Update app.py

app.py

@@ -103,30 +103,71 @@ def read_file_to_df(uploaded) -> pd.DataFrame:
         else:
             # attempt to read bytes
             content = uploaded.read()
-            try:
-                return pd.read_csv(io.BytesIO(content))
-            except Exception:
-                return pd.read_excel(io.BytesIO(content))
-        # now path-based read
-        if path.lower().endswith(".csv"):
-            return pd.read_csv(path)
-        elif path.lower().endswith((".xls", ".xlsx")):
-            return pd.read_excel(path)
-        elif path.lower().endswith(".json"):
-            return pd.read_json(path)
-        else:
-            # try csv then excel then json
-            try:
-                return pd.read_csv(path)
-            except Exception:
-                try:
-                    return pd.read_excel(path)
-                except Exception:
-                    return pd.read_json(path)
+            return _read_bytes_content(content)
+
+        return _read_file_path(path)
+        
     except Exception as e:
-        print("read_file_to_df error:", e)
+        print(f"read_file_to_df error: {e}")
+
+        try:
+          if 'path' in locals():
+            return pd.read_csv(path, encoding_errors='ignore', engine='python')
+        except Exception:
+          pass
         raise
 
+def _read_bytes_content(content) -> pd.DataFrame:
+  formats_to_try = [
+      ('csv', lambda: pd.read_csv(io.BytesIO(content))),
+      ('csv_utf8', lambda: pd.read_csv(io.BytesIO(content), encoding='utf-8')),
+      ('csv_latin1', lambda: pd.read_csv(io.BytesIO(content), encoding='latin1')),
+      ('csv_ignore', lambda: pd.read_csv(io.BytesIO(content), encoding_errors='ignore')),
+      ('excel', lambda: pd.read_excel(io.BytesIO(content))),
+      ('json', lambda: pd.read_json(io.BytesIO(content))),
+  ]
+  for format_name, reader_func in formats_to_try:
+    try:
+      return reader_func()
+    except Exception as e:
+      print(f"Failed to read as {format_name}: {e}")
+      continue
+
+  raise ValueError("Could not read file with any supported format")
+
+def _read_file_path(path) -> pd.DataFrame:
+    """Handle file path reading with multiple format attempts"""
+    file_ext = os.path.splitext(path)[1].lower()
+    
+    if file_ext in ['.csv', '.txt', '.tsv']:
+        encodings = [None, 'utf-8', 'latin1', 'cp1252', 'iso-8859-1']
+        for encoding in encodings:
+            try:
+                if file_ext == '.tsv':
+                    return pd.read_csv(path, sep='\t', encoding=encoding, encoding_errors='ignore')
+                else:
+                    return pd.read_csv(path, encoding=encoding, encoding_errors='ignore')
+            except Exception:
+                continue
+    
+    elif file_ext in ['.xlsx', '.xls', '.xlsm', '.xlsb']:
+        return pd.read_excel(path)
+    
+    elif file_ext == '.json':
+        return pd.read_json(path)
+    
+    elif file_ext in ['.parquet']:
+        return pd.read_parquet(path)
+    
+    elif file_ext in ['.feather']:
+        return pd.read_feather(path)
+    
+    # Final fallback
+    try:
+        return pd.read_csv(path, encoding_errors='ignore', engine='python')
+    except Exception:
+        return pd.read_excel(path)
+
 def comprehensive_data_profile(df: pd.DataFrame) -> Dict[str, Any]:
     """Enhanced data profiling with comprehensive analysis"""
     if df is None or df.empty:
@@ -233,36 +274,38 @@ def detect_outliers_iqr(series):
     return ((series < lower_bound) | (series > upper_bound)).sum()
 
 def profile_to_enhanced_markdown(profile: Dict[str, Any]) -> str:
-    """Convert comprehensive profile to rich markdown with visual indicators"""
+    """Convert comprehensive profile to rich markdown with better formatting"""
     if not profile:
         return "No data loaded."
     
     md = []
     
     # Header with key metrics
-    md.append(f"## 📊 Comprehensive Data Profile Report")
+    md.append("# 📊 Comprehensive Data Profile Report")
     md.append("---")
     
-    # Dataset Overview
-    md.append("### 🎯 Dataset Overview")
-    md.append(f"- **Rows:** {profile['rows']:,}")
-    md.append(f"- **Columns:** {profile['columns']}")
-    md.append(f"- **Memory Usage:** {profile['memory_usage']:.2f} MB")
-    md.append(f"- **Duplicate Rows:** {profile['duplicate_rows']} ({profile['duplicate_pct']:.2%})")
+    # Dataset Overview in a compact grid
+    md.append("## 🎯 Dataset Overview")
+    with io.StringIO() as overview:
+        overview.write(f"**Rows:** {profile['rows']:,} | ")
+        overview.write(f"**Columns:** {profile['columns']} | ")
+        overview.write(f"**Memory:** {profile['memory_usage']:.2f} MB | ")
+        overview.write(f"**Duplicates:** {profile['duplicate_rows']} ({profile['duplicate_pct']:.2%})")
+        md.append(overview.getvalue())
     md.append("")
     
     # Data Quality Scorecard
-    md.append("### 📈 Data Quality Scorecard")
+    md.append("## 📈 Data Quality Scorecard")
     quality = profile["quality_metrics"]
-    md.append(f"- **Completeness:** {quality['completeness']:.2%}")
-    md.append(f"- **Uniqueness:** {quality['uniqueness']:.2%}")
+    md.append(f"**Completeness:** {quality['completeness']:.2%} | ")
+    md.append(f"**Uniqueness:** {quality['uniqueness']:.2%}")
     md.append("")
     
     # Column Type Summary
-    md.append("### 🗂️ Column Type Summary")
-    md.append(f"- **Numeric Columns:** {len(profile['numeric_cols'])}")
-    md.append(f"- **Categorical Columns:** {len(profile['categorical_cols'])}")
-    md.append(f"- **DateTime Columns:** {len(profile['datetime_cols'])}")
+    md.append("## 🗂️ Column Type Summary")
+    md.append(f"**Numeric:** {len(profile['numeric_cols'])} | ")
+    md.append(f"**Categorical:** {len(profile['categorical_cols'])} | ")
+    md.append(f"**DateTime:** {len(profile['datetime_cols'])}")
     md.append("")
     
     # Detailed Column Analysis
@@ -761,6 +804,45 @@ css = """
   margin-top: 8px;
   text-align: center;
 }
+
+/* Improved table styling for profile report */
+#profile-report table {
+    width: 100%;
+    border-collapse: collapse;
+    font-size: 14px;
+    table-layout: fixed;
+}
+
+#profile-report th, #profile-report td {
+    padding: 8px 12px;
+    border: 1px solid #ddd;
+    text-align: left;
+    word-wrap: break-word;
+    white-space: nowrap;
+    overflow: hidden;
+    text-overflow: ellipsis;
+}
+
+#profile-report th {
+    background-color: #f5f5f5;
+    font-weight: 600;
+}
+
+#profile-report tr:nth-child(even) {
+    background-color: #f9f9f9;
+}
+
+/* Ensure markdown content uses full width */
+.markdown-body {
+    max-width: 100% !important;
+}
+
+/* Better scrolling for large content */
+.gr-markdown {
+    max-height: 70vh;
+    overflow-y: auto;
+}
+
 """
 
 vanta_html = """
@@ -824,31 +906,36 @@ with gr.Blocks(css=css, title="DataSynth — Analytics Hub") as demo:
 
     # --- Main app (hidden until login) ---
     with gr.Column(visible=False) as main_area:
-        gr.Markdown("## Workspace")
-        with gr.Tabs():
-            with gr.TabItem("Data"):
-                gr.Markdown("Upload CSV / Excel / JSON for comprehensive profiling and analysis.")
-                upload = gr.File(label="Upload CSV / Excel / JSON", file_types=[".csv", ".xlsx", ".xls", ".json"])
+        gr.Markdown("# 🚀 DataSynth Analytics Workspace")
+        with gr.Tabs() as main_tabs:
+            with gr.TabItem("📊 Data Profiling"):
+                gr.Markdown("### 📁 Upload & Analyze Your Dataset")
+                upload = gr.File(label="Upload Dataset", file_types=[".csv", ".xlsx", ".xls", ".xlsm", ".xlsb", ".json", ".parquet", ".feather", ".txt", ".tsv"],
+                                 type="filepath")
                 with gr.Row():
-                    profile_btn = gr.Button("📊 Data Profiling", variant="primary")
-                    view_data_btn = gr.Button("👀 View Data", variant="secondary")
-                    download_raw_btn = gr.Button("📥 Download Raw CSV")
+                    profile_btn = gr.Button("🚀 Run Comprehensive Data Profiling", variant="primary", size="lg")
+                    #view_data_btn = gr.Button("👀 View Data", variant="secondary")
+                    #download_raw_btn = gr.Button("📥 Download Raw CSV")
                 with gr.Tabs() as data_tabs:
-                    with gr.TabItem("Profile Report"):
-                        profile_md = gr.Markdown("No dataset loaded. Upload data and click 'Data Profiling'.")
-
-                    with gr.TabItem("Data Preview"):
-                        sample_table = gr.Dataframe(interactive=False, label="Sample Data (First 100 rows)")
-
-                    with gr.TabItem("Visualizations"):
-                        with gr.Row():
-                            dist_plot1 = gr.Plot(label="Distribution Plot 1")
-                            dist_plot2 = gr.Plot(label="Distribution Plot 2")
-                        with gr.Row():
-                            dist_plot3 = gr.Plot(label="Distribution Plot 3")
-                            corr_plot = gr.Plot(label="Correlation Heatmap")
+                    with gr.TabItem("📊 Profile Report"):
+                        profile_md = gr.Markdown(
+                            "No dataset loaded. Upload your data and click 'Run Comprehensive Data Profiling'.",
+                            elem_id="profile-report"
+                        )
+
+                    with gr.TabItem("👁️ Data Preview"):
+                        sample_table = gr.Dataframe(
+                            interactive=False,
+                            label="Sample Data (First 100 rows)",
+                            height = 400
+                        )
+
+                    with gr.TabItem("📈 Visualizations"):
+                        gr.Markdown("### Correlation Analysis")
+                        corr_plot = gr.Plot(label="Correlation Heatmap")
+                        gr.Markdown("*Note: Only numeric columns are included in correlation analysis*")
                             
-            with gr.TabItem("Prepare"):
+            with gr.TabItem("🔧 Prepare"):
                 gr.Markdown("Data cleaning and feature engineering options.")
                 with gr.Row():
                     with gr.Column(scale=1):
@@ -868,12 +955,12 @@ with gr.Blocks(css=css, title="DataSynth — Analytics Hub") as demo:
                     with gr.Column(scale=1):
                         prep_output = gr.Markdown("Preparation preview will appear here.")
                         preview_clean = gr.Dataframe(interactive=False)
-            with gr.TabItem("Visualize (NL)"):
+            with gr.TabItem("📊 Visualize (NL)"):
                 gr.Markdown("Type a natural-language request to create a plot (e.g., 'histogram of age', 'scatter income vs age', 'bar of country').")
                 nl_input = gr.Textbox(label="Describe chart")
                 nl_btn = gr.Button("Create Chart")
                 nl_plot = gr.Plot()
-            with gr.TabItem("Model"):
+            with gr.TabItem("🤖 Model"):
                 gr.Markdown("Choose task, target variable, and model. Scaling and encoding will be applied automatically.")
                 task_select = gr.Radio(choices=["regression","classification"], value="regression", label="Task")
                 target_col = gr.Dropdown(choices=[], label="Target variable")
@@ -884,7 +971,7 @@ with gr.Blocks(css=css, title="DataSynth — Analytics Hub") as demo:
                 model_out_md = gr.Markdown("Model results will show here.")
                 model_feature_imp = gr.Dataframe(interactive=False)
                 model_plots = gr.Plot()
-            with gr.TabItem("Report"):
+            with gr.TabItem("📄 Report"):
                 gr.Markdown("Generate a short executive report that summarizes profiling, cleaning, and model results.")
                 report_btn = gr.Button("Generate Report")
                 report_download = gr.File(label="Download Report (.md)")
@@ -907,35 +994,30 @@ with gr.Blocks(css=css, title="DataSynth — Analytics Hub") as demo:
             if uploaded is None:
                 return (gr.update(value="No file uploaded."),
                         pd.DataFrame(), None, None,
-                        None, None, None, None)
+                        None)
             df = read_file_to_df(uploaded)
             prof = comprehensive_data_profile(df)
             md = profile_to_enhanced_markdown(prof)
             #create visulaizations
-            plots = create_distribution_plots(df, prof)
-            corr_plot = create_correlation_plot(df, prof)
+            corr_plot_fig = create_correlation_plot(df, prof)
 
             # Prepare plot outputs
-            plot1 = plots.get(list(plots.keys())[0]) if plots else None
-            plot2 = plots.get(list(plots.keys())[1]) if len(plots) > 1 else None
-            plot3 = plots.get(list(plots.keys())[2]) if len(plots) > 2 else None
+            tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
+            df.to_csv(tmp.name, index=False)
             # prepare choices for date and target selectors
             #cols = df.columns.tolist()
             # save df to temp csv for persistence (store path in state)
-            tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
-            df.to_csv(tmp.name, index=False)
+            #tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
+            #df.to_csv(tmp.name, index=False)
             
-            return (md, df.head(100), tmp.name, prof,
-                    plot1, plot2, plot3, corr_plot)
+            return (md, df.head(100), tmp.name, prof, corr_plot_fig)
         except Exception as e:
-            return (gr.update(value=f"Error loading file: {e}"),
-                    pd.DataFrame(), None, None,
-                    None, None, None, None)
+            return (gr.update(value=f"Error loading file: {e}"), 
+                   pd.DataFrame(), None, None, None)
 
     profile_btn.click(fn=_load_and_profile,
                       inputs=[upload],
-                      outputs=[profile_md, sample_table, df_state, profile_state,
-                               dist_plot1, dist_plot2, dist_plot3, corr_plot])
+                      outputs=[profile_md, sample_table, df_state, profile_state, corr_plot])
 
     def _view_data(uploaded):
         try: