Upload first version

app.py

@@ -0,0 +1,234 @@
+# import streamlit as st
+# import pandas as pd
+# import numpy as np
+# import matplotlib.pyplot as plt
+
+# # Placeholder for loading models
+# def load_models():
+#     # In a real scenario, you would load your pre-trained models here.
+#     return {"model_placeholder": "Loaded Model"}
+
+# # Placeholder function to classify news as ESG-related
+# def classify_esg(text, models, api_key):
+#     # Simulate ESG classification logic
+#     # This is where you would use your model to classify the text.
+#     return np.random.choice(["Yes", "No"])
+
+# # Placeholder function to determine sentiment
+# def determine_sentiment(text, models, api_key):
+#     # Simulate sentiment analysis logic
+#     # This is where you would use your model to determine the sentiment.
+#     return np.random.choice(["Positive", "Neutral", "Negative"])
+
+# # Placeholder function to run Alphalens analysis
+# def run_alphalens_analysis(data, models, api_key):
+#     # Simulate some metrics
+#     metrics = {"alpha": np.random.rand(), "beta": np.random.rand()}
+    
+#     # Generate a simple plot
+#     fig, ax = plt.subplots()
+#     ax.plot([1, 2, 3], [1, 2, 3], 'r')  # Example plot
+#     ax.set_title('Example Plot')
+    
+#     return metrics, [fig]
+
+# # Streamlit app code
+# models = load_models()
+
+# st.title('NLP Project: ESG News Analysis and Financial Impact')
+
+# api_key = st.sidebar.text_input("OpenAI API Key", type="password")
+
+# uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+# if uploaded_file is not None:
+#     data = pd.read_csv(uploaded_file)
+#     st.write("Uploaded News Data:")
+#     st.dataframe(data)
+
+#     if st.button('Classify News as ESG-related'):
+#         data['ESG'] = data['news'].apply(lambda x: classify_esg(x, models, api_key))
+#         st.write("News with ESG Classification:")
+#         st.dataframe(data)
+
+#     if st.button('Determine Sentiment'):
+#         data['Sentiment'] = data['news'].apply(lambda x: determine_sentiment(x, models, api_key))
+#         st.write("News with Sentiment Analysis:")
+#         st.dataframe(data)
+
+#     if st.button('Run Alphalens Analysis'):
+#         metrics, plots = run_alphalens_analysis(data, models, api_key)
+#         st.write("Alphalens Analysis Metrics:")
+#         st.json(metrics)
+        
+#         st.write("Alphalens Analysis Plots:")
+#         for plot in plots:
+#             st.pyplot(plot)
+
+
+import streamlit as st
+import pandas as pd
+import numpy as np
+import os
+import openai
+import json
+from getpass import getpass
+from tqdm import tqdm
+import matplotlib.pyplot as plt
+
+def get_sentiment_gpt(company, SASB, news, max_retries=5, model = 'gpt-4-turbo-2024-04-09'):
+    system_prompt = """
+    As a specialist in ESG analytics, 
+    You possess a deep understanding of evaluating environmental, social, and governance factors in the context of corporate news. 
+    Your expertise lies in discerning the underlying sentiment of news segments that pertain to a company's ESG practices, 
+    determining whether the coverage reflects a positive, negative, or neutral stance.
+    """
+
+    allowed_sentiments = ['Negative', 'Positive', 'Neutral']
+    attempt = 0
+
+    while attempt < max_retries:
+        main_prompt = f"""
+        Classify the sentiment (Only options: Positive, Negative, Neutral) of the following news: {news} |
+        The sentiment classification should be about the sections of the news talking about the company {company}. | 
+        The ESG part of the news should be around topics within the following SASB topics {SASB}
+
+        The output should be a structured JSON object with the key: "sentiment".
+
+        Here is the format I expect for the JSON object:
+
+        {{
+          "sentiment": "Enter 'Positive', 'Neutral', or 'Negative'",
+        }}
+
+        Do not return any additional text or information outside of this JSON structure.
+        """
+
+        messages = [
+          {"role": "system", "content": system_prompt},
+          {"role": "user", "content": main_prompt}
+        ]
+
+        response = openai.chat.completions.create(
+        model=model,
+        messages=messages,
+        response_format={"type": "json_object"}  # Enable JSON mode
+        )
+
+        response_json = json.loads(response.choices[0].message.content)
+        json_sentiment = response_json.get('sentiment')
+
+        if json_sentiment in allowed_sentiments:
+            return json_sentiment
+
+        attempt += 1
+
+    # After max retries, if no valid sentiment is found, handle as needed (e.g., return a default sentiment)
+    print("Failed to obtain a valid sentiment after maximum retries. Defaulting to 'Neutral'.")
+    return 'Neutral'  # Default return value if no valid sentiment is obtained
+
+
+def update_dataset_with_gpt_sentiment(df, model, column_name='GPT_based_sentiment'):
+    # Initialize the new column to store GPT-based sentiment
+    df['GPT_based_sentiment'] = None
+    
+    # Use tqdm to show a progress bar for the operation
+    for index, row in tqdm(df.iterrows(), total=len(df), desc="Processing rows"):
+        # Extract necessary information for each row
+        company = row['Company']  # Make sure this matches your DataFrame's column name
+        SASB = row['SASB']  # Make sure this matches your DataFrame's column name
+        news = row['title & content']  # Make sure this matches your DataFrame's column name
+        
+        # Call the function to get the sentiment
+        sentiment = get_sentiment_gpt(company, SASB, news, model=model)
+        
+        # Update the DataFrame with the obtained sentiment
+        df.at[index, column_name] = sentiment  # Now correctly assigns the sentiment
+        
+    return df
+
+def app_layout():
+    st.set_page_config(page_title="NLP ESG Project", page_icon="📈")
+
+    # Custom styles
+    st.markdown(
+        """
+        <style>
+        .streamlit-container {
+            background-color: #F5F5F5;
+        }
+        .stButton>button {
+            width: 100%;
+            border-radius: 10px;
+            border: none;
+            margin: 10px 0;
+            padding: 15px 20px;
+            background-color: #79AEC8;
+            color: white;
+            font-size: 18px;
+        }
+        .stButton>button:hover {
+            background-color: #6699CC;
+        }
+        </style>
+        """,
+        unsafe_allow_html=True,
+    )
+
+    # Header section
+    st.write("# NLP Project: ESG News Analysis and Financial Impact")
+    st.sidebar.write("## Configuration")
+
+    # API Key input
+    openai_api_key = st.sidebar.text_input("Enter your OpenAI API key", type="password")
+
+    # File Upload
+    st.sidebar.write("## Upload Data")
+    uploaded_file = st.sidebar.file_uploader("", type="csv")
+
+    # Investment Strategy Slider
+    st.sidebar.markdown("### Investment Strategy")
+    investment_strategy = st.sidebar.slider(
+        "Investment Strategy",
+        min_value=0.0, max_value=1.0, value=0.5, step=0.01,
+        format="",
+        help="0 is Conservative, 1 is Aggressive",
+        label_visibility="collapsed"
+    )
+    st.sidebar.text(f"Current Strategy: {'Conservative' if investment_strategy <= 0.5 else 'Aggressive'}")
+
+    # Main container
+    if uploaded_file is not None:
+        # Displaying the file
+        data = pd.read_csv(uploaded_file)
+        st.write("### Uploaded News Data:")
+        st.dataframe(data, use_container_width=True)
+
+        if st.button("🔍 Classify ESG"):
+            st.write("Classifying ESG-related news...")
+            # Placeholder - replace with actual ESG classification code
+            data['ESG'] = "Yes"  # placeholder
+
+        if st.button("😊 Determine Sentiment"):
+            st.write("Determining sentiment using GPT...")
+            # Run sentiment analysis with GPT
+            try:
+                with st.spinner("Analyzing sentiment..."):
+                    # Assume you have your API key set and a function defined to handle sentiment analysis
+                    updated_data = update_dataset_with_gpt_sentiment(data, model='gpt-4-turbo-2024-04-09')
+                    st.write("News with GPT-based Sentiment Analysis:")
+                    st.dataframe(updated_data, use_container_width=True)
+            except Exception as e:
+                st.error(f"An error occurred: {e}")
+
+        if st.button("📊 Alphalens Analysis"):
+            st.write("Alphalens analysis will be here")  # placeholder
+
+        # Expander for advanced settings
+        with st.expander("Advanced Settings"):
+            st.write("Any advanced settings and configurations will go here.")
+
+def main():
+    app_layout()
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,9 @@
+streamlit
+pandas
+numpy
+os
+openai
+json
+getpass
+tqdm
+matplotlib.pyplot