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

added manual match

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2025-01-29 20:55:36 +00:00
parent 7dd6478172
commit 0331d82f6a
1 changed files with 14 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
etl/customers/stonewater/Wave 3 Preparation.py
View file

@ -3267,15 +3267,19 @@ def revised_model():
columns={"Post Code": "Postcode"}
)
ccs_coordination = ccs_coordination[~pd.isnull(ccs_coordination["Postcode"])]
ccs_coordination = ccs_coordination[ccs_coordination["Retrofit Assessment"] != "Outstanding"]
from fuzzywuzzy import fuzz
ccs_manual_filters = {}
ccs_manual_filters = {
"35 Kittiwake Close": "Wave 2.1 Surveys/11. CCS Dorset/Kittiwake Close 35"
}
ccs_matching_lookup = []
for _, home in tqdm(ccs_coordination.iterrows(), total=len(ccs_coordination)):
# Handle the case that has the wrong postcode in the asset data
if home["Name"] in ccs_manual_filters:
filtered = retrofit_assessment_data[
retrofit_assessment_data["survey_folder"] == manual_filters[home["Name"]]
retrofit_assessment_data["survey_folder"] == ccs_manual_filters[home["Name"]]
].copy()
else:
filtered = retrofit_assessment_data[
@ -3297,11 +3301,15 @@ def revised_model():
)
)
if to_filter.sum() == 0:
to_filter = filtered["Address"].str.replace(" ,", "").str.split(",").str[0:2].str.join("") == home[
"Name"]
to_filter = (
filtered["Address"].str.replace(" ,", "").str.split(",").str[0:2].str.join("").str.lower() ==
home["Name"].lower()
)
if to_filter.sum() == 0:
to_filter = filtered["Address"].str.replace(" ,", "").str.split(",").str[0:1].str.join("") == home[
"Name"]
to_filter = (
filtered["Address"].str.replace(" ,", "").str.split(",").str[0:1].str.join("").str.lower() ==
home["Name"].lower()
)
if to_filter.sum() == 0:
# Do a fuzzy match on the name
# Find the best filter