77 lines
2.4 KiB
Python
77 lines
2.4 KiB
Python
import asyncio
|
|
import random
|
|
from datetime import date, timedelta
|
|
|
|
import polars as pl
|
|
from tqdm import tqdm
|
|
|
|
from .config import DESTINATIONS, MAX_CONCURRENT, MAX_POSTCODES, OUTPUT_DIR
|
|
from .results import results_to_dataframe, save_results
|
|
from .tfl_client import fetch_journey_times
|
|
|
|
|
|
def main():
|
|
destination = DESTINATIONS["bank"]
|
|
|
|
# Calculate next Monday at 8am
|
|
today = date.today()
|
|
days_until_monday = (7 - today.weekday()) % 7 or 7
|
|
journey_date = today + timedelta(days=days_until_monday)
|
|
journey_time = "0845"
|
|
|
|
print(f"Destination: {destination.name}")
|
|
print(
|
|
f"Journey: {journey_date.strftime('%A %Y-%m-%d')} "
|
|
f"at {journey_time[:2]}:{journey_time[2:]}"
|
|
)
|
|
|
|
postcodes_df = pl.read_parquet(OUTPUT_DIR / "postcodes_h3.parquet")
|
|
print(f"Loaded {postcodes_df.height:,} postcodes")
|
|
|
|
postcode_data = list(
|
|
zip(
|
|
postcodes_df["postcode"].to_list(),
|
|
postcodes_df["lat"].to_list(),
|
|
postcodes_df["long"].to_list(),
|
|
)
|
|
)
|
|
|
|
if MAX_POSTCODES is not None and len(postcode_data) > MAX_POSTCODES:
|
|
postcode_data = random.sample(postcode_data, MAX_POSTCODES)
|
|
print(f"Randomly sampled {MAX_POSTCODES} postcodes")
|
|
|
|
with tqdm(total=len(postcode_data), desc="Fetching journeys") as pbar:
|
|
results = asyncio.run(
|
|
fetch_journey_times(
|
|
postcode_data,
|
|
destination,
|
|
journey_date.strftime("%Y%m%d"),
|
|
journey_time,
|
|
MAX_CONCURRENT,
|
|
progress_callback=lambda _: pbar.update(1),
|
|
)
|
|
)
|
|
|
|
results_df = results_to_dataframe(results)
|
|
|
|
postcodes_processed = [pc for pc, _, _ in postcode_data]
|
|
coords_df = postcodes_df.filter(
|
|
pl.col("postcode").is_in(postcodes_processed)
|
|
).select(["postcode", "lat", "long"])
|
|
results_df = coords_df.join(results_df, on="postcode", how="left")
|
|
|
|
results_df = results_df.with_columns(
|
|
pl.lit(destination.name).alias("destination"),
|
|
pl.lit(journey_date.strftime("%Y-%m-%d")).alias("journey_date"),
|
|
pl.lit(f"{journey_time[:2]}:{journey_time[2:]}").alias("journey_time"),
|
|
)
|
|
|
|
successful = results_df.filter(pl.col("cycling").is_not_null()).height
|
|
print(f"Completed: {successful}/{len(results)} successful")
|
|
|
|
parquet_path = save_results(results_df, destination.name)
|
|
print(f"Saved to {parquet_path}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|