add more data sources

curated.py

@@ -9,7 +9,7 @@ data_sources = [
     "Arxiv",
     "S2ORC",
     "S2ORC Abstract",
-    "Pubmeds",
+    "Pubmed",
     "USPTO",
     "Hackernews",
     "Ubuntu IRC",
@@ -54,6 +54,24 @@ def get_data(data_source: str = "Freelaw", doc_id: int = 3):
         raw_sample_doc = extracted_sample_doc = json.load(
             open("data/curated_samples/s2orc_abstract_raw.json")
         )
+    elif data_source == "Pubmed":
+        raw_sample_doc = json.load(open("data/curated_samples/pubmed_raw.json"))
+        extracted_sample_doc = json.load(
+            open("data/curated_samples/pubmed_extract.json")
+        )
+    elif data_source == "DM Maths":
+        raw_sample_doc = json.load(open("data/curated_samples/dm_maths_raw.json"))
+        extracted_sample_doc = json.load(
+            open("data/curated_samples/dm_maths_extract.json")
+        )
+    elif data_source == "PG19":
+        raw_sample_doc = extracted_sample_doc = json.load(
+            open("data/curated_samples/pg19_raw.json")
+        )
+    elif data_source == "Europarl":
+        raw_sample_doc = extracted_sample_doc = json.load(
+            open("data/curated_samples/europarl_raw.json")
+        )
     else:
         raw_sample_doc = extracted_sample_doc = [{} for _ in range(10)]
 

main.py

@@ -357,11 +357,11 @@ def curated(request):
 
     return Div(
         Section(
-            H1("Curated Sources"),
+            H2("Curated Sources"),
             plotly2fasthtml(get_chart_28168342()),
-            H2("Data Preparation"),
+            H3("Data Preparation"),
             table_div,
-            H2("Data Preprocessing"),
+            H3("Data Preprocessing"),
             expander,
             id="inner-text",
         )