add twitter feature

app.py

@@ -1,4 +1,10 @@
 from transformers import pipeline
+import pandas as pd
+import re
+from tqdm import tqdm
+import matplotlib.pyplot as plt
+import twitter_scraper as ts
+
 
 import gradio as gr
 from gradio.mix import Parallel
@@ -28,11 +34,28 @@ examples = [
 def sentiment_analysis(text):
     output = sentiment_pipeline(text)
     return {elm["label"]: elm["score"] for elm in output[0]}
-    
+
 def ner(text):
     output = ner_pipeline(text)
     return {"text": text, "entities": output}
 
+def sentiment_df(df):
+    text_list = list(df["Text"].astype(str).values)
+    result = [sentiment_analysis(text) for text in text_list]
+    df['Label'] = [pred['label'] for pred in result]
+    df['Score'] = [round(pred['Score'], 3) for pred in result]
+    return df
+
+
+def twitter_analyzer(keyword, max_tweets):
+    df = ts.scrape_tweets(keyword, max_tweets=max_tweets)
+    df["Text"] = df["Text"].apply(ts.preprocess_text)
+    print("Analyzing sentiment...")
+    df = sentiment_df(df)
+    fig = plt.figure()
+    df.groupby(["Label"])["Text"].count().plot.pie(autopct="%.1f%%", figsize=(6,6))
+    return fig, df[["URL", "Text", "Label", "Score"]]
+
 sentiment_demo = gr.Interface(
     fn=sentiment_analysis,
     inputs="text",
@@ -45,7 +68,47 @@ ner_demo = gr.Interface(
     examples=examples)
 
 if __name__ == "__main__":
-    Parallel(sentiment_demo, ner_demo,
-    inputs=gr.Textbox(lines=10, label="Input Text", placeholder="Enter sentences here..."),
-    title="Entity Based Sentiment Analysis Indonesia",
-    examples=examples).launch()
+
+    with gr.Blocks() as demo:
+
+        gr.Markdown("""Entity Based Sentiment Analysis Indonesia""")
+
+        gr.Markdown(
+            """
+            """
+            )
+
+        with gr.Tab("Single Input"):
+            Parallel(
+                    sentiment_demo, ner_demo,
+                    inputs=gr.Textbox(lines=10, label="Input Text", placeholder="Enter sentences here..."),
+                    examples=examples
+                    )
+
+        with gr.Tab("Twitter"):
+            with gr.Blocks():
+                with gr.Row():
+                    with gr.Column():
+                        keyword_textbox = gr.Textbox(lines=1, label="Keyword")
+                        max_tweets_component = gr.Number(value=10, label="Total of Tweets to Scrape", precision=0)
+                        button = gr.Button("Submit")
+
+                    plot_component = gr.Plot(label="Pie Chart of Sentiments")
+                dataframe_component = gr.DataFrame(type="pandas",
+                                                label="Dataframe",
+                                                max_rows=(20,'fixed'),
+                                                overflow_row_behaviour='paginate',
+                                                wrap=True)
+
+        gr.Markdown(
+                """
+
+                """
+
+            )
+
+        button.click(twitter_analyzer,
+                    inputs=[keyword_textbox, max_tweets_component],
+                    outputs=[plot_component, dataframe_component])
+
+    demo.launch(inbrowser=True)

requirements.txt

@@ -1,2 +1,6 @@
 torch
-transformers
+transformers
+snscrape
+pandas
+matplotlib
+numpy