Update app.py

app.py

@@ -14,6 +14,7 @@ import re
 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); }
@@ -36,35 +37,44 @@ class DataExplorerApp:
         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
+            # --- 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")
-            file_input = gr.File(label="📁 Upload CSV File", file_types=[".csv"])
+            
+            # 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
+            # --- 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 file** and **enter your Gemini API key** to begin your analysis.")
+                    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():
@@ -81,7 +91,7 @@ class DataExplorerApp:
                         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
+            # --- 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(
@@ -107,7 +117,6 @@ class DataExplorerApp:
 
     def launch(self): self.demo.launch(debug=True)
 
-    # --- Backend Logic Methods ---
     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))]
@@ -115,20 +124,39 @@ class DataExplorerApp:
     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:
-            df = pd.read_csv(file_obj.name, low_memory=False)
+            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(file_obj.name)}** loaded.", *page_updates, f"{rows:,}", f"{cols}", f"{quality}%", f"{len(metadata['datetime_cols'])}",
+            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, quality = df.shape[0], df.shape[1], round((df.notna().sum().sum() / (df.size)) * 100, 1) if df.size > 0 else 0
+        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}
@@ -171,10 +199,7 @@ class DataExplorerApp:
         return *self._switch_page("co-pilot", [0,1,2,3]), question
 
     def _sanitize_and_parse_json(self, raw_text: str) -> Dict:
-        """Cleans and parses a JSON string from an LLM response."""
-        # Remove markdown code blocks
         clean_text = re.sub(r'```json\n?|```', '', raw_text).strip()
-        # Escape single backslashes that are not already escaped
         clean_text = re.sub(r'(?<!\\)\\(?!["\\/bfnrtu])', r'\\\\', clean_text)
         return json.loads(clean_text)
 
@@ -185,22 +210,14 @@ class DataExplorerApp:
         
         history.append((user_message, "Thinking... 🤔")); yield history, *[gr.update(visible=False)]*4
         
-        metadata, dtypes_head = state.get('metadata', {}), state.get('metadata', {}).get('dtypes_head', 'No metadata available.')
-        prompt = f"""You are 'Chief Data Scientist', an expert AI analyst. Your goal is to answer a user's question about a pandas DataFrame (`df`) by writing and executing Python code.
-        **Instructions:**
-        1. **Analyze:** Understand the user's intent. Infer the best plot type.
-        2. **Plan:** Briefly explain your plan.
-        3. **Code:** Write Python code. Use `fig` for plots (`template='plotly_dark'`) and `result_df` for tables.
-        4. **Insight:** Provide a one-sentence business insight.
-        5. **Respond ONLY with a single JSON object with keys: "plan", "code", "insight".**
-        **Metadata:** {dtypes_head}
-        **User Question:** "{user_message}"
+        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)
-            # CRITICAL FIX: Use the new sanitizer function
-            response_json = self._sanitize_and_parse_json(genai.GenerativeModel('gemini-1.5-flash').generate_content(prompt).text)
-            
+            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})