Update app.py with new dependencies and refactor code for Hugging Face spaces

app.py

@@ -3,28 +3,31 @@ from gnews import GNews
 import pandas as pd
 from transformers import pipeline
 from datetime import datetime, timedelta
+import matplotlib.pyplot as plt
+import tensorflow as tf
 
 
-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')
+# 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()
+#     # Get the current date
+#     current_date = datetime.utcnow()
     
-    # Calculate the date two months ago
-    two_months_ago = current_date - timedelta(days=60)
+#     # 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]
+#     # 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
+#     return df_filtered
 
 
 def extract_and_clean_titles(df):
     # Initialize an empty list to store the cleaned titles
     values_list = []
-
+    if(df.empty):
+        return 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
@@ -82,7 +85,7 @@ def calculate_weighted_average(predictions):
     return weighted_avg
 
 
-def sentiment_pie_chart(predictions):
+def sentiment_pie_chart(predictions, stock ,output_path='sentiment_pie_chart.png'):
     """
     Generates a pie chart for sentiment distribution.
     """
@@ -108,8 +111,13 @@ def sentiment_pie_chart(predictions):
     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
+    plt.title('Sentiment Analysis Results for ' + stock + ' Stock')
+
+    # Save the plot as an image file
+    plt.savefig(output_path)
+    plt.close(fig)
+    return output_path
+
 
 
 def main(stock):
@@ -117,16 +125,18 @@ def main(stock):
     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")
+    google_news = GNews(max_results=50, period='30d')
+    Company_news=google_news.get_news(stock + "stock")
     df=pd.DataFrame(Company_news)
-
+    print(df)
     #Discarding old rows
-    df=discard_old_rows(df)
-
+    # df=discard_old_rows(df)
+    if(df.empty): 
+        return "Not enough data, please increase timeframe", None
     #Cleaning the titles for sentiment analysis
     values_list=extract_and_clean_titles(df)
     
+    
     #Sentiment Analysis
     sentiment_analysis = pipeline(model=model)
 
@@ -137,13 +147,21 @@ def main(stock):
     weighted_avg=calculate_weighted_average(predictions)
 
     #Pie-Chart
-    pie_chart = sentiment_pie_chart(predictions)
+    pie_chart_path = sentiment_pie_chart(predictions, stock)
+
+    if(weighted_avg>=-0.10 and weighted_avg<=0.10):
+        return f'{weighted_avg:.2f} (Stagnant)', pie_chart_path
+    elif(weighted_avg>0.1):
+        return f'{weighted_avg:.2f} (Positive)', pie_chart_path
+    else:
+        return f'{weighted_avg:.2f} (Negative)', pie_chart_path 
+
+
 
-    return f'Weighted Sentiment Score: {weighted_avg:.2f}', pie_chart
 
 iface = gr.Interface(
     fn=main,
-    inputs="textbox",
+    inputs=["textbox"],
     outputs=["textbox","image"]
 )
 

requirements.txt

@@ -3,4 +3,7 @@ transformers
 pandas
 numpy
 gradio
-datetime
+datetime
+matplotlib
+tensorflow
+tf-keras