junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

minor export update

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2026-04-14 14:40:38 +01:00
parent 9f9cab35ef
commit 5b3385984f
1 changed files with 3 additions and 27 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
sfr/principal_pitch/2_export_data.py
View file

@ -230,7 +230,7 @@ for scenario_id in SCENARIOS:
# Get recs for this scenario
recommended_measures_df = recommendations_df[
recommendations_df["scenario_id"] == scenario_id
][["property_id", "measure_type", "estimated_cost", "default"]]
][["property_id", "measure_type", "estimated_cost", "default"]]
recommended_measures_df = recommended_measures_df[
recommended_measures_df["default"]
]
@ -238,7 +238,7 @@ for scenario_id in SCENARIOS:
post_install_sap = recommendations_df[
recommendations_df["scenario_id"] == scenario_id
][["property_id", "default", "sap_points"]]
][["property_id", "default", "sap_points"]]
post_install_sap = post_install_sap[post_install_sap["default"]]
# Sum up the sap points by property id
post_install_sap = (
@ -282,6 +282,7 @@ for scenario_id in SCENARIOS:
"windows",
"current_epc_rating",
"current_sap_points",
"original_sap_points",
"total_floor_area",
"number_of_rooms",
"lodgement_date",
@ -303,31 +304,6 @@ for scenario_id in SCENARIOS:
)
df["uprn"] = df["uprn"].astype(str)
relevant_plans = plans_df[plans_df["scenario_id"] == scenario_id]
df2 = df.merge(
relevant_plans[["property_id", "post_sap_points", "post_epc_rating"]],
how="left",
on="property_id",
suffixes=("", "_plan"),
)
print(df2["predicted_post_works_epc"].value_counts())
print(df2["post_epc_rating"].value_counts())
z = df2[
(df2["predicted_post_works_epc"] != "D")
& (df2["post_epc_rating"].astype(str) == "Epc.D")
]
df2["predicted_post_works_epc"].value_counts()
df2["post_epc_rating"].astype(str).value_counts()
df2[df2["total_retrofit_cost"] > 0].shape
getting_works = df[df["total_retrofit_cost"] > 0]
getting_works["predicted_post_works_epc"].value_counts()
df[df["predicted_post_works_sap"] == ""]
# Expected columns list
expected_columns = [
"suspended_floor_insulation",