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

Added more logic for matching

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2025-01-29 20:43:56 +00:00
parent 231069f4e3
commit 7dd6478172
1 changed files with 8 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
etl/customers/stonewater/Wave 3 Preparation.py
View file

@ -3273,7 +3273,7 @@ def revised_model():
ccs_matching_lookup = [] ccs_matching_lookup = []
for _, home in tqdm(ccs_coordination.iterrows(), total=len(ccs_coordination)): for _, home in tqdm(ccs_coordination.iterrows(), total=len(ccs_coordination)):
# Handle the case that has the wrong postcode in the asset data # Handle the case that has the wrong postcode in the asset data
if home["Name"] in manual_filters: if home["Name"] in ccs_manual_filters:
filtered = retrofit_assessment_data[ filtered = retrofit_assessment_data[
retrofit_assessment_data["survey_folder"] == manual_filters[home["Name"]] retrofit_assessment_data["survey_folder"] == manual_filters[home["Name"]]
].copy() ].copy()
@ -3297,13 +3297,16 @@ def revised_model():
) )
) )
if to_filter.sum() == 0: if to_filter.sum() == 0:
to_filter = filtered["Address"].str.split(",").str[0:2].str.join("") == home["Name"] to_filter = filtered["Address"].str.replace(" ,", "").str.split(",").str[0:2].str.join("") == home[
"Name"]
if to_filter.sum() == 0:
to_filter = filtered["Address"].str.replace(" ,", "").str.split(",").str[0:1].str.join("") == home[
"Name"]
if to_filter.sum() == 0: if to_filter.sum() == 0:
# Do a fuzzy match on the name # Do a fuzzy match on the name
# Find the best filter # Find the best filter
to_filter = filtered["Address"].str.split(",").str[0:2].str.join("").apply( to_filter = filtered["Address"].str.replace(" ,", "").str.split(",").str[0:2].str.join("").apply(
lambda x: fuzz.partial_ratio(home["Name"], x) > 9 lambda x: fuzz.partial_ratio(home["Name"], x) > 93
) )
if to_filter.sum() == 0: if to_filter.sum() == 0: