vprint( verbose, "Using output_dir: " + output_dir)
# Move old results and create a new output directory
if not(running_on_codalab) and save_previous_results:
data_io.mvdir(output_dir, output_dir+'_'+the_date)
data_io.mkdir(output_dir)
#### INVENTORY DATA (and sort dataset names alphabetically)
datanames = data_io.inventory_data(input_dir)
# Overwrite the "natural" order
#### DEBUG MODE: Show dataset list and STOP
if debug_mode>=3:
data_io.show_io(input_dir, output_dir)
print('\n****** Sample code version ' + str(version) + ' ******\n\n' + '========== DATASETS ==========\n')
data_io.write_list(datanames)
datanames = [] # Do not proceed with learning and testing
# ==================== @RESULT SUBMISSION (KEEP THIS) =====================
# Always keep this code to enable result submission of pre-calculated results
# deposited in the res/ subdirectory.
if len(datanames)>0:
vprint( verbose, "************************************************************************")
vprint( verbose, "****** Attempting to copy files (from res/) for RESULT submission ******")
vprint( verbose, "************************************************************************")
datanames = data_io.copy_results(datanames, res_dir, output_dir, verbose) # DO NOT REMOVE!
if not datanames:
vprint( verbose, "[+] Results copied to output directory, no model trained/tested")
else:
vprint( verbose, "======== Some missing results on current datasets!")
vprint( verbose, "======== Proceeding to train/test:\n")
default_input_dir="C:\\Users\\vmkocheg\\Documents\\MLContest\\Phase2\\input"
default_output_dir="C:\\Users\\vmkocheg\\Documents\\MLContest\\Phase2\\output"
if len(argv)==1: # Use the default input and output directories if no arguments are provided
input_dir = default_input_dir
output_dir = default_output_dir
else:
input_dir = argv[1]
output_dir = os.path.abspath(argv[2]);
#### INVENTORY DATA (and sort dataset names alphabetically)
datanames = data_io.inventory_data(input_dir)
#### DEBUG MODE: Show dataset list and STOP
if debug_mode>=3:
data_io.show_io(input_dir, output_dir)
data_io.write_list(datanames)
datanames = [] # Do not proceed with learning and testing
for basename in datanames: # Loop over datasets
if basename not in ["robert"]:
continue
vprint( verbose, "************************************************")
vprint( verbose, "******** Processing dataset " + basename.capitalize() + " ********")
vprint( verbose, "************************************************")
# ======== Learning on a time budget:
# Keep track of time not to exceed your time budget. Time spent to inventory data neglected.
start = time.time()