Add aggregated data

app.py

@@ -2,11 +2,60 @@ from datetime import datetime
 
 import streamlit as st
 import pandas as pd
+import matplotlib.pyplot as plt
 
 # from load_dataframe import get_data
 
 
-# Main Streamlit app
+def aggregated_data(df, aggregation_level="week"):
+
+    st.write(f"Aggregated data by {aggregation_level}")
+
+    # Create a column that indicates if a paper has any artifacts
+    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'
+    weekly_total_papers = df.resample(freq).size()
+    weekly_papers_with_artifacts = df.resample(freq)['has_artifact'].sum()
+
+    # Calculate the percentage of papers with artifacts
+    percentage_papers_with_artifacts = (weekly_papers_with_artifacts / weekly_total_papers) * 100
+
+    # Create the plot
+    plt.figure(figsize=(12, 6))
+    plt.plot(percentage_papers_with_artifacts.index, percentage_papers_with_artifacts, marker='o', linestyle='-', color='b', label='Percentage of Papers with on least 1 Artifact')
+
+    # Set the y-axis limits
+    plt.ylim(0, 100)
+    
+    plt.xlabel(aggregation_level)
+    plt.ylabel('Percentage')
+    plt.title('Percentage of Papers with Artifacts (Models, Datasets, Spaces) Over Time')
+    plt.legend()
+    plt.grid(True)
+
+    # Use Streamlit to display the plot
+    st.pyplot(plt)
+
+
+def display_data(df):
+    num_artifacts = df[(df['num_models'] > 0) | (df['num_datasets'] > 0) | (df['num_spaces'] > 0)].shape[0]
+
+    st.markdown(f"""
+    ## Number of papers: {df.shape[0]}
+    #### Number of papers with a Github link: {df['github'].notnull().sum()}
+    #### Number of papers with at least one HF artifact: {num_artifacts}
+    """)
+    
+    st.dataframe(df,
+                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():
     st.title("Hugging Face Papers KPI Dashboard")
 
@@ -14,16 +63,16 @@ def main():
     st.sidebar.title("Navigation")
     selection = st.sidebar.selectbox("Go to", ["Daily/weekly/monthly data", "Aggregated data"])
 
-    if selection == "Daily/weekly/monthly data":
-        # 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)
-        # Use date as index
-        df = df.set_index('date')
-        df.index = pd.to_datetime(df.index)
-        df = df.sort_index()
+    # 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)
+    # Use date as index
+    df = df.set_index('date')
+    df.index = pd.to_datetime(df.index)
+    df = df.sort_index()
 
+    if selection == "Daily/weekly/monthly data":
         # Button to select day, month or week
         # Add streamlit selectbox.
         view_level = st.selectbox(label="View data per day, week or month", options=["day", "week", "month"])
@@ -40,41 +89,46 @@ def main():
 
             st.write(f"Showing data for {day.strftime('%d/%m/%Y')}")
 
-            num_artifacts = df[(df['num_models'] > 0) | (df['num_datasets'] > 0) | (df['num_spaces'] > 0)].shape[0]
-
-            st.markdown(f"""
-            ## Number of papers: {df.shape[0]}
-            #### Number of papers with a Github link: {df['github'].notnull().sum()}
-            #### Number of papers with at least one HF artifact: {num_artifacts}
-            """)
-
-            st.dataframe(df,
-                        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)
+            display_data(df)
 
         elif view_level == "week":
             # make a button to select the week
-            week = st.number_input("Select week", value=datetime.today().isocalendar()[1], min_value=1, max_value=52)
+            week_number = st.number_input("Select week", value=datetime.today().isocalendar()[1], min_value=1, max_value=52)
+            
+            # Extract week number from the index
+            df['week'] = df.index.isocalendar().week
+
+            # Filter the dataframe for the desired week number
+            df = df[df['week'] == week_number]
             
-            df = df.loc[df['date'].dt.isocalendar().week == week.isocalendar().week]
+            st.write(f"Showing data for week {week_number}")
             
-            st.write(f"Showing data for {day}")
-            st.dataframe(df)
+            display_data(df)
 
         elif view_level == "month":
             # make a button to select the month, defaulting to current month
-            month = st.sidebar.date_input("Select month", value=pd.Timestamp.today().month_name())
+            month_str = st.selectbox("Select month", options=["January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December"])
+            year_str = st.selectbox("Select year", options=["2024"])
+            
+            # Filter the dataframe for the desired week number
+            month_map = {
+                'January': 1, 'February': 2, 'March': 3, 'April': 4, 
+                'May': 5, 'June': 6, 'July': 7, 'August': 8, 
+                'September': 9, 'October': 10, 'November': 11, 'December': 12
+            }
+            
+            # Convert month string to number
+            month = month_map[month_str]
+            year = int(year_str)
+            df = df[(df.index.month == month) & (df.index.year == year)]
             
-            df = df.loc[df['date'].dt.month_name() == month]
+            st.write(f"Showing data for month {month}")
             
-            st.write(f"Showing data for {day}")
-            st.dataframe(df)
+            display_data(df)
 
     elif selection == "Aggregated data":
-        st.write("Aggregated data")
+        aggregated_data(df)
+        aggregated_data(df, aggregation_level="month")
 
     else:
         st.write("Error: selection not recognized")