Update 01_🏠_Home.py

01_🏠_Home.py

@@ -10,6 +10,8 @@ import plotly_express as px
 import plotly.graph_objects as go
 from datetime import datetime as dt
 from st_aggrid import GridOptionsBuilder, AgGrid, GridUpdateMode, DataReturnMode
+from datasets import Dataset
+from huggingface_hub import Repository
 
 st.set_page_config(
     page_title="Live FinTwitter Analysis",
@@ -20,42 +22,15 @@ st.set_page_config(
 st.sidebar.header("Sentiment Analysis Score")
 
 extract_time = dt.strftime(dt.today(),"%d_%B_%y_%H_%M")
-    
-@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
+DATASET_REPO_URL = "https://huggingface.co/datasets/nickmuchi/fin_tweets"
 
+DATA_FILENAME = "tweets_data.csv"
+DATA_FILE = os.path.join("data", DATA_FILENAME)
 
+repo = Repository(
+    local_dir="tweets", clone_from=DATASET_REPO_URL
+)
     
 sentiment_classifier, topic_classifier = load_models()