junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-30 13:10:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

still working on merge

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2023-12-24 23:09:25 +00:00
parent 3f7ad82b7a
commit e21057ca61
1 changed files with 10 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
etl/eligibility/ha_15_32/ha16_app.py
View file

@ -100,12 +100,14 @@ def load_data():
survey_list["Street / Block Name"] survey_list["Street / Block Name"]
) )
# Replace " rd " with "road" # Replace " rd " with "road"
survey_list['Street / Block Name'] = df['Street / Block Name'].str.replace(r'\brd\b', 'road', regex=True) survey_list['Street / Block Name'] = survey_list['Street / Block Name'].str.replace(r'\brd\b', 'road', regex=True)
# Replace " , " with ", " # Replace " , " with ", "
survey_list['Street / Block Name'] = survey_list['Street / Block Name'].str.replace( survey_list['Street / Block Name'] = survey_list['Street / Block Name'].str.replace(
" , ", ', ', " , ", ', ',
) )
# Fix "{place} ,{place}" with "{place}, {place}"
survey_list['Street / Block Name'] = survey_list['Street / Block Name'].str.replace(r'\s*,\s*', ', ', regex=True)
# Strip whitespace # Strip whitespace
survey_list['Street / Block Name'] = survey_list['Street / Block Name'].str.strip() survey_list['Street / Block Name'] = survey_list['Street / Block Name'].str.strip()
@ -122,11 +124,18 @@ def load_data():
survey_list["Post Code"] survey_list["Post Code"]
) )
survey_list["Street / Block Name"] = survey_list["Street / Block Name"].str.replace("eccels", "eccles")
survey_list["Street / Block Name"] = survey_list["Street / Block Name"].str.replace("chatley, road", "chatley road")
survey_list["Street / Block Name"] = survey_list["Street / Block Name"].str.replace("vaughen", "Vaughan")
# We now need to merge the survey list onto the asset list # We now need to merge the survey list onto the asset list
# Could be easier just to do a search on each row, even though it's much slower # Could be easier just to do a search on each row, even though it's much slower
matched = [] matched = []
for _, row in tqdm(survey_list.iterrows(), total=len(survey_list)): for _, row in tqdm(survey_list.iterrows(), total=len(survey_list)):
if row["Street / Block Name"] in ["carleach grove"]:
continue
house_number = row["NO."] house_number = row["NO."]
if isinstance(house_number, str): if isinstance(house_number, str):
house_number = house_number.lower() house_number = house_number.lower()