def generate_signals(self,
id_dictionary: dict,
postpone_pickle: bool = False):
signal_dict = generate_signals(
a_timer=a_timer,
arb_id_dict=id_dictionary,
signal_pickle_filename=pickle_signal_filename,
normalize_strategy=signal_normalize_strategy,
force=force_signal_generation)
# postpone_pickle is simply a check whether J1979 data was present in the sample. If it was present, then wait
# to save out the signal_dictionary until correlated Signals are labeled by sample.j1979_labeling().
# if dump_to_pickle and not postpone_pickle and not path.isfile(pickle_signal_filename):
# print("\nDumping signal dictionary for " + self.output_vehicle_dir + " to " + pickle_signal_filename)
# dump(signal_dict, open(pickle_signal_filename, "wb"))
# print("\tComplete...")
return signal_dict
id_dictionary, j1979_dictionary = pre_processor.generate_arb_id_dictionary(
a_timer, tang_normalize_strategy, time_conversion, freq_analysis_accuracy,
freq_synchronous_threshold, force_pre_processing)
if j1979_dictionary:
plot_j1979(a_timer, j1979_dictionary, force_j1979_plotting)
# LEXICAL ANALYSIS #
print("\n\t\t\t##### BEGINNING LEXICAL ANALYSIS #####")
tokenize_dictionary(a_timer,
id_dictionary,
force_lexical_analysis,
include_padding=tokenize_padding,
merge=True,
max_distance=tokenization_bit_distance)
signal_dictionary = generate_signals(a_timer, id_dictionary,
pickle_signal_filename,
signal_normalize_strategy,
force_lexical_analysis)
plot_signals_by_arb_id(a_timer, id_dictionary, signal_dictionary,
force_arb_id_plotting)
# SEMANTIC ANALYSIS #
print("\n\t\t\t##### BEGINNING SEMANTIC ANALYSIS #####")
subset_df = subset_selection(a_timer,
signal_dictionary,
pickle_subset_filename,
force_semantic_analysis,
subset_size=subset_selection_size)
corr_matrix_subset = subset_correlation(subset_df, csv_correlation_filename,
force_semantic_analysis)
cluster_dict = greedy_signal_clustering(
corr_matrix_subset,