async def test_process_and_persist_v_one_option_set(self, prod_df_v, bind):
# select an entity12 from the available dataframe that is likely to have
# more than one, but not too many, associated wells (for test speed)
entity12 = (prod_df_v.groupby(
"entity12").count().iloc[:, 0].sort_values().index[2])
prod_df_v = prod_df_v.loc[prod_df_v.entity12 == entity12].copy(
deep=True)
prodset_v = prod_df_v.prodstats.to_prodset()
pexec = ProdExecutor(HoleDirection.V)
opts = calc.prodstat_option_matrix(ProdStatRange.FIRST,
months=[6],
include_zeroes=False)
ps = await pexec.process(prodset_v,
prodstat_opts=opts,
ratio_opts=opts)
await pexec.persist(ps)
expected = ps.stats.shape[0]
actual = await Model.agg.count()
assert expected == actual
assert ps.header.shape[0] == prod_df_v.reset_index().api14.unique(
).shape[0]
assert ps.monthly.shape[0] == prod_df_v.shape[0]
assert ps.stats.shape[0] > 0
async def test_process_and_persist_h_one_option_set(self, prod_df_h, bind):
prodset_h = prod_df_h.prodstats.to_prodset()
pexec = ProdExecutor(HoleDirection.H)
opts = calc.prodstat_option_matrix(ProdStatRange.FIRST,
months=[6],
include_zeroes=False)
ps = await pexec.process(prodset_h,
prodstat_opts=opts,
ratio_opts=opts)
await pexec.persist(ps)
expected = ps.stats.shape[0]
actual = await Model.agg.count()
assert expected == actual
assert ps.header.shape[0] == prod_df_h.reset_index().api14.unique(
).shape[0]
assert ps.monthly.shape[0] == prod_df_h.shape[0]
assert ps.stats.shape[0] > 0
async def test_arun_v_tiny_batch(self, prod_v, bind):
prod_v = prod_v[:5]
api14s = [x["api14"] for x in prod_v]
dispatch = MockAsyncDispatch({"data": prod_v})
opts = calc.prodstat_option_matrix(ProdStatRange.FIRST,
months=[6],
include_zeroes=False)
pexec = ProdExecutor(
HoleDirection.V,
download_kwargs={"dispatch": dispatch},
process_kwargs={
"prodstat_opts": opts,
"ratio_opts": opts
},
)
ct, ps = await pexec.arun(api14s=api14s)
actual = await ProdHeader.agg.count()
assert len(api14s) == actual
if __name__ == "__main__":
import loggers
import calc.prod # noqa
from db import db # noqa
from collector import IHSClient
# import itertools
# import multiprocessing as mp
loggers.config(level=10, formatter="funcname")
ranges = ProdStatRange.PEAKNORM
months = [3, 6]
include_zeroes = [True, False]
calc.prodstat_option_matrix(ranges=ranges,
months=months,
include_zeroes=include_zeroes)
# def get_id_sets(area: str) -> Tuple[List[str], List[str]]:
# loop = asyncio.get_event_loop()
# coroh = IHSClient.get_ids_by_area(path=IHSPath.well_h_ids, area=area)
# corov = IHSClient.get_ids_by_area(path=IHSPath.well_v_ids, area=area)
# return loop.run_until_complete(asyncio.gather(coroh, corov))
# area = "tx-upton"
# sample_size = 25
# api14h, api14v = get_id_sets(area)
# h_sample: List[str] = random.choices(api14h, k=sample_size)
# v_sample: List[str] = random.choices(api14v, k=sample_size)