def test_after_midnight():
sample_date = pendulum.datetime(2019, 1, 29, 1, tz="America/Los_Angeles")
schedule_path = "../sample_data/schedule/804_lametro-rail/2019-01-28.csv"
assert (
get_appropriate_timetable(
sample_date, f"../sample_data/schedule/{line}_{agency}"
)["path"]
== schedule_path
)
def test_arbitrary_schedule():
sample_date = pendulum.datetime(2019, 1, 31, 12, tz="America/Los_Angeles")
schedule_path = "../sample_data/schedule/804_lametro-rail/2019-01-31.csv"
assert (
get_appropriate_timetable(
sample_date, f"../sample_data/schedule/{line}_{agency}"
)["path"]
== schedule_path
)
assert (
get_date_if_exists_otherwise_previous(
sample_date, f"../sample_data/schedule/{line}_{agency}"
)
== sample_date
)
)
from helpers.timing import get_appropriate_timetable
from analyzer.summary import statistic_summary
agency = "lametro-rail"
datetime = pendulum.now("America/Los_Angeles")
master_summary = {}
count = 0
for line in range(801, 807):
count = count + 1
print("loop: {}".format(count))
schedule_base_path = f"data/schedule/{line}_{agency}"
schedule_meta = get_appropriate_timetable(datetime, schedule_base_path)
# print("\nschedule_meta path: \n" + schedule_meta["path"])
# for i in schedule_meta:
# print(schedule_meta[i])
vehicles_base_path = f"data/vehicle_tracking/processed/{line}_{agency}"
vehicles_meta = get_appropriate_timetable(datetime, vehicles_base_path)
# print("\nvehicles_meta path: \n" + vehicles_meta["path"])
# for i in vehicles_meta:
# print(vehicles_meta[i])
# if the schdeule data and vehicle dates don't match, run "query_vehicles.sh" or
# process_vehicles.sh to update files before proceeding
if schedule_meta["date"] == vehicles_meta["date"]:
continue
vehicles = pd.read_csv(vehicles_meta["path"],
from helpers.upload import upload
import pendulum
from helpers.timing import get_appropriate_timetable
now = pendulum.now("America/Los_Angeles")
agency = "lametro-rail"
for line in range(801, 807):
vehicles_base_path = f"data/vehicle_tracking/processed/{line}_{agency}"
vehicles_meta = get_appropriate_timetable(now, vehicles_base_path)
date = vehicles_meta["date"]
positions_path = vehicles_meta["path"]
upload(positions_path, positions_path)
summary_path = f"data/summaries/{date}.json"
upload(summary_path, summary_path)
import pendulum
import pandas as pd
from analyzer.process_vehicles import (
preprocess,
determine_vehicle_paths,
get_track,
process_raw_vehicles,
)
from helpers.timing import get_appropriate_timetable
agency = "lametro-rail"
datetime = pendulum.now("America/Los_Angeles")
print(f"The current time is {datetime.to_iso8601_string()}")
for line in range(801, 807):
schedule = get_appropriate_timetable(datetime,
f"data/schedule/{line}_{agency}")
print(schedule["path"])
print("start: ", schedule["start"])
print("end: ", schedule["end"])
raw_vehicle_files = determine_vehicle_paths(
f"data/vehicle_tracking/raw/{line}_{agency}", schedule["start"],
schedule["end"])
array = [preprocess(path) for path in raw_vehicle_files]
print("Preprocessing complete")
cleaned = [row for row in array if row is not None]
print("Cleaning complete")
df = pd.concat(cleaned)
track = get_track(line, f"data/line_info/{line}")
print("got track")
processed = process_raw_vehicles(df, track)
print("Processing complete (big job)")