def station_set_training(station_name: str, enabled: bool):
station = Station.get_or_none(Station.name == station_name)
if station is None:
raise HTTPException(404, 'station not found')
else:
log.info(f'Setting training enabled: {enabled} for {station}')
station.is_training = enabled
station.save()
if not enabled:
model = train_model(station)
station.trained_model = serialize_model(model)
station.save()
return {'status': 'ok'}
#solcast.loc[solcast.Azimuth<=-1] = solcast.loc[solcast.Azimuth<=-1] + 360
est_dhi = solcast.Ghi - solcast.Dni * np.cos(solcast.Zenith)
model, batch, validation_data, callbacks, x_test_scaled, y_test_scaled, y_test, y_scaler = ml.model_generation(
solcast,
target_output,
batch_size=256,
sequence_length=24,
training_len=0.75,
validation_len=0.225)
model = ml.train_model(model,
batch,
validation_data,
x_test_scaled,
y_test_scaled,
callbacks,
epoch_size=25,
epoch_steps=100)
ml.save_model(model, 'model.h5')
output = ml.load_models('model.h5')
import importlib
importlib.reload(ml)
start_idx = 0
length = 500
target_names = target_output
y_pred, y_true, x = ml.plot_comparison(x_test_scaled,
y_test,
def test_truth_table(self):
build_train_set()
train_model(prob_thresh=prob_thresh)
match_query = """
SELECT
company_projects.*,
web_certificates.url_key
FROM
web_certificates
LEFT JOIN
attempted_matches
ON
web_certificates.cert_id = attempted_matches.cert_id
LEFT JOIN
company_projects
ON
attempted_matches.project_id = company_projects.project_id
LEFT JOIN
base_urls
ON
base_urls.source = web_certificates.source
WHERE
company_projects.closed=1
AND
attempted_matches.ground_truth=1
AND
attempted_matches.multi_phase=0
AND
attempted_matches.validate=0
"""
corr_web_certs_query = """
SELECT
web_certificates.*
FROM
web_certificates
LEFT JOIN
attempted_matches
ON
web_certificates.cert_id = attempted_matches.cert_id
LEFT JOIN
company_projects
ON
attempted_matches.project_id = company_projects.project_id
LEFT JOIN
base_urls
ON
base_urls.source = web_certificates.source
WHERE
company_projects.closed=1
AND
attempted_matches.ground_truth=1
AND
attempted_matches.multi_phase=0
AND
attempted_matches.validate=0
"""
with create_connection() as conn:
test_company_projects = pd.read_sql(match_query, conn)
test_web_df = pd.read_sql(corr_web_certs_query, conn)
test_web_df = wrangle(test_web_df)
results = match(
company_projects=test_company_projects,
df_web=test_web_df,
test=True,
prob_thresh=prob_thresh,
version="new",
)
# confrim 100% recall with below assert
qty_actual_matches = int(len(results)**0.5)
qty_found_matches = results[results.pred_match == 1].title.nunique()
self.assertTrue(
qty_found_matches == qty_actual_matches,
msg=
f"qty_found_matches({qty_found_matches}) not equal qty_actual_matches({qty_actual_matches})",
)
# make sure not more than 25% false positives with below assert
false_positives = len(
results[results.pred_match == 1]) - qty_found_matches
self.assertTrue(
false_positives <= round(qty_actual_matches * 0.25, 1),
msg=
f"found too many false positives ({false_positives}) out of total test projects ({qty_actual_matches})",
)
# test single sample
sample_company = pd.DataFrame(
{
"cert_id": "99999",
"project_id": "99999",
"job_number": "2387",
"city": "Ottawa",
"address": "2562 Del Zotto Ave., Ottawa, Ontario",
"title": "DWS Building Expansion",
"owner": "Douglas Stalker",
"contractor": "GNC",
"engineer": "Goodkey",
"address_lat": 45.312234,
"address_lng": -75.623789,
"receiver_emails_dump": "{'alex': '*****@*****.**'}",
"closed": "0",
},
index=range(1),
)
sample_web = pd.DataFrame(
{
"cert_id": "99998",
"pub_date": "2019-03-06",
"city": "Ottawa-Carleton",
"address": "2562 Del Zotto Avenue, Gloucester, Ontario",
"title":
"Construct a 1 storey storage addition to a 2 storey office/industrial building",
"owner": "Doug Stalker, DWS Roofing",
"contractor": "GNC Constructors Inc.",
"engineer": None,
"address_lat": 45.312234,
"address_lng": -75.623789,
"url_key": "B0046A36-3F1C-11E9-9A87-005056AA6F02",
"source": "dcn",
},
index=range(1),
)
is_match, prob = match(
company_projects=sample_company,
df_web=sample_web,
test=True,
version="new").iloc[0][["pred_match", "pred_prob"]]
self.assertTrue(
is_match,
msg=
f"Project #{sample_company.job_number} did not match successfully. Match probability returned was {prob}.",
)
# test same sample but using db retreival
results = match(
company_projects=sample_company,
since="2019-03-05",
until="2019-03-07",
test=True,
version="new",
)
prob_from_db_cert = (
results[results.contractor == "gnc"].iloc[0].pred_prob
) #'gnc' is what is returned from the wrangling funcs
self.assertTrue(round(prob, 2) == round(prob_from_db_cert, 2))
# make sure validation runs
validate_model(prob_thresh=prob_thresh, test=True)