refactored code to run in huggingface spaces

app.py

@@ -0,0 +1,151 @@
+import gradio as gr
+from gnews import GNews
+import pandas as pd
+from transformers import pipeline
+from datetime import datetime, timedelta
+
+
+def discard_old_rows(df):
+    # Convert the 'published date' column to datetime
+    df['published date'] = pd.to_datetime(df['published date'], format='%a, %d %b %Y %H:%M:%S %Z')
+    
+    # Get the current date
+    current_date = datetime.utcnow()
+    
+    # Calculate the date two months ago
+    two_months_ago = current_date - timedelta(days=60)
+    
+    # Filter the DataFrame to keep only the rows with 'published date' within the last two months
+    df_filtered = df[df['published date'] >= two_months_ago]
+    
+    return df_filtered
+
+
+def extract_and_clean_titles(df):
+    # Initialize an empty list to store the cleaned titles
+    values_list = []
+
+    # Iterate over each value in the 'title' column of the DataFrame
+    for value in df['title']:
+        # Find the position of the first hyphen in the title
+        index = value.find('-')
+
+        # Extract the part of the title before the hyphen
+        # If there's no hyphen, use the entire title
+        extracted_value = value[:index] if index >= 0 else value
+
+        # Remove any occurrences of '...' from the extracted value
+        cleaned_value = extracted_value.replace('...', '')
+
+        # Append the cleaned value to the list
+        values_list.append(cleaned_value)
+
+    # Return the list of cleaned titles
+    return values_list
+
+
+def analyze_sentiments(values_list, sentiment_analysis):
+    # Initialize an empty list to store the sentiment predictions
+    prediction = []
+
+    # Iterate over each news title in the values_list
+    for news in values_list:
+        # Perform sentiment analysis on the current news title
+        sentiment = sentiment_analysis(news)
+
+        # Append the resulting sentiment to the prediction list
+        prediction.append(sentiment)
+
+    # Return the list of sentiment predictions
+    return prediction
+
+
+def calculate_weighted_average(predictions):
+    # Initialize the weighted average score to zero
+    weighted_avg = 0
+
+    # Iterate over each prediction in the predictions list
+    for i in predictions:
+        # Check if the label of the first sentiment prediction is 'positive'
+        if i[0]['label'] == 'positive':
+            # Add the score to the weighted average (positive sentiment)
+            weighted_avg += 1 * i[0]['score']
+        # Check if the label of the first sentiment prediction is 'negative'
+        elif i[0]['label'] == 'negative':
+            # Subtract the score from the weighted average (negative sentiment)
+            weighted_avg += -1 * i[0]['score']
+
+    # Calculate the weighted average by dividing by the number of predictions
+    weighted_avg /= len(predictions)
+
+    # Return the calculated weighted average
+    return weighted_avg
+
+
+def sentiment_pie_chart(predictions):
+    """
+    Generates a pie chart for sentiment distribution.
+    """
+    positive_count = 0
+    negative_count = 0
+    neutral_count = 0
+
+    for item in predictions:
+        label = item[0]['label']
+        if label == 'positive':
+            positive_count += 1
+        elif label == 'negative':
+            negative_count += 1
+        elif label == 'neutral':
+            neutral_count += 1
+
+    labels = ['Positive', 'Negative', 'Neutral']
+    sizes = [positive_count, negative_count, neutral_count]
+    colors = ['#66BB6A', '#EF5350', '#42A5F5']
+
+    fig, ax = plt.subplots()
+    ax.pie(sizes, labels=labels, colors=colors, autopct='%1.1f%%', startangle=90, pctdistance=0.85)
+    center_circle = plt.Circle((0, 0), 0.70, fc='white')
+    fig.gca().add_artist(center_circle)
+    ax.axis('equal')
+    plt.title('Sentiment Analysis Results')
+    return fig
+
+
+def main(stock):
+    #Specifying model 
+    model="mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis"
+    
+    #Scraping top data from google news
+    google_news = GNews()
+    Company_news=google_news.get_news(stock + "share")
+    df=pd.DataFrame(Company_news)
+
+    #Discarding old rows
+    df=discard_old_rows(df)
+
+    #Cleaning the titles for sentiment analysis
+    values_list=extract_and_clean_titles(df)
+    
+    #Sentiment Analysis
+    sentiment_analysis = pipeline(model=model)
+
+    #Predictions
+    predictions=analyze_sentiments(values_list,sentiment_analysis)
+
+    #Weighted Average
+    weighted_avg=calculate_weighted_average(predictions)
+
+    #Pie-Chart
+    pie_chart = sentiment_pie_chart(predictions)
+
+    return f'Weighted Sentiment Score: {weighted_avg:.2f}', pie_chart
+
+iface = gr.Interface(
+    fn=main,
+    inputs=gr.inputs.Textbox(label="Stock"),
+    outputs=[gr.outputs.Textbox(label="Weighted Sentiment Score"), gr.outputs.Plot(label="Sentiment Distribution")]
+)
+
+if __name__ == "__main__":
+    iface.launch()