Add application file

app.py

@@ -1,4 +1,66 @@
 import streamlit as st
+import numpy as np
+import pandas as pd
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+st.set_page_config(layout="wide")
+
+st.header("HuggingFace 🤗 Posts leaderboard")
+
+st.write(
+    """Data Source: https://huggingface.co/datasets/maxiw/hf-posts \t Created by: https://huggingface.co/singhsidhukuldeep"""
+)
+
+df = pd.read_json("hf://datasets/maxiw/hf-posts/posts.jsonl", lines=True)
+
+df["publishedAt"] = pd.to_datetime(df.publishedAt)
+print(df.columns)
+
+# Get min and max dates from the DataFrame
+min_date = df["publishedAt"].min().to_pydatetime()
+max_date = df["publishedAt"].max().to_pydatetime()
+
+# Create the double-ended slider
+date_range = st.slider(
+    "Select Date Range",
+    min_value=min_date,
+    max_value=max_date,
+    value=(min_date, max_date),
+    format="DD/MMM/YYYY",
+)
+metrics = ["totalUniqueImpressions", "totalReactions", "numComments", "Num of posts"]
+selected_metric = st.selectbox(
+    "Sort by:",
+    options=metrics,
+    index=0,
+)
+# Filter the DataFrame based on selected date range
+mask = df["publishedAt"].between(*date_range)
+df = df[mask]
+
+
+df["Name"] = df.author.apply(lambda x: x["fullname"])
+df["username"] = df.author.apply(lambda x: x["name"])
+df["totalReactions"] = df.reactions.apply(lambda x: sum([_["count"] for _ in x]))
+df["Num of posts"] = 1
+data = (
+    df.groupby(["username", "Name"])[metrics]
+    .sum()
+    .sort_values(selected_metric, ascending=False)
+    .reset_index()
+)
+data.index = np.arange(1, len(data) + 1)
+data.index.name = "Rank"
+
+
+def make_clickable(val):
+    return f'<a target="_blank" href="https://huggingface.co/{val}">{val}</a>'
+
+
+df_styled = data.style.format({"username": make_clickable})
+st.write(
+    f"""<center>{df_styled.to_html(escape=False, index=False)}""",
+    unsafe_allow_html=True,
+)
+
+
+# st.dataframe(data=df_styled, width=100_000)