junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-07-12 13:29:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

building out aggregation

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-01-02 18:23:52 +00:00
parent 748dc14271
commit 2156f6b076
2 changed files with 20 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
backend/SearchEpc.py
View file

@ -437,6 +437,7 @@ class SearchEpc:
if not epc_data.empty: if not epc_data.empty:
# Further processing of the EPC data # Further processing of the EPC data
epc_data['lodgement-datetime'] = pd.to_datetime(epc_data['lodgement-datetime'])
epc_data = epc_data.sort_values("lodgement-datetime", ascending=False).groupby("uprn").head(1) epc_data = epc_data.sort_values("lodgement-datetime", ascending=False).groupby("uprn").head(1)
epc_data["house_number"] = epc_data["address"].apply(lambda add1: self.get_house_number(add1)) epc_data["house_number"] = epc_data["address"].apply(lambda add1: self.get_house_number(add1))
epc_data["numeric_house_number"] = epc_data["house_number"].apply( epc_data["numeric_house_number"] = epc_data["house_number"].apply(
@ -505,7 +506,6 @@ class SearchEpc:
built_form=built_form, built_form=built_form,
property_type=property_type property_type=property_type
) )
epc_data['lodgement-datetime'] = pd.to_datetime(epc_data['lodgement-datetime'])
# For each attribute, we need to determine the datatype and use an appropriate method # For each attribute, we need to determine the datatype and use an appropriate method
# to estimate. # to estimate.

19
etl/testing_data/estimate_epc.py
View file

@ -113,3 +113,22 @@ def app():
"tenure": epc["tenure"], "tenure": epc["tenure"],
} }
) )
# Get aggregate performance figures
results_df = pd.DataFrame(results)
avg_numeric_succes = results_df["numeric_success"].median()
avg_categorical_sucess = results_df["categorical_success"].median()
# Group by tenure
by_tenure = results_df.groupby("tenure").agg(
{"numeric_success": "median", "categorical_success": "median", "uprn": "count"}
)
# By property type - we also want to see how many properties we have for each property type
by_property_type = results_df.groupby("property_type").agg(
{"numeric_success": "median", "categorical_success": "median", "uprn": "count"}
)
# By property_type & built form
by_property_type_built_form = results_df.groupby(["property_type", "built_form"]).agg(
{"numeric_success": "median", "categorical_success": "median", "uprn": "count"}
)