import pandas as pd
import json
import re


def parse_balances(path_to_logs):
    list_of_balances_dicts = []
    count_of_decode_errors = 0

    with open(path_to_logs, 'r') as logs:
        rows = logs.readlines()
        for row in rows:
            if row.find('balance') != -1:
                try:
                    list_of_balances_dicts.append(json.loads(row[row.find('balance') + len('balance: '):]))
                except json.JSONDecodeError:
                    count_of_decode_errors += 1

    return (list_of_balances_dicts, count_of_decode_errors)


def create_balances_csv(path_to_logs, name='mm_balances.csv'):
    balances, errors_count = parse_balances(path_to_logs)
    print(f'balances rows = {len(balances)}; errors count = {errors_count}')

    df = pd.DataFrame(balances)
    df['update_time'] = pd.to_datetime(df['update_time'] * 1e6).dt.round('1s')
    df = df.drop_duplicates(subset=['asset', 'update_time']).sort_values('update_time')
    df.to_csv(name, index=False)

    return df