mkdir(args.output_dir)
chdir(args.output_dir)
print('Reading sample ' + file)
sample = Sample(make="",
model="",
year="",
sample_number=0, # NOTE we only process one file
sample_path=file,
kfold_n=args.kfold_n)
try:
# TODO This comment came with the original code I'm wondering if it means that the Validation step later in the process is not working
# Cross validation parameters for finding an optimal tokenization inversion distance threshold -- NOT WORKING?
print("\nData import and Pre-Processing for " + sample.output_vehicle_dir)
id_dict, j1979_dict, pid_dict = sample.pre_process()
if j1979_dict:
sample.plot_j1979(j1979_dict, vehicle_number=args.vehicle_name)
# LEXICAL ANALYSIS #
print("\n\t##### BEGINNING LEXICAL ANALYSIS OF " + sample.output_vehicle_dir + " #####")
sample.tokenize_dictionary(id_dict)
signal_dict = sample.generate_signals(id_dict, bool(j1979_dict))
sample.plot_arb_ids(id_dict, signal_dict, vehicle_number=args.vehicle_name)
# LEXICAL ANALYSIS #
print("\n\t##### BEGINNING SEMANTIC ANALYSIS OF " + sample.output_vehicle_dir + " #####")
corr_matrix, combined_df = sample.generate_correlation_matrix(signal_dict)
if j1979_dict:
signal_dict, j1979_correlation = sample.j1979_labeling(j1979_dict, signal_dict, combined_df)
cluster_dict, linkage_matrix = sample.cluster_signals(corr_matrix)
sample.plot_clusters(cluster_dict, signal_dict, bool(j1979_dict), vehicle_number=args.vehicle_name)
sample.plot_dendrogram(linkage_matrix, vehicle_number=args.vehicle_name)
except KeyboardInterrupt:
print("Keyboard interupt pressed program quit")
