add tables

main.py

@@ -1,6 +1,7 @@
 from fasthtml.common import *
 from fasthtml.components import *
 from fasthtml.components import D_title, D_article, D_front_matter, D_contents, D_byline
+from fasthtml.components import HR
 from plotly import graph_objects as go
 from fh_plotly import plotly2fasthtml
 import pandas as pd
@@ -309,8 +310,45 @@ def get_chart_28168342():
 
 @app.get("/curated")
 def curated():
+    hr = HR()
+    data_preparation_steps = pd.DataFrame(
+        {
+            "Method": [
+                "HTTP/FTP dumps",
+                "Web crawling",
+                "Archive snapshot",
+                "Generated",
+                "Curated",
+            ],
+            "Description": [
+                "Acquiring data from HTTP/FTP dumps",
+                "Crawling websites to extract data",
+                "Working with archive dumps",
+                "Generating synthetic data",
+                "High quality curated data",
+            ],
+            "Source": [
+                "Freelaw | Wikipedia | PhilPapers | Arxiv | S2ORC | Pubmeds",
+                "USPTO | Hackernews | Ubuntu IRC",
+                "StackExchange",
+                "DM Maths",
+                "PG19 | Europarl",
+            ],
+        }
+    )
+
+    data_preparation_steps.style.set_properties(
+        **{"padding-top": "10px", "padding-bottom": "10px"}
+    )
+    table_html = data_preparation_steps.to_html(index=False, border=0)
+    table_div = Div(NotStr(table_html), cls="l-body-outset")
     return Div(
-        H2("Curated Sources"), plotly2fasthtml(get_chart_28168342()), id="inner-text"
+        H1("Curated Sources"),
+        plotly2fasthtml(get_chart_28168342()),
+        H2("Data Preparation"),
+        table_div,
+        H2("Data Preprocessing"),
+        id="inner-text",
     )