Alex Galarce
5b88185611
[daip2-9] basic code refactor - unreferenced functions and reorganize existing files * remove unreferenced functions in ac_funcs.py * move compare_output.py * move file_counting.py * move merge_issue_regex.py * remove unreferenced functions in postprocessing_funcs.py * clean up preprocessing_funcs.py * move prerun.py * move table_analysis.py and textract_template.py to scripts * remove unreferenced functions in table_funcs.py * moved tin_pull.py to scripts * move detect_complex.py and remove merge_funcs.py * clean up dict operations and utils, mark functions in utils for destinations * removed errant import Approved-by: Katon Minhas
99 lines
2.9 KiB
Python
99 lines
2.9 KiB
Python
import concurrent.futures
|
|
import traceback
|
|
import re
|
|
import os
|
|
import pandas as pd
|
|
|
|
import utils
|
|
import config
|
|
import preprocessing_funcs
|
|
|
|
COMPLEX_LIST = []
|
|
|
|
|
|
def count_reimbursements(page_text: str) -> int:
|
|
"""Count number of reimbursement items found on a page text, through use of a
|
|
regex that catches either '$' or '%'.
|
|
|
|
Args:
|
|
page_text (str): Input page text, as a string
|
|
|
|
Returns:
|
|
int: Number of reimbursement items
|
|
"""
|
|
pattern = r"[%$]"
|
|
matches = re.findall(pattern, page_text)
|
|
return len(matches)
|
|
|
|
|
|
def detect_complex(filename, contract_text):
|
|
print(f"Processing {filename}")
|
|
contract_text = preprocessing_funcs.clean_newlines(contract_text)
|
|
contract_text = preprocessing_funcs.clean_law_symbols(contract_text)
|
|
text_dict = preprocessing_funcs.split_text(contract_text)
|
|
rate_dict = {}
|
|
table_dict = {}
|
|
for page_num, page_text in text_dict.items():
|
|
rate_dict[page_num] = count_reimbursements(page_text)
|
|
table_dict[page_num] = "-------Table Start--------" in page_text
|
|
|
|
page_count, consecutive_page_count, consecutive_rate_count = 0, 0, 0
|
|
|
|
for page_num in table_dict.keys():
|
|
if table_dict[page_num] and rate_dict[page_num] > 0:
|
|
consecutive_rate_count += rate_dict[page_num]
|
|
consecutive_page_count += 1
|
|
else:
|
|
if consecutive_rate_count >= config.RATE_THRESHOLD:
|
|
page_count += consecutive_page_count
|
|
consecutive_page_count, consecutive_rate_count = 0, 0
|
|
|
|
COMPLEX_LIST.append(
|
|
{"Filename": filename, "COMPLEX_FLAG": page_count >= config.TABLE_THRESHOLD}
|
|
)
|
|
|
|
|
|
def process_item(contract):
|
|
data = s3_client.get_object(Bucket=config.BUCKET, Key=contract)
|
|
contents = data["Body"].read()
|
|
contract_text = contents.decode("utf-8")
|
|
|
|
detect_complex(contract, contract_text)
|
|
|
|
|
|
s3_client = config.S3_CLIENT
|
|
|
|
file_list = []
|
|
paginator = s3_client.get_paginator("list_objects_v2")
|
|
pages = paginator.paginate(Bucket=config.BUCKET, Prefix=config.PREFIX)
|
|
for page in pages:
|
|
for obj in page["Contents"]:
|
|
if not obj["Key"].endswith("/"):
|
|
file_list.append(obj["Key"])
|
|
|
|
contract_list = sorted(file_list)
|
|
files = {}
|
|
|
|
with concurrent.futures.ThreadPoolExecutor(
|
|
max_workers=config.COMPLEX_MAX_WORKERS
|
|
) as executor:
|
|
# Process each item individually
|
|
futures = [executor.submit(process_item, contract) for contract in contract_list]
|
|
|
|
# Wait for all futures to complete
|
|
for future in concurrent.futures.as_completed(futures):
|
|
# Retrieve any exceptions raised by the thread
|
|
try:
|
|
future.result()
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|
|
|
|
complex_df = pd.DataFrame(COMPLEX_LIST)
|
|
# complex_df.to_csv(os.path.join(config.COMPLEX_OUTPUT_PATH, config.COMPLEX_OUTPUT_FILENAME))
|
|
|
|
complex_df.to_csv(
|
|
os.path.join(
|
|
config.COMPLEX_OUTPUT_PATH, "TX_priority_tin_complex_categorization.csv"
|
|
)
|
|
)
|