app.py

import gradio as gr
import pandas as pd
import numpy as np
import plotly.express as px
import io
import json
import warnings
import google.generativeai as genai
import os
from typing import List, Dict, Any, Tuple, Optional
import re

# --- Configuration & Constants ---
warnings.filterwarnings('ignore')
MAX_DASHBOARD_PLOTS = 10
CSS = """
/* --- Phoenix UI Professional Dark CSS --- */
#app-title { text-align: center; font-weight: 800; font-size: 2.5rem; color: #f9fafb; padding-top: 10px; }
.stat-card { border-radius: 12px !important; padding: 20px !important; background: #1f2937 !important; border: 1px solid #374151 !important; text-align: center; transition: all 0.3s ease; }
.stat-card:hover { transform: translateY(-5px); box-shadow: 0 10px 15px -3px rgba(0,0,0,0.1), 0 4px 6px -2px rgba(0,0,0,0.05); }
.stat-card-title { font-size: 16px; font-weight: 500; color: #9ca3af !important; margin-bottom: 8px; }
.stat-card-value { font-size: 32px; font-weight: 700; color: #f9fafb !important; }
.sidebar { background-color: #111827 !important; padding: 15px; border-right: 1px solid #374151 !important; min-height: 100vh; }
.sidebar .gr-button { width: 100%; text-align: left !important; background: none !important; border: none !important; box-shadow: none !important; color: #d1d5db !important; font-size: 16px !important; padding: 12px 10px !important; margin-bottom: 8px !important; border-radius: 8px !important; transition: background-color 0.2s ease; }
.sidebar .gr-button:hover { background-color: #374151 !important; }
.sidebar .gr-button.selected { background-color: #4f46e5 !important; font-weight: 600 !important; color: white !important; }
.explanation-block { background-color: #1e3a8a !important; border-left: 4px solid #3b82f6 !important; padding: 12px; color: #e5e7eb !important; border-radius: 4px; }
"""

class DataExplorerApp:
    """A professional-grade, AI-powered data exploration application."""

    def __init__(self):
        self.demo = self._build_ui()

    def _build_ui(self) -> gr.Blocks:
        with gr.Blocks(theme=gr.themes.Glass(primary_hue="indigo", secondary_hue="blue"), css=CSS, title="AI Data Explorer Pro") as demo:
            state_var = gr.State({})
            
            # --- Component Definition ---
            cockpit_btn = gr.Button("📊 Data Cockpit", elem_classes="selected", elem_id="cockpit")
            deep_dive_btn = gr.Button("🔍 Deep Dive Builder", elem_id="deep_dive")
            copilot_btn = gr.Button("🤖 Chief Data Scientist", elem_id="co-pilot")
            
            # UPDATED: File input now accepts multiple types
            file_input = gr.File(
                label="📁 Upload Data File",
                file_types=[".csv", ".txt", ".xls", ".xlsx"]
            )
            
            status_output = gr.Markdown("Status: Awaiting data...")
            api_key_input = gr.Textbox(label="🔑 Gemini API Key", type="password", placeholder="Enter key to enable AI...")
            suggestion_btn = gr.Button("Get Smart Suggestions", variant="secondary", interactive=False)
            
            rows_stat, cols_stat = gr.Textbox("0", interactive=False, show_label=False), gr.Textbox("0", interactive=False, show_label=False)
            quality_stat, time_cols_stat = gr.Textbox("0%", interactive=False, show_label=False), gr.Textbox("0", interactive=False, show_label=False)
            suggestion_buttons = [gr.Button(visible=False) for _ in range(5)]
            
            plot_type_dd = gr.Dropdown(['histogram', 'bar', 'scatter', 'box'], label="Plot Type", value='histogram')
            x_col_dd = gr.Dropdown([], label="X-Axis / Column", interactive=False)
            y_col_dd = gr.Dropdown([], label="Y-Axis (for Scatter/Box)", visible=False, interactive=False)
            add_plot_btn, clear_plots_btn = gr.Button("Add to Dashboard", variant="primary", interactive=False), gr.Button("Clear Dashboard", interactive=False)
            dashboard_plots = [gr.Plot(visible=False) for _ in range(MAX_DASHBOARD_PLOTS)]
            
            chatbot = gr.Chatbot(height=500, label="Conversation", show_copy_button=True, avatar_images=(None, "bot.png"))
            copilot_explanation, copilot_code = gr.Markdown(visible=False, elem_classes="explanation-block"), gr.Code(language="python", visible=False, label="Executed Code")
            copilot_plot, copilot_table = gr.Plot(visible=False, label="Generated Visualization"), gr.Dataframe(visible=False, label="Generated Table", wrap=True)
            chat_input, chat_submit_btn = gr.Textbox(label="Your Question", placeholder="e.g., 'What is the relationship between age and salary?'", scale=4), gr.Button("Ask AI", variant="primary", interactive=False)
            
            # --- Layout Arrangement ---
            with gr.Row():
                with gr.Column(scale=1, elem_classes="sidebar"):
                    gr.Markdown("## 🚀 AI Explorer Pro", elem_id="app-title"); cockpit_btn; deep_dive_btn; copilot_btn; gr.Markdown("---")
                    file_input; status_output; gr.Markdown("---"); api_key_input; suggestion_btn
                with gr.Column(scale=4):
                    welcome_page, cockpit_page, deep_dive_page, copilot_page = [gr.Column(visible=i==0) for i in range(4)]
                    with welcome_page: gr.Markdown("# Welcome to the AI Data Explorer Pro\n> Please **upload a CSV, TXT, or Excel file** and **enter your Gemini API key** to begin your analysis.")
                    with cockpit_page:
                        gr.Markdown("## 📊 Data Cockpit: At-a-Glance Overview")
                        with gr.Row():
                            for title, stat_comp in [("Rows", rows_stat), ("Columns", cols_stat), ("Data Quality", quality_stat), ("Date/Time Cols", time_cols_stat)]:
                                with gr.Column(elem_classes="stat-card"): gr.Markdown(f"<div class='stat-card-title'>{title}</div>"); stat_comp
                        with gr.Accordion(label="✨ AI Smart Suggestions", open=True): [btn for btn in suggestion_buttons]
                    with deep_dive_page:
                        gr.Markdown("## 🔍 Deep Dive: Manual Dashboard Builder"); gr.Markdown("Construct visualizations to investigate specific relationships.")
                        with gr.Row(): plot_type_dd; x_col_dd; y_col_dd
                        with gr.Row(): add_plot_btn; clear_plots_btn
                        with gr.Column(): [plot for plot in dashboard_plots]
                    with copilot_page:
                        gr.Markdown("## 🤖 Chief Data Scientist: Your AI Partner"); chatbot
                        with gr.Accordion("AI's Detailed Response", open=True): copilot_explanation; copilot_code; copilot_plot; copilot_table
                        with gr.Row(): chat_input; chat_submit_btn
            
            # --- Event Handlers Registration ---
            pages, nav_buttons = [welcome_page, cockpit_page, deep_dive_page, copilot_page], [cockpit_btn, deep_dive_btn, copilot_btn]
            for i, btn in enumerate(nav_buttons):
                btn.click(lambda id=btn.elem_id: self._switch_page(id, pages), outputs=pages).then(
                    lambda i=i: [gr.update(elem_classes="selected" if j==i else "") for j in range(len(nav_buttons))], outputs=nav_buttons)

            file_input.upload(self.load_and_process_file, inputs=[file_input], outputs=[
                state_var, status_output, *pages, rows_stat, cols_stat, quality_stat, time_cols_stat, x_col_dd, y_col_dd, add_plot_btn])

            api_key_input.change(lambda x: gr.update(interactive=bool(x)), inputs=[api_key_input], outputs=[suggestion_btn])
            chat_input.change(lambda x: gr.update(interactive=bool(x.strip())), inputs=[chat_input], outputs=[chat_submit_btn])
            
            plot_type_dd.change(self._update_plot_controls, inputs=[plot_type_dd], outputs=[y_col_dd])
            add_plot_btn.click(self.add_plot_to_dashboard, inputs=[state_var, x_col_dd, y_col_dd, plot_type_dd], outputs=[state_var, clear_plots_btn, *dashboard_plots])
            clear_plots_btn.click(self.clear_dashboard, inputs=[state_var], outputs=[state_var, clear_plots_btn, *dashboard_plots])
            
            suggestion_btn.click(self.get_ai_suggestions, inputs=[state_var, api_key_input], outputs=suggestion_buttons)
            for btn in suggestion_buttons:
                btn.click(self.handle_suggestion_click, inputs=[btn], outputs=[*pages, chat_input])
            
            chat_submit_btn.click(self.respond_to_chat, [state_var, api_key_input, chat_input, chatbot], [chatbot, copilot_explanation, copilot_code, copilot_plot, copilot_table]).then(lambda: "", outputs=[chat_input])
            chat_input.submit(self.respond_to_chat, [state_var, api_key_input, chat_input, chatbot], [chatbot, copilot_explanation, copilot_code, copilot_plot, copilot_table]).then(lambda: "", outputs=[chat_input])
        return demo

    def launch(self): self.demo.launch(debug=True)

    def _switch_page(self, page_id: str, all_pages: List) -> List[gr.update]:
        visibility = {"welcome":0, "cockpit":1, "deep_dive":2, "co-pilot":3}
        return [gr.update(visible=i == visibility.get(page_id, 0)) for i in range(len(all_pages))]
    
    def _update_plot_controls(self, plot_type: str) -> gr.update: return gr.update(visible=plot_type in ['scatter', 'box'])

    def load_and_process_file(self, file_obj: Any) -> Tuple[Any, ...]:
        """Intelligently loads data from CSV, TXT, or Excel files."""
        try:
            filename = file_obj.name
            extension = os.path.splitext(filename)[1].lower()
            
            if extension == '.csv':
                df = pd.read_csv(filename)
            elif extension == '.txt':
                # Use sep=None to auto-detect the delimiter (tabs, spaces, etc.)
                df = pd.read_csv(filename, sep=None, engine='python')
            elif extension in ['.xls', '.xlsx']:
                df = pd.read_excel(filename)
            else:
                raise ValueError(f"Unsupported file type: {extension}")
            
            # Continue with processing once the DataFrame is loaded
            for col in df.select_dtypes(include=['object']).columns:
                try: df[col] = pd.to_datetime(df[col], errors='raise')
                except (ValueError, TypeError): continue
            
            metadata = self._extract_dataset_metadata(df)
            state = {'df': df, 'metadata': metadata, 'dashboard_plots': []}
            rows, cols, quality = metadata['shape'][0], metadata['shape'][1], metadata['data_quality']
            page_updates = self._switch_page("cockpit", [0,1,2,3])
            return (state, f"✅ **{os.path.basename(filename)}** loaded.", *page_updates, f"{rows:,}", f"{cols}", f"{quality}%", f"{len(metadata['datetime_cols'])}",
                    gr.update(choices=metadata['columns'], interactive=True), gr.update(choices=metadata['columns'], interactive=True), gr.update(interactive=True))
        except Exception as e:
            gr.Error(f"File Load Error: {e}"); page_updates = self._switch_page("welcome", [0,1,2,3]);
            return {}, f"❌ Error: {e}", *page_updates, "0", "0", "0%", "0", gr.update(choices=[], interactive=False), gr.update(choices=[], interactive=False), gr.update(interactive=False)

    def _extract_dataset_metadata(self, df: pd.DataFrame) -> Dict[str, Any]:
        rows, cols = df.shape
        quality = round((df.notna().sum().sum() / df.size) * 100, 1) if df.size > 0 else 0
        return {'shape': (rows, cols), 'columns': df.columns.tolist(), 'numeric_cols': df.select_dtypes(include=np.number).columns.tolist(),
                'categorical_cols': df.select_dtypes(include=['object', 'category']).columns.tolist(), 'datetime_cols': df.select_dtypes(include=['datetime64', 'datetime64[ns]']).columns.tolist(),
                'dtypes_head': df.head(3).to_string(), 'data_quality': quality}

    def add_plot_to_dashboard(self, state: Dict, x_col: str, y_col: Optional[str], plot_type: str) -> List[Any]:
        dashboard_plots = state.get('dashboard_plots', [])
        if len(dashboard_plots) >= MAX_DASHBOARD_PLOTS:
            gr.Warning(f"Dashboard is full. Max {MAX_DASHBOARD_PLOTS} plots."); return [state, gr.update(interactive=True), *self._get_plot_updates(state)]
        if not x_col: gr.Warning("Please select an X-axis column."); return [state, gr.update(interactive=True), *self._get_plot_updates(state)]
        df, title = state.get('df'), f"{plot_type.capitalize()}: {y_col} by {x_col}" if y_col and plot_type in ['box', 'scatter'] else f"Distribution of {x_col}"
        try:
            fig=None;
            if plot_type == 'histogram': fig = px.histogram(df, x=x_col, title=title)
            elif plot_type == 'box': fig = px.box(df, x=x_col, y=y_col, title=title)
            elif plot_type == 'scatter': fig = px.scatter(df, x=x_col, y=y_col, title=title, trendline="ols")
            elif plot_type == 'bar': fig = px.bar(df[x_col].value_counts().nlargest(20), title=f"Top 20 for {x_col}")
            if fig:
                fig.update_layout(template="plotly_dark"); dashboard_plots.append(fig); gr.Info(f"Added '{title}' to dashboard.")
            return [state, gr.update(interactive=True), *self._get_plot_updates(state)]
        except Exception as e: gr.Error(f"Plotting Error: {e}"); return [state, gr.update(interactive=True), *self._get_plot_updates(state)]
    
    def _get_plot_updates(self, state: Dict) -> List[gr.update]:
        plots = state.get('dashboard_plots', [])
        return [gr.update(value=plots[i] if i < len(plots) else None, visible=i < len(plots)) for i in range(MAX_DASHBOARD_PLOTS)]

    def clear_dashboard(self, state: Dict) -> List[Any]:
        state['dashboard_plots'] = []; gr.Info("Dashboard cleared."); return [state, gr.update(interactive=False), *self._get_plot_updates(state)]

    def get_ai_suggestions(self, state: Dict, api_key: str) -> List[gr.update]:
        if not api_key: gr.Warning("API Key is required."); return [gr.update(visible=False)]*5
        if not state: gr.Warning("Please load data first."); return [gr.update(visible=False)]*5
        metadata, columns = state.get('metadata', {}), state.get('metadata', {}).get('columns', [])
        prompt = f"From columns {columns}, generate 4 impactful analytical questions. Return ONLY a JSON list of strings."
        try:
            genai.configure(api_key=api_key); suggestions = json.loads(genai.GenerativeModel('gemini-1.5-flash').generate_content(prompt).text)
            return [gr.Button(s, visible=True) for s in suggestions] + [gr.Button(visible=False)] * (5 - len(suggestions))
        except Exception as e: gr.Error(f"AI Suggestion Error: {e}"); return [gr.update(visible=False)]*5

    def handle_suggestion_click(self, question: str) -> Tuple[gr.update, ...]:
        return *self._switch_page("co-pilot", [0,1,2,3]), question

    def _sanitize_and_parse_json(self, raw_text: str) -> Dict:
        clean_text = re.sub(r'```json\n?|```', '', raw_text).strip()
        clean_text = re.sub(r'(?<!\\)\\(?!["\\/bfnrtu])', r'\\\\', clean_text)
        return json.loads(clean_text)

    def respond_to_chat(self, state: Dict, api_key: str, user_message: str, history: List) -> Any:
        if not user_message.strip(): return history, *[gr.update()]*4
        if not api_key or not state:
            history.append((user_message, "I need a Gemini API key and a dataset to work.")); return history, *[gr.update(visible=False)]*4
        
        history.append((user_message, "Thinking... 🤔")); yield history, *[gr.update(visible=False)]*4
        
        metadata = state.get('metadata', {}); dtypes_head = metadata.get('dtypes_head', 'No metadata available.')
        prompt = f"""You are 'Chief Data Scientist', an expert AI analyst...
        Respond ONLY with a single JSON object with keys: "plan", "code", "insight".
        Metadata: {dtypes_head}
        User Question: "{user_message}"
        """
        try:
            genai.configure(api_key=api_key); response_json = self._sanitize_and_parse_json(genai.GenerativeModel('gemini-1.5-flash').generate_content(prompt).text)
            plan, code, insight = response_json.get("plan"), response_json.get("code"), response_json.get("insight")
            stdout, fig, df_result, error = self._safe_exec(code, {'df': state['df'], 'px': px, 'pd': pd})
            
            history[-1] = (user_message, f"**Plan:** {plan}")
            explanation = f"**Insight:** {insight}"
            if stdout: explanation += f"\n\n**Console Output:**\n```\n{stdout}\n```"
            if error: gr.Error(f"AI Code Execution Failed: {error}")
            
            yield (history, gr.update(visible=bool(explanation), value=explanation), gr.update(visible=bool(code), value=code),
                   gr.update(visible=bool(fig), value=fig), gr.update(visible=bool(df_result is not None), value=df_result))
        except Exception as e:
            history[-1] = (user_message, f"I encountered an error processing the AI response. Please rephrase your question.\n\n**Details:** `{str(e)}`")
            yield history, *[gr.update(visible=False)]*4
            
    def _safe_exec(self, code_string: str, local_vars: Dict) -> Tuple[Any, ...]:
        try:
            output_buffer = io.StringIO()
            with redirect_stdout(output_buffer): exec(code_string, globals(), local_vars)
            return output_buffer.getvalue(), local_vars.get('fig'), local_vars.get('result_df'), None
        except Exception as e: return None, None, None, str(e)

if __name__ == "__main__":
    if not os.path.exists("bot.png"):
        try:
            from PIL import Image
            Image.new('RGB', (1, 1)).save('bot.png')
        except ImportError: print("Pillow not installed, cannot create dummy bot.png.")
    
    app = DataExplorerApp()
    app.launch()