add filter option for readme length

app.py

@@ -10,6 +10,7 @@ from httpx import Client
 from huggingface_hub import hf_hub_url, list_datasets
 from tqdm.auto import tqdm
 from tqdm.contrib.concurrent import thread_map
+from huggingface_hub import DatasetCard
 
 load_dotenv()
 
@@ -50,7 +51,8 @@ def get_readme_len(dataset):
         url = hf_hub_url(dataset["id"], "README.md", repo_type="dataset")
         resp = client.get(url)
         if resp.status_code == 200:
-            dataset["len"] = len(resp.text)
+            card = DatasetCard(resp.text)
+            dataset["len"] = len(card.text)
             return dataset
     except Exception as e:
         print(e)
@@ -115,8 +117,7 @@ def prep_dataframe(remove_orgs_and_users=remove_orgs, columns_to_drop=columns_to
     return df
 
 
-def filter_df_by_max_age(max_age_days=None):
-    df = prep_dataframe()
+def filter_df_by_max_age(df, max_age_days=None):
     df = df.dropna(subset=["created"])
     now = datetime.now()
     if max_age_days is not None:
@@ -126,15 +127,38 @@ def filter_df_by_max_age(max_age_days=None):
     return df
 
 
-def filter_by_readme_len(df, min_len=None, max_len=None):
-    pass
+def filter_by_readme_len(df, min_len=None):
+    if min_len is not None:
+        df = df[df["len"] >= min_len]
+    return df
+
+
+def filter_df(max_age_days=None, min_len=None):
+    df = prep_dataframe()
+    if max_age_days is not None:
+        df = filter_df_by_max_age(df, max_age_days=max_age_days)
+    if min_len is not None:
+        df = filter_by_readme_len(df, min_len=min_len)
+    return df
 
 
 with gr.Blocks() as demo:
     max_age_days = gr.Slider(
         label="Max Age (days)", value=7, minimum=0, maximum=90, step=1, interactive=True
     )
-    output = gr.DataFrame(prep_dataframe(), datatype="markdown", min_width=160 * 2.5)
-    max_age_days.input(filter_df_by_max_age, inputs=[max_age_days], outputs=[output])
+
+    min_len = gr.Slider(
+        label="Minimum README Length",
+        value=300,
+        minimum=0,
+        maximum=1000,
+        step=50,
+        interactive=True,
+    )
+
+    output = gr.DataFrame(filter_df, datatype="markdown", min_width=160 * 2.5)
+    max_age_days.input(filter_df, inputs=[max_age_days, min_len], outputs=[output])
+    min_len.input(filter_df, inputs=[max_age_days, min_len], outputs=[output])
+
 
 demo.launch()