Update curated.py

curated.py

@@ -514,6 +514,63 @@ freelaw_examples = Div(
     ),
 )
 
+def get_se_data(data_source: str = "StackExchange", doc_id: int = 3, target: str = "foo"):
+    doc_id = max(0, min(int(doc_id), 9))
+
+    if data_source == "StackExchange":
+        raw_sample_doc = json.load(open("data/curated_samples/stackexchange_raw.json"))
+        extracted_sample_doc = json.load(
+            open("data/curated_samples/stackexchange_extract.json")
+        )
+    else:
+        raw_sample_doc = extracted_sample_doc = [{} for _ in range(10)]
+
+    raw_json = raw_sample_doc[doc_id]
+    extracted_json = extracted_sample_doc[doc_id]
+    return view_data(
+        raw_json,
+        extracted_json,
+        doc_id=doc_id,
+        data_source="StackExchange",
+        data_sources="StackExchange",
+        target=target,
+    )
+
+se_examples = Div(
+    Div(
+        get_se_data(target=gen_random_id()),
+        style="border: 1px solid #ccc; padding: 20px;",
+    ),
+)
+
+def get_phil_data(data_source: str = "PhilPapers", doc_id: int = 3, target: str = "foo"):
+    doc_id = max(0, min(int(doc_id), 9))
+
+    if data_source == "PhilPapers":
+        raw_sample_doc = extracted_sample_doc = json.load(
+            open("data/curated_samples/philpapers_raw.json")
+        )
+    else:
+        raw_sample_doc = extracted_sample_doc = [{} for _ in range(10)]
+
+    raw_json = raw_sample_doc[doc_id]
+    extracted_json = extracted_sample_doc[doc_id]
+    return view_data(
+        raw_json,
+        extracted_json,
+        doc_id=doc_id,
+        data_source="PhilPapers",
+        data_sources="PhilPapers",
+        target=target,
+    )
+
+phil_examples = Div(
+    Div(
+        get_phil_data(target=gen_random_id()),
+        style="border: 1px solid #ccc; padding: 20px;",
+    ),
+)
+
 filtering_process = Div(
     Section(
           H3("This section contains the specific filtering steps taken for all 14 curated datasets."),
@@ -643,10 +700,10 @@ filtering_process = Div(
             Li("Many filters were used to clean the phil papers like double whitespaces, new lines etc. All filter details are here: https://github.com/thoppe/The-Pile-PhilPapers/blob/master/pdf_filter.py"),
         ),
         table_div_phil,
-      #  Details(
-      #      Summary("Phil Papers Filtering Examples"),
-       #     phil_examples,
-       # ),
+        Details(
+            Summary("Phil Papers Filtering Examples"),
+            phil_examples,
+        ),
         ),
     ),
     Section(
@@ -751,10 +808,10 @@ filtering_process = Div(
             Li("Minimum Word Count Filter: 10"),
         ),
         table_div_se,
-       # Details(
-       #     Summary("StackExchange Filtering Examples"),
-       #     se_examples,
-       # ),
+        Details(
+            Summary("StackExchange Filtering Examples"),
+            se_examples,
+        ),
         ),
     ),
     Section(