Create app.py

app.py

@@ -0,0 +1,62 @@
+# bsky2M_emojis_streamlit.py
+
+# Packages required 
+import streamlit as st 
+from datasets import load_dataset 
+import emoji 
+from dateutil import parser 
+from collections import Counter 
+import plotly.express as px 
+import pandas as pd 
+from collections import defaultdict 
+
+
+# Streamlit app title 
+st.title("Top 200 Most Frequent Emojis in Bluesky Posts")
+
+# Step 1: Load the Dataset 
+# Load the dataset 
+dataset = load_dataset("alpindale/two-million-bluesky-posts")
+
+# Access the first split
+data = dataset['train']
+
+# Step 2: Extract Emojis from Text 
+def extract_emojis(text):
+    return [e['emoji'] for e in emoji.emoji_list(text)]
+
+# Apply the function to the 'text' column and ensure the dataset is updated 
+data = data.map(lambda x: {"emojis": extract_emojis(x["text"])}) 
+
+# Step 3: Convert created_ad to Datatime 
+# Convert 'created_at' to datetime 
+data = data.map(lambda x: {"created_at": parser.isoparse(x["created_at"])})
+
+# Step 4: Count Emoji Frequencies 
+# Flatten the list of emojis
+all_emojis = [emoji for entry in data for emoji in entry["emojis"]]
+
+# Count the frequency of each emoji
+emoji_counts = Counter(all_emojis)
+
+# Step 5: Visualize Emoji Frequencies
+# Get the top 200 most common emojis
+top_emojis = emoji_counts.most_common(200)
+
+# Extract emojis and their counts 
+emojis, counts = zip(*top_emojis)
+
+# Create a DataFrame for Plotly
+df = pd.DataFrame({'Emojis': emojis, 'Frequency': counts})
+
+# Display the dataframe in the Streamlit app 
+st.write('### Top 200 Emojis Dataframe')
+st.dataframe(df)
+
+# Plot the bar chart
+fig = px.bar(df, x='Emojis', y='Frequency', title='Top 200 Most Frequent Emojis')
+fig.update_xaxes(title_text='Emojis')
+fig.update_yaxes(title_text='Frequency')
+
+# Display the plot in the Streamlit app 
+st.plotly_chart(fig)