Publish partner pool simulator space

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 7860
+
+CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.headless=true"]

README.md

@@ -1,10 +1,18 @@
 ---
-title: Partner-Pool-Simulator 05-2026
-emoji: 📚
+title: Partner Pool Simulator 05-2026
+emoji: 📊
 colorFrom: blue
-colorTo: yellow
+colorTo: green
 sdk: docker
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Partner Pool Assumption Simulator
+
+Transparent Streamlit prototype for `S7-K · Personal Relationship`.
+
+This Space is a public demo for estimating how relationship criteria narrow an assumed demographic pool. Current coefficients are demo assumptions and must not be interpreted as factual population counts.
+
+Source study:
+
+- [K-RnD-Lab / SPHERE-I-SCIENCE](https://github.com/K-RnD-Lab/SPHERE-I-SCIENCE/tree/main/S7%20%E2%80%94%20%F0%9F%93%9A%20K%20Life%20OS/S7-K%20%C2%B7%20%F0%9F%91%A5%20Personal%20Relationship/R1a-partner-pool-assumption-simulator)

app.py

@@ -0,0 +1,100 @@
+from __future__ import annotations
+
+import pandas as pd
+import plotly.express as px
+import streamlit as st
+
+from src.assumptions import BASELINE, DATA_QUALITY_NOTES
+from src.model_pool import Criteria, estimate_pool, sensitivity_table
+
+
+st.set_page_config(
+    page_title="Partner Pool Assumption Simulator",
+    page_icon="S7",
+    layout="wide",
+)
+
+st.title("Partner Pool Assumption Simulator")
+st.caption("S7-K · Personal Relationship · transparent demo model")
+
+st.info(
+    "Prototype status: current numbers are demo assumptions. Use this app to test model logic, "
+    "not to claim a factual count of available partners."
+)
+
+with st.sidebar:
+    st.header("Scenario")
+    base_population = st.number_input(
+        "Baseline population",
+        min_value=10_000,
+        max_value=50_000_000,
+        value=BASELINE.total_reference_population,
+        step=50_000,
+    )
+    age_min, age_max = st.slider("Age range", 18, 70, (28, 42))
+    region_scope = st.selectbox(
+        "Region scope",
+        ["all_ukraine", "large_cities", "kyiv_region", "western_regions"],
+        format_func=lambda value: value.replace("_", " ").title(),
+    )
+    relationship_status = st.selectbox(
+        "Relationship status",
+        ["any", "not_married", "single_or_divorced"],
+        format_func=lambda value: value.replace("_", " ").title(),
+    )
+    min_height = st.slider("Minimum height, cm", 150, 205, 175)
+    income_level = st.selectbox(
+        "Income threshold",
+        ["any", "above_median", "top_25", "top_10"],
+        format_func=lambda value: value.replace("_", " ").title(),
+    )
+    education_level = st.selectbox(
+        "Education filter",
+        ["any", "higher_education", "graduate_plus"],
+        format_func=lambda value: value.replace("_", " ").title(),
+    )
+
+criteria = Criteria(
+    base_population=base_population,
+    age_min=age_min,
+    age_max=age_max,
+    region_scope=region_scope,
+    relationship_status=relationship_status,
+    min_height_cm=min_height,
+    income_level=income_level,
+    education_level=education_level,
+)
+
+estimate = estimate_pool(criteria)
+steps = sensitivity_table(criteria)
+
+col_a, col_b, col_c = st.columns(3)
+col_a.metric("Conservative estimate", f"{estimate.conservative:,.0f}")
+col_b.metric("Central estimate", f"{estimate.central:,.0f}")
+col_c.metric("Optimistic estimate", f"{estimate.optimistic:,.0f}")
+
+st.subheader("What narrows the pool")
+step_df = pd.DataFrame(steps)
+fig = px.bar(
+    step_df,
+    x="factor",
+    y="remaining",
+    text="remaining",
+    title="Remaining estimated pool after each criterion",
+)
+fig.update_traces(texttemplate="%{text:,.0f}", textposition="outside")
+fig.update_layout(yaxis_title="Estimated remaining pool", xaxis_title="")
+st.plotly_chart(fig, use_container_width=True)
+
+st.subheader("Scenario details")
+st.dataframe(step_df, use_container_width=True, hide_index=True)
+
+st.subheader("Data quality notes")
+for note in DATA_QUALITY_NOTES:
+    st.write(f"- **{note['label']}**: {note['note']}")
+
+st.subheader("Interpretation guardrails")
+st.write(
+    "This model estimates a demographic scenario, not compatibility, attraction, safety, or relationship success. "
+    "A stricter filter can make a pool smaller, but it does not define a person's real-life chances."
+)

data/sources.yml

@@ -0,0 +1,59 @@
+sources:
+  - id: ukraine_nowpop
+    name: Ukraine NowPop
+    url: https://nowpop.org/
+    use_for:
+      - population_by_age_sex_region
+    status: candidate
+    confidence: medium
+    notes: Current population estimates should be reviewed for license, geographic granularity, and update cadence.
+
+  - id: ukrstat
+    name: State Statistics Service of Ukraine
+    url: https://stat.gov.ua/
+    use_for:
+      - baseline_demography
+      - wages
+      - social_indicators
+    status: candidate
+    confidence: medium
+    notes: Official source, but some demographic series may lag wartime mobility.
+
+  - id: ministry_of_justice_marriage
+    name: Ministry of Justice marriage and divorce administrative data
+    url: https://minjust.gov.ua/
+    use_for:
+      - marriages
+      - divorces
+    status: candidate
+    confidence: medium
+    notes: Useful for flow indicators, not a direct measure of single or available population.
+
+  - id: opendatabot_marriage_divorce
+    name: Opendatabot marriage/divorce analytics
+    url: https://opendatabot.ua/
+    use_for:
+      - public_context
+      - administrative_data_summary
+    status: candidate
+    confidence: low_to_medium
+    notes: Aggregated public analytics; validate against primary Ministry of Justice releases before using in model coefficients.
+
+  - id: ncd_risc_height
+    name: NCD Risk Factor Collaboration anthropometric data
+    url: https://ncdrisc.org/
+    use_for:
+      - height_distribution_proxy
+    status: candidate_proxy
+    confidence: low
+    notes: Use only if Ukraine-specific height distribution is unavailable; label as proxy.
+
+  - id: world_bank_living_conditions
+    name: World Bank Ukraine living conditions updates
+    url: https://www.worldbank.org/en/country/ukraine
+    use_for:
+      - income_context
+      - living_conditions_context
+    status: candidate
+    confidence: medium
+    notes: Useful for context and uncertainty framing rather than direct demographic filtering.

requirements.txt

@@ -0,0 +1,4 @@
+streamlit>=1.35
+pandas>=2.2
+plotly>=5.22
+PyYAML>=6.0

src/__init__.py

@@ -0,0 +1 @@
+

src/assumptions.py

@@ -0,0 +1,76 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class BaselineAssumptions:
+    total_reference_population: int = 10_000_000
+    uncertainty_low: float = 0.72
+    uncertainty_high: float = 1.28
+
+
+BASELINE = BaselineAssumptions()
+
+AGE_BAND_FACTORS = {
+    "18-24": 0.12,
+    "25-34": 0.22,
+    "35-44": 0.20,
+    "45-54": 0.18,
+    "55-70": 0.28,
+}
+
+REGION_FACTORS = {
+    "all_ukraine": 1.0,
+    "large_cities": 0.34,
+    "kyiv_region": 0.13,
+    "western_regions": 0.24,
+}
+
+RELATIONSHIP_STATUS_FACTORS = {
+    "any": 1.0,
+    "not_married": 0.46,
+    "single_or_divorced": 0.32,
+}
+
+HEIGHT_FACTORS = {
+    160: 0.92,
+    165: 0.82,
+    170: 0.67,
+    175: 0.48,
+    180: 0.28,
+    185: 0.13,
+    190: 0.04,
+}
+
+INCOME_FACTORS = {
+    "any": 1.0,
+    "above_median": 0.42,
+    "top_25": 0.25,
+    "top_10": 0.10,
+}
+
+EDUCATION_FACTORS = {
+    "any": 1.0,
+    "higher_education": 0.38,
+    "graduate_plus": 0.16,
+}
+
+DATA_QUALITY_NOTES = [
+    {
+        "label": "Population",
+        "note": "Replace demo baseline with current age-sex population estimates before publication.",
+    },
+    {
+        "label": "Relationship status",
+        "note": "Official marital status does not equal real availability; label as estimated.",
+    },
+    {
+        "label": "Income",
+        "note": "Income and salary filters are sensitive to self-employment and informal earnings.",
+    },
+    {
+        "label": "Height",
+        "note": "Height currently requires proxy distribution unless a Ukraine-specific source is validated.",
+    },
+]

src/model_pool.py

@@ -0,0 +1,111 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+from .assumptions import (
+    AGE_BAND_FACTORS,
+    BASELINE,
+    EDUCATION_FACTORS,
+    HEIGHT_FACTORS,
+    INCOME_FACTORS,
+    REGION_FACTORS,
+    RELATIONSHIP_STATUS_FACTORS,
+)
+
+
+@dataclass(frozen=True)
+class Criteria:
+    base_population: int
+    age_min: int
+    age_max: int
+    region_scope: str
+    relationship_status: str
+    min_height_cm: int
+    income_level: str
+    education_level: str
+
+
+@dataclass(frozen=True)
+class PoolEstimate:
+    conservative: float
+    central: float
+    optimistic: float
+
+
+def age_factor(age_min: int, age_max: int) -> float:
+    bands = {
+        "18-24": (18, 24),
+        "25-34": (25, 34),
+        "35-44": (35, 44),
+        "45-54": (45, 54),
+        "55-70": (55, 70),
+    }
+    selected = 0.0
+    for label, (band_min, band_max) in bands.items():
+        overlap_min = max(age_min, band_min)
+        overlap_max = min(age_max, band_max)
+        if overlap_min <= overlap_max:
+            band_width = band_max - band_min + 1
+            overlap_width = overlap_max - overlap_min + 1
+            selected += AGE_BAND_FACTORS[label] * (overlap_width / band_width)
+    return max(0.01, min(selected, 1.0))
+
+
+def height_factor(min_height_cm: int) -> float:
+    thresholds = sorted(HEIGHT_FACTORS)
+    if min_height_cm <= thresholds[0]:
+        return HEIGHT_FACTORS[thresholds[0]]
+    if min_height_cm >= thresholds[-1]:
+        return HEIGHT_FACTORS[thresholds[-1]]
+
+    lower = max(threshold for threshold in thresholds if threshold <= min_height_cm)
+    upper = min(threshold for threshold in thresholds if threshold >= min_height_cm)
+    if lower == upper:
+        return HEIGHT_FACTORS[lower]
+
+    ratio = (min_height_cm - lower) / (upper - lower)
+    return HEIGHT_FACTORS[lower] + ratio * (HEIGHT_FACTORS[upper] - HEIGHT_FACTORS[lower])
+
+
+def model_factors(criteria: Criteria) -> list[tuple[str, float]]:
+    return [
+        ("Age range", age_factor(criteria.age_min, criteria.age_max)),
+        ("Region scope", REGION_FACTORS[criteria.region_scope]),
+        ("Relationship status", RELATIONSHIP_STATUS_FACTORS[criteria.relationship_status]),
+        ("Minimum height", height_factor(criteria.min_height_cm)),
+        ("Income threshold", INCOME_FACTORS[criteria.income_level]),
+        ("Education filter", EDUCATION_FACTORS[criteria.education_level]),
+    ]
+
+
+def central_estimate(criteria: Criteria) -> float:
+    value = float(criteria.base_population)
+    for _, factor in model_factors(criteria):
+        value *= factor
+    return value
+
+
+def estimate_pool(criteria: Criteria) -> PoolEstimate:
+    central = central_estimate(criteria)
+    return PoolEstimate(
+        conservative=central * BASELINE.uncertainty_low,
+        central=central,
+        optimistic=central * BASELINE.uncertainty_high,
+    )
+
+
+def sensitivity_table(criteria: Criteria) -> list[dict[str, float | str]]:
+    remaining = float(criteria.base_population)
+    rows: list[dict[str, float | str]] = [
+        {"factor": "Baseline", "coefficient": 1.0, "remaining": remaining}
+    ]
+    for label, coefficient in model_factors(criteria):
+        remaining *= coefficient
+        rows.append(
+            {
+                "factor": label,
+                "coefficient": round(coefficient, 4),
+                "remaining": round(remaining, 2),
+            }
+        )
+    return rows