mirror of
https://github.com/Hestia-Homes/survey-extraction.git
synced 2026-06-30 13:10:56 +00:00
next one
This commit is contained in:
Jun-te Kim
parent
1fef7bf29c
commit
80758b35f8
2 changed files with 235 additions and 88 deletions
169
etl/month_end_automation_wave_2_no_16.py
Normal file
169
etl/month_end_automation_wave_2_no_16.py
Normal file
|
|
@ -0,0 +1,169 @@
|
|||
# Wave 2's month end automation
|
||||
from tqdm import tqdm
|
||||
from monday import MondayClient
|
||||
from etl.osmosis_complaince_address_to_files import get_all_items, extract_asset_ids
|
||||
from pprint import pprint
|
||||
import pandas as pd
|
||||
import json
|
||||
|
||||
monday_key = "eyJhbGciOiJIUzI1NiJ9.eyJ0aWQiOjQ5ODc2ODQxOCwiYWFpIjoxMSwidWlkIjozNjE3ODAzNCwiaWFkIjoiMjAyNS0wNC0xMVQxMToyMzoxNy40NjdaIiwicGVyIjoibWU6d3JpdGUiLCJhY3RpZCI6MTM5OTc4MjMsInJnbiI6InVzZTEifQ.-2Lit4s46ZF6AXuMW9t0TxIaFLkHqD4Yo-PyM9i2XZY"
|
||||
monday = MondayClient(monday_key)
|
||||
# NCHA SHDF Wave 3 On Hold
|
||||
board_ids = ["6946967610"]
|
||||
|
||||
for board in tqdm(board_ids):
|
||||
board_data = monday.boards.fetch_boards_by_id(board)
|
||||
columns = board_data["data"]["boards"][0]["columns"]
|
||||
col_id_map = {col["title"].lower(): col["id"] for col in columns}
|
||||
reversed_col_id_map = {v: k for k, v in col_id_map.items()}
|
||||
|
||||
|
||||
items = get_all_items(board, monday)
|
||||
|
||||
all_records = []
|
||||
for row in tqdm(items):
|
||||
data = {}
|
||||
data.update({"address": row['name']})
|
||||
data.update({"client": row['group']['title']})
|
||||
for col in row.get("column_values", []):
|
||||
if col.get("id") in reversed_col_id_map:
|
||||
if col.get("type") == "file":
|
||||
value = col.get("value")
|
||||
no_of_files = 0
|
||||
|
||||
if value:
|
||||
value = json.loads(col["value"])
|
||||
no_of_files = len(value.get('files', []))
|
||||
data.update({reversed_col_id_map[col.get("id")]: no_of_files})
|
||||
elif "no show" in reversed_col_id_map[col.get("id")]:
|
||||
def extract_number_from_text(text):
|
||||
number_str = ''
|
||||
|
||||
for char in text:
|
||||
if char.isnumeric():
|
||||
number_str += char
|
||||
elif number_str:
|
||||
break # stop once a number sequence ends
|
||||
|
||||
return int(number_str) if number_str else None
|
||||
text = col.get("text")
|
||||
if text is None:
|
||||
data.update({
|
||||
reversed_col_id_map[col.get("id")]: col.get("text")
|
||||
})
|
||||
else:
|
||||
data.update({
|
||||
reversed_col_id_map[col.get("id")]: extract_number_from_text(text)
|
||||
})
|
||||
else:
|
||||
data.update({
|
||||
reversed_col_id_map[col.get("id")]: col.get("text")
|
||||
})
|
||||
all_records.append(data)
|
||||
|
||||
# Convert to DataFrame
|
||||
df = pd.DataFrame(all_records)
|
||||
|
||||
filtered_dfs = []
|
||||
|
||||
def get_df(df, column_name, success_critera, job_name):
|
||||
_ = df[
|
||||
df[column_name].str.lower().isin(success_critera)
|
||||
].copy()
|
||||
_["job_type"] = job_name
|
||||
return _
|
||||
|
||||
# RA
|
||||
ra = get_df(df, "ra", ["completed"], "RA")
|
||||
filtered_dfs.append(ra)
|
||||
|
||||
|
||||
# PRE- ATT
|
||||
att = get_df(df, "att", ["completed"], "ATT")
|
||||
filtered_dfs.append(att)
|
||||
|
||||
# V1 Coordination
|
||||
v1 = get_df(df, "coordination status".lower(), [
|
||||
"rc complete",
|
||||
], "V1 Coordination")
|
||||
filtered_dfs.append(v1)
|
||||
|
||||
# V2 Coordination
|
||||
# v2 = get_df(df, "mtp v2 status", ["rc v2 complete"], "V2 Coordination")
|
||||
# filtered_dfs.append(v2)
|
||||
|
||||
# # V3 Coordination
|
||||
# v3 = get_df(df, "v3 rc status", ["uploaded"], "V3 Coordination")
|
||||
# filtered_dfs.append(v3)
|
||||
|
||||
# v3 = get_df(df, "v3 invoice status", ["to be invoice"], "V3 Coordination")
|
||||
# filtered_dfs.append(v3)
|
||||
|
||||
# Design stage 1
|
||||
# design1 = get_df(df, "design invoice status", ["to invoice"], "Design")
|
||||
# filtered_dfs.append(design1)
|
||||
|
||||
# Design revision
|
||||
# design2 = get_df(df, "design revision invoice", [
|
||||
# "Rev. A to invoice".lower(),
|
||||
# "Rev. B to invoice".lower(),
|
||||
# "Rev. C to invoice".lower(),
|
||||
# "Rev. D to invoice".lower(),
|
||||
# ], "Design Revision")
|
||||
# filtered_dfs.append(design2)
|
||||
|
||||
# Lodgement Phase 1
|
||||
lodg1 = get_df(df, "lodg. phase 1 invoice status".lower(), ["to invoice"], "Lodgement Phase 1")
|
||||
filtered_dfs.append(lodg1)
|
||||
|
||||
|
||||
# Full Lodgement Phase
|
||||
full_lodgement = get_df(df, "full lodgement invoice status".lower(), ["to invoice"], "Full Lodgement")
|
||||
filtered_dfs.append(full_lodgement)
|
||||
|
||||
# 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 ATT
|
||||
post_att = get_df(df, "post att", ["done", "post att complete"], "POST ATT")
|
||||
filtered_dfs.append(post_att)
|
||||
|
||||
# Retrofit Evaluation
|
||||
retro = get_df(df, "retrofit evaluation", ["done"], "Retrofit Evaluation")
|
||||
filtered_dfs.append(retro)
|
||||
|
||||
# RA NO Show
|
||||
ra_ns = df[
|
||||
df["ra no show evidence"].fillna(-9999) != df["ra no show invoice"].fillna(-9999)
|
||||
].copy()
|
||||
ra_ns["job_type"] = "RA NO SHOW"
|
||||
filtered_dfs.append(ra_ns)
|
||||
|
||||
|
||||
# ATT NO Show
|
||||
att_ns = df[
|
||||
df["att no show evidence"].fillna(-9999) != df["att no show invoice"].fillna(-9999)
|
||||
].copy()
|
||||
att_ns["job_type"] = "ATT NO SHOW"
|
||||
filtered_dfs.append(att_ns)
|
||||
|
||||
|
||||
# Post visit no show
|
||||
# epc_ns = df[
|
||||
# df["epc no show evidence"].fillna(-9999) != df["epc no show invoice"].fillna(-9999)
|
||||
# ].copy()
|
||||
# epc_ns["job_type"] = "EPC NO SHOW"
|
||||
# filtered_dfs.append(epc_ns)
|
||||
|
||||
final_df = pd.concat(filtered_dfs).reset_index(drop=True)
|
||||
|
||||
final_df[['address', 'client', 'job_type']]
|
||||
|
|
@ -9,11 +9,15 @@ import json
|
|||
|
||||
monday_key = "eyJhbGciOiJIUzI1NiJ9.eyJ0aWQiOjQ5ODc2ODQxOCwiYWFpIjoxMSwidWlkIjozNjE3ODAzNCwiaWFkIjoiMjAyNS0wNC0xMVQxMToyMzoxNy40NjdaIiwicGVyIjoibWU6d3JpdGUiLCJhY3RpZCI6MTM5OTc4MjMsInJnbiI6InVzZTEifQ.-2Lit4s46ZF6AXuMW9t0TxIaFLkHqD4Yo-PyM9i2XZY"
|
||||
monday = MondayClient(monday_key)
|
||||
# WCHG Walkups-Operations
|
||||
board_ids = ["9349630181"]
|
||||
board_ids = [
|
||||
# "9349630181", # WCHG Walkups-Operations
|
||||
"8829428746", # 2502 Accent Housing
|
||||
|
||||
]
|
||||
|
||||
|
||||
for board in tqdm(board_ids):
|
||||
print(f"working on board {board}")
|
||||
board_data = monday.boards.fetch_boards_by_id(board)
|
||||
columns = board_data["data"]["boards"][0]["columns"]
|
||||
col_id_map = {col["title"].lower(): col["id"] for col in columns}
|
||||
|
|
@ -68,81 +72,69 @@ df = pd.DataFrame(all_records)
|
|||
|
||||
filtered_dfs = []
|
||||
|
||||
|
||||
def get_df(df, column_name, success_critera, job_name):
|
||||
if column_name in col_id_map:
|
||||
_ = df[
|
||||
df[column_name].str.lower().isin(success_critera)
|
||||
].copy()
|
||||
_["job_type"] = job_name
|
||||
return _
|
||||
else:
|
||||
print(f"failed to find {column_name}")
|
||||
|
||||
|
||||
# RA
|
||||
ra = df[
|
||||
df["ra invoicing status"].str.lower().isin(["to invoice"])
|
||||
].copy()
|
||||
ra["job_type"] = "RA"
|
||||
filtered_dfs.append(ra)
|
||||
ra = get_df(df, "ra invoicing status", ["to invoice"], "RA")
|
||||
if ra is not None:
|
||||
filtered_dfs.append(ra)
|
||||
|
||||
|
||||
# ATT
|
||||
att = df[
|
||||
df["pre att invoicing status"].str.lower().isin(["to invoice"])
|
||||
].copy()
|
||||
att["job_type"] = "ATT"
|
||||
filtered_dfs.append(att)
|
||||
att = get_df(df, "post att invoicing status", ["to invoice"], "ATT")
|
||||
if att is not None:
|
||||
filtered_dfs.append(att)
|
||||
|
||||
# V1 Coordination
|
||||
v1 = df[
|
||||
df["mtp invoicing status"].str.lower().isin(["(v1) ioe/mtp to invoice"])
|
||||
].copy()
|
||||
modeling = get_df(df, "mtp invoicing status", ["modelling to invoice"], "V3 Coordination")
|
||||
if modeling is not None:
|
||||
filtered_dfs.append(modeling)
|
||||
|
||||
v1["job_type"] = "V1 Coordination"
|
||||
filtered_dfs.append(v1)
|
||||
v1 = get_df(df, "mtp invoicing status", ["(v1) ioe/mtp to invoice"], "V1 Coordination")
|
||||
if v1 is not None:
|
||||
filtered_dfs.append(v1)
|
||||
|
||||
# V2 Coordination
|
||||
v2 = df[
|
||||
df["mtp invoicing status"].str.lower().isin(["(v2) ioe/mtp to invoice"])
|
||||
].copy()
|
||||
v2 = get_df(df, "mtp invoicing status", ["(v2) ioe/mtp to invoice"], "V2 Coordination")
|
||||
if v2 is not None:
|
||||
filtered_dfs.append(v2)
|
||||
|
||||
v2["job_type"] = "V2 Coordination"
|
||||
filtered_dfs.append(v2)
|
||||
v3 = get_df(df, "mtp invoicing status", ["(v3) ioe/mtp to invoice"], "V3 Coordination")
|
||||
if v3 is not None:
|
||||
filtered_dfs.append(v3)
|
||||
|
||||
# V3 Coordination
|
||||
v3 = df[
|
||||
df["mtp invoicing status"].str.lower().isin(["(v3) ioe/mtp to invoice"])
|
||||
].copy()
|
||||
|
||||
v3["job_type"] = "V3 Coordination"
|
||||
filtered_dfs.append(v3)
|
||||
|
||||
# Design stage 1
|
||||
design1 = df[
|
||||
df["design invoicing status"].str.lower().isin(["to invoice"])
|
||||
].copy()
|
||||
design1["job_type"] = "Design"
|
||||
filtered_dfs.append(design1)
|
||||
design1 = get_df(df, "design invoicing status", ["to invoice"], "Design")
|
||||
if design1 is not None:
|
||||
filtered_dfs.append(design1)
|
||||
|
||||
# Design Revision
|
||||
revision_letter = ['a', 'b', 'c', 'd']
|
||||
for letter in revision_letter:
|
||||
design2 = df[
|
||||
df["design revision invoice"].str.lower().isin([f"rev. {letter} to invoice"])
|
||||
].copy()
|
||||
design2["job_type"] = "Design Revision"
|
||||
filtered_dfs.append(design2)
|
||||
design = get_df(df, "design revision invoice", [f"rev. {letter} to invoice"], "Design Revision")
|
||||
if design is not None:
|
||||
filtered_dfs.append(design)
|
||||
|
||||
# Lodgement Phase 1
|
||||
lodg1 = df[
|
||||
df["lodgement phase 1 invoicing status"].str.lower().isin(["to invoice"])
|
||||
].copy()
|
||||
lodg1["job_type"] = "Lodgement Phase 1"
|
||||
filtered_dfs.append(lodg1)
|
||||
lodg1 = get_df(df, "lodgement phase 1 invoicing status", ["to invoice"], "Lodgement Phase 1")
|
||||
if lodg1 is not None:
|
||||
filtered_dfs(lodg1)
|
||||
|
||||
# Full Lodgement Phase
|
||||
lodg2 = df[
|
||||
df["full lodgement invoicing status"].str.lower().isin(["to invoice"])
|
||||
].copy()
|
||||
lodg2["job_type"] = "Full Lodgement"
|
||||
filtered_dfs.append(lodg2)
|
||||
lodg2 = get_df(df, "full lodgement invoicing status", ["to invoice"], "Full Lodgement")
|
||||
if lodg2 is not None:
|
||||
filtered_dfs.append(lodg2)
|
||||
|
||||
# POST EPC
|
||||
post_epc = df[
|
||||
df["post epc & eval. invoicing status"].str.lower().isin(["to invoice"])
|
||||
].copy()
|
||||
post_epc["job_type"] = "POST EPC"
|
||||
filtered_dfs.append(post_epc)
|
||||
post_epc = get_df(df, "post epc & eval. invoicing status", ["to invoice"], "POST EPC")
|
||||
if post_epc is not None:
|
||||
filtered_dfs.append(post_epc)
|
||||
|
||||
|
||||
# # POST EPR, not right now
|
||||
|
|
@ -152,45 +144,31 @@ filtered_dfs.append(post_epc)
|
|||
# post_epr["job_type"] = "POST ATT"
|
||||
# filtered_dfs.append(post_epr)
|
||||
|
||||
|
||||
# Post ATT
|
||||
post_att = df[
|
||||
df["post att invoicing status"].str.lower().isin(["to invoice"])
|
||||
].copy()
|
||||
post_att["job_type"] = "POST ATT"
|
||||
filtered_dfs.append(post_att)
|
||||
|
||||
post_att = get_df(df, "post att invoicing status", ["to invoice"], "POST ATT")
|
||||
if post_att is not None:
|
||||
filtered_dfs.append(post_epc)
|
||||
|
||||
# Retrofit Evaluation
|
||||
retro = df[
|
||||
df["rc stage 2 invoicing status"].str.lower().isin(["to invoice"])
|
||||
].copy()
|
||||
retro["job_type"] = "RC stage 2"
|
||||
filtered_dfs.append(retro)
|
||||
rc = get_df(df, "rc stage 2 invoicing status", ["to invoice"], "RC stage 2")
|
||||
if rc is not None:
|
||||
filtered_dfs.append(rc)
|
||||
|
||||
# RA NO Show
|
||||
ra_ns = df[
|
||||
df["ra no show invoice"].str.lower().isin(["to invoice","to invoice (+1 previous no show)", "to invoice (+2 previous no shows)"])
|
||||
].copy()
|
||||
ra_ns["job_type"] = "RA NO SHOW"
|
||||
filtered_dfs.append(ra_ns)
|
||||
ra_ns = get_df(df,"ra no show invoice", ["to invoice","to invoice (+1 previous no show)", "to invoice (+2 previous no shows)"], "RA NO SHOW")
|
||||
if ra_ns is not None:
|
||||
filtered_dfs.append(ra_ns)
|
||||
|
||||
|
||||
# ATT NO Show
|
||||
att_ns = df[
|
||||
df["pre att no show invoice"].str.lower().isin(["to invoice","to invoice (+1 previous no show)", "to invoice (+2 previous no shows)"])
|
||||
].copy()
|
||||
att_ns["job_type"] = "ATT NO SHOW"
|
||||
filtered_dfs.append(att_ns)
|
||||
att_ns = get_df(df, "pre att no show invoice", ["to invoice","to invoice (+1 previous no show)", "to invoice (+2 previous no shows)"], "ATT NO SHOW")
|
||||
if att_ns is not None:
|
||||
filtered_dfs.append(att_ns)
|
||||
|
||||
|
||||
# Post visit no show
|
||||
#post work no show invoice
|
||||
epc_ns = df[
|
||||
df["post works no show invoice"].str.lower().isin(["to invoice","to invoice (+1 previous no show)", "to invoice (+2 previous no shows)"])
|
||||
].copy()
|
||||
epc_ns["job_type"] = "EPC NO SHOW"
|
||||
filtered_dfs.append(epc_ns)
|
||||
epc_ns = get_df(df, "post works no show invoice", ["to invoice","to invoice (+1 previous no show)", "to invoice (+2 previous no shows)"], "EPC NO SHOW")
|
||||
if epc_ns is not None:
|
||||
filtered_dfs.append(epc_ns)
|
||||
|
||||
final_df = pd.concat(filtered_dfs).reset_index(drop=True)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue