Katon Minhas
45 lines
1.1 KiB
Python
45 lines
1.1 KiB
Python
import pandas as pd
|
|
import re
|
|
import json
|
|
import csv
|
|
from io import StringIO
|
|
import config
|
|
import ast
|
|
import os
|
|
|
|
import utils
|
|
import postprocess
|
|
import postprocessingfuncs
|
|
import preprocess
|
|
import table_funcs
|
|
import prompts
|
|
import prompt_funcs
|
|
import claude_funcs
|
|
|
|
|
|
# all_dfs = []
|
|
# for file in os.listdir('output'):
|
|
# if 'combined_results_post_processed.csv' in os.listdir(os.path.join('output', file)):
|
|
# try:
|
|
# df = pd.read_csv(f'output/{file}/combined_results_post_processed.csv')
|
|
# all_dfs.append(df)
|
|
# except:
|
|
# continue
|
|
|
|
# final_df = pd.concat(all_dfs, ignore_index=True)
|
|
# final_df.to_excel('output_consolidated/test_20240610_batch1.xlsx')
|
|
|
|
|
|
input_dict = utils.read_input()
|
|
|
|
(filename, contract_text) = list(input_dict.items())[0]
|
|
|
|
contract_text = preprocess.clean_newlines(contract_text)
|
|
text_dict = preprocess.split_text(contract_text)
|
|
text_dict = table_funcs.align_and_format_tables(text_dict)
|
|
text_dict = preprocess.highlight_rates(text_dict)
|
|
|
|
bu_results = prompt_funcs.run_bottom_up_primary({'5' : text_dict['5']}, 4000) # Returns list of dictionaries
|
|
print(bu_results)
|
|
|