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