41 lines
1.5 KiB
Python
41 lines
1.5 KiB
Python
import asyncio
|
|
from pathlib import Path
|
|
from data_access import Listing
|
|
import pandas as pd
|
|
|
|
|
|
async def export_to_csv(
|
|
listings: list[Listing],
|
|
output_file: Path,
|
|
columns: list[str],
|
|
) -> None:
|
|
ds = await asyncio.gather(*[listing.dict_nicely() for listing in listings])
|
|
df = pd.DataFrame(ds)
|
|
# read decisions on file
|
|
decisions_path = "data/decisions.json"
|
|
decisions = pd.read_json(decisions_path)
|
|
df.loc[:, "decision"] = df.identifier.apply(lambda x: decisions.get(x))
|
|
|
|
# remove all entries where we didnt calculate transit time (probably due to a too far distance)
|
|
# df2 = df[df.travel_time_fastest.notna()]
|
|
df2 = df
|
|
|
|
# drop columns
|
|
# dropcolumns = ['distance_per_transit', 'duration_static', 'distance']
|
|
# s1 = df2['travel_time_fastest'].apply(pd.Series).drop(dropcolumns, axis=1)
|
|
# s1 = df2
|
|
|
|
# fill in gap values for service charge and lease left. This is for excel so we can use filters better there
|
|
df2.loc[:, "service_charge"] = df2.service_charge.fillna(-1)
|
|
df2.loc[:, "lease_left"] = df2.lease_left.fillna(-1)
|
|
df2.loc[:, "sqm_ocr"] = df2.sqm_ocr.fillna(-1)
|
|
|
|
df3 = df2
|
|
# df3 = pd.concat([df2.drop(['travel_time_fastest', 'travel_time_second'], axis=1), s1], axis=1)
|
|
# df3.loc[:, 'duration'] = (df3.loc[:, ['duration']].min(axis=1) / 60).round()
|
|
df3.shape
|
|
df4 = df3
|
|
|
|
df5 = df4[columns]
|
|
df6 = df5.sort_values(by=["price_per_sqm"], ascending=True)
|
|
df6.to_csv(str(output_file), index=False)
|