Update app.py

app.py

@@ -1,44 +1,83 @@
-from deepsparse import Pipeline
-import time
-import gradio as gr
+import streamlit as st
+import pandas as pd
+import numpy as np
+import plotly.express as px
+from wordcloud import WordCloud, STOPWORDS
+import matplotlib.pyplot as plt
 
-task = "zero_shot_text_classification"
-sparse_classification_pipeline = Pipeline.create(
-    task=task,
-    model_path="zoo:nlp/text_classification/distilbert-none/pytorch/huggingface/mnli/pruned80_quant-none-vnni",
-    model_scheme="mnli",
-    model_config={"hypothesis_template": "This text is related to {}"},
-)
+st.set_option('deprecation.showPyplotGlobalUse', False)
 
-def run_pipeline(text):
-    sparse_start = time.perf_counter()
-    sparse_output = sparse_classification_pipeline(sequences=text, labels=['politics', 'public health', 'Europe'])
-    sparse_result = dict(sparse_output)
-    sparse_end = time.perf_counter()
-    sparse_duration = (sparse_end - sparse_start) * 1000.0
-    dict_r = {
-        sparse_result['labels'][0]: sparse_result['scores'][0],
-        sparse_result['labels'][1]: sparse_result['scores'][1],
-        sparse_result['labels'][2]: sparse_result['scores'][2]
-    }
-    return dict_r, sparse_duration
+DATA_ = pd.read_csv("Tweets.csv")
+st.title("Sentiment Analysis of Tweets about US Airlines")
+st.sidebar.title("Sentiment Analysis of Tweets about US Airlines")
+st.markdown("This application is a streamlit dashboard to analyze the sentiment of Tweets")
+st.sidebar.markdown("This application is a streamlit dashboard to analyze the sentiment of Tweets")
 
-with gr.Blocks() as demo:
-    with gr.Row():
-        with gr.Column():
-            text = gr.Textbox(placeholder="Enter text here...", label="Text", lines=5, width=500)
-            btn = gr.Button("Submit", style="info", size="lg", block=True)
 
-        with gr.Column():
-           
-            sparse_answers = gr.Label(label="Sparse Model Answers", num_top_classes=3, style="info")
-            sparse_duration = gr.Number(label="Sparse Latency (ms)", style="success", size="lg")
+def run():
+    
+    @st.cache(persist=True)
+    def load_data():
+        DATA_['tweet_created'] = pd.to_datetime(DATA_['tweet_created'])
+        return DATA_
+    data = load_data()
+    
+    st.sidebar.subheader("Show random tweet")
+    random_tweet = st.sidebar.radio('Sentiment', ('positive', 'neutral', 'negative'))
+    st.sidebar.markdown(data.query('airline_sentiment == @random_tweet')[["text"]].sample(n=1).iat[0,0])
+    
+    st.sidebar.markdown("### Number of tweets by sentiment")
+    select = st.sidebar.selectbox('Visualization type', ['Histogram', 'Pie chart'])
+    sentiment_count = data['airline_sentiment'].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 == "Histogram":
+            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("When and Where are users tweeting from?")
+    hour = st.sidebar.slider("Hour of day", 0,23)
+    modified_data = data[data['tweet_created'].dt.hour == hour]
+    if not st.sidebar.checkbox("Close", True, key='1'):
+        st.markdown("### Tweets locations based on the time of date")
+        st.markdown("%i tweets between %i:00 and %i:00" % (len(modified_data), hour, (hour+1)%24))
+        st.map(modified_data)
+        if st.sidebar.checkbox("Show Raw Data", False):
+            st.write(modified_data)
+    st.sidebar.subheader("Breakdown airline tweets by sentiment")
+    choice = st.sidebar.multiselect('Pick airline', ('US Airways', 'United', 'American', 'Southwest', 'Delta', 'Virgin America'), key='0')
 
-    btn.click(
-        run_pipeline,
-        inputs=[text],
-        outputs=[sparse_answers, sparse_duration],
-    )
+    if len(choice) > 0:
+        choice_data = data[data.airline.isin(choice)]
+        fig_choice = px.histogram(choice_data, x='airline',
+        y='airline_sentiment',
+        histfunc = 'count', color = 'airline_sentiment',
+        facet_col='airline_sentiment',
+        labels={'airline_sentiment':'tweets'}, height=600, width=800)
+        st.plotly_chart(fig_choice)
+    
 
-if __name__ == "__main__":
-    demo.launch()
+    st.sidebar.header("Word Cloud")
+    word_sentiment = st.sidebar.radio('Display word cloud for what sentiment?',('positive', 'neutral','negative'))
+
+    if not st.sidebar.checkbox("Close", True, key='3'):
+        st.header('Word cloud for %s sentiment' % (word_sentiment))
+        df = data[data['airline_sentiment']==word_sentiment]
+        words = ' '.join(df['text'])
+        processed_words = ' '.join([word for word in words.split() if 'http' not in word and not word.startswith('@') and word !='RT'])
+        wordcloud = WordCloud(stopwords=STOPWORDS,
+        background_color='white', height=640, width=800).generate(processed_words)
+        plt.imshow(wordcloud)
+        plt.xticks([])
+        plt.yticks([])
+        st.pyplot() 
+            
+            
+if __name__ == '__main__':
+    run()