Create 01_🏠_Home.py

01_🏠_Home.py

@@ -0,0 +1,173 @@
+import streamlit as st
+from variables import *
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import pipeline, AutoTokenizer
+from optimum.pipelines import pipeline
+import tweepy
+import pandas as pd
+import numpy as np
+import plotly_express as px
+import plotly.graph_objects as go
+from st_aggrid import GridOptionsBuilder, AgGrid, GridUpdateMode, DataReturnMode
+
+st.set_page_config(
+    page_title="Live FinTwitter Analysis",
+    page_icon="📈",
+    layout="wide",
+)
+
+st.sidebar.header("Sentiment Analysis Score")
+    
+@st.experimental_singleton(suppress_st_warning=True)
+def load_models():
+    '''load sentimant and topic clssification models'''
+    sent_pipe = pipeline(task,model=sent_model_id, tokenizer=sent_model_id)
+    topic_pipe = pipeline(task, model=topic_model_id, tokenizer=topic_model_id)
+    
+    return sent_pipe, topic_pipe
+
+@st.cache(allow_output_mutation=True, suppress_st_warning=True)
+def process_tweets(df,df_users):
+    '''process tweets into a dataframe'''
+    
+    df['author'] = df['author'].astype(np.int64)
+    
+    df_merged = df.merge(df_users, on='author')
+
+    tweet_list = df_merged['tweet'].tolist()
+    
+    sentiment, topic = pd.DataFrame(sentiment_classifier(tweet_list)), pd.DataFrame(topic_classifier(tweet_list))
+    
+    sentiment.rename(columns={'score':'sentiment_confidence','label':'sentiment'}, inplace=True)
+    
+    topic.rename(columns={'score':'topic_confidence','label':'topic'}, inplace=True)
+    
+    df_group = pd.concat([df_merged,sentiment,topic],axis=1)
+
+    df_group[['sentiment_confidence','topic_confidence']] = df_group[['sentiment_confidence','topic_confidence']].round(2).mul(100)
+
+    df_tweets = df_group[['creation_time','username','tweet','sentiment','topic','sentiment_confidence','topic_confidence']]
+
+    df_tweets = df_tweets.sort_values(by=['creation_time'],ascending=False)
+
+    return df_tweets
+
+
+    
+sentiment_classifier, topic_classifier = load_models()
+    
+st.title('Live FinTwitter Sentiment & Topic Analysis with Tweepy and Transformers')
+
+st.markdown(
+    """
+    This app uses Tweepy to extract tweets from twitter based on a list of popular accounts that tweet about markets/finance: 
+    - The stream of tweets is processed via HuggingFace models for finance tweet sentiment and topic analysis:  
+        - [Topic Classification](https://huggingface.co/nickmuchi/finbert-tone-finetuned-finance-topic-classification)  
+        - [Sentiment Analysis](https://huggingface.co/nickmuchi/finbert-tone-finetuned-fintwitter-classification)  
+    - The resulting sentiments and corresponding tweets are displayed, with graphs tracking the live sentiment and topics of financial market tweets in the Visualisation tab.  
+    """
+    )
+    
+refresh_stream = st.button('Refresh Stream')
+
+if "update_but" not in st.session_state:
+    st.session_state.update_but = False
+
+if refresh_stream or st.session_state.update_but:
+    st.session_state.update_but = True
+    
+    client = tweepy.Client(CONFIG['bearer_token'], wait_on_rate_limit=True)
+    
+    users = []
+    all_tweets = []
+    
+    for res in tweepy.Paginator(client.get_list_tweets,
+        id="1083517925049266176",
+        user_fields=['username'],
+        tweet_fields=['created_at','text'],
+        expansions=['author_id'],
+        max_results=100):
+        
+        all_tweets.append(res)
+    
+
+    with st.spinner('Generating sentiment and topic classification of tweets...'):
+
+        tweets = [response.data for response in all_tweets]
+        users = [response.includes['users'] for response in all_tweets]
+
+        flat_users = [x for i in users for x in i]
+        flat_tweets = [x for i in tweets for x in i]
+        
+        data = [(tweet.data['author_id'],tweet.data['text'],tweet.data['created_at']) for tweet in flat_tweets]
+        df = pd.DataFrame(data,columns=['author','tweet','creation_time'])
+        
+        df['tweet'] = df['tweet'].replace(r'https?://\S+', '', regex=True).replace(r'www\S+', '', regex=True)
+               
+        users = client.get_users(ids=df['author'].unique().tolist())
+
+        df_users = pd.DataFrame(data=list(set([(user.id,user.username) for user in users.data])),columns=['author','username'])
+
+        df_tweets = process_tweets(df,df_users)
+    
+        st.session_state['tdf'] = df_tweets
+
+    with st.container():
+
+        st.write("Table of Influential FinTweets")
+
+        gb = GridOptionsBuilder.from_dataframe(df_tweets)
+        gb.configure_pagination(paginationPageSize=30,paginationAutoPageSize=False) #Add pagination
+        gb.configure_side_bar() #Add a sidebar
+        gb.configure_selection('multiple', use_checkbox=True, groupSelectsChildren="Group checkbox select children")
+        gb.configure_column('tweet',wrapText=True,autoHeight=True)#Enable multi-row selection
+        gridOptions = gb.build()
+        
+        AgGrid(
+            df_tweets,
+            gridOptions=gridOptions,
+            data_return_mode='AS_INPUT', 
+            update_mode='MODEL_CHANGED', 
+            fit_columns_on_grid_load=False,
+            enable_enterprise_modules=True,
+            theme='streamlit', #Add theme color to the table
+            height=550, 
+            width='100%'        
+        )
+        
+    ## Display sentiment score
+    pos_perc = df_tweets[df_tweets['sentiment']=='Bullish'].count()[0]*100/df_tweets.shape[0]
+    neg_perc = df_tweets[df_tweets['sentiment']=='Bearish'].count()[0]*100/df_tweets.shape[0]
+    neu_perc = df_tweets[df_tweets['sentiment']=='Neutral'].count()[0]*100/df_tweets.shape[0]
+    
+    sentiment_score = neu_perc+pos_perc-neg_perc
+    
+    fig_1 = go.Figure()
+    
+    fig_1.add_trace(go.Indicator(
+        mode = "delta",
+        value = sentiment_score,
+        domain = {'row': 1, 'column': 1}))
+    
+    fig_1.update_layout(
+        template = {'data' : {'indicator': [{
+            'title': {'text': "Sentiment Score"},
+            'mode' : "number+delta+gauge",
+            'delta' : {'reference': 50}}]
+                             }},
+        autosize=False,
+        width=250,
+        height=250,
+        margin=dict(
+            l=5,
+            r=5,
+            b=5,
+            pad=2
+        )
+    )
+    
+    with st.sidebar:
+    
+        st.plotly_chart(fig_1)
+
+st.markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-fintweet-sentiment-analysis)")