app.py

from datetime import datetime

import streamlit as st
import pandas as pd

# from load_dataframe import get_data


# Main Streamlit app
def main():
    st.title("Hugging Face Papers KPI Dashboard")

    # 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
    # Note that it's a string, not a datetime
    df = df.set_index('date')
    df.index = pd.to_datetime(df.index).strftime('%d-%m-%Y')
    df = df.sort_index()

    # 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"])

    if view_level == "day":
        # make a button to select the day, defaulting to today
        day = st.date_input("Select day", value="today", format="DD/MM/YYYY")
        # convert to the day of a Pandas Timestamp
        day = pd.Timestamp(day)

        print("Day:", day)

        df = df.loc[day.strftime('%d-%m-%Y'):day.strftime('%d-%m-%Y')]

        st.write(f"Showing data for {day.strftime('%d/%m/%Y')}")

        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: {df['num_models'].sum()}
        """)

        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)

    elif view_level == "week":
        # make a button to select the week
        week = st.sidebar.date_input("Select week", value=pd.Timestamp.today().isocalendar())
        
        df = df.loc[df['date'].dt.isocalendar().week == week.isocalendar().week]
        
        st.write(f"Showing data for {day}")
        st.dataframe(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())
        
        df = df.loc[df['date'].dt.month_name() == month]
        
        st.write(f"Showing data for {day}")
        st.dataframe(df)

    # Display data based on aggregation level



if __name__ == "__main__":
    main()