41 lines
1.6 KiB
Python
41 lines
1.6 KiB
Python
from io import StringIO
|
|
|
|
import polars as pl
|
|
|
|
import data
|
|
from data import etl_cache
|
|
|
|
d = data.load()
|
|
|
|
def property_capacities_weekdays(id: int, scrapeDate: str):
|
|
|
|
file = f"etl_property_capacities_weekdays_{id}.obj"
|
|
obj = etl_cache.openObj(file)
|
|
if obj:
|
|
return obj
|
|
|
|
extractions = d.extractions_propId_scrapeDate(id, scrapeDate).pl()
|
|
weekdays = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
|
|
df_calendar = pl.DataFrame()
|
|
numWeeks = 0
|
|
|
|
for row in extractions.rows(named=True):
|
|
scrapeDate = row['created_at']
|
|
df_calendar = pl.read_json(StringIO(row['calendar']))
|
|
columnTitles = df_calendar.columns
|
|
df_calendar = df_calendar.transpose()
|
|
df_calendar = df_calendar.with_columns(pl.Series(name="dates", values=columnTitles))
|
|
df_calendar = df_calendar.with_columns((pl.col("dates").str.to_date()))
|
|
numWeeks = round((df_calendar.get_column("dates").max() - df_calendar.get_column("dates").min()).days / 7, 0)
|
|
df_calendar = df_calendar.with_columns(pl.col("dates").dt.weekday().alias("weekday_num"))
|
|
df_calendar = df_calendar.with_columns(pl.col("dates").dt.strftime("%A").alias("weekday"))
|
|
df_calendar = df_calendar.drop("dates")
|
|
|
|
df_calendar = df_calendar.group_by(["weekday", "weekday_num"]).agg(pl.col("column_0").sum())
|
|
df_calendar = df_calendar.with_columns((pl.col("column_0") / numWeeks / 2 * 100).alias("column_0"))
|
|
df_calendar = df_calendar.sort('weekday_num')
|
|
df_calendar = df_calendar.drop('weekday_num')
|
|
|
|
result = {"scraping-date": scrapeDate, "weekdays": df_calendar['weekday'].to_list(), 'capacities': df_calendar['column_0'].to_list()}
|
|
etl_cache.saveObj(file, result)
|
|
return result |