevs = []
subset_chi_squares = []
if len(unique_values) == 1:
winner_threshold = unique_values[0]
df[column_name] = np.where(df[column_name] <= winner_threshold,
"<=" + str(winner_threshold),
">" + str(winner_threshold))
return df
for i in range(0, len(unique_values) - 1):
threshold = unique_values[i]
subset1 = df[df[column_name] <= threshold]
subset2 = df[df[column_name] > threshold]
subset1_rows = subset1.shape[0]
subset2_rows = subset2.shape[0]
total_instances = df.shape[0] #subset1_rows+subset2_rows
subset1_probability = subset1_rows / total_instances
subset2_probability = subset2_rows / total_instances
if algorithm == 'ID3' or algorithm == 'C4.5':
threshold_gain = entropy - subset1_probability * Training.calculateEntropy(
subset1,
config) - subset2_probability * Training.calculateEntropy(
subset2, config)
subset_gains.append(threshold_gain)
if algorithm == 'C4.5': #C4.5 also need gain in the block above. That's why, instead of else if we used direct if condition here
threshold_splitinfo = -subset1_probability * math.log(
subset1_probability, 2) - subset2_probability * math.log(
subset2_probability, 2)
gainratio = threshold_gain / threshold_splitinfo
subset_gainratios.append(gainratio)
elif algorithm == 'CART':
decision_for_subset1 = subset1['Decision'].value_counts().tolist()
decision_for_subset2 = subset2['Decision'].value_counts().tolist()
gini_subset1 = 1
gini_subset2 = 1
for j in range(0, len(decision_for_subset1)):
gini_subset1 = gini_subset1 - math.pow(
(decision_for_subset1[j] / subset1_rows), 2)
for j in range(0, len(decision_for_subset2)):
gini_subset2 = gini_subset2 - math.pow(
(decision_for_subset2[j] / subset2_rows), 2)
gini = (subset1_rows / total_instances) * gini_subset1 + (
subset2_rows / total_instances) * gini_subset2
subset_ginis.append(gini)
elif algorithm == "CHAID":
#subset1 = high, subset2 = normal
unique_decisions = df['Decision'].unique() #Yes, No
num_of_decisions = len(unique_decisions) #2
subset1_expected = subset1.shape[0] / num_of_decisions
subset2_expected = subset2.shape[0] / num_of_decisions
chi_square = 0
for d in unique_decisions: #Yes, No
#decision = Yes
subset1_d = subset1[subset1["Decision"] == d] #high, yes
subset2_d = subset2[subset2["Decision"] == d] #normal, yes
subset1_d_chi_square = math.sqrt(
((subset1_d.shape[0] - subset1_expected) *
(subset1_d.shape[0] - subset1_expected)) /
subset1_expected)
subset2_d_chi_square = math.sqrt(
((subset2_d.shape[0] - subset2_expected) *
(subset2_d.shape[0] - subset2_expected)) /
subset2_expected)
chi_square = chi_square + subset1_d_chi_square + subset2_d_chi_square
subset_chi_squares.append(chi_square)
#----------------------------------
elif algorithm == 'Regression':
superset_stdev = df['Decision'].std(ddof=0)
subset1_stdev = subset1['Decision'].std(ddof=0)
subset2_stdev = subset2['Decision'].std(ddof=0)
threshold_weighted_stdev = (
subset1_rows / total_instances) * subset1_stdev + (
subset2_rows / total_instances) * subset2_stdev
threshold_reducted_stdev = superset_stdev - threshold_weighted_stdev
subset_red_stdevs.append(threshold_reducted_stdev)
#----------------------------------
if algorithm == "C4.5":
winner_one = subset_gainratios.index(max(subset_gainratios))
elif algorithm == "ID3": #actually, ID3 does not support for continuous features but we can still do it
winner_one = subset_gains.index(max(subset_gains))
elif algorithm == "CART":
winner_one = subset_ginis.index(min(subset_ginis))
elif algorithm == "CHAID":
winner_one = subset_chi_squares.index(max(subset_chi_squares))
elif algorithm == "Regression":
winner_one = subset_red_stdevs.index(max(subset_red_stdevs))
winner_threshold = unique_values[winner_one]
#print(column_name,": ", winner_threshold," in ", unique_values)
#print("theshold is ",winner_threshold," for ",column_name)
df[column_name] = np.where(df[column_name] <= winner_threshold,
"<=" + str(winner_threshold),
">" + str(winner_threshold))
return df
def apply(df, config, header, dataset_features):
models = []
alphas = []
initializeAlphaFile()
num_of_weak_classifier = config['num_of_weak_classifier']
#------------------------
rows = df.shape[0]
columns = df.shape[1]
final_predictions = pd.DataFrame(np.zeros([rows, 1]),
columns=['prediction'])
worksheet = df.copy()
worksheet['Weight'] = 1 / rows #uniform distribution initially
final_predictions = pd.DataFrame(np.zeros((df.shape[0], 2)),
columns=['Prediction', 'Actual'])
final_predictions['Actual'] = df['Decision']
#for i in range(0, num_of_weak_classifier):
pbar = tqdm(range(0, num_of_weak_classifier), desc='Adaboosting')
for i in pbar:
worksheet['Decision'] = worksheet['Weight'] * worksheet['Decision']
root = 1
file = "outputs/rules/rules_" + str(i) + ".py"
functions.createFile(file, header)
#print(worksheet)
Training.buildDecisionTree(worksheet.drop(columns=['Weight']),
root,
file,
config,
dataset_features,
parent_level=0,
leaf_id=0,
parents='root')
#---------------------------------------
moduleName = "outputs/rules/rules_" + str(i)
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description)
models.append(myrules)
#---------------------------------------
df['Epoch'] = i
worksheet['Prediction'] = df.apply(findPrediction, axis=1)
df = df.drop(columns=['Epoch'])
#---------------------------------------
worksheet['Actual'] = df['Decision']
worksheet['Loss'] = abs(worksheet['Actual'] -
worksheet['Prediction']) / 2
worksheet[
'Weight_Times_Loss'] = worksheet['Loss'] * worksheet['Weight']
epsilon = worksheet['Weight_Times_Loss'].sum()
alpha = math.log(
(1 - epsilon) /
epsilon) / 2 #use alpha to update weights in the next round
alphas.append(alpha)
#-----------------------------
#store alpha
addEpochAlpha(i, alpha)
#-----------------------------
worksheet['Alpha'] = alpha
worksheet['New_Weights'] = worksheet['Weight'] * (
-alpha * worksheet['Actual'] * worksheet['Prediction']).apply(
math.exp)
#normalize
worksheet['New_Weights'] = worksheet['New_Weights'] / worksheet[
'New_Weights'].sum()
worksheet['Weight'] = worksheet['New_Weights']
worksheet['Decision'] = df['Decision']
final_predictions['Prediction'] = final_predictions[
'Prediction'] + worksheet['Alpha'] * worksheet['Prediction']
#print(final_predictions)
worksheet = worksheet.drop(columns=[
'New_Weights', 'Prediction', 'Actual', 'Loss', 'Weight_Times_Loss',
'Alpha'
])
mae = (np.abs(final_predictions['Prediction'].apply(functions.sign) -
final_predictions['Actual']) /
2).sum() / final_predictions.shape[0]
#print(mae)
pbar.set_description("Epoch %d. Loss: %d. Process: " % (i + 1, mae))
#------------------------------
final_predictions['Prediction'] = final_predictions['Prediction'].apply(
functions.sign)
final_predictions['Absolute_Error'] = np.abs(
final_predictions['Actual'] - final_predictions['Prediction']) / 2
#print(final_predictions)
mae = final_predictions['Absolute_Error'].sum(
) / final_predictions.shape[0]
print("Loss (MAE) found ", mae, " with ", num_of_weak_classifier,
' weak classifiers')
return models, alphas
def processContinuousFeatures(algorithm, df, column_name, entropy, config):
unique_values = sorted(df[column_name].unique())
#print(column_name,"->",unique_values)
subset_gainratios = []
subset_gains = []
subset_ginis = []
subset_red_stdevs = []
if len(unique_values) == 1:
winner_threshold = unique_values[0]
df[column_name] = np.where(df[column_name] <= winner_threshold,
"<=" + str(winner_threshold),
">" + str(winner_threshold))
return df
for i in range(0, len(unique_values) - 1):
threshold = unique_values[i]
subset1 = df[df[column_name] <= threshold]
subset2 = df[df[column_name] > threshold]
subset1_rows = subset1.shape[0]
subset2_rows = subset2.shape[0]
total_instances = df.shape[0] #subset1_rows+subset2_rows
subset1_probability = subset1_rows / total_instances
subset2_probability = subset2_rows / total_instances
if algorithm == 'ID3' or algorithm == 'C4.5':
threshold_gain = entropy - subset1_probability * Training.calculateEntropy(
subset1,
config) - subset2_probability * Training.calculateEntropy(
subset2, config)
subset_gains.append(threshold_gain)
if algorithm == 'C4.5': #C4.5 also need gain in the block above. That's why, instead of else if we used direct if condition here
threshold_splitinfo = -subset1_probability * math.log(
subset1_probability, 2) - subset2_probability * math.log(
subset2_probability, 2)
gainratio = threshold_gain / threshold_splitinfo
subset_gainratios.append(gainratio)
elif algorithm == 'CART':
decision_for_subset1 = subset1['Decision'].value_counts().tolist()
decision_for_subset2 = subset2['Decision'].value_counts().tolist()
gini_subset1 = 1
gini_subset2 = 1
for j in range(0, len(decision_for_subset1)):
gini_subset1 = gini_subset1 - math.pow(
(decision_for_subset1[j] / subset1_rows), 2)
for j in range(0, len(decision_for_subset2)):
gini_subset2 = gini_subset2 - math.pow(
(decision_for_subset2[j] / subset2_rows), 2)
gini = (subset1_rows / total_instances) * gini_subset1 + (
subset2_rows / total_instances) * gini_subset2
subset_ginis.append(gini)
#----------------------------------
elif algorithm == 'Regression':
superset_stdev = df['Decision'].std(ddof=0)
subset1_stdev = subset1['Decision'].std(ddof=0)
subset2_stdev = subset2['Decision'].std(ddof=0)
threshold_weighted_stdev = (
subset1_rows / total_instances) * subset1_stdev + (
subset2_rows / total_instances) * subset2_stdev
threshold_reducted_stdev = superset_stdev - threshold_weighted_stdev
subset_red_stdevs.append(threshold_reducted_stdev)
#----------------------------------
if algorithm == "C4.5":
winner_one = subset_gainratios.index(max(subset_gainratios))
elif algorithm == "ID3": #actually, ID3 does not support for continuous features but we can still do it
winner_one = subset_gains.index(max(subset_gains))
elif algorithm == "CART":
winner_one = subset_ginis.index(min(subset_ginis))
elif algorithm == "Regression":
winner_one = subset_red_stdevs.index(max(subset_red_stdevs))
winner_threshold = unique_values[winner_one]
#print("theshold is ",winner_threshold," for ",column_name)
df[column_name] = np.where(df[column_name] <= winner_threshold,
"<=" + str(winner_threshold),
">" + str(winner_threshold))
return df
def fit(df, config):
target_label = df.columns[len(df.columns)-1]
if target_label != 'Decision':
print("Expected: Decision, Existing: ",target_label)
raise ValueError('Please confirm that name of the target column is "Decision" and it is put to the right in pandas data frame')
#------------------------
#handle NaN values
nan_values = []
for column in df.columns:
if df[column].dtypes != 'object':
min_value = df[column].min()
idx = df[df[column].isna()].index
nan_value = []
nan_value.append(column)
if idx.shape[0] > 0:
df.loc[idx, column] = min_value - 1
nan_value.append(min_value - 1)
min_value - 1
#print("NaN values are replaced to ", min_value - 1, " in column ", column)
else:
nan_value.append(None)
nan_values.append(nan_value)
#------------------------
#initialize params and folders
config = functions.initializeParams(config)
functions.initializeFolders()
#------------------------
algorithm = config['algorithm']
valid_algorithms = ['ID3', 'C4.5', 'CART', 'CHAID', 'Regression']
if algorithm not in valid_algorithms:
raise ValueError('Invalid algorithm passed. You passed ', algorithm," but valid algorithms are ",valid_algorithms)
#------------------------
enableRandomForest = config['enableRandomForest']
num_of_trees = config['num_of_trees']
enableMultitasking = config['enableMultitasking'] #no longer used. check to remove this variable.
enableGBM = config['enableGBM']
epochs = config['epochs']
learning_rate = config['learning_rate']
enableAdaboost = config['enableAdaboost']
enableParallelism = config['enableParallelism']
#this will handle basic decision stumps. parallelism is not required.
if enableRandomForest == True:
config['enableParallelism'] = False
enableParallelism = False
#------------------------
raw_df = df.copy()
num_of_rows = df.shape[0]; num_of_columns = df.shape[1]
if algorithm == 'Regression':
if df['Decision'].dtypes == 'object':
raise ValueError('Regression trees cannot be applied for nominal target values! You can either change the algorithm or data set.')
if df['Decision'].dtypes != 'object': #this must be regression tree even if it is not mentioned in algorithm
algorithm = 'Regression'
config['algorithm'] = 'Regression'
global_stdev = df['Decision'].std(ddof=0)
if enableGBM == True:
print("Gradient Boosting Machines...")
algorithm = 'Regression'
config['algorithm'] = 'Regression'
if enableAdaboost == True:
#enableParallelism = False
for j in range(0, num_of_columns):
column_name = df.columns[j]
if df[column_name].dtypes == 'object':
raise ValueError('Adaboost must be run on numeric data set for both features and target')
#-------------------------
print(algorithm," tree is going to be built...")
dataset_features = dict() #initialize a dictionary. this is going to be used to check features numeric or nominal. numeric features should be transformed to nominal values based on scales.
header = "def findDecision(obj): #"
num_of_columns = df.shape[1]-1
for i in range(0, num_of_columns):
column_name = df.columns[i]
dataset_features[column_name] = df[column_name].dtypes
header = header + "obj[" + str(i) +"]: "+column_name
if i != num_of_columns - 1:
header = header + ", "
header = header + "\n"
#------------------------
begin = time.time()
trees = []; alphas = []
if enableAdaboost == True:
trees, alphas = adaboost.apply(df, config, header, dataset_features)
elif enableGBM == True:
if df['Decision'].dtypes == 'object': #transform classification problem to regression
trees, alphas = gbm.classifier(df, config, header, dataset_features)
classification = True
else: #regression
trees = gbm.regressor(df, config, header, dataset_features)
classification = False
elif enableRandomForest == True:
trees = randomforest.apply(df, config, header, dataset_features)
else: #regular decision tree building
root = 1; file = "outputs/rules/rules.py"
functions.createFile(file, header)
if enableParallelism == True:
json_file = "outputs/rules/rules.json"
functions.createFile(json_file, "[\n")
trees = Training.buildDecisionTree(df,root,file, config, dataset_features
, 0, 0, 'root')
print("finished in ",time.time() - begin," seconds")
obj = {
"trees": trees,
"alphas": alphas,
"config": config,
"nan_values": nan_values
}
return obj
def fit(df, config={}, validation_df=None):
"""
Parameters:
df (pandas data frame): Training data frame. The target column must be named as 'Decision' and it has to be in the last column
config (dictionary):
config = {
'algorithm' (string): ID3, 'C4.5, CART, CHAID or Regression
'enableParallelism' (boolean): False
'enableGBM' (boolean): True,
'epochs' (int): 7,
'learning_rate' (int): 1,
'enableRandomForest' (boolean): True,
'num_of_trees' (int): 5,
'enableAdaboost' (boolean): True,
'num_of_weak_classifier' (int): 4
}
validation_df (pandas data frame): if nothing is passed to validation data frame, then the function validates built trees for training data frame
Returns:
chefboost model
"""
process_id = os.getpid()
base_df = df.copy()
target_label = df.columns[len(df.columns) - 1]
if target_label != 'Decision':
print("Expected: Decision, Existing: ", target_label)
raise ValueError(
'Please confirm that name of the target column is "Decision" and it is put to the right in pandas data frame'
)
#------------------------
#handle NaN values
nan_values = []
for column in df.columns:
if df[column].dtypes != 'object':
min_value = df[column].min()
idx = df[df[column].isna()].index
nan_value = []
nan_value.append(column)
if idx.shape[0] > 0:
df.loc[idx, column] = min_value - 1
nan_value.append(min_value - 1)
min_value - 1
#print("NaN values are replaced to ", min_value - 1, " in column ", column)
else:
nan_value.append(None)
nan_values.append(nan_value)
#------------------------
#initialize params and folders
config = functions.initializeParams(config)
functions.initializeFolders()
#------------------------
algorithm = config['algorithm']
valid_algorithms = ['ID3', 'C4.5', 'CART', 'CHAID', 'Regression']
if algorithm not in valid_algorithms:
raise ValueError('Invalid algorithm passed. You passed ', algorithm,
" but valid algorithms are ", valid_algorithms)
#------------------------
enableRandomForest = config['enableRandomForest']
num_of_trees = config['num_of_trees']
enableMultitasking = config[
'enableMultitasking'] #no longer used. check to remove this variable.
enableGBM = config['enableGBM']
epochs = config['epochs']
learning_rate = config['learning_rate']
enableAdaboost = config['enableAdaboost']
enableParallelism = config['enableParallelism']
#------------------------
if enableParallelism == True:
print("[INFO]: ", config["num_cores"],
"CPU cores will be allocated in parallel running")
#------------------------
raw_df = df.copy()
num_of_rows = df.shape[0]
num_of_columns = df.shape[1]
if algorithm == 'Regression':
if df['Decision'].dtypes == 'object':
raise ValueError(
'Regression trees cannot be applied for nominal target values! You can either change the algorithm or data set.'
)
if df['Decision'].dtypes != 'object': #this must be regression tree even if it is not mentioned in algorithm
if algorithm != 'Regression':
print(
"WARNING: You set the algorithm to ", algorithm,
" but the Decision column of your data set has non-object type."
)
print(
"That's why, the algorithm is set to Regression to handle the data set."
)
algorithm = 'Regression'
config['algorithm'] = 'Regression'
global_stdev = df['Decision'].std(ddof=0)
if enableGBM == True:
print("Gradient Boosting Machines...")
algorithm = 'Regression'
config['algorithm'] = 'Regression'
if enableAdaboost == True:
#enableParallelism = False
for j in range(0, num_of_columns):
column_name = df.columns[j]
if df[column_name].dtypes == 'object':
raise ValueError(
'Adaboost must be run on numeric data set for both features and target'
)
#-------------------------
print(algorithm, " tree is going to be built...")
dataset_features = dict(
) #initialize a dictionary. this is going to be used to check features numeric or nominal. numeric features should be transformed to nominal values based on scales.
header = "def findDecision(obj): #"
num_of_columns = df.shape[1] - 1
for i in range(0, num_of_columns):
column_name = df.columns[i]
dataset_features[column_name] = df[column_name].dtypes
header = header + "obj[" + str(i) + "]: " + column_name
if i != num_of_columns - 1:
header = header + ", "
header = header + "\n"
#------------------------
begin = time.time()
trees = []
alphas = []
if enableAdaboost == True:
trees, alphas = adaboost.apply(df,
config,
header,
dataset_features,
validation_df=validation_df)
elif enableGBM == True:
if df['Decision'].dtypes == 'object': #transform classification problem to regression
trees, alphas = gbm.classifier(df,
config,
header,
dataset_features,
validation_df=validation_df)
classification = True
else: #regression
trees = gbm.regressor(df,
config,
header,
dataset_features,
validation_df=validation_df)
classification = False
elif enableRandomForest == True:
trees = randomforest.apply(df,
config,
header,
dataset_features,
validation_df=validation_df,
process_id=process_id)
else: #regular decision tree building
root = 1
file = "outputs/rules/rules.py"
functions.createFile(file, header)
if enableParallelism == True:
json_file = "outputs/rules/rules.json"
functions.createFile(json_file, "[\n")
trees = Training.buildDecisionTree(df,
root=root,
file=file,
config=config,
dataset_features=dataset_features,
parent_level=0,
leaf_id=0,
parents='root',
validation_df=validation_df,
main_process_id=process_id)
print("-------------------------")
print("finished in ", time.time() - begin, " seconds")
obj = {
"trees": trees,
"alphas": alphas,
"config": config,
"nan_values": nan_values
}
#-----------------------------------------
#train set accuracy
df = base_df.copy()
evaluate(obj, df, task='train')
#validation set accuracy
if isinstance(validation_df, pd.DataFrame):
evaluate(obj, validation_df, task='validation')
#-----------------------------------------
return obj
def regressor(df, config, header, dataset_features):
models = []
algorithm = config['algorithm']
enableRandomForest = config['enableRandomForest']
num_of_trees = config['num_of_trees']
enableMultitasking = config['enableMultitasking']
enableGBM = config['enableGBM']
epochs = config['epochs']
learning_rate = config['learning_rate']
enableAdaboost = config['enableAdaboost']
#------------------------------
boosted_from = 0
boosted_to = 0
#------------------------------
base_df = df.copy()
#gbm will manipulate actuals. store its raw version.
target_values = base_df['Decision'].values
num_of_instances = target_values.shape[0]
root = 1
file = "outputs/rules/rules0.py"
functions.createFile(file, header)
Training.buildDecisionTree(df, root, file, config,
dataset_features) #generate rules0
df = base_df.copy()
base_df['Boosted_Prediction'] = 0
#------------------------------
pbar = tqdm(range(1, epochs + 1), desc='Boosting')
#for index in range(1,epochs+1):
#for index in tqdm(range(1,epochs+1), desc='Boosting'):
for index in pbar:
#print("epoch ",index," - ",end='')
loss = 0
#run data(i-1) and rules(i-1), save data1
#dynamic import
moduleName = "outputs/rules/rules%s" % (index - 1)
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname,
description) #rules0
models.append(myrules)
new_data_set = "outputs/data/data%s.csv" % (index)
f = open(new_data_set, "w")
#put header in the following file
columns = df.shape[1]
mae = 0
#----------------------------------------
df['Epoch'] = index
df['Prediction'] = df.apply(findPrediction, axis=1)
base_df['Boosted_Prediction'] += df['Prediction']
loss = (base_df['Boosted_Prediction'] -
base_df['Decision']).pow(2).sum()
if index == 1:
boosted_from = loss / num_of_instances
elif index == epochs:
boosted_to = loss / num_of_instances
df['Decision'] = int(learning_rate) * (df['Decision'] -
df['Prediction'])
df = df.drop(columns=['Epoch', 'Prediction'])
#---------------------------------
df.to_csv(new_data_set, index=False)
#data(i) created
#---------------------------------
file = "outputs/rules/rules" + str(index) + ".py"
functions.createFile(file, header)
current_df = df.copy()
Training.buildDecisionTree(df, root, file, config, dataset_features)
df = current_df.copy(
) #numeric features require this restoration to apply findDecision function
#rules(i) created
loss = loss / num_of_instances
#print("epoch ",index," - loss: ",loss)
#print("loss: ",loss)
pbar.set_description("Epoch %d. Loss: %d. Process: " % (index, loss))
#---------------------------------
print(num_of_instances, " instances are boosted from ", boosted_from,
" to ", boosted_to, " in ", epochs, " epochs")
return models
def classifier(df, config, header, dataset_features):
models = []
print("gradient boosting for classification")
epochs = config['epochs']
temp_df = df.copy()
original_dataset = df.copy()
worksheet = df.copy()
classes = df['Decision'].unique()
boosted_predictions = np.zeros([df.shape[0], len(classes)])
pbar = tqdm(range(0, epochs), desc='Boosting')
#store actual set, we will use this to calculate loss
actual_set = pd.DataFrame(np.zeros([df.shape[0], len(classes)]),
columns=classes)
for i in range(0, len(classes)):
current_class = classes[i]
actual_set[current_class] = np.where(df['Decision'] == current_class,
1, 0)
actual_set = actual_set.values #transform it to numpy array
#for epoch in range(0, epochs):
for epoch in pbar:
for i in range(0, len(classes)):
current_class = classes[i]
if epoch == 0:
temp_df['Decision'] = np.where(df['Decision'] == current_class,
1, 0)
worksheet['Y_' + str(i)] = temp_df['Decision']
else:
temp_df['Decision'] = worksheet['Y-P_' + str(i)]
predictions = []
#change data type for decision column
temp_df[['Decision']].astype('int64')
root = 1
file = "outputs/rules/rules-for-" + current_class + "-round-" + str(
epoch) + ".py"
functions.createFile(file, header)
Training.buildDecisionTree(temp_df, root, file, config,
dataset_features)
#decision rules created
#----------------------------
#dynamic import
moduleName = "outputs/rules/rules-for-" + current_class + "-round-" + str(
epoch)
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname,
description) #rules0
models.append(myrules)
num_of_columns = df.shape[1]
for row, instance in df.iterrows():
features = []
for j in range(0, num_of_columns - 1): #iterate on features
features.append(instance[j])
actual = temp_df.loc[row]['Decision']
prediction = myrules.findDecision(features)
predictions.append(prediction)
#----------------------------
if epoch == 0:
worksheet['F_' + str(i)] = 0
else:
worksheet['F_' + str(i)] = pd.Series(predictions).values
boosted_predictions[:, i] = boosted_predictions[:, i] + worksheet[
'F_' + str(i)].values.astype(np.float32)
#print(boosted_predictions[0:5,:])
worksheet['P_' + str(i)] = 0
#----------------------------
temp_df = df.copy() #restoration
for row, instance in worksheet.iterrows():
f_scores = []
for i in range(0, len(classes)):
f_scores.append(instance['F_' + str(i)])
probabilities = functions.softmax(f_scores)
for j in range(0, len(probabilities)):
instance['P_' + str(j)] = probabilities[j]
worksheet.loc[row] = instance
for i in range(0, len(classes)):
worksheet['Y-P_' +
str(i)] = worksheet['Y_' + str(i)] - worksheet['P_' +
str(i)]
prediction_set = np.zeros([df.shape[0], len(classes)])
for i in range(0, boosted_predictions.shape[0]):
predicted_index = np.argmax(boosted_predictions[i])
prediction_set[i][predicted_index] = 1
#----------------------------
#find loss for this epoch: prediction_set vs actual_set
classified = 0
for i in range(0, actual_set.shape[0]):
actual = np.argmax(actual_set[i])
prediction = np.argmax(prediction_set[i])
#print("actual: ",actual," - prediction: ",prediction)
if actual == prediction:
classified = classified + 1
accuracy = str(100 * classified / actual_set.shape[0]) + "%"
#----------------------------
#print(worksheet.head())
#print("round ",epoch+1)
pbar.set_description("Epoch %d. Accuracy: %s. Process: " %
(epoch + 1, accuracy))
return models, classes
def apply(df, config, header, dataset_features, validation_df = None, process_id = None):
models = []
num_of_trees = config['num_of_trees']
parallelism_on = config["enableParallelism"]
#TODO: is this logical for 48x2 cores?
#config["enableParallelism"] = False #run each tree in parallel but each branch in serial
#TODO: reconstruct for parallel run is problematic. you should reconstruct based on tree id.
input_params = []
pbar = tqdm(range(0, num_of_trees), desc='Bagging')
for i in pbar:
pbar.set_description("Sub decision tree %d is processing" % (i+1))
subset = df.sample(frac=1/num_of_trees)
root = 1
moduleName = "outputs/rules/rule_"+str(i)
file = moduleName+".py"
functions.createFile(file, header)
if parallelism_on: #parallel run
input_params.append((subset, root, file, config, dataset_features, 0, 0, 'root', i, None, process_id))
else: #serial run
Training.buildDecisionTree(subset,root, file, config, dataset_features, parent_level = 0, leaf_id = 0, parents = 'root', tree_id = i, main_process_id = process_id)
#-------------------------------
if parallelism_on:
num_cores = config["num_cores"]
#---------------------------------
if num_of_trees <= num_cores:
POOL_SIZE = num_of_trees
else:
POOL_SIZE = num_cores
with closing(multiprocessing.Pool(POOL_SIZE)) as pool:
funclist = []
for input_param in input_params:
f = pool.apply_async(buildDecisionTree, [*input_param])
funclist.append(f)
#all functions registered here
#results = []
for f in tqdm(funclist):
branch_results = f.get(timeout = 100000)
#results.append(branch_results)
pool.close()
pool.terminate()
#-------------------------------
#collect models for both serial and parallel here
for i in range(0, num_of_trees):
moduleName = "outputs/rules/rule_"+str(i)
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description)
models.append(myrules)
#-------------------------------
return models
def regressor(df, config, header, dataset_features, validation_df = None, process_id = None):
models = []
#we will update decisions in every epoch, this will be used to restore
base_actuals = df.Decision.values
algorithm = config['algorithm']
enableRandomForest = config['enableRandomForest']
num_of_trees = config['num_of_trees']
enableMultitasking = config['enableMultitasking']
enableGBM = config['enableGBM']
epochs = config['epochs']
learning_rate = config['learning_rate']
enableAdaboost = config['enableAdaboost']
#------------------------------
boosted_from = 0; boosted_to = 0
#------------------------------
base_df = df.copy()
#gbm will manipulate actuals. store its raw version.
target_values = base_df['Decision'].values
num_of_instances = target_values.shape[0]
root = 1
file = "outputs/rules/rules0.py"; json_file = "outputs/rules/rules0.json"
functions.createFile(file, header)
functions.createFile(json_file, "[\n")
Training.buildDecisionTree(df,root,file, config, dataset_features
, parent_level = 0, leaf_id = 0, parents = 'root') #generate rules0
#functions.storeRule(json_file," {}]")
df = base_df.copy()
base_df['Boosted_Prediction'] = 0
#------------------------------
best_epoch_idx = 0; best_epoch_loss = 1000000
pbar = tqdm(range(1, epochs+1), desc='Boosting')
#for index in range(1,epochs+1):
#for index in tqdm(range(1,epochs+1), desc='Boosting'):
for index in pbar:
#print("epoch ",index," - ",end='')
loss = 0
#run data(i-1) and rules(i-1), save data1
#dynamic import
moduleName = "outputs/rules/rules%s" % (index-1)
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description) #rules0
models.append(myrules)
new_data_set = "outputs/data/data%s.csv" % (index)
f = open(new_data_set, "w")
#put header in the following file
columns = df.shape[1]
mae = 0
#----------------------------------------
df['Epoch'] = index
df['Prediction'] = df.apply(findPrediction, axis=1)
base_df['Boosted_Prediction'] += df['Prediction']
loss = (base_df['Boosted_Prediction'] - base_df['Decision']).pow(2).sum()
current_loss = loss / num_of_instances #mse
if index == 1:
boosted_from = current_loss * 1
elif index == epochs:
boosted_to = current_loss * 1
if current_loss < best_epoch_loss:
best_epoch_loss = current_loss * 1
best_epoch_idx = index * 1
df['Decision'] = int(learning_rate)*(df['Decision'] - df['Prediction'])
df = df.drop(columns = ['Epoch', 'Prediction'])
#---------------------------------
df.to_csv(new_data_set, index=False)
#data(i) created
#---------------------------------
file = "outputs/rules/rules"+str(index)+".py"
json_file = "outputs/rules/rules"+str(index)+".json"
functions.createFile(file, header)
functions.createFile(json_file, "[\n")
current_df = df.copy()
Training.buildDecisionTree(df,root,file, config, dataset_features
, parent_level = 0, leaf_id = 0, parents = 'root', main_process_id = process_id)
#functions.storeRule(json_file," {}]")
df = current_df.copy() #numeric features require this restoration to apply findDecision function
#rules(i) created
loss = loss / num_of_instances
#print("epoch ",index," - loss: ",loss)
#print("loss: ",loss)
pbar.set_description("Epoch %d. Loss: %d. Process: " % (index, loss))
gc.collect()
#---------------------------------
print("The best epoch is ", best_epoch_idx," with ", best_epoch_loss," loss value")
models = models[0:best_epoch_idx]
config["epochs"] = best_epoch_idx
print("MSE of ",num_of_instances," instances are boosted from ",boosted_from," to ",best_epoch_loss," in ",epochs," epochs")
return models
def apply(df, config, header, dataset_features):
models = []
num_of_trees = config['num_of_trees']
pbar = tqdm(range(0, num_of_trees), desc='Bagging')
for i in pbar:
#for i in range(0, num_of_trees):
pbar.set_description("Sub decision tree %d is processing" % (i + 1))
subset = df.sample(frac=1 / num_of_trees)
root = 1
moduleName = "outputs/rules/rule_" + str(i)
file = moduleName + ".py"
json_file = moduleName + ".json"
functions.createFile(file, header)
functions.createFile(json_file, "[\n")
Training.buildDecisionTree(subset,
root,
file,
config,
dataset_features,
parent_level=0,
leaf_id=0,
parents='root')
functions.storeRule(json_file, "{}]")
#--------------------------------
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description)
models.append(myrules)
#-------------------------------
#check regression or classification
if df['Decision'].dtypes == 'object': problem_type = 'classification'
else: problem_type = 'regression'
actual_values = df['Decision'].values
num_of_features = df.shape[1] - 1 #discard Decision
number_of_instances = df.shape[0]
global_predictions = []
#if classification get the max number of prediction
if problem_type == 'classification':
for i in range(0, num_of_trees):
moduleName = "outputs/rules/rule_" + str(i)
fp, pathname, description = imp.find_module(moduleName)
myrules = imp.load_module(moduleName, fp, pathname, description)
predictions = []
for index, instance in df.iterrows():
params = []
for j in range(0, num_of_features):
params.append(instance[j])
#index row, i th column
prediction = myrules.findDecision(params)
predictions.append(prediction)
#print(i,"th tree prediction: ",prediction)
#print(predictions)
global_predictions.append(predictions)
#-------------------------------
classified = 0
for index in range(0, len(actual_values)):
actual = actual_values[index]
predictions = []
for i in range(0, num_of_trees):
prediction = global_predictions[i][index]
if prediction != None: #why None exists in some cases?
predictions.append(prediction)
predictions = np.array(predictions)
unique_values = np.unique(predictions)
if unique_values.shape[0] == 1:
prediction = unique_values[0]
else:
counts = []
for unique in unique_values:
count = 0
for j in predictions:
if unique == j:
count = count + 1
counts.append(count)
#print("unique: ",unique_values)
#print("counts: ",counts)
prediction = None
if len(counts) > 0:
max_index = np.argmax(np.array(counts))
prediction = unique_values[max_index]
#print(index,". actual: ",actual," - prediction: ", prediction)
if actual == prediction:
classified = classified + 1
print("Accuracy: ", 100 * classified / number_of_instances, "% on ",
number_of_instances, " instances")
return models