def compute_subgraph_metrics(dataset, n_jobs, limit):
print("--- Subgraph Metrics ---")
print(f"Dataset: {dataset}")
print(f"Num Jobs: {n_jobs}")
print(f"Limit: {limit}")
print("---------------------------")
# paths
conf = Config(dataset)
output_fpath = f"{conf.data_root}/subgraph_metrics.csv"
json_fpaths = json_paths_iter(conf.conversations_no_embs_jsons_dir,
limit=limit)
# compute metrics
print("Computing metrics ...")
if n_jobs == 1:
metrics = [compute_metrics(json_fpath) \
for json_fpath in tqdm(json_fpaths)]
else:
parallel = Parallel(n_jobs=n_jobs, verbose=10)
metrics = parallel(
delayed(compute_metrics)(json_fpath) \
for json_fpath in json_fpaths
)
print("Output:", len(metrics))
# output to csv
print("Outputting tree metrics to CSV ...")
write_dicts_to_csv(metrics, output_fpath)
print("Done!")
def compute_user_metrics(dataset, n_jobs=1, limit=None):
print("--- User Metrics ---")
print(f"Dataset: {dataset}")
print(f"Num Jobs: {n_jobs}")
print(f"Limit: {limit}")
print("----------------------------")
toxicity_threshold = 0.531
conf = Config(dataset)
json_fpaths = json_paths_iter(conf.conversations_no_embs_jsons_dir,
limit=limit)
# all_user_conv_stats = [
# compute_user_conversation_stats(json_fpath, toxicity_threshold) \
# for json_fpath in json_fpaths]
parallel = Parallel(n_jobs=n_jobs, verbose=10)
all_user_conv_stats = parallel(
delayed(compute_user_conversation_stats)(
json_fpath,
toxicity_threshold
) \
for json_fpath in json_fpaths
)
print("Aggregating user metrics ...")
user_stats = agg_user_stats(all_user_conv_stats)
user_stats_csv = [{"user_id": u_id, **u_stats} \
for u_id, u_stats in user_stats.items()]
# out_json_fpath = f"{conf.data_root}/user_metrics.json.gz"
# json.dump(user_stats, gzip.open(out_json_fpath, "wt"), indent=2)
out_csv_fpath = f"{conf.data_root}/user_metrics.csv"
write_dicts_to_csv(user_stats_csv, out_csv_fpath)
print("Done!")
def compute_toxicity_metrics(dataset, n_jobs=1, limit=None):
print("--- Toxicity Metrics ---")
print(f"Dataset: {dataset}")
print(f"Num Jobs: {n_jobs}")
print(f"Limit: {limit}")
print("----------------------------")
# paths
conf = Config(dataset)
output_fpath = f"{conf.data_root}/toxicity.csv"
# iterator
json_fpaths = json_paths_iter(
conf.conversations_no_embs_jsons_dir,
limit=limit
)
# compute metrics
print("Computing metrics ...")
if n_jobs == 1:
metrics = [toxicity_metrics(json_fpath) \
for json_fpath in tqdm(json_fpaths)]
else:
parallel = Parallel(n_jobs=n_jobs, verbose=10)
metrics = parallel(
delayed(toxicity_metrics)(json_fpath) \
for json_fpath in json_fpaths
)
print("Metrics computed:", len(metrics))
print("Outputting metrics to CSV ...")
write_dicts_to_csv(metrics, output_fpath)
print("Done!")