move path into config

climateqa/engine/talk_to_data/config.py

@@ -0,0 +1,11 @@
+# Path configuration for climateqa project
+
+# IPCC dataset path
+IPCC_DATASET_URL = "hf://datasets/ekimetrics/ipcc-atlas"
+
+# DRIAS dataset paths
+DRIAS_DATASET_URL = "hf://datasets/timeki/drias_db"
+
+# Table paths
+DRIAS_MEAN_ANNUAL_TEMPERATURE_PATH = f"{DRIAS_DATASET_URL}/mean_annual_temperature.parquet"
+IPCC_COORDINATES_PATH = f"{IPCC_DATASET_URL}/coordinates.parquet"

climateqa/engine/talk_to_data/drias/queries.py

@@ -1,4 +1,5 @@
 from typing import TypedDict
+from climateqa.engine.talk_to_data.config import DRIAS_DATASET_URL
 
 class IndicatorPerYearAtLocationQueryParams(TypedDict, total=False):
     """Parameters for querying an indicator's values over time at a location.
@@ -36,7 +37,7 @@ def indicator_per_year_at_location_query(
     if indicator_column is None or latitude is None or longitude is None: # If one parameter is missing, returns an empty query
         return ""
     
-    table = f"'hf://datasets/timeki/drias_db/{table.lower()}.parquet'"
+    table = f"'{DRIAS_DATASET_URL}/{table.lower()}.parquet'"
 
     sql_query = f"SELECT year, {indicator_column}, model\nFROM {table}\nWHERE latitude = {latitude} \nAnd longitude = {longitude} \nOrder by Year"
 
@@ -76,7 +77,7 @@ def indicator_for_given_year_query(
     if year is None or indicator_column is None: # If one parameter is missing, returns an empty query
         return ""
     
-    table = f"'hf://datasets/timeki/drias_db/{table.lower()}.parquet'"
+    table = f"'{DRIAS_DATASET_URL}/{table.lower()}.parquet'"
 
     sql_query = f"Select {indicator_column}, latitude, longitude, model\nFrom {table}\nWhere year = {year}"
     return sql_query    

climateqa/engine/talk_to_data/input_processing.py

@@ -5,7 +5,7 @@ from geopy.geocoders import Nominatim
 from climateqa.engine.llm import get_llm
 import duckdb
 import os 
-from climateqa.engine.talk_to_data.ipcc.config import IPCC_DATASET_URL
+from climateqa.engine.talk_to_data.config import DRIAS_MEAN_ANNUAL_TEMPERATURE_PATH, IPCC_COORDINATES_PATH
 from climateqa.engine.talk_to_data.objects.llm_outputs import ArrayOutput
 from climateqa.engine.talk_to_data.objects.location import Location
 from climateqa.engine.talk_to_data.objects.plot import Plot
@@ -78,12 +78,12 @@ def nearest_neighbour_sql(location: tuple, mode: Literal['DRIAS', 'IPCC']) -> tu
     conn = duckdb.connect()
 
     if mode == 'DRIAS':
-        table_path = f"'hf://datasets/timeki/drias_db/mean_annual_temperature.parquet'"
+        table_path = f"'{DRIAS_MEAN_ANNUAL_TEMPERATURE_PATH}'"
         results = conn.sql(
             f"SELECT latitude, longitude FROM {table_path} WHERE latitude BETWEEN {lat - 0.3} AND {lat + 0.3} AND longitude BETWEEN {long - 0.3} AND {long + 0.3}"
         ).fetchdf()
     else:
-        table_path = f"'{IPCC_DATASET_URL}/coordinates.parquet'"
+        table_path = f"'{IPCC_COORDINATES_PATH}'"
         results = conn.sql(
             f"SELECT latitude, longitude, admin1 FROM {table_path} WHERE latitude BETWEEN {lat - 0.5} AND {lat + 0.5} AND longitude BETWEEN {long - 0.5} AND {long + 0.5}"
         ).fetchdf()

climateqa/engine/talk_to_data/ipcc/config.py

@@ -1,7 +1,8 @@
 from climateqa.engine.talk_to_data.ui_config import PRECIPITATION_COLORSCALE, TEMPERATURE_COLORSCALE
+from climateqa.engine.talk_to_data.config import IPCC_DATASET_URL
 
 
-IPCC_DATASET_URL = "hf://datasets/ekimetrics/ipcc-atlas"
+# IPCC_DATASET_URL = "hf://datasets/ekimetrics/ipcc-atlas"
 IPCC_TABLES = [
     "mean_temperature",
     "total_precipitation",

climateqa/engine/talk_to_data/ipcc/queries.py

@@ -1,7 +1,7 @@
 from typing import TypedDict, Optional
 
-from climateqa.engine.talk_to_data.ipcc.config import HUGE_MACRO_COUNTRIES, IPCC_DATASET_URL, MACRO_COUNTRIES
-
+from climateqa.engine.talk_to_data.ipcc.config import HUGE_MACRO_COUNTRIES, MACRO_COUNTRIES
+from climateqa.engine.talk_to_data.config import IPCC_DATASET_URL
 class IndicatorPerYearAtLocationQueryParams(TypedDict, total=False):
     """
     Parameters for querying the evolution of an indicator per year at a specific location.