adding year as variable

.envrc

@@ -0,0 +1,3 @@
+source venv/bin/activate
+dotenv
+export PASSWORD=VA.TlSR#Z%mu**Q9

Makefile

@@ -38,6 +38,6 @@ api-container-push:
 	docker push us-east1-docker.pkg.dev/cities-429602/cities/cities-api
 
 run-api-local:
-	sudo -E docker run --rm -it -e PORT=8081 -e PASSWORD -p 3001:8081 cities-api
+	docker run --rm -it -e PORT=8081 -e PASSWORD -p 3001:8081 cities-api
 
 FORCE:

api/Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3
+FROM python:3.12
 
 WORKDIR /usr/src/app
 

api/main.py

@@ -197,37 +197,34 @@ async def read_blue_zone(year: Year, radius: Radius, db=Depends(get_db)):
         ],
     }
 
-
 @app.get("/predict")
 async def read_predict(
-    blue_zone_radius: Radius,
-    yellow_zone_line_radius: Radius,
-    yellow_zone_stop_radius: Radius,
-    blue_zone_limit: Limit,
-    yellow_zone_limit: Limit,
-    year: Year,
-    db=Depends(get_db),
-    predictor=Depends(get_predictor),
-):
-    result = predictor.predict_cumulative(
+        blue_zone_radius: Radius,
+        yellow_zone_line_radius: Radius,
+        yellow_zone_stop_radius: Radius,
+        blue_zone_limit: Limit,
+        yellow_zone_limit: Limit,
+        year: Year,
+        db=Depends(get_db),
+        predictor=Depends(get_predictor),
+    ):
+
+    result = predictor.predict_cumulative_by_year(
         db,
-        intervention=(
-            {
-                "radius_blue": blue_zone_radius,
-                "limit_blue": blue_zone_limit,
-                "radius_yellow_line": yellow_zone_line_radius,
-                "radius_yellow_stop": yellow_zone_stop_radius,
-                "limit_yellow": yellow_zone_limit,
-                "reform_year": year,
-            }
-        ),
+        intervention={
+            "radius_blue": blue_zone_radius,
+            "limit_blue": blue_zone_limit,
+            "radius_yellow_line": yellow_zone_line_radius,
+            "radius_yellow_stop": yellow_zone_stop_radius,
+            "limit_yellow": yellow_zone_limit,
+            "reform_year": year,
+        },
     )
     return {
         "census_tracts": [str(t) for t in result["census_tracts"]],
-        "housing_units_factual": [t.item() for t in result["housing_units_factual"]],
-        "housing_units_counterfactual": [
-            t.tolist() for t in result["housing_units_counterfactual"]
-        ],
+        "years": result["years"],
+        "housing_units_factual": result["housing_units_factual"],
+        "housing_units_counterfactual": result["housing_units_counterfactual"],
     }
 
 

cities/deployment/tracts_minneapolis/predict.py

@@ -161,14 +161,15 @@ def _tracts_intervention(
             TractsModelPredictor.tracts_intervention_sql, conn, params=params
         )
         return torch.tensor(df["intervention"].values, dtype=torch.float32)
-
-    def predict_cumulative(self, conn, intervention):
-        """Predict the total number of housing units built from 2011-2020 under intervention.
+    
+    def predict_cumulative_by_year(self, conn, intervention):
+        """Predict the cumulative number of housing units built from 2011-2019 under intervention, by year.
 
         Returns a dictionary with keys:
         - 'census_tracts': the tracts considered
-        - 'housing_units_factual': total housing units built according to real housing data
-        - 'housing_units_counterfactual': samples from prediction of total housing units built
+        - 'years': the years considered (2011-2019)
+        - 'housing_units_factual': cumulative housing units built according to real housing data, by year
+        - 'housing_units_counterfactual': samples from prediction of cumulative housing units built, by year
         """
         pyro.clear_param_store()
         pyro.get_param_store().load(self.param_path)
@@ -191,38 +192,49 @@ def predict_cumulative(self, conn, intervention):
         f_housing_units = self.data["continuous"]["housing_units_original"]
         cf_housing_units = result * self.housing_units_std + self.housing_units_mean
 
-        # calculate cumulative housing units (factual)
-        f_totals = {}
-        for i in range(tracts.shape[0]):
-            key = tracts[i].item()
-            if key not in f_totals:
-                f_totals[key] = 0
-            f_totals[key] += f_housing_units[i]
+        # Organize cumulative data by year and tract
+        f_data = {}
+        cf_data = {}
+        unique_years = sorted(set(years.tolist()))
+        unique_years = [year for year in unique_years if year <= 2019]  # Exclude years after 2019
+        unique_tracts = sorted(set(tracts.tolist()))
+
+        for year in unique_years:
+            f_data[year] = {tract: 0 for tract in unique_tracts}
+            cf_data[year] = {tract: [0] * 100 for tract in unique_tracts}
 
-        # calculate cumulative housing units (counterfactual)
-        cf_totals = {}
         for i in range(tracts.shape[0]):
             year = years[i].item()
-            key = tracts[i].item()
-            if key not in cf_totals:
-                cf_totals[key] = 0
+            if year > 2019:
+                continue  # Skip data for years after 2019
+            tract = tracts[i].item()
+
+            # Update factual data
+            for y in unique_years:
+                if y >= year:
+                    f_data[y][tract] += f_housing_units[i].item()
+
+            # Update counterfactual data
             if year < intervention["reform_year"]:
-                cf_totals[key] += f_housing_units[i]
+                for y in unique_years:
+                    if y >= year:
+                        cf_data[y][tract] = [x + f_housing_units[i].item() for x in cf_data[y][tract]]
             else:
-                cf_totals[key] = cf_totals[key] + cf_housing_units[:, i]
-        cf_totals = {k: torch.clamp(v, 0) for k, v in cf_totals.items()}
+                for y in unique_years:
+                    if y >= year:
+                        cf_data[y][tract] = [x + y for x, y in zip(cf_data[y][tract], cf_housing_units[:, i].tolist())]
 
-        census_tracts = list(cf_totals.keys())
-        f_housing_units = [f_totals[k] for k in census_tracts]
-        cf_housing_units = [cf_totals[k] for k in census_tracts]
+        # Convert to lists for easier JSON serialization
+        housing_units_factual = [[f_data[year][tract] for tract in unique_tracts] for year in unique_years]
+        housing_units_counterfactual = [[cf_data[year][tract] for tract in unique_tracts] for year in unique_years]
 
         return {
-            "census_tracts": census_tracts,
-            "housing_units_factual": f_housing_units,
-            "housing_units_counterfactual": cf_housing_units,
+            "census_tracts": unique_tracts,
+            "years": unique_years,
+            "housing_units_factual": housing_units_factual,
+            "housing_units_counterfactual": housing_units_counterfactual,
         }
 
-
 if __name__ == "__main__":
     import time