InfoLeaseExtract/NI_sum.py

import os
import pandas as pd
from datetime import datetime as dt, timedelta
import sys, getopt
import re
from pathlib import Path
import time
from pprint import pprint as prt
import numpy as np

contract_number_regex = "\d{3}-\d{7}-\d{3}"

def create_line_divider(breakage_list: list):
    """
    This allows for the creation of a custom data extractor
    Breakage list defines the split points that will be used for the line
    Example
    Given breakage_list [10, 20, 30]
    using slot_num 0 in the resulting extract_line_slot will yield
    characters 0 - 10 from the string. 
    Slot 1 would give characters 10 - 20
    """
    def extract_line_slot(slot_num : int, line_string: str, debug : bool = False):
        """
        Pulls data from a line/string using break points defined by the
        parent function.
        ONLY USE THIS FUNCTION THROUGH CREATION USING 'create_line_extractor'
        Will automatically convert numbers to floats
        """
        assert(slot_num < len(breakage_list)+1)
        low_range = 0 if slot_num == 0 else breakage_list[slot_num-1]
        high_range = len(line_string) if slot_num == len(breakage_list) else breakage_list[slot_num]
        data = line_string[low_range:high_range].strip().replace(",", "")
        try: data = float(data)
        except: pass
        if debug:
            print(f"Slot num: {slot_num} | Low: {low_range} | High: {high_range} | Data: {data}")
        return data
    return extract_line_slot


def net_invest_trial_balance(report: str, save_name: str):
    lines = report.splitlines()
    extracted_data_dict = {
        'CUSTOMER NAME' :  [],
        'CURR INT RCVB' :  [],
        'UNEARNED BLENDED' :  [],
        'BLEND NET INV' :  [],
        'LEASE NUMBER' :  [],
        'GROSS CONTRACT' :  [],
        'CURR RENT RCVB' :  [],
        'UNEARN FIN' :  [],
        'END DEPOSIT' :  [],
        'SEC DEPOSIT' :  [],
        'LEASE PYMTS' :  [],
        'TOTAL' :  [],
        'CONTRACT STAT' :  [],
        'PAYMENTS RCVD' :  [],
        'REM RENT RCVB' :  [],
        'UNEARN RESID' :  [],
        'PROV LOSS' :  [],
        'NET RESERVE' :  [],
        'UNEARN INC' :  [],
        'BAL REMAINING' :  [],
        'RESIDUAL' :  [],
        'UNPAID INT' :  [],
        'NET INV' :  [],
        'UNEARNED IDC' :  [],
        "LESSOR": []
    }
    lessors = []
    columns = list(extracted_data_dict.keys())
    line0 = list(zip(columns[0:4], [0,3,4,5]))
    line1 = list(zip(columns[4:12], [i for i in range(0,8)]))
    line2 = list(zip(columns[12:19], [i for i in range(0,7)]))
    line3 = list(zip(columns[19:-1], [i for i in range(1,6)]))

    for l in [line0,line1,line2,line3]:
        print(f"\n{l}")

    data_extractor = create_line_divider([18,32,50,66,84,100,117])
    for line in enumerate(lines):
        slot1 = data_extractor(0,line[1],False)
        if type(slot1) != str : continue
        if re.search(contract_number_regex, slot1) != None:
                data_section = lines[line[0]-1:line[0]+3]

                if data_section[0].find(".") == -1:
                    data_section[0] = lines[line[0]-2]
                for ds in enumerate(data_section):
                    if ds[1].find(".") == -1:
                        if ds[0] < len(data_section) -1:
                            for i in range(ds[0], len(data_section)-1):
                                #print(f"{i}: { data_section[i]}")
                                data_section[i] = data_section[i+1]
                                #print(f"DELTA| {i}: { data_section[i]}")
                            data_section[3] = lines[line[0]+3]
                        else:
                            data_section[3] = lines[line[0]+3]
                        
                        
                # [print(f"\n{d[0]}: {d[1]}") for d in enumerate(data_section)]
                # print('\n')
                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[0], False)) for c in line0]
                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[1], False)) for c in line1]
                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[2], False)) for c in line2]
                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[3], False)) for c in line3]
                extracted_data_dict["LESSOR"].append(extracted_data_dict["LEASE NUMBER"][-1][0:3])
                if extracted_data_dict["LESSOR"][-1] not in lessors:
                    print(extracted_data_dict["LESSOR"][-1])
                    lessors.append(extracted_data_dict["LESSOR"][-1])      
                    print(lessors)
    for c in columns:
        print(f"C: {c} | {len(extracted_data_dict[c])}")
    print(lessors)
    dataframe = pd.DataFrame(extracted_data_dict)

    summary_series = []
    for lessor in lessors:
        reduced_df = dataframe.loc[dataframe["LESSOR"] == lessor]
        del reduced_df["CUSTOMER NAME"]
        del reduced_df["LEASE NUMBER"]
        del reduced_df["CONTRACT STAT"]
        reduced_df = reduced_df.replace("", np.NaN)
        reduced_df = reduced_df.replace("REVOLV", np.NaN)
        reduced_df = reduced_df.replace("ING ACCOUNT", np.NaN)
        summation = reduced_df.sum(skipna=True, axis=0)
        summation["LESSOR"] = lessor
        summation["CONTRACT COUNT"] = len(reduced_df.index)
        summary_series.append(summation)
    summary_df = pd.concat(summary_series, axis=1).transpose().set_index("LESSOR")
    prt(summary_df)
    with pd.ExcelWriter(save_name) as writer:  
        dataframe.to_excel(writer, index=False, sheet_name="data")
        pd.DataFrame(summary_df).to_excel(writer, index=True, sheet_name="Summary")
    return dataframe












with open("/config/workspace/LEAF/IL Extract SRC/2022.05.20 Net Investment", errors="replace") as rep_file:
    report = rep_file.read()

prt(net_invest_trial_balance(report, "520_NI_TEST.xlsx"))