diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/reto_parsing.py | 46 |
1 files changed, 33 insertions, 13 deletions
diff --git a/python/reto_parsing.py b/python/reto_parsing.py index a5ed60d9..52ba5604 100644 --- a/python/reto_parsing.py +++ b/python/reto_parsing.py @@ -4,15 +4,16 @@ from pathlib import Path from dateutil.parser import parse import datetime import re +from math import isnan csv_data = {} reto_dir = Path("/home/serenitas/flint/retozip") for zip_f in reto_dir.iterdir(): if zip_f.name.endswith(".zip"): zip_file = ZipFile(zip_f) - fname = zip_file.namelist()[0] + fname = zip_file.namelist()[2] df = pd.read_csv(zip_file.open(fname)) - breakpoint() + gross_exposure = pd.read_csv(zip_file.open(zip_file.namelist()[0])) try: if len(df.columns) == 3: date = parse(df.columns[2]).date() @@ -28,18 +29,37 @@ for zip_f in reto_dir.iterdir(): year = int(re.search("\d{4}", zip_f.name)[0]) date = datetime.date(year, date.month, date.day) try: - returns = df.set_index([df.columns[0]]).to_dict()[df.columns[1]][ - "Gross Return" - ] + gross_exposure = gross_exposure.set_index([gross_exposure.columns[0]]).loc[ + "Gross Exposure" + ][0] + if "x" in str(gross_exposure): + gross_exposure = float(gross_exposure.removesuffix("x")) * 100 + try: + gross_exposure = float(str(gross_exposure).removesuffix("%")) + except: + breakpoint() + pass except KeyError: - returns = df.set_index([df.columns[0]]).to_dict()[df.columns[1]][ - "ross Return" - ] - except: - breakpoint() - print(zip_f.name) - csv_data[date] = returns + df = gross_exposure.set_index([gross_exposure.columns[0]]).to_dict() + dictionary_values = df[[*df][0]] + for k, v in dictionary_values.items(): + if "ross H" in str(k): + gross_exposure = v + if "x" in str(gross_exposure): + gross_exposure = float(gross_exposure.removesuffix("x")) * 100 + try: + gross_exposure = float(str(gross_exposure).removesuffix("%")) + except: + breakpoint() + pass + if isnan(gross_exposure): + print(zip_f) + pass + # except: + # breakpoint() + # print(zip_f.name) + csv_data[date] = gross_exposure pd.DataFrame.from_dict(csv_data, orient="index").to_csv( - "/home/serenitas/flint/test_returns.csv" + "/home/serenitas/flint/gross_exposure_returns.csv" ) print("hi") |