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

completed ha25 analysis

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2023-12-28 14:08:40 +00:00
parent 776bca7c24
commit a40c1670cb
1 changed files with 53 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

53
etl/eligibility/ha_15_32/ha25_app.py
View file

@ -450,6 +450,46 @@ def get_epc_data(data, cleaned, cleaning_data, created_at):
return results_df, scoring_data, nodata
def analyse_results(results_df, data, eco4_prospects_survey_list):
analysis_data = data[["row_id", "survey_key", "warmfront_identified"]].merge(
results_df, how="left", on="row_id"
)
warmfront_identified = analysis_data[analysis_data["warmfront_identified"]]
# Of the ECO jobs, what proportion to we get right
success_rate = (warmfront_identified["eco4_eligible"] | warmfront_identified["gbis_eligible"]).sum() / \
warmfront_identified.shape[
0]
# No gbis for this
# gbis_success_rate = warmfront_identified_gbis["gbis_eligible"].sum() / warmfront_identified_gbis.shape[0]
# Additional identified
additional_identified_eco = analysis_data[
(analysis_data["eco4_eligible"] == True) & (analysis_data["warmfront_identified"] == False)
]
additional_identified_eco["eligibility_classification"].value_counts()
additional_identified_gbis = analysis_data[
(analysis_data["gbis_eligible"] == True) & (analysis_data["eco4_eligible"] == False) & (
analysis_data["warmfront_identified"] == False
)
].shape[0]
# Future
additional_identified_eco_future = analysis_data[
(analysis_data["eco4_eligible_future"] == True) & (analysis_data["warmfront_identified"] == False)
].shape[0]
additional_identified_gbis_future = analysis_data[
(analysis_data["gbis_eligible_future"] == True) & (analysis_data["eco4_eligible_future"] == False) & (
analysis_data["warmfront_identified"] == False
)
].shape[0]
def app():
data, eco4_prospects_survey_list = load_data()
@ -466,3 +506,16 @@ def app():
)
created_at = datetime.now().isoformat()
results_df, scoring_data, nodata = get_epc_data(data, cleaned, cleaning_data, created_at)
# Pickle the outputs
# import pickle
# with open("ha25.pickle", "wb") as f:
# pickle.dump(
# {
# "results_df": results_df,
# "scoring_data": scoring_data,
# "nodata": nodata
# },
# f
# )