Update app.py

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 import pandas as pd
 import numpy as np
 import plotly.express as px
-from plotly.graph_objects import Figure
+import plotly.graph_objects as go
 from ydata_profiling import ProfileReport
 from streamlit_pandas_profiling import st_profile_report
 import os
@@ -14,11 +14,10 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings import HuggingFaceEmbeddings
 import re
 from scipy import stats
-from sklearn.preprocessing import StandardScaler, LabelEncoder
+from sklearn.preprocessing import StandardScaler, LabelEncoder, OneHotEncoder
 import tempfile
-import json
 
-# Set page config
+# Set page config as the first Streamlit command
 st.set_page_config(page_title="Data-Vision Pro", layout="wide")
 
 # Load environment variables
@@ -27,160 +26,172 @@ load_dotenv()
 # Initialize Groq client
 client = Groq(api_key=os.getenv("GROQ_API_KEY"))
 
-# Initialize HuggingFace embeddings
+# Initialize HuggingFace embeddings for FAISS
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
-# Custom HTML/JS for Enhanced UI
-custom_html = """
-<style>
-  :root {
-    --silver-light: #D8D8D8;
-    --silver-dark: #B8B8B8;
-    --blue: #5C89BC;
-    --blue-dark: #4E73A0;
-    --blue-light: #6EA8E0;
-    --gold: #A87E01;
-    --shadow-color: rgba(0,0,0,0.1);
-  }
-  .stApp {
-    background: linear-gradient(135deg, var(--silver-light) 0%, var(--silver-dark) 100%);
-    font-family: 'Inter', sans-serif;
-    transition: all 0.3s ease;
-  }
-  .header {
-    background: linear-gradient(90deg, var(--blue) 80%, var(--blue-dark) 100%);
-    color: white;
-    padding: 20px;
-    border-radius: 16px 16px 0 0;
-    text-align: center;
-    box-shadow: 0 4px 12px var(--shadow-color);
-  }
-  .nav-tabs {
-    display: flex;
-    justify-content: space-around;
-    padding: 10px 0;
-    background: var(--silver-light);
-    border-bottom: 2px solid var(--gold);
-  }
-  .nav-tab {
-    padding: 10px 20px;
-    cursor: pointer;
-    color: var(--blue);
-    font-weight: 600;
-    transition: all 0.3s ease;
-  }
-  .nav-tab.active {
-    color: var(--gold);
-    border-bottom: 2px solid var(--gold);
-    background: white;
-    border-radius: 8px 8px 0 0;
-  }
-  .tab-content { display: none; padding: 20px; }
-  .tab-content.active { display: block; }
-  .chat-container {
-    background: white;
-    border-radius: 16px;
-    padding: 20px;
-    box-shadow: 0 6px 16px var(--shadow-color);
-    margin-top: 20px;
-  }
-  .message {
-    padding: 10px 15px;
-    margin: 5px 0;
-    border-radius: 12px;
-    max-width: 80%;
-  }
-  .user-message {
-    background: linear-gradient(45deg, var(--blue), var(--blue-light));
-    color: white;
-    margin-left: auto;
-  }
-  .bot-message {
-    background: #F0F0F0;
-    margin-right: auto;
-  }
-  .metrics {
-    display: flex;
-    gap: 20px;
-    margin: 10px 0;
-  }
-  .metric {
-    background: #F0F0F0;
-    padding: 10px;
-    border-radius: 8px;
-  }
-</style>
-<div class="header">
-  <h1>Data-Vision Pro</h1>
-  <div>Advanced Data Analysis with Groq Inference</div>
-</div>
-<div class="nav-tabs">
-  <div class="nav-tab active" data-tab="upload">Data Upload</div>
-  <div class="nav-tab" data-tab="cleaning">Data Cleaning</div>
-  <div class="nav-tab" data-tab="eda">EDA</div>
-</div>
-<div id="upload" class="tab-content active">
-  <h2>📤 Data Upload & Profiling</h2>
-  <div id="upload-output"></div>
-</div>
-<div id="cleaning" class="tab-content">
-  <h2>🧹 Data Cleaning</h2>
-  <div id="cleaning-output"></div>
-</div>
-<div id="eda" class="tab-content">
-  <h2>🔍 Interactive Data Explorer</h2>
-  <div id="eda-output"></div>
-</div>
-<div class="chat-container">
-  <h2>💬 AI Chatbot Assistant (RAG Enabled)</h2>
-  <div id="chat" style="max-height:300px; overflow-y:auto;"></div>
-  <input id="chat-input" placeholder="Ask me anything..." style="width:80%;">
-  <button onclick="sendChat()">Send</button>
-</div>
-<script>
-  // Tab Navigation
-  document.querySelectorAll('.nav-tab').forEach(tab => {
-    tab.addEventListener('click', () => {
-      document.querySelectorAll('.nav-tab').forEach(t => t.classList.remove('active'));
-      document.querySelectorAll('.tab-content').forEach(c => c.classList.remove('active'));
-      tab.classList.add('active');
-      document.getElementById(tab.dataset.tab).classList.add('active');
-      document.getElementById('app-mode').value = tab.dataset.tab.charAt(0).toUpperCase() + tab.dataset.tab.slice(1);
-    });
-  });
-
-  // Chat Functionality
-  function sendChat() {
-    const input = document.getElementById('chat-input');
-    const message = input.value.trim();
-    if (!message) return;
-    input.value = '';
-    const chat = document.getElementById('chat');
-    chat.innerHTML += `<div class="message user-message">${message}</div>`;
-    chat.scrollTop = chat.scrollHeight;
-
-    // Trigger Streamlit event via hidden input
-    document.getElementById('chat-trigger').value = message;
-    document.getElementById('chat-trigger').dispatchEvent(new Event('change'));
-  }
-
-  // Listen for bot responses from Streamlit
-  document.addEventListener('bot_response', (e) => {
-    const chat = document.getElementById('chat');
-    chat.innerHTML += `<div class="message bot-message">${e.detail}</div>`;
-    chat.scrollTop = chat.scrollHeight;
-  });
-</script>
-"""
-
-# Helper Functions (unchanged)
+# Custom CSS with Modernized Silver, Blue, and Gold Theme + Responsiveness
+st.markdown("""
+    <style>
+    :root {
+        --silver-light: #D8D8D8;
+        --silver-dark: #B8B8B8;
+        --blue: #5C89BC;
+        --blue-dark: #4E73A0;
+        --blue-light: #6EA8E0;
+        --gold: #A87E01;
+        --text-color: #333333;
+        --shadow-color: rgba(0,0,0,0.1);
+        --shadow-color-stronger: rgba(0,0,0,0.2);
+    }
+    .stApp {
+        background: linear-gradient(135deg, var(--silver-light) 0%, var(--silver-dark) 100%);
+        font-family: 'Inter', sans-serif;
+        max-width: 900px;
+        margin: 0 auto;
+        padding: 10px;
+        transition: all 0.3s ease;
+    }
+    .header {
+        background: linear-gradient(90deg, var(--blue) 80%, var(--blue-dark) 100%);
+        color: white;
+        padding: 20px;
+        border-radius: 16px 16px 0 0;
+        box-shadow: 0 4px 12px var(--shadow-color);
+        text-align: center;
+        transition: transform 0.2s ease;
+    }
+    .header:hover {
+        transform: translateY(-2px);
+        box-shadow: 0 4px 12px var(--shadow-color-stronger);
+    }
+    .header-title {
+        font-size: 1.5rem;
+        font-weight: 700;
+        margin: 0;
+    }
+    .header-subtitle {
+        font-size: 0.9rem;
+        margin-top: 8px;
+        opacity: 0.9;
+    }
+    .sidebar .sidebar-content {
+        background-color: white;
+        border-radius: 16px;
+        box-shadow: 0 6px 16px var(--shadow-color);
+        padding: 20px;
+        transition: box-shadow 0.3s ease;
+    }
+    .sidebar .sidebar-content:hover {
+        box-shadow: 0 8px 20px var(--shadow-color-stronger);
+    }
+    .chat-container {
+        background-color: white;
+        border-radius: 16px;
+        box-shadow: 0 6px 16px var(--shadow-color);
+        padding: 20px;
+        margin-top: 25px;
+        transition: box-shadow 0.3s ease;
+    }
+    .chat-container:hover {
+        box-shadow: 0 8px 20px var(--shadow-color-stronger);
+    }
+    .user-message {
+        background: linear-gradient(45deg, var(--blue), var(--blue-light));
+        color: white;
+        border-radius: 20px 20px 6px 20px;
+        padding: 14px 18px;
+        margin-left: auto;
+        max-width: 80%;
+        margin-bottom: 12px;
+        box-shadow: 0 2px 8px var(--blue-dark);
+        transition: transform 0.2s ease;
+    }
+    .user-message:hover {
+        transform: scale(1.02);
+    }
+    .bot-message {
+        background-color: #F0F0F0;
+        color: var(--text-color);
+        border-radius: 20px 20px 20px 6px;
+        padding: 14px 18px;
+        margin-right: auto;
+        max-width: 80%;
+        margin-bottom: 12px;
+        box-shadow: 0 2px 8px var(--shadow-color);
+        transition: transform 0.2s ease;
+    }
+    .bot-message:hover {
+        transform: scale(1.02);
+    }
+    .footer {
+        text-align: center;
+        margin-top: 20px;
+        color: var(--text-color);
+        font-size: 0.8rem;
+    }
+    .tech-badge {
+        display: inline-block;
+        background-color: #E6ECEF;
+        color: var(--blue);
+        padding: 4px 8px;
+        border-radius: 12px;
+        font-size: 0.7rem;
+        margin: 0 4px;
+    }
+    h2 {
+        color: var(--blue);
+        border-bottom: 2px solid var(--gold);
+        padding-bottom: 5px;
+        font-size: 1.5rem;
+        font-weight: 700;
+    }
+    .stButton > button {
+        background-color: var(--gold);
+        color: white;
+        border-radius: 12px;
+        padding: 10px 20px;
+        border: none;
+        box-shadow: 0 4px 12px var(--shadow-color);
+        font-weight: 600;
+        transition: all 0.3s ease;
+    }
+    .stButton > button:hover {
+        background-color: #8C6B01;
+        transform: translateY(-2px);
+        box-shadow: 0 6px 16px var(--shadow-color-stronger);
+    }
+    @media (max-width: 768px) {
+        .header-title {
+            font-size: 1.2rem;
+        }
+        .header-subtitle {
+            font-size: 0.8rem;
+        }
+        .chat-container, .sidebar .sidebar-content {
+            padding: 10px;
+        }
+        .stApp {
+            padding: 5px;
+        }
+        h2 {
+            font-size: 1.2rem;
+        }
+    }
+    </style>
+""", unsafe_allow_html=True)
+
+# Helper Functions
+def enhance_section_title(title):
+    st.markdown(f"<h2 style='border-bottom: 2px solid var(--gold); padding-bottom: 5px; color: var(--blue);'>{title}</h2>", unsafe_allow_html=True)
+
 def update_cleaned_data(df):
     st.session_state.cleaned_data = df
     if 'data_versions' not in st.session_state:
         st.session_state.data_versions = [st.session_state.raw_data.copy()]
     st.session_state.data_versions.append(df.copy())
     st.session_state.dataset_text = convert_df_to_text(df)
-    return "✅ Action completed successfully!"
+    st.success("✅ Action completed successfully!")
+    st.rerun()
 
 def convert_df_to_text(df):
     text = f"Dataset Summary: {df.shape[0]} rows, {df.shape[1]} columns\n"
@@ -227,33 +238,61 @@ def extract_plot_data(plot_info, df):
     x_col = plot_info["x"]
     y_col = plot_info["y"] if "y" in plot_info else None
     data = pd.read_json(plot_info["data"])
-    plot_text = f"Plot Type: {plot_type}\nX-Axis: {x_col}\n"
+    plot_text = f"Plot Type: {plot_type}\n"
+    plot_text += f"X-Axis: {x_col}\n"
     if y_col:
         plot_text += f"Y-Axis: {y_col}\n"
     if plot_type == "Scatter Plot" and y_col:
         correlation = data[x_col].corr(data[y_col])
         slope, intercept, r_value, p_value, std_err = stats.linregress(data[x_col].dropna(), data[y_col].dropna())
-        plot_text += f"Correlation: {correlation:.2f}\nLinear Regression: Slope={slope:.2f}, Intercept={intercept:.2f}, R²={r_value**2:.2f}, p-value={p_value:.4f}\n"
+        plot_text += f"Correlation: {correlation:.2f}\n"
+        plot_text += f"Linear Regression: Slope={slope:.2f}, Intercept={intercept:.2f}, R²={r_value**2:.2f}, p-value={p_value:.4f}\n"
+        plot_text += f"X Stats: Mean={data[x_col].mean():.2f}, Std={data[x_col].std():.2f}, Min={data[x_col].min():.2f}, Max={data[x_col].max():.2f}\n"
+        plot_text += f"Y Stats: Mean={data[y_col].mean():.2f}, Std={data[y_col].std():.2f}, Min={data[y_col].min():.2f}, Max={data[y_col].max():.2f}\n"
+    elif plot_type == "Histogram":
+        plot_text += f"Stats: Mean={data[x_col].mean():.2f}, Median={data[x_col].median():.2f}, Std={data[x_col].std():.2f}\n"
+        plot_text += f"Skewness: {data[x_col].skew():.2f}\n"
+        plot_text += f"Range: [{data[x_col].min():.2f}, {data[x_col].max():.2f}]\n"
+    elif plot_type == "Box Plot" and y_col:
+        q1, q3 = data[y_col].quantile(0.25), data[y_col].quantile(0.75)
+        iqr = q3 - q1
+        plot_text += f"Y Stats: Median={data[y_col].median():.2f}, Q1={q1:.2f}, Q3={q3:.2f}, IQR={iqr:.2f}\n"
+        plot_text += f"Outliers: {len(data[y_col][(data[y_col] < q1 - 1.5 * iqr) | (data[y_col] > q3 + 1.5 * iqr)])} potential outliers\n"
+    elif plot_type == "Line Chart" and y_col:
+        plot_text += f"Y Stats: Mean={data[y_col].mean():.2f}, Std={data[y_col].std():.2f}, Trend={'increasing' if data[y_col].iloc[-1] > data[y_col].iloc[0] else 'decreasing'}\n"
+    elif plot_type == "Bar Chart":
+        plot_text += f"Counts: {data[x_col].value_counts().to_dict()}\n"
+    elif plot_type == "Correlation Matrix":
+        corr = data.corr()
+        plot_text += "Correlation Matrix:\n"
+        for col1 in corr.columns:
+            for col2 in corr.index:
+                if col1 < col2:
+                    plot_text += f"{col1} vs {col2}: {corr.loc[col2, col1]:.2f}\n"
     return plot_text
 
 def get_chatbot_response(user_input, app_mode, vector_store=None, model="llama3-70b-8192"):
     system_prompt = (
-        f"You are an AI assistant in Data-Vision Pro, on the '{app_mode}' page:\n"
-        "- Data Upload: Upload CSV/XLSX files, view stats, or generate reports.\n"
-        "- Data Cleaning: Clean data (e.g., handle missing values, encode variables).\n"
-        "- EDA: Visualize data (e.g., scatter plots, histograms) and analyze plots.\n"
-        "Use context if provided."
+        "You are an AI assistant in Data-Vision Pro, a data analysis app with RAG capabilities. "
+        f"The user is on the '{app_mode}' page:\n"
+        "- **Data Upload**: Upload CSV/XLSX files, view stats, or generate reports.\n"
+        "- **Data Cleaning**: Clean data (e.g., handle missing values, encode variables).\n"
+        "- **EDA**: Visualize data (e.g., scatter plots, histograms) and analyze plots.\n"
+        "When analyzing plots, provide detailed insights based on numerical data extracted from them."
     )
     context = ""
     if vector_store:
         docs = vector_store.similarity_search(user_input, k=3)
         if docs:
-            context = "\n\nContext:\n" + "\n".join([f"- {doc.page_content}" for doc in docs])
+            context = "\n\nDataset and Plot Context:\n" + "\n".join([f"- {doc.page_content}" for doc in docs])
+            system_prompt += f"Use this dataset and plot context to augment your response:\n{context}"
+    else:
+        system_prompt += "No dataset or plot data is loaded. Assist based on app functionality."
     try:
         response = client.chat.completions.create(
             model=model,
             messages=[
-                {"role": "system", "content": system_prompt + context},
+                {"role": "system", "content": system_prompt},
                 {"role": "user", "content": user_input}
             ],
             temperature=0.7,
@@ -263,164 +302,379 @@ def get_chatbot_response(user_input, app_mode, vector_store=None, model="llama3-
     except Exception as e:
         return f"Error: {str(e)}"
 
-def parse_command(command, df):
-    command = command.lower().strip()
-    if "drop columns" in command:
-        columns = command.replace("drop columns", "").strip().split(',')
-        valid_cols = [col.strip() for col in columns if col.strip() in df.columns]
-        if valid_cols:
-            df = df.drop(columns=valid_cols)
+# Command Functions
+def drop_columns(columns):
+    if 'cleaned_data' in st.session_state:
+        df = st.session_state.cleaned_data.copy()
+        columns_to_drop = [col.strip() for col in columns.split(',')]
+        valid_columns = [col for col in columns_to_drop if col in df.columns]
+        if valid_columns:
+            df.drop(valid_columns, axis=1, inplace=True)
             update_cleaned_data(df)
-            return df, f"Dropped columns: {', '.join(valid_cols)}"
-        return df, "No valid columns to drop."
-    elif "scatter plot of" in command:
-        match = re.search(r"([\w\s]+)\s+vs\s+([\w\s]+)", command)
-        if match:
-            x, y = match.group(1).strip(), match.group(2).strip()
-            if x in df.columns and y in df.columns:
-                fig = px.scatter(df, x=x, y=y)
-                plot_info = {"type": "Scatter Plot", "x": x, "y": y, "data": df[[x, y]].to_json()}
-                return df, fig, plot_info
-        return df, None, "Invalid scatter plot command."
-    elif "histogram of" in command:
-        col = command.replace("histogram of", "").strip()
-        if col in df.columns:
-            fig = px.histogram(df, x=col)
-            plot_info = {"type": "Histogram", "x": col, "data": df[[col]].to_json()}
-            return df, fig, plot_info
-        return df, None, "Invalid histogram command."
-    elif "analyze plot" in command and "last_plot" in st.session_state:
-        plot_info = st.session_state.last_plot
-        plot_text = extract_plot_data(plot_info, df)
-        st.session_state.vector_store = update_vector_store_with_plot(plot_text, st.session_state.vector_store)
-        return df, plot_text
-    return df, None, None
+            return f"Dropped columns: {', '.join(valid_columns)}"
+        else:
+            return "No valid columns found to drop."
+    return "No dataset loaded."
 
-# Main App
-def main():
-    # Render Custom HTML
-    st.markdown(custom_html, unsafe_allow_html=True)
+def generate_scatter_plot(params):
+    df = st.session_state.cleaned_data
+    match = re.search(r"([\w\s]+)\s+vs\s+([\w\s]+)", params)
+    if match and len(match.groups()) >= 2:
+        x_axis, y_axis = match.group(1).strip(), match.group(2).strip()
+        if x_axis in df.columns and y_axis in df.columns:
+            fig = px.scatter(df, x=x_axis, y=y_axis, title=f'Scatter Plot of {x_axis} vs {y_axis}')
+            st.plotly_chart(fig)
+            st.session_state.last_plot = {"type": "Scatter Plot", "x": x_axis, "y": y_axis, "data": df[[x_axis, y_axis]].to_json()}
+            return f"Generated scatter plot of {x_axis} vs {y_axis}"
+    return "Invalid columns for scatter plot."
+
+def generate_histogram(params):
+    df = st.session_state.cleaned_data
+    x_axis = params.strip()
+    if x_axis in df.columns:
+        fig = px.histogram(df, x=x_axis, title=f'Histogram of {x_axis}')
+        st.plotly_chart(fig)
+        st.session_state.last_plot = {"type": "Histogram", "x": x_axis, "data": df[[x_axis]].to_json()}
+        return f"Generated histogram of {x_axis}"
+    return "Invalid column for histogram."
+
+def analyze_plot():
+    if "last_plot" not in st.session_state:
+        return "No plot available to analyze."
+    plot_info = st.session_state.last_plot
+    df = pd.read_json(plot_info["data"])
+    plot_text = extract_plot_data(plot_info, df)
+    return f"Analysis of the last plot:\n{plot_text}"
+
+def parse_command(command):
+    command = command.lower().strip()
+    if "drop columns" in command or "drop column" in command:
+        columns = command.replace("drop columns", "").replace("drop column", "").strip()
+        return drop_columns, columns
+    elif "show a scatter plot" in command or "scatter plot of" in command:
+        params = command.replace("show a scatter plot of", "").replace("scatter plot of", "").strip()
+        return generate_scatter_plot, params
+    elif "show a histogram" in command or "histogram of" in command:
+        params = command.replace("show a histogram of", "").replace("histogram of", "").strip()
+        return generate_histogram, params
+    elif "analyze plot" in command:
+        return lambda x: analyze_plot(), None
+    return None, command
 
-    # Hidden Inputs for JS Interaction
-    if 'app_mode' not in st.session_state:
-        st.session_state.app_mode = "Data Upload"
-    st.markdown(f'<input id="app-mode" type="hidden" value="{st.session_state.app_mode}">', unsafe_allow_html=True)
-    st.markdown('<input id="chat-trigger" type="hidden">', unsafe_allow_html=True)
+# Dataset Preview Function
+def display_dataset_preview():
+    if 'cleaned_data' in st.session_state:
+        st.subheader("Current Dataset Preview")
+        st.dataframe(st.session_state.cleaned_data.head(10), use_container_width=True)
+        st.markdown("---")
 
-    # Sidebar
+# Main App
+def main():
+    # Header
+    st.markdown("""
+        <div class="header">
+            <h1 class="header-title">Data-Vision Pro</h1>
+            <div class="header-subtitle">Advanced Data Analysis with Groq Inference</div>
+        </div>
+    """, unsafe_allow_html=True)
+    
+    # Sidebar Navigation
     with st.sidebar:
         st.markdown("### 🔮 Data-Vision Pro")
-        model = st.selectbox("Select Groq Model", ["llama3-70b-8192", "llama3-8b-8192", "mixtral-8x7b-32768", "gemma-7b-it"], index=0)
+        st.markdown("Your AI-powered data analysis suite with RAG.")
+        st.markdown("---")
+        app_mode = st.selectbox(
+            "Navigation",
+            ["Data Upload", "Data Cleaning", "EDA"],
+            format_func=lambda x: f"📌 {x}"
+        )
+        model = st.selectbox(
+            "Select Groq Model",
+            ["llama3-70b-8192", "llama3-8b-8192", "mixtral-8x7b-32768", "gemma-7b-it"],
+            index=0
+        )
+        if app_mode == "Data Upload":
+            st.info("⬆️ Upload your CSV or XLSX dataset to begin.")
+        elif app_mode == "Data Cleaning":
+            st.info("🧹 Clean and preprocess your data.")
+        elif app_mode == "EDA":
+            st.info("🔍 Explore your data visually.")
+        
         if 'cleaned_data' in st.session_state:
             csv = st.session_state.cleaned_data.to_csv(index=False)
-            st.download_button(label="Download Cleaned Data", data=csv, file_name='cleaned_data.csv', mime='text/csv')
-
+            st.download_button(
+                label="Download Cleaned Data",
+                data=csv,
+                file_name='cleaned_data.csv',
+                mime='text/csv',
+            )
+        st.markdown("---")
+        st.markdown("Built with <span class='tech-badge'>Streamlit</span> + <span class='tech-badge'>Groq</span>", unsafe_allow_html=True)
+    
     # Initialize Session State
     if 'vector_store' not in st.session_state:
         st.session_state.vector_store = None
     if 'chat_history' not in st.session_state:
         st.session_state.chat_history = []
-
-    # App Logic
-    if st.session_state.app_mode == "Data Upload":
-        uploaded_file = st.file_uploader("Choose a file", type=["csv", "xlsx"])
+    
+    # Display Dataset Preview
+    display_dataset_preview()
+    
+    # App Pages
+    if app_mode == "Data Upload":
+        st.header("📤 Data Upload & Profiling")
+        uploaded_file = st.file_uploader("Choose a file", type=["csv", "xlsx"], key="file_uploader")
         if uploaded_file:
-            if uploaded_file.name.endswith('.csv'):
-                df = pd.read_csv(uploaded_file)
-            else:
-                df = pd.read_excel(uploaded_file)
-            st.session_state.raw_data = df
-            st.session_state.cleaned_data = df.copy()
-            st.session_state.dataset_text = convert_df_to_text(df)
-            st.session_state.vector_store = create_vector_store(st.session_state.dataset_text)
-            if 'data_versions' not in st.session_state:
-                st.session_state.data_versions = [df.copy()]
-            metrics_html = f"""
-            <div class="metrics">
-              <div class="metric">Rows: {df.shape[0]}</div>
-              <div class="metric">Columns: {df.shape[1]}</div>
-              <div class="metric">Missing: {df.isna().sum().sum()}</div>
-            </div>
-            <pre>{df.head().to_string()}</pre>
-            """
-            st.markdown(f'<div id="upload-output">{metrics_html}</div>', unsafe_allow_html=True)
-            if st.button("Generate Full Profile Report"):
-                with st.spinner("Generating report..."):
-                    pr = ProfileReport(df, explorative=True)
-                    st_profile_report(pr)
+            st.session_state.pop('raw_data', None)
+            st.session_state.pop('cleaned_data', None)
+            st.session_state.pop('data_versions', None)
+            try:
+                if uploaded_file.name.endswith('.csv'):
+                    df = pd.read_csv(uploaded_file)
+                else:
+                    df = pd.read_excel(uploaded_file)
+                if df.empty:
+                    st.error("Uploaded file is empty.")
+                    st.stop()
+                st.session_state.raw_data = df
+                st.session_state.cleaned_data = df.copy()
+                st.session_state.dataset_text = convert_df_to_text(df)
+                st.session_state.vector_store = create_vector_store(st.session_state.dataset_text)
+                if 'data_versions' not in st.session_state:
+                    st.session_state.data_versions = [df.copy()]
+                col1, col2, col3 = st.columns(3)
+                with col1: st.metric("Rows", df.shape[0])
+                with col2: st.metric("Columns", df.shape[1])
+                with col3: st.metric("Missing Values", df.isna().sum().sum())
+                if st.checkbox("Show Data Preview"):
+                    st.dataframe(df.head(10), use_container_width=True)
+                if st.button("Generate Full Profile Report"):
+                    with st.spinner("Generating report..."):
+                        pr = ProfileReport(df, explorative=True)
+                        st_profile_report(pr)
+                st.success("✅ Data loaded successfully!")
+            except Exception as e:
+                st.error(f"An error occurred: {str(e)}")
 
-    elif st.session_state.app_mode == "Data Cleaning":
-        if 'cleaned_data' not in st.session_state:
-            st.warning("Please upload data first.")
+    elif app_mode == "Data Cleaning":
+        st.header("🧹 Smart Data Cleaning")
+        if 'raw_data' not in st.session_state:
+            st.warning("Please upload data first in the Data Upload section.")
+            st.stop()
+        if 'cleaned_data' in st.session_state:
+            df = st.session_state.cleaned_data.copy()
         else:
-            df = st.session_state.cleaned_data
-            metrics_html = f"""
-            <div class="metrics">
-              <div class="metric">Rows: {df.shape[0]}</div>
-              <div class="metric">Columns: {df.shape[1]}</div>
-              <div class="metric">Missing: {df.isna().sum().sum()}</div>
-            </div>
-            """
-            st.markdown(f'<div id="cleaning-output">{metrics_html}</div>', unsafe_allow_html=True)
-            cols_to_drop = st.multiselect("Select columns to drop", df.columns)
-            if cols_to_drop and st.button("Drop Columns"):
-                df = df.drop(columns=cols_to_drop)
-                update_cleaned_data(df)
-                st.rerun()
-
-    elif st.session_state.app_mode == "EDA":
+            st.session_state.cleaned_data = st.session_state.raw_data.copy()
+            df = st.session_state.cleaned_data.copy()
+
+        enhance_section_title("📊 Data Health Dashboard")
+        with st.expander("Explore Data Health Metrics", expanded=True):
+            col1, col2, col3 = st.columns(3)
+            with col1: st.metric("Columns", len(df.columns))
+            with col2: st.metric("Rows", len(df))
+            with col3: st.metric("Missing Values", df.isna().sum().sum())
+            if st.button("Generate Detailed Health Report"):
+                with st.spinner("Generating report..."):
+                    profile = ProfileReport(df, minimal=True)
+                    st_profile_report(profile)
+            if 'data_versions' in st.session_state and len(st.session_state.data_versions) > 1:
+                if st.button("Undo Last Action"):
+                    st.session_state.data_versions.pop()
+                    st.session_state.cleaned_data = st.session_state.data_versions[-1].copy()
+                    st.session_state.dataset_text = convert_df_to_text(st.session_state.cleaned_data)
+                    st.session_state.vector_store = create_vector_store(st.session_state.dataset_text)
+                    st.rerun()
+
+        with st.expander("🛠️ Data Cleaning Operations", expanded=True):
+            enhance_section_title("🔍 Missing Values Treatment")
+            missing_cols = df.columns[df.isna().any()].tolist()
+            if missing_cols:
+                cols = st.multiselect("Select columns with missing values", missing_cols)
+                method = st.selectbox("Choose imputation method", [
+                    "Drop Missing Values", "Fill with Mean/Median", "Fill with Custom Value", "Forward Fill", "Backward Fill"
+                ])
+                if method == "Fill with Custom Value":
+                    custom_val = st.text_input("Enter custom value:")
+                if st.button("Apply Missing Value Treatment"):
+                    new_df = df.copy()
+                    if method == "Drop Missing Values":
+                        new_df = new_df.dropna(subset=cols)
+                    elif method == "Fill with Mean/Median":
+                        for col in cols:
+                            if pd.api.types.is_numeric_dtype(new_df[col]):
+                                new_df[col] = new_df[col].fillna(new_df[col].median())
+                            else:
+                                new_df[col] = new_df[col].fillna(new_df[col].mode()[0])
+                    elif method == "Fill with Custom Value" and custom_val:
+                        new_df[cols] = new_df[cols].fillna(custom_val)
+                    elif method == "Forward Fill":
+                        new_df[cols] = new_df[cols].ffill()
+                    elif method == "Backward Fill":
+                        new_df[cols] = new_df[cols].bfill()
+                    update_cleaned_data(new_df)
+            else:
+                st.success("✨ No missing values detected!")
+
+            enhance_section_title("🔄 Data Type Conversion")
+            col_to_convert = st.selectbox("Select column to convert", df.columns)
+            new_type = st.selectbox("Select new data type", ["String", "Integer", "Float", "Boolean", "Datetime"])
+            if new_type == "Datetime":
+                date_format = st.text_input("Enter date format (e.g., %Y-%m-%d):", "%Y-%m-%d")
+            if st.button("Convert Data Type"):
+                new_df = df.copy()
+                if new_type == "String":
+                    new_df[col_to_convert] = new_df[col_to_convert].astype(str)
+                elif new_type == "Integer":
+                    new_df[col_to_convert] = pd.to_numeric(new_df[col_to_convert], errors='coerce').astype('Int64')
+                elif new_type == "Float":
+                    new_df[col_to_convert] = pd.to_numeric(new_df[col_to_convert], errors='coerce')
+                elif new_type == "Boolean":
+                    new_df[col_to_convert] = new_df[col_to_convert].astype(bool)
+                elif new_type == "Datetime":
+                    new_df[col_to_convert] = pd.to_datetime(new_df[col_to_convert], format=date_format, errors='coerce')
+                update_cleaned_data(new_df)
+
+            enhance_section_title("🗑️ Drop Columns")
+            columns_to_drop = st.multiselect("Select columns to remove", df.columns)
+            if columns_to_drop and st.button("Confirm Column Removal"):
+                new_df = df.copy()
+                new_df = new_df.drop(columns=columns_to_drop)
+                update_cleaned_data(new_df)
+
+            enhance_section_title("🔢 Encoding Options")
+            encoding_method = st.radio("Choose encoding method", ("Label Encoding", "One-Hot Encoding"))
+            data_to_encode = st.multiselect("Select columns to encode", df.select_dtypes(include='object').columns)
+            if data_to_encode and st.button("Apply Encoding"):
+                new_df = df.copy()
+                if encoding_method == "Label Encoding":
+                    for col in data_to_encode:
+                        le = LabelEncoder()
+                        new_df[col] = le.fit_transform(new_df[col].astype(str))
+                elif encoding_method == "One-Hot Encoding":
+                    new_df = pd.get_dummies(new_df, columns=data_to_encode, drop_first=True, dtype=int)
+                update_cleaned_data(new_df)
+
+            enhance_section_title("📏 StandardScaler")
+            scale_cols = st.multiselect("Select numerical columns to scale", df.select_dtypes(include=np.number).columns)
+            if scale_cols and st.button("Apply StandardScaler"):
+                new_df = df.copy()
+                scaler = StandardScaler()
+                new_df[scale_cols] = scaler.fit_transform(new_df[scale_cols])
+                update_cleaned_data(new_df)
+
+    elif app_mode == "EDA":
+        st.header("🔍 Interactive Data Explorer")
         if 'cleaned_data' not in st.session_state:
-            st.warning("Please upload data first.")
-        else:
-            df = st.session_state.cleaned_data
-            metrics_html = f"""
-            <div class="metrics">
-              <div class="metric">Rows: {df.shape[0]}</div>
-              <div class="metric">Columns: {df.shape[1]}</div>
-              <div class="metric">Missing: {df.isna().sum().sum()}</div>
-            </div>
-            """
-            st.markdown(f'<div id="eda-output">{metrics_html}</div>', unsafe_allow_html=True)
-            plot_type = st.selectbox("Choose visualization type", ["Scatter Plot", "Histogram"])
-            x_axis = st.selectbox("X-axis", df.columns)
-            y_axis = st.selectbox("Y-axis", df.columns) if plot_type == "Scatter Plot" else None
-            if st.button("Generate Plot"):
-                if plot_type == "Scatter Plot" and x_axis and y_axis:
-                    fig = px.scatter(df, x=x_axis, y=y_axis)
-                    st.session_state.last_plot = {"type": "Scatter Plot", "x": x_axis, "y": y_axis, "data": df[[x_axis, y_axis]].to_json()}
-                elif plot_type == "Histogram" and x_axis:
-                    fig = px.histogram(df, x=x_axis)
-                    st.session_state.last_plot = {"type": "Histogram", "x": x_axis, "data": df[[x_axis]].to_json()}
-                st.plotly_chart(fig)
-
-    # Chatbot Logic (Moved to Bottom, Fixed Session State Issue)
-    if "chat_trigger" not in st.session_state:
-        st.session_state.chat_trigger = ""
-    chat_input = st.session_state.chat_trigger
-    if chat_input:
-        st.session_state.chat_history.append({"role": "user", "content": chat_input})
-        df = st.session_state.cleaned_data if 'cleaned_data' in st.session_state else pd.DataFrame()
-        new_df, result, plot_info = parse_command(chat_input, df)
-        if isinstance(result, Figure):
-            st.plotly_chart(result)
-            st.session_state.last_plot = plot_info
-            st.session_state.vector_store = update_vector_store_with_plot(extract_plot_data(plot_info, new_df), st.session_state.vector_store)
-            response = f"Generated {plot_info['type'].lower()}."
-        elif isinstance(result, str):
-            response = result
-            if "Dropped columns" in response:
-                st.session_state.cleaned_data = new_df
-                st.session_state.vector_store = create_vector_store(convert_df_to_text(new_df))
-                st.rerun()
-        else:
-            response = get_chatbot_response(chat_input, st.session_state.app_mode, st.session_state.vector_store, model)
-        st.session_state.chat_history.append({"role": "assistant", "content": response})
-        st.markdown(f"""
-        <script>
-          document.dispatchEvent(new CustomEvent('bot_response', {{ detail: {json.dumps(response)} }}));
-        </script>
-        """, unsafe_allow_html=True)
-        st.session_state.chat_trigger = ""  # Reset after processing
+            st.warning("Please upload and clean data first.")
+            st.stop()
+        df = st.session_state.cleaned_data.copy()
+
+        enhance_section_title("Dataset Overview")
+        with st.container():
+            col1, col2, col3, col4 = st.columns(4)
+            col1.metric("Total Rows", df.shape[0])
+            col2.metric("Total Columns", df.shape[1])
+            missing_percentage = df.isna().sum().sum() / df.size * 100
+            col3.metric("Missing Values", f"{df.isna().sum().sum()} ({missing_percentage:.1f}%)")
+            col4.metric("Duplicates", df.duplicated().sum())
+
+        tab1, tab2, tab3 = st.tabs(["Quick Preview", "Column Types", "Missing Matrix"])
+        with tab1:
+            st.write("First few rows of the dataset:")
+            st.dataframe(df.head(), use_container_width=True)
+        with tab2:
+            st.write("Column Data Types:")
+            type_counts = df.dtypes.value_counts().reset_index()
+            type_counts.columns = ['Type', 'Count']
+            st.dataframe(type_counts, use_container_width=True)
+        with tab3:
+            st.write("Missing Values Matrix:")
+            fig_missing = px.imshow(df.isna(), color_continuous_scale=['#e0e0e0', '#66c2a5'])
+            fig_missing.update_layout(coloraxis_colorscale=[[0, 'lightgrey'], [1, '#FF4B4B']])
+            st.plotly_chart(fig_missing, use_container_width=True)
+
+        enhance_section_title("Interactive Visualization Builder")
+        with st.container():
+            col1, col2 = st.columns([1, 3])
+            with col1:
+                plot_type = st.selectbox("Choose visualization type", [
+                    "Scatter Plot", "Histogram", "Box Plot", "Line Chart", "Bar Chart", "Correlation Matrix"
+                ])
+                x_axis = st.selectbox("X-axis", df.columns) if plot_type != "Correlation Matrix" else None
+                y_axis = st.selectbox("Y-axis", df.columns) if plot_type in ["Scatter Plot", "Box Plot", "Line Chart"] else None
+                color_by = st.selectbox("Color encoding", ["None"] + df.columns.tolist(), format_func=lambda x: "No color" if x == "None" else x) if plot_type != "Correlation Matrix" else None
+
+            with col2:
+                try:
+                    fig = None
+                    if plot_type == "Scatter Plot" and x_axis and y_axis:
+                        fig = px.scatter(df, x=x_axis, y=y_axis, color=color_by if color_by != "None" else None, title=f'Scatter Plot of {x_axis} vs {y_axis}')
+                    elif plot_type == "Histogram" and x_axis:
+                        fig = px.histogram(df, x=x_axis, color=color_by if color_by != "None" else None, nbins=30, title=f'Histogram of {x_axis}')
+                    elif plot_type == "Box Plot" and x_axis and y_axis:
+                        fig = px.box(df, x=x_axis, y=y_axis, color=color_by if color_by != "None" else None, title=f'Box Plot of {x_axis} vs {y_axis}')
+                    elif plot_type == "Line Chart" and x_axis and y_axis:
+                        fig = px.line(df, x=x_axis, y=y_axis, color=color_by if color_by != "None" else None, title=f'Line Chart of {x_axis} vs {y_axis}')
+                    elif plot_type == "Bar Chart" and x_axis:
+                        fig = px.bar(df, x=x_axis, color=color_by if color_by != "None" else None, title=f'Bar Chart of {x_axis}')
+                    elif plot_type == "Correlation Matrix":
+                        numeric_df = df.select_dtypes(include=np.number)
+                        if len(numeric_df.columns) > 1:
+                            corr = numeric_df.corr()
+                            fig = px.imshow(corr, text_auto=True, color_continuous_scale='RdBu_r', zmin=-1, zmax=1, title='Correlation Matrix')
+
+                    if fig:
+                        fig.update_layout(template="plotly_white")
+                        st.plotly_chart(fig, use_container_width=True)
+                        st.session_state.last_plot = {
+                            "type": plot_type,
+                            "x": x_axis,
+                            "y": y_axis,
+                            "data": df[[x_axis, y_axis]].to_json() if y_axis else df[[x_axis]].to_json()
+                        }
+                        plot_text = extract_plot_data(st.session_state.last_plot, df)
+                        st.session_state.vector_store = update_vector_store_with_plot(plot_text, st.session_state.vector_store)
+                        with st.expander("Extracted Plot Data"):
+                            st.text(plot_text)
+                    else:
+                        st.error("Please provide required inputs for the selected plot type.")
+                except Exception as e:
+                    st.error(f"Couldn't create visualization: {str(e)}")
+
+    # Chatbot Section
+    st.markdown("---")
+    st.markdown('<div class="chat-container">', unsafe_allow_html=True)
+    st.subheader("💬 AI Chatbot Assistant (RAG Enabled)")
+    st.info("Ask about your data or app features! Try: 'drop columns X, Y', 'scatter plot of X vs Y', 'analyze plot'")
+    
+    for message in st.session_state.chat_history:
+        with st.chat_message(message["role"]):
+            st.markdown(f'<div class="{message["role"]}-message">{message["content"]}</div>', unsafe_allow_html=True)
+    
+    user_input = st.chat_input("Ask me anything...")
+    if user_input:
+        st.session_state.chat_history.append({"role": "user", "content": user_input})
+        with st.chat_message("user"):
+            st.markdown(f'<div class="user-message">{user_input}</div>', unsafe_allow_html=True)
+        with st.spinner("Processing..."):
+            func, param = parse_command(user_input)
+            if func:
+                response = func(param) if param else func(None)
+            else:
+                response = get_chatbot_response(user_input, app_mode, st.session_state.vector_store, model)
+            st.session_state.chat_history.append({"role": "assistant", "content": response})
+        with st.chat_message("assistant"):
+            st.markdown(f'<div class="bot-message">{response}</div>', unsafe_allow_html=True)
+    
+    st.markdown('</div>', unsafe_allow_html=True)
+    
+    # Footer
+    st.markdown("""
+        <div class="footer">
+            <div>Built with <span class="tech-badge">Streamlit</span> + <span class="tech-badge">Groq</span> + <span class="tech-badge">LangChain</span> + <span class="tech-badge">FAISS</span></div>
+            <div style="margin-top: 8px;">Fast inference for data insights</div>
+        </div>
+    """, unsafe_allow_html=True)
 
 if __name__ == "__main__":
     main()