junte/survey-extraction
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/survey-extraction.git synced 2026-06-30 13:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

next board

Browse source
This commit is contained in:
Jun-te Kim 2025-07-29 11:41:55 +00:00
parent 42dca1c88a
commit c297a87776
2 changed files with 55 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
etl/month_end_automation_wave_2_layout.py
View file

@ -16,13 +16,13 @@ rate_card_data = {
"job_type": [
"RA", "ATT", "Coordination Stage 1 v1", "Coordination Stage 1 v2 remodel", "Coordination Stage 1 v3 remodel",
"Design Archetype", "Design Repetitive", "Coordination Stage 2", "Lodgement phase 1", "Full lodgement phase 2",
"Post EPC", "Post ATT", "retrofit evaluation",
"Post EPR", "Post EPC", "Post ATT", "retrofit evaluation",
"RA no show", "ATT no show", "post EPC no show"
],
"rate": [
207.65, 101, 186.4, 98, 98,
450, 150, 163, 135, 120,
45, 90.5, 40,
"Mariaane Please tell me", 45, 90.5, 40,
25, 25, 25
]
}
@ -122,8 +122,8 @@ filtered_dfs.append(v3)
# Coordination stage 2 Please complete
cors2 = df[
df["rc stg. 2"].str.lower().isin(["to invoice", "completed"])
]
df["rc stg. 2"].str.lower().isin(["to invoice"])
].copy()
cors2["joby_type"] = "Coordination Stage 2"
filtered_dfs.append(cors2)
@ -174,7 +174,7 @@ filtered_dfs.append(post_epc)
post_epr = df[
df["post-epc status"].str.lower().isin(["post epr completed"])
].copy()
post_epr["job_type"] = "Post ATT"
post_epr["job_type"] = "Post EPR"
filtered_dfs.append(post_epr)
@ -233,4 +233,4 @@ import datetime
timestamp = datetime.datetime.now().strftime('%Y-%m-%d_%H-%M')
attribute = ['address', 'client', 'job_type', 'rate']
combined_with_rates[attribute].to_csv(f'NCHA SHDF Westville Wave 1 & 2_{timestamp}.csv', index=False)
combined_with_rates[attribute].to_excel(f'NCHA SHDF Westville Wave 1 & 2_{timestamp}.xlsx', index=False)

68
etl/month_end_automation_wave_2_no_16.py
View file

@ -11,6 +11,23 @@ monday = MondayClient(monday_key)
# NCHA SHDF Wave 3 On Hold
board_ids = ["6946967610"]
rate_card_data = {
"job_type": [
"RA", "ATT", "Coordination Stage 1 v1", "Coordination Stage 1 v2 remodel", "Coordination Stage 1 v3 remodel",
"Design Archetype", "Design Repetitive", "Coordination Stage 2", "Lodgement phase 1", "Full lodgement phase 2",
"Post EPR", "Post EPC", "Post ATT", "retrofit evaluation",
"RA no show", "ATT no show", "post EPC no show"
],
"rate": [
207.65, 101, 186.4, 98, 98,
450, 150, 163, 135, 120,
"Marianne EPR Please", 45, 90.5, 40,
25, 25, 25
]
}
rate_card_df = pd.DataFrame(rate_card_data)
for board in tqdm(board_ids):
board_data = monday.boards.fetch_boards_by_id(board)
columns = board_data["data"]["boards"][0]["columns"]
@ -85,32 +102,35 @@ filtered_dfs.append(att)
# V1 Coordination
v1 = get_df(df, "coordination status".lower(), [
"rc complete",
], "V1 Coordination")
], "Coordination Stage 1 v1")
filtered_dfs.append(v1)
# V2 Coordination
# v2 = get_df(df, "mtp v2 status", ["rc v2 complete"], "V2 Coordination")
# v2 = get_df(df, "mtp v2 status", ["rc v2 complete"], "Coordination Stage 1 v2 remodel")
# filtered_dfs.append(v2)
# # V3 Coordination
# v3 = get_df(df, "v3 rc status", ["uploaded"], "V3 Coordination")
# v3 = get_df(df, "v3 rc status", ["uploaded"], "Coordination Stage 1 v3 remode")
# filtered_dfs.append(v3)
# v3 = get_df(df, "v3 invoice status", ["to be invoice"], "V3 Coordination")
# filtered_dfs.append(v3)
# Coordination stage 2 Please complete
# cors2 = df[
# df["rc stg. 2"].str.lower().isin(["to invoice", "completed"])
# ]
# cors2["joby_type"] = "Coordination Stage 2"
# filtered_dfs.append(cors2)
cors2 = df[
df["rc stg. 2"].str.lower().isin(["to invoice"])
]
cors2["joby_type"] = "Coordination Stage 2"
filtered_dfs.append(cors2)
# Design stage 1
# Design Archetype
# design1 = get_df(df, "design invoice status", ["to invoice"], "Design")
# filtered_dfs.append(design1)
# Design revision
# Design Repetitive
# Design Revision
# design2 = get_df(df, "design revision invoice", [
# "Rev. A to invoice".lower(),
# "Rev. B to invoice".lower(),
@ -125,20 +145,20 @@ filtered_dfs.append(lodg1)
# Full Lodgement Phase
full_lodgement = get_df(df, "full lodgement invoice status".lower(), ["to invoice"], "Full Lodgement")
full_lodgement = get_df(df, "full lodgement invoice status".lower(), ["to invoice"], "Full lodgement phase 2")
filtered_dfs.append(full_lodgement)
# POST EPC
post_epc = get_df(df, "lodged epc", ["complete", "complete & lodged",], "POST EPC")
post_epc = get_df(df, "lodged epc", ["complete", "complete & lodged",], "Post EPC")
filtered_dfs.append(post_epc)
# # POST EPR
# post_epr = df[
# df["post-epc status"].str.lower().isin(["post epr completed"])
# ].copy()
# post_epr["job_type"] = "POST ATT"
# filtered_dfs.append(post_epr)
# POST EPR
post_epr = df[
df["lodged epc"].str.lower().isin(["post epr completed"])
].copy()
post_epr["job_type"] = "POST EPR"
filtered_dfs.append(post_epr)
# Post ATT
post_att = get_df(df, "post att", ["done", "post att complete"], "POST ATT")
@ -175,4 +195,14 @@ filtered_dfs.append(att_ns)
final_df = pd.concat(filtered_dfs).reset_index(drop=True)
final_df[['address', 'client', 'job_type']]
final_df["job_type"] = final_df["job_type"].str.lower()
rate_card_df["job_type"] = rate_card_df["job_type"].str.lower()
# Now perform the merge
combined_with_rates = final_df.merge(rate_card_df, on="job_type", how="left")
import datetime
timestamp = datetime.datetime.now().strftime('%Y-%m-%d_%H-%M')
attribute = ['address', 'client', 'job_type', 'rate']
combined_with_rates[attribute].to_excel(f'NCHA SHDF Wave 3 On Hold_{timestamp}.xlsx', index=False)