Update app.py

app.py

@@ -2,6 +2,14 @@ import streamlit as st
 import numpy as np
 import transformers
 import torch
+import pandas as pd
+import plotly.express as px
+
+
+df = pd.read_csv('Eval_subset.csv')
+st.set_page_config(
+    page_title="Twitter Sentiment Analyzer", page_icon="📊", layout="wide"
+)
 
 
 @st.cache_resource
@@ -12,18 +20,61 @@ def get_model():
 
 tokenizer, model = get_model()
 
+st.header("Covid19 Twitter Sentimental Analysis")
+st.text("This app uses Distilbert-base-uncased for the analysis.")
+add_text_sidebar = st.sidebar.title("Menu")
+#add_text_sidebar = st.sidebar.text("Just some random text.")
+with st.sidebar:
+    st.title("Twitter Sentiment Analyzer")
+
+    st.markdown(
+        """
+        <div style="text-align: justify;">
+            This app performs sentiment analysis on the latest tweets based on 
+            the entered search term. Since the app can only predict positive or 
+            negative, and neutral sentiment, it is more suitable towards analyzing the 
+            sentiment of brand, product, service, company, or person. 
+            Only English tweets are supported.
+        </div>
+        """,
+        unsafe_allow_html=True,
+    )
+
+st.sidebar.markdown("### Number of tweets by sentiment")
+select = st.sidebar.selectbox('Visualization type', ['Bar plot', 'Pie chart'], key='1')
+sentiment_count = df['safe_text'].value_counts()
+sentiment_count = pd.DataFrame({'Sentiment':sentiment_count.index, 'Tweets':sentiment_count.values})
+if not st.sidebar.checkbox("Hide", True):
+    st.markdown("### Number of tweets by sentiment")
+    if select == 'Bar plot':
+        fig = px.bar(sentiment_count, x='Sentiment', y='Tweets', color='Tweets', height=500)
+        st.plotly_chart(fig)
+    else:
+        fig = px.pie(sentiment_count, values='Tweets', names='Sentiment')
+        st.plotly_chart(fig)
+ 
+ 
+st.sidebar.subheader("Show random tweet")
+random_tweet = st.sidebar.radio('Sentiment', ('positive', 'neutral', 'negative'))
+st.sidebar.markdown(df['safe_text'])
+
 
+st.markdown("[Github link](https://github.com/tmtsmrsl/TwitterSentimentAnalyzer)")
+st.markdown('Created by Foster,Kwasi,Linda,Stella,Joshua,Bright')
 user_input = st.text_area('Enter text to predict')
 button = st.button('predict')
 
 
-
-# Define the Helper function    
+# Define Helper Function
 label = {0: 'Negative', 1:'Neutral', 2:'Positive'}
 
+
+      
+
 if user_input and button:
     test_input = tokenizer([user_input],return_tensors='pt')
-    
+    st.slider("Number of tweets", min_value=100, max_value=2000, key="user_input")
+
     # Test output
     output = model(**test_input)
     st.write('Logits:',output.logits)