UI perfomance fixes

FALLBACK_REPORT.md

@@ -53,4 +53,4 @@
 | unordered | optimized_reentry | unique_users | time_to_convert | ✗ No |  |
 | unordered | optimized_reentry | unique_users | cohort_analysis | ✗ No |  |
 
-## Recommendations
+## Recommendations

core/calculator.py

@@ -1006,7 +1006,7 @@ def calculate_funnel_metrics(
         Returns:
             FunnelResults object with all calculated metrics
         """
-        start_time = time.time()
+        time.time()
 
         if len(funnel_steps) < 2:
             return FunnelResults(
@@ -1088,7 +1088,7 @@ def _calculate_funnel_metrics_polars(
             existing_events_in_data = set(
                 polars_df.select("event_name").unique().to_series().to_list()
             )
-            funnel_steps_in_data = set(funnel_steps) & existing_events_in_data
+            set(funnel_steps) & existing_events_in_data
 
             zero_counts = [0] * len(funnel_steps)
             drop_offs = [0] * len(funnel_steps)
@@ -1167,7 +1167,6 @@ def _calculate_funnel_metrics_polars(
 
             # Ensure consistent data types between DataFrames
             # Get the schema of segment_polars_df
-            segment_schema = segment_polars_df.schema
 
             # Cast user_id in both DataFrames to string to ensure consistent types
             segment_polars_df = segment_polars_df.with_columns(
@@ -1272,7 +1271,7 @@ def _calculate_funnel_metrics_pandas(
                 return FunnelResults([], [], [], [], [])
             # Events exist but none match funnel steps - check if any of the funnel steps exist in the data at all
             existing_events_in_data = set(events_df["event_name"].unique())
-            funnel_steps_in_data = set(funnel_steps) & existing_events_in_data
+            set(funnel_steps) & existing_events_in_data
 
             zero_counts = [0] * len(funnel_steps)
             drop_offs = [0] * len(funnel_steps)
@@ -2013,7 +2012,7 @@ def _calculate_timeseries_metrics_pandas(
 
         # Define first and last steps
         first_step = funnel_steps[0]
-        last_step = funnel_steps[-1]
+        funnel_steps[-1]
         conversion_window_hours = self.config.conversion_window_hours
 
         try:
@@ -3250,7 +3249,7 @@ def _calculate_path_analysis_polars_optimized(
                     # Fully vectorized approach for between-steps analysis
                     try:
                         # Get unique user IDs with valid conversion pairs
-                        user_ids = conversion_pairs.select("user_id").unique()
+                        conversion_pairs.select("user_id").unique()
 
                         # Create a lazy frame with step pairs information
                         step_pairs_lazy = conversion_pairs.lazy().select(
@@ -3785,7 +3784,7 @@ def _analyze_between_steps_polars(
                         continue
 
                     step_A_time = user_A[0, "step_A_time"]
-                    conversion_window = timedelta(hours=self.config.conversion_window_hours)
+                    timedelta(hours=self.config.conversion_window_hours)
 
                     # Find first B after A within conversion window
                     potential_Bs = user_B.filter(
@@ -4576,7 +4575,7 @@ def _calculate_unique_pairs_funnel_polars(
             users_count.append(count)
 
             # For unique pairs, conversion rate is step-to-step
-            step_conversion_rate = (
+            (
                 (count / len(prev_step_users) * 100) if len(prev_step_users) > 0 else 0
             )
             # But we also track overall conversion rate from first step for consistency
@@ -5694,7 +5693,7 @@ def _user_did_later_steps_before_current(
         try:
             # Get the funnel sequence from the order that steps appear in the overall dataset
             # This is a heuristic but works for most cases
-            all_funnel_events = all_events_df["event_name"].unique()
+            all_events_df["event_name"].unique()
 
             # For the test case, we know the sequence should be: Sign Up -> Email Verification -> First Login
             # When checking Email Verification after Sign Up, we should see if First Login happened before Email Verification
@@ -5888,7 +5887,7 @@ def _calculate_unique_pairs_funnel(
             users_count.append(count)
 
             # For unique pairs, conversion rate is step-to-step
-            step_conversion_rate = (
+            (
                 (count / len(prev_step_users) * 100) if len(prev_step_users) > 0 else 0
             )
             # But we also track overall conversion rate from first step
@@ -5929,7 +5928,7 @@ def _user_did_later_steps_before_current_polars(
         try:
             # Find the indices of steps in the funnel
             try:
-                prev_step_idx = funnel_steps.index(prev_step)
+                funnel_steps.index(prev_step)
                 current_step_idx = funnel_steps.index(current_step)
             except ValueError:
                 # If the steps aren't in the funnel, we can't determine order

core/data_source.py

@@ -322,7 +322,7 @@ def _load_from_file_pandas_fallback(self, uploaded_file) -> pd.DataFrame:
 
             return df
 
-        except Exception as e:
+        except Exception:
             return pd.DataFrame()
 
     def connect_clickhouse(
@@ -338,7 +338,7 @@ def connect_clickhouse(
                 database=database,
             )
             # Test connection
-            result = self.clickhouse_client.query("SELECT 1")
+            self.clickhouse_client.query("SELECT 1")
             return True
         except Exception as e:
             st.error(f"ClickHouse connection failed: {str(e)}")

quick_benchmark.py

@@ -106,7 +106,7 @@ def quick_benchmark():
     # Test statistics (optimized)
     print("   Testing _calculate_process_statistics_optimized...")
     start_time = time.time()
-    statistics = analyzer._calculate_process_statistics_optimized(
+    analyzer._calculate_process_statistics_optimized(
         journey_df, activities, transitions
     )
     stats_time = time.time() - start_time
@@ -141,7 +141,7 @@ def quick_benchmark():
 
     print("   Without cycles:")
     start_time = time.time()
-    result_no_cycles = analyzer.discover_process_mining_structure(
+    analyzer.discover_process_mining_structure(
         df, min_frequency=1, include_cycles=False
     )
     time_no_cycles = time.time() - start_time
@@ -151,7 +151,7 @@ def quick_benchmark():
 
     print("   With cycles:")
     start_time = time.time()
-    result_with_cycles = analyzer.discover_process_mining_structure(
+    analyzer.discover_process_mining_structure(
         df, min_frequency=1, include_cycles=True
     )
     time_with_cycles = time.time() - start_time

run_tests.py

@@ -405,12 +405,10 @@ def generate_test_report() -> TestResult:
         stdout = result.stdout
         stderr = result.stderr
         # For pytest, exit code 1 with fixture errors is acceptable
-        success = result.returncode in [0, 1]  # Accept both success and fixture errors
     except Exception as e:
         print(f"❌ Error running pytest: {e}")
         stdout = ""
         stderr = str(e)
-        success = False
 
     # Parse the output to extract test statistics
     passed = 0
@@ -428,10 +426,9 @@ def generate_test_report() -> TestResult:
     summary_matches = re.findall(summary_pattern, combined_output)
 
     # Look for the final summary line (usually the last one)
-    main_summary = ""
     for match in summary_matches:
         if any(word in match.lower() for word in ["passed", "failed", "error", "skipped"]):
-            main_summary = match
+            pass
 
     # Extract individual numbers using separate patterns from the entire output
     passed_match = re.search(r"(\d+) passed", combined_output)

scalability_test.py

@@ -125,15 +125,15 @@ def scalability_test():
 
         # Test without cycles
         start_time = time.time()
-        result_no_cycles = analyzer.discover_process_mining_structure(
+        analyzer.discover_process_mining_structure(
             df, min_frequency=10, include_cycles=False
         )
         time_no_cycles = time.time() - start_time
         print(f"{time_no_cycles:>8.2f}s", end="     ")
 
         # Test with cycles
         start_time = time.time()
-        result_with_cycles = analyzer.discover_process_mining_structure(
+        analyzer.discover_process_mining_structure(
             df, min_frequency=10, include_cycles=True
         )
         time_with_cycles = time.time() - start_time

tests/test_app_ui.py

@@ -57,7 +57,7 @@ def load_sample_data(self) -> None:
                 if attempt < max_retries - 1:  # Don't run on last attempt
                     self.at.run(timeout=10)  # Re-run to refresh state
 
-        except Exception as e:
+        except Exception:
             # If button interaction fails, manually load sample data for testing
             from datetime import datetime, timedelta
 
@@ -151,7 +151,7 @@ def build_funnel(self, steps: List[str]) -> None:
             try:
                 # Check the checkbox for this event
                 self.at.checkbox(key=checkbox_key).check().run()
-            except Exception as e:
+            except Exception:
                 # If checkbox interaction fails, manually add to session state for testing
                 if step not in self.at.session_state.funnel_steps:
                     self.at.session_state.funnel_steps.append(step)
@@ -195,7 +195,7 @@ def analyze_funnel(self) -> None:
         except KeyError:
             # If analyze button not available, skip this test (button might not be rendered yet)
             pytest.skip("Analyze button not available - UI might not be fully rendered")
-        except Exception as e:
+        except Exception:
             # If analysis fails, create mock results for testing UI flow
             from models import FunnelResults
 

tests/test_conversion_logic_debug.py

@@ -65,7 +65,7 @@ def test_debug_conversion_rate_calculation(self):
 
         overall_started = overall_results.users_count[0]
         overall_completed = overall_results.users_count[1]
-        overall_conversion = overall_results.conversion_rates[1]
+        overall_results.conversion_rates[1]
 
         print(
             f"   Manual verification: {overall_completed}/{overall_started} = {(overall_completed / overall_started * 100):.2f}%"

tests/test_data_source_advanced.py

@@ -426,10 +426,6 @@ def test_load_unsupported_file_format(self, data_manager):
 
     def test_load_corrupted_csv_file(self, data_manager):
         """Test loading corrupted CSV file."""
-        corrupted_csv = """user_id,event_name,timestamp
-user_001,Sign Up,2024-01-01
-user_002,"Incomplete quote
-user_003,Login,"""  # Corrupted CSV
 
         # Create mock file
         mock_file = Mock()

tests/test_integration_flow.py

@@ -323,7 +323,7 @@ def test_all_counting_methods_integration(self, integration_test_data):
             "First Login",
             "First Purchase",
         ]
-        base_config = FunnelConfig(conversion_window_hours=24, reentry_mode=ReentryMode.FIRST_ONLY)
+        FunnelConfig(conversion_window_hours=24, reentry_mode=ReentryMode.FIRST_ONLY)
 
         results = {}
 
@@ -684,7 +684,7 @@ def test_performance_integration(self, base_timestamp):
 
         # Visualization
         visualizer = FunnelVisualizer()
-        chart = visualizer.create_funnel_chart(results)
+        visualizer.create_funnel_chart(results)
 
         end_time = time.time()
         total_time = end_time - start_time

tests/test_polars_fallback_detection.py

@@ -286,7 +286,7 @@ def test_problematic_lazy_frame_path_analysis(self, create_lazy_frame, log_captu
 
         # Convert to regular Polars DataFrame and then to Pandas
         polars_df = lazy_df.collect()
-        pandas_df = polars_df.to_pandas()
+        polars_df.to_pandas()
 
         # Setup
         steps = ["Step1", "Step2", "Step3"]

tests/test_polars_path_analysis.py

@@ -691,7 +691,7 @@ def track_call(name):
         calculator = FunnelCalculator(config, use_polars=True)
 
         # Calculate funnel metrics
-        results = calculator.calculate_funnel_metrics(test_df, funnel_steps)
+        calculator.calculate_funnel_metrics(test_df, funnel_steps)
 
         # Check if we've fallen back to Pandas
         pandas_used = "_calculate_funnel_metrics_pandas" in call_sequence
@@ -797,7 +797,7 @@ def test_conversion_window_edge_cases():
         try:
             # Test with Polars implementation directly
             calculator = FunnelCalculator(config, use_polars=True)
-            results = calculator.calculate_funnel_metrics(test_df, funnel_steps)
+            calculator.calculate_funnel_metrics(test_df, funnel_steps)
             print(f"✅ Polars implementation succeeded with {window_str} window")
 
         except Exception as e:

tests/test_process_mining_comprehensive.py

@@ -263,7 +263,7 @@ def test_completion_rate_insights(self, insight_data):
         )
 
         # Should generate completion rate insights
-        completion_insights = [
+        [
             insight
             for insight in process_data.insights
             if "completion" in insight.lower() or "complete" in insight.lower()

tests/test_realistic_discrepancy.py

@@ -235,7 +235,6 @@ def test_cross_period_conversion_issue(self, problematic_data, calculator):
         Test the specific issue where users start in one period but convert in another.
         This is likely the root cause of the discrepancy.
         """
-        steps = ["step1", "step2"]
 
         print("\n=== CROSS-PERIOD CONVERSION ANALYSIS ===")
 

tests/test_timeseries_analysis.py

@@ -400,7 +400,7 @@ def test_timeseries_performance_monitoring(self):
         calculator = FunnelCalculator(config)
 
         # Performance metrics should be empty initially
-        initial_metrics = calculator.get_performance_report()
+        calculator.get_performance_report()
 
         # Create minimal test data and run calculation
         events_df = pd.DataFrame(

ui/visualization/visualizer.py

@@ -1557,7 +1557,7 @@ def create_enhanced_path_analysis_chart(self, path_data: PathAnalysisData) -> go
             node_categories[len(labels) - 1] = "funnel_step"
 
         # Process conversion and drop-off flows with enhanced categorization
-        node_index = len(funnel_steps)
+        len(funnel_steps)
 
         # Create a color map for consistent coloring across all datasets
         semantic_colors = {