AI Data Analysis Agent

import tempfile
import csv
import pandas as pd

def preprocess_and_save(file):
    """Preprocess and save uploaded file with proper type detection."""
    try:
        # Read the uploaded file
        if file.name.endswith('.csv'):
            df = pd.read_csv(file, encoding='utf-8', 
                           na_values=['NA', 'N/A', 'missing'])
        elif file.name.endswith('.xlsx'):
            df = pd.read_excel(file, 
                             na_values=['NA', 'N/A', 'missing'])
        else:
            return None, None, None
        
        # Ensure string columns are properly quoted
        for col in df.select_dtypes(include=['object']):
            df[col] = df[col].astype(str).replace({r'"': '""'}, regex=True)
        
        # Parse dates and numeric columns
        for col in df.columns:
            if 'date' in col.lower():
                df[col] = pd.to_datetime(df[col], errors='coerce')
            elif df[col].dtype == 'object':
                try:
                    df[col] = pd.to_numeric(df[col])
                except (ValueError, TypeError):
                    pass
        
        # Save to temporary CSV
        with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as temp_file:
            temp_path = temp_file.name
            df.to_csv(temp_path, index=False, quoting=csv.QUOTE_ALL)
        
        return temp_path, df.columns.tolist(), df
        
    except Exception as e:
        st.error(f"Error processing file: {e}")
        return None, None, None

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckdb import DuckDbTools
from agno.tools.pandas import PandasTools
import streamlit as st

# Initialize DuckDB tools
duckdb_tools = DuckDbTools()

# Load data into DuckDB
duckdb_tools.load_local_csv_to_table(
    path=temp_path,
    table="uploaded_data",
)

# Create the AI Data Analyst Agent
data_analyst_agent = Agent(
    model=OpenAIChat(id="gpt-4o", api_key=openai_key),
    tools=[duckdb_tools, PandasTools()],
    system_message="""
    You are an expert data analyst. Use the 'uploaded_data' table 
    to answer user queries. Generate SQL queries using DuckDB tools 
    to solve the user's query. Provide clear and concise answers 
    with the results.
    """,
    markdown=True,
)

# Process user query
user_query = "What are the top 5 customers by total purchase amount?"
response = data_analyst_agent.run(user_query)

# Display results
st.markdown(response.content)

import streamlit as st

st.title("📊 Data Analyst Agent")

# Sidebar for API keys
with st.sidebar:
    st.header("API Keys")
    openai_key = st.text_input("Enter your OpenAI API key:", type="password")
    if openai_key:
        st.session_state.openai_key = openai_key
        st.success("API key saved!")
    else:
        st.warning("Please enter your OpenAI API key to proceed.")

# File upload
uploaded_file = st.file_uploader("Upload a CSV or Excel file", 
                                 type=["csv", "xlsx"])

if uploaded_file and "openai_key" in st.session_state:
    # Preprocess data
    temp_path, columns, df = preprocess_and_save(uploaded_file)
    
    if temp_path:
        # Display uploaded data
        st.write("Uploaded Data:")
        st.dataframe(df)
        st.write("Columns:", columns)
        
        # Initialize agent (code shown above)
        # ...
        
        # Query interface
        user_query = st.text_area("Ask a query about the data:")
        
        st.info("💡 Check your terminal for clearer agent output")
        
        if st.button("Submit Query"):
            if user_query.strip():
                with st.spinner('Processing your query...'):
                    response = data_analyst_agent.run(user_query)
                    st.markdown(response.content)
            else:
                st.warning("Please enter a query.")

for col in df.columns:
    # Date detection
    if 'date' in col.lower():
        df[col] = pd.to_datetime(df[col], errors='coerce')
    
    # Numeric conversion
    elif df[col].dtype == 'object':
        try:
            df[col] = pd.to_numeric(df[col])
        except (ValueError, TypeError):
            pass  # Keep as string