Skip to content

Commit

Permalink
[feat] 광역의회 다양성 지수 계산, DB에 저장
Browse files Browse the repository at this point in the history
  • Loading branch information
@pingpingy1
pingpingy1 committed Nov 27, 2023
1 parent c795ec6 commit 69bae9a
Showing 1 changed file with 130 additions and 6 deletions.
136 changes: 130 additions & 6 deletions analysis/diversity_db.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,11 @@
from db.client import client


# ====================================
# Diversity index calculations
# ====================================


def count(data, stair=0):
"""
Returns a counter object of the data, while stairing them to appropriate bins if stair > 0
Expand Down Expand Up @@ -50,7 +55,12 @@ def shannon(data, stair=0, opts=True):
return sh_idx


def save_to_mongo(localId: int, factor: str, stair=0, opts=False) -> None:
# ====================================
# Local council diversity statistics
# ====================================


def save_to_mongo_local(localId: int, factor: str, stair=0, opts=False) -> None:
factor_field = {"age": "age", "gender": "gender", "party": "jdName"}
data = [
councilor[factor_field[factor]]
Expand All @@ -68,6 +78,7 @@ def save_to_mongo(localId: int, factor: str, stair=0, opts=False) -> None:
def calculate_rank_local(factor: str) -> None:
result = client["stats"]["diversity_index"].aggregate(
[
{"$match": {"localId": {"$ne": None}}},
{"$sort": {f"{factor}DiversityIndex": -1}},
{"$group": {"_id": "", "items": {"$push": "$$ROOT"}}},
{"$unwind": {"path": "$items", "includeArrayIndex": "items.rank"}},
Expand All @@ -82,7 +93,7 @@ def calculate_rank_local(factor: str) -> None:
)


def calculate_age_diversity_rank_history() -> None:
def calculate_age_diversity_rank_history_local() -> None:
for councilor_type in ["elected", "candidate"]:
for localId in range(1, 227):
docs = client["stats"]["age_hist"].find(
Expand Down Expand Up @@ -146,12 +157,125 @@ def calculate_age_diversity_rank_history() -> None:
)


# ====================================
# Metro council diversity statistics
# ====================================


def save_to_mongo_metro(metroId: int, factor: str, stair=0, opts=False) -> None:
factor_field = {"age": "age", "gender": "gender", "party": "jdName"}
data = [
councilor[factor_field[factor]]
for councilor in client["council"]["metro_councilor"].find({"metroId": metroId})
]
# print(f"{metroId} {factor}")
# print(data)
client["stats"].get_collection("diversity_index").update_one(
{"metroId": metroId},
{"$set": {f"{factor}DiversityIndex": gini_simpson(data, stair, opts)}},
upsert=True,
)


def calculate_rank_metro(factor: str) -> None:
result = client["stats"]["diversity_index"].aggregate(
[
{"$match": {"metroId": {"$ne": None}}},
{"$sort": {f"{factor}DiversityIndex": -1}},
{"$group": {"_id": "", "items": {"$push": "$$ROOT"}}},
{"$unwind": {"path": "$items", "includeArrayIndex": "items.rank"}},
{"$replaceRoot": {"newRoot": "$items"}},
{"$addFields": {"rank": {"$add": ["$rank", 1]}}},
]
)
for doc in result:
client["stats"]["diversity_index"].find_one_and_update(
{"metroId": doc["metroId"]},
{"$set": {f"{factor}DiversityRank": int(doc["rank"])}},
)


def calculate_age_diversity_rank_history_metro() -> None:
for councilor_type in ["elected", "candidate"]:
for metroId in range(1, 18):
docs = client["stats"]["age_hist"].find(
{
"councilorType": councilor_type,
"method": "equal",
"level": 1,
"metroId": metroId,
}
)
for doc in docs:
diversity_index = gini_simpson(
[
group["minAge"]
for group in doc["data"]
for _ in range(group["count"])
],
stair=10,
)
client["stats"]["age_hist"].find_one_and_update(
{
"councilorType": councilor_type,
"method": "equal",
"level": 1,
"metroId": metroId,
"year": doc["year"],
},
{"$set": {"diversityIndex": diversity_index}},
)

years = list({doc["year"] for doc in client["stats"]["age_hist"].find()})

for year in years:
result = client["stats"]["age_hist"].aggregate(
[
{
"$match": {
"councilorType": councilor_type,
"method": "equal",
"level": 1,
"year": year,
}
},
{"$sort": {"diversityIndex": -1}},
{"$group": {"_id": "", "items": {"$push": "$$ROOT"}}},
{"$unwind": {"path": "$items", "includeArrayIndex": "items.rank"}},
{"$replaceRoot": {"newRoot": "$items"}},
{"$addFields": {"rank": {"$add": ["$rank", 1]}}},
]
)
for doc in result:
client["stats"]["age_hist"].find_one_and_update(
{
"councilorType": councilor_type,
"method": "equal",
"level": 1,
"metroId": doc["metroId"],
"year": year,
},
{"$set": {"diversityRank": int(doc["rank"])}},
)


if __name__ == "__main__":
# for localId in range(1, 227):
# save_to_mongo(localId, "age", stair=10)
# save_to_mongo(localId, "gender")
# save_to_mongo(localId, "party")
# save_to_mongo_local(localId, "age", stair=10)
# save_to_mongo_local(localId, "gender")
# save_to_mongo_local(localId, "party")
# calculate_rank_local("age")
# calculate_rank_local("gender")
# calculate_rank_local("party")
calculate_age_diversity_rank_history()
calculate_age_diversity_rank_history_local()

# for metroId in range(1, 18):
# if metroId in [8, 17]:
# continue
# save_to_mongo_metro(metroId, "age", stair=10)
# save_to_mongo_metro(metroId, "gender")
# save_to_mongo_metro(metroId, "party")
# calculate_rank_metro("age")
# calculate_rank_metro("gender")
# calculate_rank_metro("party")
# calculate_age_diversity_rank_history_metro()

0 comments on commit 69bae9a

Please sign in to comment.