mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-06-30 13:10:47 +00:00
tweaking
This commit is contained in:
Khalim Conn-Kowlessar
parent
67f97feb18
commit
efba61c6ac
1 changed files with 83 additions and 38 deletions
|
|
@ -1719,6 +1719,72 @@ def propsed_wave_3_sample():
|
|||
# Tier 2: We have a property in the same archetype that was surveyed and is below EPC D
|
||||
#
|
||||
|
||||
def match_property_to_surveyed(property, survey_results_with_original_features):
|
||||
surveyed = survey_results_with_original_features[
|
||||
(
|
||||
survey_results_with_original_features["Property Type"] ==
|
||||
property["Property Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Wall Type"] ==
|
||||
property["Wall Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Roof Type"] ==
|
||||
property["Roof Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Heating"] ==
|
||||
property["Heating"]
|
||||
)
|
||||
].copy()
|
||||
|
||||
if not surveyed.empty:
|
||||
return surveyed
|
||||
|
||||
surveyed = survey_results_with_original_features[
|
||||
(
|
||||
survey_results_with_original_features["Property Type"] ==
|
||||
property["Property Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Wall Type"] ==
|
||||
property["Wall Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Roof Type"].str.split(":").str[0] ==
|
||||
property["Roof Type"].split(":")[0]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Heating"] ==
|
||||
property["Heating"]
|
||||
)
|
||||
].copy()
|
||||
|
||||
if not surveyed.empty:
|
||||
return surveyed
|
||||
|
||||
surveyed = survey_results_with_original_features[
|
||||
(
|
||||
survey_results_with_original_features["Property Type"] ==
|
||||
property["Property Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Wall Type"] ==
|
||||
property["Wall Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Roof Type"].str.split(":").str[0] ==
|
||||
property["Roof Type"].split(":")[0]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Heating"].str.split(":").str[0] ==
|
||||
property["Heating"].split(":")[0]
|
||||
)
|
||||
].copy()
|
||||
|
||||
return surveyed
|
||||
|
||||
results = []
|
||||
for region in tqdm(unique_postal_regions):
|
||||
# Take all of the properties in that region
|
||||
|
|
@ -1757,6 +1823,7 @@ def propsed_wave_3_sample():
|
|||
][["Archetype ID", "Current EPC Band"]].drop_duplicates()
|
||||
|
||||
if region_surveyed["Archetype ID"].duplicated().sum():
|
||||
|
||||
region_surveyed = []
|
||||
for arch_id in archetypes:
|
||||
for _, property in region_assets[region_assets["Archetype ID"] == arch_id].iterrows():
|
||||
|
|
@ -1765,6 +1832,12 @@ def propsed_wave_3_sample():
|
|||
].copy()
|
||||
if archetype_data.empty:
|
||||
continue
|
||||
if archetype_data.shape[0] > 1:
|
||||
# Look for an exact match, or as close as possible
|
||||
archetype_data_filtered = match_property_to_surveyed(property, archetype_data)
|
||||
if not archetype_data_filtered.empty:
|
||||
archetype_data = archetype_data_filtered
|
||||
|
||||
archetype_data["distance_meters"] = haversine(
|
||||
lat1=property.latitude, lon1=property.longitude,
|
||||
lat2=archetype_data["latitude"].values, lon2=archetype_data["longitude"].values
|
||||
|
|
@ -1899,28 +1972,15 @@ def propsed_wave_3_sample():
|
|||
# This means that this archetype was never surveyed and so we need to find a sufficiently similar property
|
||||
final_missed_matches = []
|
||||
for a_id in missed_addressids:
|
||||
|
||||
match_type = "3 - compared to similar properties"
|
||||
|
||||
property = asset_list[asset_list["Address ID"] == a_id].squeeze()
|
||||
|
||||
surveyed = survey_results_with_original_features[
|
||||
(
|
||||
survey_results_with_original_features["Property Type"] ==
|
||||
property["Property Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Wall Type"] ==
|
||||
property["Wall Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Roof Type"] ==
|
||||
property["Roof Type"]
|
||||
) &
|
||||
(
|
||||
survey_results_with_original_features["Heating"] ==
|
||||
property["Heating"]
|
||||
)
|
||||
].copy()
|
||||
surveyed = match_property_to_surveyed(property, survey_results_with_original_features)
|
||||
|
||||
if surveyed.empty:
|
||||
match_type = "3 - compared to similar properties, relaxed"
|
||||
# In this case, we do one additional check where we filter on everything the same apart from heating,
|
||||
# where we do a slightly more rough match
|
||||
surveyed = survey_results_with_original_features[
|
||||
|
|
@ -2026,14 +2086,12 @@ def propsed_wave_3_sample():
|
|||
expected_epc = sap_to_epc(expected_sap)
|
||||
|
||||
if expected_epc in ["C", "B", "A"]:
|
||||
tier = "5 - EPC C or above"
|
||||
else:
|
||||
tier = "3 - similar property, weighted on distance"
|
||||
match_type = "5 - EPC C or above"
|
||||
|
||||
final_missed_matches.append(
|
||||
{
|
||||
"Address ID": a_id,
|
||||
"Confidence Tier": tier,
|
||||
"Confidence Tier": match_type,
|
||||
"Current EPC Band": expected_epc
|
||||
}
|
||||
)
|
||||
|
|
@ -2197,22 +2255,9 @@ def propsed_wave_3_sample():
|
|||
# '2 - same archetype',
|
||||
# '3 - similar property, weighted on distance'
|
||||
|
||||
gain_columns = [
|
||||
'1 - Archetype surveyed',
|
||||
'1 - property was surveyed',
|
||||
'2 - same archetype',
|
||||
'3 - similar property, weighted on distance'
|
||||
]
|
||||
#
|
||||
# Loss is the sum of these columns:
|
||||
# '4 - no similar property, needs survey to confirm',
|
||||
# '5 - EPC C or above', '5 - property was surveyed'
|
||||
gain_columns = sorted([x for x in results["Confidence Tier"].unique() if "1 - " in x or "2 - " in x or "3 - " in x])
|
||||
loss_columns = sorted([x for x in results["Confidence Tier"].unique() if "4 - " in x or "5 - " in x])
|
||||
|
||||
loss_columns = [
|
||||
'4 - no similar property, needs survey to confirm',
|
||||
'5 - EPC C or above',
|
||||
'5 - property was surveyed'
|
||||
]
|
||||
geographic_summary["Gain"] = geographic_summary[gain_columns].sum(axis=1)
|
||||
geographic_summary["Loss"] = geographic_summary[loss_columns].sum(axis=1)
|
||||
|
||||
|
|
@ -2283,7 +2328,7 @@ def propsed_wave_3_sample():
|
|||
|
||||
# Remaining loss allowed
|
||||
# remaining_loss_constraint = 230 - region_totals["Loss"]
|
||||
remaining_loss_constraint = 250
|
||||
remaining_loss_constraint = 220
|
||||
postcode_selected_rows, _ = optimise(
|
||||
gain=postcode_summary_unselected_regions["Gain"].values,
|
||||
loss=postcode_summary_unselected_regions["Loss"].values,
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue