More improvements

app.py

@@ -15,7 +15,7 @@ def aggregated_data(df, aggregation_level="week"):
     df['has_artifact'] = (df['num_models'] > 0) | (df['num_datasets'] > 0) | (df['num_spaces'] > 0)
 
     # Resample by week
-    freq = 'W' if aggregation_level == "week" else 'M'
+    freq = 'W' if aggregation_level == "week" else 'ME'
     weekly_total_papers = df.resample(freq).size()
     weekly_papers_with_artifacts = df.resample(freq)['has_artifact'].sum()
 
@@ -64,6 +64,14 @@ def display_data(df):
                 column_config={"github": st.column_config.LinkColumn(),
                                 "paper_page": st.column_config.LinkColumn()},
                 width=2000)
+    
+    st.write("Papers with a HF mention in README but no artifacts")
+    st.dataframe(df[(df['hf_mention'] == 1) & (~df['has_artifact'])],
+                hide_index=True,
+                column_order=("paper_page", "title", "github", "num_models", "num_datasets", "num_spaces"),
+                column_config={"github": st.column_config.LinkColumn(),
+                                "paper_page": st.column_config.LinkColumn()},
+                width=2000)
 
 
 def main():
@@ -75,8 +83,8 @@ def main():
 
     # TODO use this instead
     # df = get_data()
-    df = pd.read_csv('/Users/nielsrogge/Downloads/daily_papers_enriched (1).csv')
-    df = df.drop(['Unnamed: 0'], axis=1)
+    df = pd.read_csv('/Users/nielsrogge/Downloads/daily_papers_enriched (3).csv')
+    df = df.drop(['Unnamed: 0'], axis=1) if 'Unnamed: 0' in df.columns else df
     # Use date as index
     df = df.set_index('date')
     df.index = pd.to_datetime(df.index)