utils.py

# select and finalize the best model in the active run
best_model = automl() #returns the best model based on CV score

# select and finalize the best model based on 'F1' on hold_out set
best_model_holdout = automl(optimize = 'F1', use_holdout = True)

# save model
save_model(model, 'c:/path-to-directory/model-name')

# load model
model = load_model('c:/path-to-directory/model-name')

# retrieve score grid as pandas df
dt = create_model('dt')
dt_results = pull() #this will store dt score grid as pandas df

# get global environment variable
X_train = get_config('X_train') #returns X_train dataset after preprocessing
seed = get_config('seed') returns seed from global environment

# set global environment variable
set_seed(seed, 999) #seed set to 999 in global environment of active run

# get experiment logs as csv file
logs = get_logs() #for active run by default

# get system logs for audit
system_logs = get_system_logs() #read logs.log file from active directory