Create tab1_works.py

mylab/tab1_works.py

@@ -0,0 +1,190 @@
+import streamlit as st
+import pandas as pd
+import plotly.express as px
+from pandasai import Agent
+from langchain_community.embeddings.openai import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_openai import ChatOpenAI
+from langchain.chains import RetrievalQA
+from langchain.schema import Document
+import os
+import re
+
+# Set title
+st.title("Data Analyzer")
+
+# API keys
+api_key = os.getenv("OPENAI_API_KEY")
+pandasai_api_key = os.getenv("PANDASAI_API_KEY")
+
+if not api_key or not pandasai_api_key:
+    st.warning("API keys for OpenAI or PandasAI are missing. Ensure both keys are set in environment variables.")
+
+# Add session reset button
+if st.button("Reset Session"):
+    for key in list(st.session_state.keys()):
+        del st.session_state[key]
+    st.experimental_rerun()
+
+# Function to validate and clean dataset
+def validate_and_clean_dataset(df):
+    # Rename columns for consistency
+    df.columns = [col.strip().lower().replace(" ", "_") for col in df.columns]
+    # Check for missing values
+    if df.isnull().values.any():
+        st.warning("Dataset contains missing values. Consider cleaning the data.")
+    return df
+
+# Function to load datasets into session
+def load_dataset_into_session():
+    input_option = st.radio(
+        "Select Dataset Input:",
+        ["Use Repo Directory Dataset", "Use Hugging Face Dataset", "Upload CSV File"],
+    )
+
+    # Option 1: Load dataset from the repo directory
+    if input_option == "Use Repo Directory Dataset":
+        file_path = "./source/test.csv"
+        if st.button("Load Dataset"):
+            try:
+                st.session_state.df = pd.read_csv(file_path)
+                st.session_state.df = validate_and_clean_dataset(st.session_state.df)
+                st.success(f"File loaded successfully from '{file_path}'!")
+            except Exception as e:
+                st.error(f"Error loading dataset from the repo directory: {e}")
+
+    # Option 2: Load dataset from Hugging Face
+    elif input_option == "Use Hugging Face Dataset":
+        dataset_name = st.text_input(
+            "Enter Hugging Face Dataset Name:", value="HUPD/hupd"
+        )
+        if st.button("Load Hugging Face Dataset"):
+            try:
+                from datasets import load_dataset
+                dataset = load_dataset(dataset_name, split="train", trust_remote_code=True)
+                if hasattr(dataset, "to_pandas"):
+                    st.session_state.df = dataset.to_pandas()
+                else:
+                    st.session_state.df = pd.DataFrame(dataset)
+                st.session_state.df = validate_and_clean_dataset(st.session_state.df)
+                st.success(f"Hugging Face Dataset '{dataset_name}' loaded successfully!")
+            except Exception as e:
+                st.error(f"Error loading Hugging Face dataset: {e}")
+
+    # Option 3: Upload CSV File
+    elif input_option == "Upload CSV File":
+        uploaded_file = st.file_uploader("Upload a CSV File:", type=["csv"])
+        if uploaded_file:
+            try:
+                st.session_state.df = pd.read_csv(uploaded_file)
+                st.session_state.df = validate_and_clean_dataset(st.session_state.df)
+                st.success("File uploaded successfully!")
+            except Exception as e:
+                st.error(f"Error reading uploaded file: {e}")
+
+load_dataset_into_session()
+
+# Check if the dataset and API keys are loaded
+if "df" in st.session_state and api_key and pandasai_api_key:
+    # Set API keys
+    os.environ["OPENAI_API_KEY"] = api_key
+    os.environ["PANDASAI_API_KEY"] = pandasai_api_key
+
+    df = st.session_state.df
+    st.write("Dataset Preview:")
+    st.write(df.head())  # Ensure the dataset preview is displayed only once
+
+    # Set up PandasAI Agent
+    try:
+        agent = Agent(df)
+        st.info("PandasAI Agent initialized successfully.")
+    except Exception as e:
+        st.error(f"Error initializing PandasAI Agent: {str(e)}")
+
+    # Convert dataframe into documents
+    try:
+        documents = [
+            Document(
+                page_content=", ".join([f"{col}: {row[col]}" for col in df.columns]),
+                metadata={"index": index}
+            )
+            for index, row in df.iterrows()
+        ]
+        st.info("Documents created successfully for RAG.")
+    except Exception as e:
+        st.error(f"Error creating documents for RAG: {str(e)}")
+
+    # Set up RAG
+    try:
+        embeddings = OpenAIEmbeddings()
+        vectorstore = FAISS.from_documents(documents, embeddings)
+        retriever = vectorstore.as_retriever()
+        qa_chain = RetrievalQA.from_chain_type(
+            llm=ChatOpenAI(),
+            chain_type="stuff",
+            retriever=retriever
+        )
+        st.info("RAG setup completed successfully.")
+    except Exception as e:
+        st.error(f"Error setting up RAG: {str(e)}")
+
+    # Create tabs
+    tab1, tab2, tab3 = st.tabs(["PandasAI Analysis", "RAG Q&A", "Data Visualization"])
+
+    with tab1:
+        st.subheader("Data Analysis with PandasAI")
+        pandas_question = st.text_input("Ask a question about the dataset (PandasAI):")
+        if pandas_question:
+            try:
+                result = agent.chat(pandas_question)
+                st.write("PandasAI Answer:", result)
+                if hasattr(agent, "last_output"):
+                    st.write("PandasAI Intermediate Output:", agent.last_output)
+            except Exception as e:
+                st.error(f"PandasAI encountered an error: {str(e)}")
+                # Fallback: Direct pandas filtering
+                if "patent_number" in pandas_question.lower() and "decision" in pandas_question.lower():
+                    try:
+                        match = re.search(r'\d{7,}', pandas_question)
+                        if match:
+                            patent_number = match.group()
+                            decision = df.loc[df['patent_number'] == int(patent_number), 'decision']
+                            st.write(f"Fallback Answer: The decision for patent {patent_number} is '{decision.iloc[0]}'.")
+                        else:
+                            st.write("Could not extract patent number from the query.")
+                    except Exception as fallback_error:
+                        st.error(f"Fallback processing failed: {fallback_error}")
+
+    with tab2:
+        st.subheader("Q&A with RAG")
+        rag_question = st.text_input("Ask a question about the dataset (RAG):")
+        if rag_question:
+            try:
+                result = qa_chain.run(rag_question)
+                st.write("RAG Answer:", result)
+            except Exception as e:
+                st.error(f"RAG encountered an error: {str(e)}")
+
+    with tab3:
+        st.subheader("Data Visualization")
+        viz_question = st.text_input("What kind of graph would you like? (e.g., 'Show a scatter plot of salary vs experience')")
+        if viz_question:
+            try:
+                result = agent.chat(viz_question)
+                code_pattern = r'```python\n(.*?)\n```'
+                code_match = re.search(code_pattern, result, re.DOTALL)
+                
+                if code_match:
+                    viz_code = code_match.group(1)
+                    exec(viz_code)
+                else:
+                    st.write("Unable to generate the graph. Showing fallback example.")
+                    fig = px.scatter(df, x=df.columns[0], y=df.columns[1])
+                    st.plotly_chart(fig)
+            except Exception as e:
+                st.error(f"An error occurred during visualization: {str(e)}")
+else:
+    if not api_key:
+        st.warning("Please set the OpenAI API key in environment variables.")
+    if not pandasai_api_key:
+        st.warning("Please set the PandasAI API key in environment variables.")