add autogenerated tab

app.py

@@ -14,7 +14,7 @@ pd.options.plotting.backend = "plotly"
 
 
 def download_dataset():
-    return load_dataset("open-source-metrics/model-repos-stats", split="train")
+    return load_dataset("open-source-metrics/model-repos-stats", split="train", ignore_verifications=True)
 
 
 def _clean_tags(tags: Optional[Union[str, List[str]]]):
@@ -30,6 +30,16 @@ def _clean_tags(tags: Optional[Union[str, List[str]]]):
         return []
 
 
+def _is_generated_from_tag(tags):
+    return any("generated" in tag for tag in tags)
+
+
+def _parse_tags_for_generated(tags):
+    for tag in tags:
+        if "generated" in tag:
+            return tag
+
+
 def prep_dataset():
     ds = download_dataset()
     df = ds.to_pandas()
@@ -39,8 +49,10 @@ def prep_dataset():
     df["has_languages"] = df.languages.apply(len) > 0
     df["has_tags"] = df.tags.apply(len) > 0
     df["has_dataset"] = df.datasets.apply(len) > 0
-    df["has_co2"] = df.co2.isnull()
+    df["has_co2"] = df.co2.notnull()
     df["has_co2"] = df.co2.apply(lambda x: x is not None)
+    df['has_license'] = df.license.notnull()
+    df['is_generated'] = df.tags.apply(_is_generated_from_tag)
     df = df.drop(columns=["Unnamed: 0"])
     df.to_parquet("data.parquet")
     return df
@@ -148,6 +160,14 @@ def metadata_coverage_by_library(metadata_field):
     return df.groupby("library")[metadata_field].mean().sort_values().plot.barh()
 
 
+def metadata_coverage_by_autogenerated(metadata_field):
+    df = load_data()
+    subset_df = df[df['is_generated']].copy(deep=True)
+    subset_df.reset_index()
+    subset_df['autogenerated-from'] = subset_df.tags.apply(_parse_tags_for_generated)
+    return subset_df.groupby("autogenerated-from")[metadata_field].mean().sort_values().plot.barh()
+
+
 df = load_data()
 top_n = df.library.value_counts().shape[0]
 libraries = [library for library in df.library.unique() if library]
@@ -200,6 +220,12 @@ with gr.Blocks() as demo:
         metadata_field.change(
             metadata_coverage_by_library, [metadata_field], plot, queue=False
         )
+    with gr.Tab("Auto generated model cards"):
+        metadata_field = gr.Dropdown(choices=metadata_coverage_columns)
+        plot = gr.Plot()
+        metadata_field.change(
+            metadata_coverage_by_autogenerated, [metadata_field], plot, queue=False
+        )
 
     with gr.Tab("Model Cards"):
         gr.Markdown(