Katon Minhas
bb279b45fd
Cnc fl main * prov type moved * comment out invalid prov2 bc it's overly restrictive * Update prompt template to ensure N/A rather than blanks * Update AC multi-prompt template. Update prompts to ensure all keys are present and N/As are filled * Update AC postprocessing * Update clean_tin() to add N/A for values other than 10 digits * update tin postprocessing * Update npi postprocessing * Add 'Filename:' to the start of all filenames * Update group TIN/NPI postprocessing * Update parent agreement code * fix health plan state mapping * Update B postprocessing * Updated indicators, re-ordering * Update postprocessing - all columns included and reordered * Ensure Pages is included in AC-only output * Remove excess print statements * remove example_test to pass pipeline * Fix parent agreement code for AC * Updated postprocessing for NPI/TIN other * Update prompts for N explicitely on AC prompt-based indicators * Updated main and utils for more intuitive filtering * Updated file_counting to match new main process * update test * Add example_test Approved-by: Michael McGuinness
111 lines
2.8 KiB
Python
111 lines
2.8 KiB
Python
import pandas as pd
|
|
import re
|
|
import os
|
|
import numpy as np
|
|
|
|
import postprocessing_funcs
|
|
import valid
|
|
import prompts
|
|
import claude_funcs
|
|
import config
|
|
import utils
|
|
|
|
|
|
def b_postprocess(filename, df, pages):
|
|
|
|
if df.shape[0] > 0:
|
|
# Metadata fields
|
|
df.drop('Filename', axis=1, inplace=True)
|
|
|
|
df["Contract Name"] = 'Filename: ' + filename
|
|
df["Parent Agreement Code"] = postprocessing_funcs.get_parent_agreement_code(
|
|
filename
|
|
)
|
|
df["Pages"] = pages
|
|
|
|
# Add Single Code, Multiple Rate
|
|
df = postprocessing_funcs.add_scmr(df)
|
|
|
|
# Filter Add Ons
|
|
df = postprocessing_funcs.filter_add_ons(df)
|
|
|
|
# Clean MSR
|
|
df = postprocessing_funcs.clean_msr_lesser(df)
|
|
|
|
# Clean Default
|
|
df = postprocessing_funcs.clean_default_term(df)
|
|
|
|
# Clean Prov 2
|
|
df = postprocessing_funcs.clean_prov_2(df)
|
|
|
|
# Clean Lesser Of Rate
|
|
df = postprocessing_funcs.clean_lesser_rate(df)
|
|
|
|
# Clean LOB
|
|
df = postprocessing_funcs.clean_lob(df, filename)
|
|
|
|
# Rename and reorder
|
|
df.rename(columns=valid.B_MAPPING, inplace=True)
|
|
|
|
column_order = [col for col in valid.B_MAPPING.values() if col in df.columns]
|
|
final_df = df[column_order]
|
|
|
|
return final_df
|
|
else:
|
|
return df
|
|
|
|
def ac_postprocess(df, filename, pages):
|
|
|
|
if df.shape[0] > 0:
|
|
|
|
df["Contract Name"] = 'Filename: ' + filename
|
|
|
|
df["Pages"] = pages
|
|
|
|
df["Parent Agreement Code"] = postprocessing_funcs.get_parent_agreement_code(
|
|
filename
|
|
)
|
|
|
|
df = df.fillna("")
|
|
|
|
df = postprocessing_funcs.clean_term_clause(df)
|
|
|
|
df = postprocessing_funcs.clean_auto_renewal_ind(df)
|
|
|
|
df = postprocessing_funcs.get_tin_from_filename(df)
|
|
|
|
df = postprocessing_funcs.clean_tin(df)
|
|
|
|
df = postprocessing_funcs.clean_npi(df)
|
|
|
|
df = postprocessing_funcs.clean_network_access_fees(df)
|
|
|
|
df = postprocessing_funcs.clean_health_plan_state(df)
|
|
|
|
df = postprocessing_funcs.clean_notice_provider_name_and_address(df)
|
|
|
|
df = postprocessing_funcs.clean_policies_and_procedures(df)
|
|
|
|
df = postprocessing_funcs.clean_tin_npi_other(df)
|
|
|
|
df = df.apply(lambda x: x.map(postprocessing_funcs.replace_null_terms))
|
|
|
|
df = df.apply(lambda x: x.map(postprocessing_funcs.replace_quotes))
|
|
|
|
# Derive Indicators
|
|
df = df.apply(postprocessing_funcs.derive_indicators, axis=1)
|
|
|
|
# Rename and Reorder
|
|
df = df.rename(columns=valid.AC_MAPPING)
|
|
column_order = [col for col in valid.ABC_COLUMNS if col in df.columns] + [
|
|
col for col in df.columns if col not in valid.ABC_COLUMNS
|
|
]
|
|
|
|
final_df = df[column_order]
|
|
|
|
return final_df
|
|
else:
|
|
return df
|
|
|
|
|