undo experiment

data_access.py

@@ -19,16 +19,9 @@ def get_gdelt_data(
     con = duckdb.connect(database=':memory:')
 
     # Create view of the dataset
-    # con.execute("""
-    #     CREATE VIEW negative_tone AS (
-    #         SELECT * 
-    #         FROM read_parquet('hf://datasets/dwb2023/gdelt-gkg-march2020-v2@~parquet/default/negative_tone/*.parquet')
-    #     );
-    # """)
-
     con.execute("""
         CREATE VIEW negative_tone AS (
-            SELECT GKGRECORDID, SourceCollectionIdentifier, DATE, SourceCommonName, DocumentIdentifier, "V2.1Quotations", tone, V1Counts, "V2.1Counts", "V2.1Amounts", V1Themes, V2EnhancedThemes, V1Locations, V2EnhancedLocations, V1Persons, V2EnhancedPersons, V1Organizations, V2EnhancedOrganizations, "V2.1AllNames"
+            SELECT * 
             FROM read_parquet('hf://datasets/dwb2023/gdelt-gkg-march2020-v2@~parquet/default/negative_tone/*.parquet')
         );
     """)
@@ -44,7 +37,7 @@ def get_gdelt_data(
         "V1Locations IS NOT NULL",
         "V1Persons IS NOT NULL",
         "V1Organizations IS NOT NULL",
-        #"V2GCAM IS NOT NULL",
+        "V2GCAM IS NOT NULL",
         "\"V2.1Quotations\" IS NOT NULL",
         "tone <= ?"
     ]
@@ -120,6 +113,6 @@ GDELT_CATEGORIES = {
     "Names": ["V2.1AllNames"],
     "Counts": ["V2.1Counts", "V1Counts"],
     "Amounts": ["V2.1Amounts"],
-    #"V2GCAM": ["V2GCAM"],
+    "V2GCAM": ["V2GCAM"],
     "V2.1EnhancedDates": ["V2.1EnhancedDates"],
 }