sdgs year v2
This commit is contained in:
Debby
@@ -8,7 +8,7 @@ Filtering Order:
|
||||
3. Filter complete indicators PER COUNTRY (auto-detect start year, no gaps)
|
||||
4. Filter countries with ALL pillars (FIXED SET)
|
||||
5. Filter indicators with consistent presence across FIXED countries
|
||||
6. Determine SDG start year & assign framework (MDGs/SDGs) per ROW per year
|
||||
6. Determine SDG start year & assign framework (MDGs/SDGs) per indicator PER ROW
|
||||
7. Verify no gaps
|
||||
8. Calculate norm_value_1_100 per indicator per country (min-max, direction-aware)
|
||||
9. Calculate YoY per indicator per country
|
||||
@@ -22,18 +22,17 @@ NORMALISASI (Step 8):
|
||||
sehingga nilai antar negara dan antar tahun tetap comparable
|
||||
- Kolom ini memungkinkan perbandingan antar indikator yang berbeda satuan di Looker Studio
|
||||
|
||||
FRAMEWORK LOGIC (Per-Row, bukan per indikator):
|
||||
- sdg_start_year dideteksi dari data: tahun pertama indikator FIES lengkap
|
||||
FRAMEWORK LOGIC (FIX - Row-Level Assignment):
|
||||
- SDG start year dideteksi dari data: tahun pertama indikator FIES/anaemia lengkap
|
||||
di semua fixed countries (setelah Step 3-5 filter selesai)
|
||||
- Proxy deteksi sdg_start_year: HANYA FIES ("food insecurity", "food insecure")
|
||||
Anemia TIDAK dipakai sebagai proxy karena datanya sudah ada sebelum era SDGs
|
||||
- Framework di-assign PER BARIS (per year), bukan per indikator:
|
||||
* row['year'] >= sdg_start_year AND nama ada di SDG_INDICATOR_KEYWORDS -> 'SDGs'
|
||||
- Framework di-assign PER BARIS (per tahun), bukan per indikator:
|
||||
* Jika row['year'] < sdg_start_year -> selalu 'MDGs'
|
||||
* Jika row['year'] >= sdg_start_year DAN
|
||||
nama ada di SDG_INDICATOR_KEYWORDS -> 'SDGs'
|
||||
* Selain itu -> 'MDGs'
|
||||
- Ini menangani indikator "shared" (anemia, stunting, wasting, undernourishment)
|
||||
yang datanya ada sebelum SDGs:
|
||||
* row lama (year < sdg_start_year) -> 'MDGs'
|
||||
* row baru (year >= sdg_start_year) -> 'SDGs'
|
||||
- Dengan demikian, indikator seperti "Prevalence of anemia" yang datanya dimulai
|
||||
sebelum era SDGs akan berlabel 'MDGs' untuk tahun-tahun pra-SDGs dan 'SDGs'
|
||||
untuk tahun-tahun pasca (>= sdg_start_year).
|
||||
"""
|
||||
|
||||
import pandas as pd
|
||||
@@ -61,16 +60,13 @@ from google.cloud import bigquery
|
||||
|
||||
# =============================================================================
|
||||
# SDG INDICATOR KEYWORDS
|
||||
# Daftar nama indikator (lowercase) yang masuk SDG framework.
|
||||
# Indikator ini akan di-assign 'SDGs' untuk baris dengan year >= sdg_start_year,
|
||||
# dan 'MDGs' untuk baris dengan year < sdg_start_year.
|
||||
# =============================================================================
|
||||
|
||||
SDG_INDICATOR_KEYWORDS = frozenset([
|
||||
# TARGET 2.1.1 — Prevalence of undernourishment (shared: ada sebelum SDGs)
|
||||
# TARGET 2.1.1 — Prevalence of undernourishment (shared, sudah ada sebelum SDGs)
|
||||
"prevalence of undernourishment (percent) (3-year average)",
|
||||
"number of people undernourished (million) (3-year average)",
|
||||
# TARGET 2.1.2 — FIES (SDGs only — murni baru di era SDGs)
|
||||
# TARGET 2.1.2 — FIES (SDGs only)
|
||||
"prevalence of severe food insecurity in the total population (percent) (3-year average)",
|
||||
"prevalence of severe food insecurity in the male adult population (percent) (3-year average)",
|
||||
"prevalence of severe food insecurity in the female adult population (percent) (3-year average)",
|
||||
@@ -83,35 +79,24 @@ SDG_INDICATOR_KEYWORDS = frozenset([
|
||||
"number of moderately or severely food insecure people (million) (3-year average)",
|
||||
"number of moderately or severely food insecure male adults (million) (3-year average)",
|
||||
"number of moderately or severely food insecure female adults (million) (3-year average)",
|
||||
# TARGET 2.2.1 — Stunting (shared: ada sebelum SDGs)
|
||||
# TARGET 2.2.1 — Stunting (shared)
|
||||
"percentage of children under 5 years of age who are stunted (modelled estimates) (percent)",
|
||||
"number of children under 5 years of age who are stunted (modeled estimates) (million)",
|
||||
# TARGET 2.2.2 — Wasting & Overweight (shared: ada sebelum SDGs)
|
||||
# TARGET 2.2.2 — Wasting & Overweight (shared)
|
||||
"percentage of children under 5 years affected by wasting (percent)",
|
||||
"number of children under 5 years affected by wasting (million)",
|
||||
"percentage of children under 5 years of age who are overweight (modelled estimates) (percent)",
|
||||
"number of children under 5 years of age who are overweight (modeled estimates) (million)",
|
||||
# TARGET 2.2.3 — Anaemia (shared: data ada sebelum SDGs, listed here agar
|
||||
# baris >= sdg_start_year di-assign 'SDGs')
|
||||
# TARGET 2.2.3 — Anaemia (SDGs only — listed here so rows >= sdg_start_year become SDGs)
|
||||
"prevalence of anemia among women of reproductive age (15-49 years) (percent)",
|
||||
"number of women of reproductive age (15-49 years) affected by anemia (million)",
|
||||
])
|
||||
|
||||
# =============================================================================
|
||||
# SDG ERA PROXY KEYWORDS
|
||||
# HANYA indikator yang MURNI baru di era SDGs (FIES saja).
|
||||
# Dipakai untuk mendeteksi sdg_start_year dari data.
|
||||
#
|
||||
# PENTING — Anemia/anaemia TIDAK dipakai sebagai proxy:
|
||||
# Data anemia sudah ada sebelum era SDGs sehingga actual_start_year-nya
|
||||
# lebih awal dari sdg_start_year. Jika dipakai sebagai proxy, sdg_start_year
|
||||
# akan terdeteksi terlalu awal dan seluruh baris anemia akan menjadi 'SDGs'.
|
||||
# FIES adalah satu-satunya indikator yang benar-benar murni baru di era SDGs
|
||||
# dan dapat dipakai sebagai penanda tahun mulainya era SDGs.
|
||||
# =============================================================================
|
||||
# Proxy keywords untuk deteksi era SDGs dari data (indikator murni baru di SDGs)
|
||||
_SDG_ERA_PROXY_KEYWORDS = frozenset([
|
||||
"food insecurity",
|
||||
"food insecure",
|
||||
"anemia",
|
||||
"anaemia",
|
||||
])
|
||||
|
||||
# =============================================================================
|
||||
@@ -143,41 +128,33 @@ def assign_condition(norm_value_1_100: float) -> str:
|
||||
return 'moderate'
|
||||
|
||||
|
||||
def assign_framework_per_row(
|
||||
def assign_framework_for_row(
|
||||
indicator_name: str,
|
||||
year: int,
|
||||
row_year: int,
|
||||
sdg_start_year: int,
|
||||
) -> str:
|
||||
"""
|
||||
Tentukan framework (MDGs/SDGs) per BARIS (per row year), bukan per indikator.
|
||||
Tentukan framework (MDGs/SDGs) PER BARIS (per tahun), bukan per indikator.
|
||||
|
||||
Logic:
|
||||
- 'SDGs' jika KEDUA kondisi terpenuhi:
|
||||
1. Nama indikator ada di SDG_INDICATOR_KEYWORDS
|
||||
2. year (tahun baris ini) >= sdg_start_year
|
||||
- 'MDGs' untuk semua kasus lain.
|
||||
- Jika row_year < sdg_start_year → selalu 'MDGs', apapun nama indikatornya.
|
||||
- Jika row_year >= sdg_start_year DAN nama ada di SDG_INDICATOR_KEYWORDS → 'SDGs'.
|
||||
- Selain itu → 'MDGs'.
|
||||
|
||||
Mengapa per row, bukan per indikator?
|
||||
Indikator "shared" seperti anemia, stunting, wasting, undernourishment
|
||||
memiliki data yang ada SEBELUM era SDGs dimulai. Jika assign dilakukan
|
||||
per indikator menggunakan actual_start_year, indikator-indikator ini
|
||||
akan selalu di-assign 'MDGs' karena actual_start_year < sdg_start_year.
|
||||
Dengan assign per row menggunakan year baris:
|
||||
- baris lama (year < sdg_start_year) -> 'MDGs' (benar: belum era SDGs)
|
||||
- baris baru (year >= sdg_start_year) -> 'SDGs' (benar: sudah era SDGs)
|
||||
|
||||
Contoh anemia (sdg_start_year = 2016):
|
||||
- row year=2013 -> 'MDGs'
|
||||
- row year=2014 -> 'MDGs'
|
||||
- row year=2015 -> 'MDGs'
|
||||
- row year=2016 -> 'SDGs'
|
||||
- row year=2017 -> 'SDGs'
|
||||
- ...
|
||||
Dengan cara ini, indikator seperti "Prevalence of anemia" yang datanya
|
||||
ada sebelum era SDGs akan berlabel 'MDGs' untuk tahun-tahun pra-SDGs,
|
||||
dan 'SDGs' untuk tahun-tahun pasca sdg_start_year.
|
||||
"""
|
||||
# Tahun sebelum era SDGs → selalu MDGs
|
||||
if row_year < sdg_start_year:
|
||||
return 'MDGs'
|
||||
|
||||
# Tahun >= sdg_start_year: cek apakah nama ada di SDG list
|
||||
name_lower = str(indicator_name).lower().strip()
|
||||
in_sdg_list = name_lower in SDG_INDICATOR_KEYWORDS
|
||||
if in_sdg_list and int(year) >= sdg_start_year:
|
||||
if name_lower in SDG_INDICATOR_KEYWORDS:
|
||||
return 'SDGs'
|
||||
|
||||
# Tidak ada di SDG list → MDGs
|
||||
return 'MDGs'
|
||||
|
||||
|
||||
@@ -197,11 +174,10 @@ class AnalyticalLayerLoader:
|
||||
norm_value_1_100, <- min-max norm per indikator, skala 1-100, direction-aware
|
||||
yoy_change, yoy_pct
|
||||
|
||||
Catatan framework:
|
||||
Framework di-assign PER BARIS (per year), sehingga indikator shared
|
||||
seperti anemia dapat memiliki framework berbeda di baris yang berbeda:
|
||||
- baris sebelum sdg_start_year -> 'MDGs'
|
||||
- baris sejak sdg_start_year -> 'SDGs'
|
||||
PERUBAHAN (framework fix):
|
||||
- framework di-assign per baris (per tahun), bukan per indikator.
|
||||
- Baris dengan year < sdg_start_year selalu 'MDGs'.
|
||||
- Baris dengan year >= sdg_start_year dan nama di SDG_INDICATOR_KEYWORDS → 'SDGs'.
|
||||
"""
|
||||
|
||||
def __init__(self, client: bigquery.Client):
|
||||
@@ -306,14 +282,6 @@ class AnalyticalLayerLoader:
|
||||
self.logger.info("STEP 2: DETERMINE YEAR BOUNDARIES")
|
||||
self.logger.info("=" * 80)
|
||||
|
||||
# Filter single years only (is_year_range == False)
|
||||
if 'is_year_range' in self.df_clean.columns:
|
||||
before = len(self.df_clean)
|
||||
self.df_clean = self.df_clean[self.df_clean['is_year_range'] == False].copy()
|
||||
self.logger.info(
|
||||
f" Filter single years only: {before:,} -> {len(self.df_clean):,} rows"
|
||||
)
|
||||
|
||||
# baseline_year = 2023 hardcode (syarat dosen: minimal 2023)
|
||||
df_baseline = self.df_clean[self.df_clean['year'] == self.baseline_year]
|
||||
baseline_indicator_count = df_baseline['indicator_id'].nunique()
|
||||
@@ -529,11 +497,6 @@ class AnalyticalLayerLoader:
|
||||
self.logger.info(f"\n [+] Valid: {len(valid_indicators)}")
|
||||
self.logger.info(f" [-] Removed: {len(removed_indicators)}")
|
||||
|
||||
if removed_indicators:
|
||||
self.logger.info(f"\n Removed indicators:")
|
||||
for item in removed_indicators:
|
||||
self.logger.info(f" [-] {item['indicator_name'][:60]} | {item['reason']}")
|
||||
|
||||
if not valid_indicators:
|
||||
raise ValueError("No valid indicators found after filtering!")
|
||||
|
||||
@@ -559,18 +522,13 @@ class AnalyticalLayerLoader:
|
||||
return self.df_clean
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# STEP 6: DETERMINE SDG START YEAR & ASSIGN FRAMEWORK PER ROW
|
||||
# STEP 6: DETERMINE SDG START YEAR & ASSIGN FRAMEWORK (ROW-LEVEL FIX)
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def determine_sdg_start_year(self):
|
||||
self.logger.info("\n" + "=" * 80)
|
||||
self.logger.info("STEP 6: DETERMINE SDG START YEAR & ASSIGN FRAMEWORK PER ROW")
|
||||
self.logger.info("STEP 6: DETERMINE SDG START YEAR & ASSIGN FRAMEWORK (ROW-LEVEL)")
|
||||
self.logger.info("=" * 80)
|
||||
self.logger.info(
|
||||
" Proxy: FIES only (food insecurity/food insecure).\n"
|
||||
" Anemia TIDAK dipakai sebagai proxy — datanya ada sebelum era SDGs.\n"
|
||||
" Framework di-assign PER BARIS (year), bukan per indikator."
|
||||
)
|
||||
|
||||
# actual_start_year per indikator = max(min_year per country)
|
||||
# = konsisten dengan max_start_year di Step 5
|
||||
@@ -583,7 +541,7 @@ class AnalyticalLayerLoader:
|
||||
)
|
||||
indicator_actual_start.columns = ['indicator_id', 'indicator_name', 'actual_start_year']
|
||||
|
||||
# Deteksi sdg_start_year dari proxy SDGs-only (FIES saja, BUKAN anemia)
|
||||
# Deteksi sdg_start_year dari proxy SDGs-only (FIES & anaemia)
|
||||
proxy_mask = indicator_actual_start['indicator_name'].str.lower().apply(
|
||||
lambda n: any(kw in n for kw in _SDG_ERA_PROXY_KEYWORDS)
|
||||
)
|
||||
@@ -591,78 +549,71 @@ class AnalyticalLayerLoader:
|
||||
|
||||
if df_proxy.empty:
|
||||
raise ValueError(
|
||||
"Tidak ada indikator proxy SDGs (FIES) yang lolos filter. "
|
||||
"Pastikan indikator FIES (food insecurity/food insecure) ada di data."
|
||||
"Tidak ada indikator proxy SDGs (FIES/anaemia) yang lolos filter. "
|
||||
"Pastikan indikator FIES dan anaemia ada di data."
|
||||
)
|
||||
|
||||
self.sdg_start_year = int(df_proxy['actual_start_year'].min())
|
||||
self.logger.info(f"\n sdg_start_year = {self.sdg_start_year}")
|
||||
self.logger.info(f" Proxy indicators (FIES only):")
|
||||
self.logger.info(f" Proxy indicators (penentu sdg_start_year):")
|
||||
for _, row in df_proxy.iterrows():
|
||||
self.logger.info(f" [{int(row['actual_start_year'])}] {row['indicator_name']}")
|
||||
|
||||
# ----------------------------------------------------------------
|
||||
# Assign framework PER BARIS menggunakan year baris, bukan actual_start_year
|
||||
# Sehingga indikator "shared" (anemia, stunting, dll) mendapat:
|
||||
# - 'MDGs' untuk baris sebelum sdg_start_year
|
||||
# - 'SDGs' untuk baris sejak sdg_start_year
|
||||
# ----------------------------------------------------------------
|
||||
# ------------------------------------------------------------------
|
||||
# FIX: Assign framework PER BARIS (per tahun), bukan per indikator
|
||||
# ------------------------------------------------------------------
|
||||
# Logic:
|
||||
# row['year'] < sdg_start_year → 'MDGs' (apapun nama indikatornya)
|
||||
# row['year'] >= sdg_start_year + nama di SDG_INDICATOR_KEYWORDS → 'SDGs'
|
||||
# selain itu → 'MDGs'
|
||||
# ------------------------------------------------------------------
|
||||
self.logger.info(f"\n Assigning framework PER ROW (year-level)...")
|
||||
self.logger.info(f" Rule: year < {self.sdg_start_year} → MDGs (always)")
|
||||
self.logger.info(f" Rule: year >= {self.sdg_start_year} + name in SDG list → SDGs")
|
||||
self.logger.info(f" Rule: year >= {self.sdg_start_year} + name NOT in SDG list → MDGs")
|
||||
|
||||
self.df_clean['framework'] = self.df_clean.apply(
|
||||
lambda row: assign_framework_per_row(
|
||||
lambda row: assign_framework_for_row(
|
||||
indicator_name = row['indicator_name'],
|
||||
year = int(row['year']),
|
||||
row_year = int(row['year']),
|
||||
sdg_start_year = self.sdg_start_year,
|
||||
),
|
||||
axis=1
|
||||
)
|
||||
|
||||
# ----------------------------------------------------------------
|
||||
# Logging: ringkasan per indikator (frameworks apa yang muncul)
|
||||
# ----------------------------------------------------------------
|
||||
ind_fw_summary = (
|
||||
self.df_clean
|
||||
.groupby(['indicator_id', 'indicator_name'])['framework']
|
||||
.unique()
|
||||
.reset_index()
|
||||
)
|
||||
ind_fw_summary['frameworks'] = ind_fw_summary['framework'].apply(
|
||||
lambda x: '/'.join(sorted(x))
|
||||
)
|
||||
ind_fw_summary = ind_fw_summary.merge(
|
||||
indicator_actual_start[['indicator_id', 'actual_start_year']],
|
||||
on='indicator_id', how='left'
|
||||
)
|
||||
|
||||
self.logger.info(f"\n Framework assignment per indikator:")
|
||||
self.logger.info(f" {'-'*85}")
|
||||
self.logger.info(f" {'ID':<5} {'Frameworks':<18} {'ActualStart':<13} {'Indicator Name'}")
|
||||
self.logger.info(f" {'-'*85}")
|
||||
for _, row in ind_fw_summary.sort_values(
|
||||
['frameworks', 'actual_start_year', 'indicator_name']
|
||||
).iterrows():
|
||||
# Log ringkasan per indikator untuk verifikasi
|
||||
self.logger.info(f"\n {'Framework Assignment per Indicator (sample)':}")
|
||||
self.logger.info(f" {'-'*95}")
|
||||
self.logger.info(
|
||||
f" {int(row['indicator_id']):<5} {row['frameworks']:<18} "
|
||||
f"{int(row['actual_start_year']):<13} {row['indicator_name'][:48]}"
|
||||
f" {'ID':<5} {'Indicator Name':<50} "
|
||||
f"{'Pre-SDG rows':<15} {'MDGs rows':<12} {'SDGs rows'}"
|
||||
)
|
||||
self.logger.info(f" {'-'*95}")
|
||||
|
||||
# Indikator dengan framework split (MDGs/SDGs) — highlight untuk validasi
|
||||
split_inds = ind_fw_summary[ind_fw_summary['frameworks'] == 'MDGs/SDGs']
|
||||
if not split_inds.empty:
|
||||
for ind_id, grp in self.df_clean.groupby('indicator_id'):
|
||||
ind_name = grp['indicator_name'].iloc[0]
|
||||
pre_sdg = (grp['year'] < self.sdg_start_year).sum()
|
||||
mdgs_rows = (grp['framework'] == 'MDGs').sum()
|
||||
sdgs_rows = (grp['framework'] == 'SDGs').sum()
|
||||
self.logger.info(
|
||||
f"\n [INFO] {len(split_inds)} indikator memiliki framework split "
|
||||
f"(MDGs sebelum {self.sdg_start_year}, SDGs sejak {self.sdg_start_year}):"
|
||||
f" {int(ind_id):<5} {ind_name[:48]:<50} "
|
||||
f"{pre_sdg:<15} {mdgs_rows:<12} {sdgs_rows}"
|
||||
)
|
||||
for _, row in split_inds.iterrows():
|
||||
self.logger.info(f" - {row['indicator_name'][:60]}")
|
||||
|
||||
fw_summary = self.df_clean['framework'].value_counts()
|
||||
self.logger.info(
|
||||
f"\n Ringkasan rows: " +
|
||||
" | ".join(f"{fw}: {cnt:,}" for fw, cnt in fw_summary.items())
|
||||
)
|
||||
self.logger.info(f"\n Ringkasan rows: " + " | ".join(
|
||||
f"{fw}: {cnt:,}" for fw, cnt in fw_summary.items()
|
||||
))
|
||||
|
||||
# Ringkasan unique indicators per framework di tahun terbaru (end_year)
|
||||
end_year_df = self.df_clean[self.df_clean['year'] == self.end_year]
|
||||
fw_ind_summary = end_year_df.groupby('framework')['indicator_id'].nunique()
|
||||
self.logger.info(f" Indicators di year={self.end_year}: " + " | ".join(
|
||||
f"{fw}: {cnt}" for fw, cnt in fw_ind_summary.items()
|
||||
))
|
||||
|
||||
self.logger.info(
|
||||
f"\n [OK] 'framework' ditambahkan per row — "
|
||||
f"\n [OK] 'framework' ditambahkan (row-level) — "
|
||||
f"MDGs: {(self.df_clean['framework'] == 'MDGs').sum():,} rows | "
|
||||
f"SDGs: {(self.df_clean['framework'] == 'SDGs').sum():,} rows"
|
||||
)
|
||||
@@ -700,7 +651,7 @@ class AnalyticalLayerLoader:
|
||||
return True
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# STEP 8: CALCULATE NORM_VALUE_1_100 PER INDICATOR
|
||||
# STEP 8: CALCULATE NORM_VALUE_1_100 PER INDICATOR PER COUNTRY
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def calculate_norm_value(self):
|
||||
@@ -862,45 +813,40 @@ class AnalyticalLayerLoader:
|
||||
'start_year', 'end_year', 'country_count'
|
||||
]
|
||||
|
||||
# Framework summary per indikator (bisa MDGs, SDGs, atau MDGs/SDGs split)
|
||||
ind_fw = (
|
||||
self.df_clean
|
||||
# Framework per indikator di end_year (untuk display — representasi terbaru)
|
||||
fw_at_end = (
|
||||
self.df_clean[self.df_clean['year'] == self.end_year]
|
||||
.groupby('indicator_id')['framework']
|
||||
.unique()
|
||||
.first()
|
||||
.reset_index()
|
||||
)
|
||||
ind_fw['framework_label'] = ind_fw['framework'].apply(
|
||||
lambda x: '/'.join(sorted(x))
|
||||
)
|
||||
indicator_details = indicator_details.merge(
|
||||
ind_fw[['indicator_id', 'framework_label']],
|
||||
on='indicator_id', how='left'
|
||||
)
|
||||
indicator_details = indicator_details.merge(fw_at_end, on='indicator_id', how='left')
|
||||
indicator_details['framework'] = indicator_details['framework'].fillna('MDGs')
|
||||
|
||||
indicator_details['year_range'] = (
|
||||
indicator_details['start_year'].astype(int).astype(str) + '-' +
|
||||
indicator_details['end_year'].astype(int).astype(str)
|
||||
)
|
||||
indicator_details = indicator_details.sort_values(
|
||||
['framework_label', 'pillar_name', 'start_year', 'indicator_name']
|
||||
['framework', 'pillar_name', 'start_year', 'indicator_name']
|
||||
)
|
||||
|
||||
self.logger.info(f"\nTotal Indicators: {len(indicator_details)}")
|
||||
self.logger.info(f"Framework breakdown (per indicator label):")
|
||||
for fw, count in indicator_details.groupby('framework_label').size().items():
|
||||
self.logger.info(f"Framework breakdown (at end_year={self.end_year}):")
|
||||
for fw, count in indicator_details.groupby('framework').size().items():
|
||||
self.logger.info(f" {fw}: {count} indicators")
|
||||
|
||||
self.logger.info(f"\n{'-'*115}")
|
||||
self.logger.info(f"\n{'-'*110}")
|
||||
self.logger.info(
|
||||
f"{'ID':<5} {'Indicator Name':<55} {'Pillar':<15} "
|
||||
f"{'Framework':<15} {'Years':<12} {'Dir':<8} {'Countries'}"
|
||||
f"{'Framework':<10} {'Years':<12} {'Dir':<8} {'Countries'}"
|
||||
)
|
||||
self.logger.info(f"{'-'*115}")
|
||||
self.logger.info(f"{'-'*110}")
|
||||
for _, row in indicator_details.iterrows():
|
||||
direction = 'higher+' if row['direction'] == 'higher_better' else 'lower-'
|
||||
self.logger.info(
|
||||
f"{int(row['indicator_id']):<5} {row['indicator_name'][:52]:<55} "
|
||||
f"{row['pillar_name'][:13]:<15} {row['framework_label']:<15} "
|
||||
f"{row['pillar_name'][:13]:<15} {row['framework']:<10} "
|
||||
f"{row['year_range']:<12} {direction:<8} {int(row['country_count'])}"
|
||||
)
|
||||
|
||||
@@ -969,16 +915,14 @@ class AnalyticalLayerLoader:
|
||||
for fw, cnt in fw_dist_rows.items():
|
||||
self.logger.info(f" {fw}: {cnt:,} rows")
|
||||
|
||||
# Framework distribution per indikator (label)
|
||||
ind_fw_label = (
|
||||
analytical_df
|
||||
.groupby('indicator_id')['framework']
|
||||
.unique()
|
||||
.apply(lambda x: '/'.join(sorted(x)))
|
||||
# Framework distribution per unique indicator (at end_year)
|
||||
fw_dist_ind = (
|
||||
analytical_df[analytical_df['year'] == self.end_year]
|
||||
.drop_duplicates('indicator_id')['framework']
|
||||
.value_counts()
|
||||
)
|
||||
self.logger.info(f" Framework distribution (per indicator label):")
|
||||
for fw, cnt in ind_fw_label.items():
|
||||
self.logger.info(f" Framework distribution (indicators at year={self.end_year}):")
|
||||
for fw, cnt in fw_dist_ind.items():
|
||||
self.logger.info(f" {fw}: {cnt} indicators")
|
||||
|
||||
self.logger.info(
|
||||
@@ -1028,9 +972,8 @@ class AnalyticalLayerLoader:
|
||||
'sdg_start_year' : self.sdg_start_year,
|
||||
'fixed_countries' : len(self.selected_country_ids),
|
||||
'norm_scale' : '1-100 per indicator global minmax direction-aware',
|
||||
'framework_assignment' : 'per-row by year (not per-indicator)',
|
||||
'sdg_proxy_keywords' : list(_SDG_ERA_PROXY_KEYWORDS),
|
||||
'condition_thresholds' : {
|
||||
'framework_logic' : 'row-level: year < sdg_start_year → MDGs always',
|
||||
'condition_thresholds': {
|
||||
'bad' : f'< {THRESHOLD_BAD}',
|
||||
'moderate': f'{THRESHOLD_BAD}-{THRESHOLD_GOOD}',
|
||||
'good' : f'> {THRESHOLD_GOOD}',
|
||||
@@ -1038,10 +981,9 @@ class AnalyticalLayerLoader:
|
||||
}),
|
||||
'validation_metrics' : json.dumps({
|
||||
'fixed_countries' : len(self.selected_country_ids),
|
||||
'total_indicators' : int(self.df_clean['indicator_id'].nunique()),
|
||||
'total_indicators': int(self.df_clean['indicator_id'].nunique()),
|
||||
'sdg_start_year' : self.sdg_start_year,
|
||||
'framework_dist_rows' : fw_dist_rows.to_dict(),
|
||||
'framework_dist_inds' : ind_fw_label.to_dict(),
|
||||
'framework_dist_rows': fw_dist_rows.to_dict(),
|
||||
})
|
||||
}
|
||||
save_etl_metadata(self.client, metadata)
|
||||
@@ -1064,9 +1006,8 @@ class AnalyticalLayerLoader:
|
||||
self.logger.info("\n" + "=" * 80)
|
||||
self.logger.info("Output: fact_asean_food_security_selected -> fs_asean_gold")
|
||||
self.logger.info("Kolom baru: norm_value_1_100 (min-max 1-100, direction-aware)")
|
||||
self.logger.info("Framework: per-row by year (shared indicators split MDGs/SDGs)")
|
||||
self.logger.info(f"SDG Proxy: FIES only (food insecurity/food insecure)")
|
||||
self.logger.info(f"Condition threshold: bad<{THRESHOLD_BAD}, good>{THRESHOLD_GOOD}")
|
||||
self.logger.info("Framework: row-level (year < sdg_start_year → MDGs always)")
|
||||
self.logger.info("=" * 80)
|
||||
|
||||
self.load_source_data()
|
||||
@@ -1074,7 +1015,7 @@ class AnalyticalLayerLoader:
|
||||
self.filter_complete_indicators_per_country()
|
||||
self.select_countries_with_all_pillars()
|
||||
self.filter_indicators_consistent_across_fixed_countries()
|
||||
self.determine_sdg_start_year() # Step 6: per-row framework assignment
|
||||
self.determine_sdg_start_year()
|
||||
self.verify_no_gaps()
|
||||
self.calculate_norm_value() # Step 8: norm_value_1_100
|
||||
self.calculate_yoy() # Step 9: yoy_change, yoy_pct
|
||||
@@ -1116,8 +1057,8 @@ if __name__ == "__main__":
|
||||
print("BIGQUERY ANALYTICAL LAYER - DATA FILTERING")
|
||||
print("Output: fact_asean_food_security_selected -> fs_asean_gold")
|
||||
print(f"Norm: min-max 1-100 per indicator, direction-aware")
|
||||
print(f"Framework: per-row by year | SDG Proxy: FIES only")
|
||||
print(f"Condition threshold: bad<{THRESHOLD_BAD}, good>{THRESHOLD_GOOD}")
|
||||
print(f"Framework: row-level (year < sdg_start_year → MDGs always)")
|
||||
print("=" * 80)
|
||||
|
||||
logger = setup_logging()
|
||||
|
||||
Reference in New Issue
Block a user