Update process_interview.py

process_interview.py

@@ -363,7 +363,7 @@ def analyze_interviewee_voice(audio_path: str, utterances: List[Dict]) -> Dict:
         intensities = []
         for segment in segments:
             rms = np.mean(librosa.feature.rms(y=segment)[0]) if len(segment) > 0 else 0.0
-            intensities.append(float(rms))  # Fix: Use append instead of extend
+            intensities.append(float(rms))
         intensity_mean = np.mean(intensities) if intensities else 0
         intensity_std = np.std(intensities) if intensities else 0
         shimmer = np.mean(np.abs(np.diff(intensities))) / intensity_mean if len(intensities) > 1 and intensity_mean > 0 else 0
@@ -420,14 +420,15 @@ def generate_anxiety_confidence_chart(composite_scores: Dict, chart_buffer):
                     ha='center', color='black', fontweight='bold', fontsize=10)
         ax.grid(True, axis='y', linestyle='--', alpha=0.7)
         plt.tight_layout()
-        plt.savefig(chart_buffer, format='png', bbox_inches='tight', dpi=100)
+        plt.savefig(chart_buffer, format='png', bbox_inches='tight', dpi=300)
         plt.close(fig)
     except Exception as e:
         logger.error(f"Error generating chart: {str(e)}")
 
 def calculate_acceptance_probability(analysis_data: Dict) -> float:
     voice = analysis_data.get('voice_analysis', {})
-    if 'error' in voice: return 50.0
+    if 'error' in voice:
+        return 50.0
     w_confidence, w_anxiety, w_fluency, w_speaking_rate, w_filler_repetition, w_content_strengths = 0.35, -0.25, 0.2, 0.15, -0.15, 0.25
     confidence_score = voice.get('composite_scores', {}).get('confidence', 0.0)
     anxiety_score = voice.get('composite_scores', {}).get('anxiety', 0.0)
@@ -523,10 +524,10 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
         story.append(Paragraph("Candidate Interview Analysis", h1))
         story.append(Paragraph(f"Generated: {time.strftime('%B %d, %Y')}", ParagraphStyle(name='Date', alignment=1, fontSize=8, textColor=colors.HexColor('#666666'), fontName='Helvetica')))
         story.append(Spacer(1, 0.3*inch))
-        acceptance_prob = float(np.mean([np.mean([np.mean([analysis_data['acceptance_probability'], 0.0])])]))  # Ensure float
+        acceptance_prob = analysis_data.get('acceptance_probability', 50.0)
         story.append(Paragraph("Hiring Suitability Snapshot", h2))
         prob_color = colors.HexColor('#2E7D32') if acceptance_prob >= 80 else (colors.HexColor('#F57C00') if acceptance_prob >= 60 else colors.HexColor('#D32F2F'))
-        story.append(Paragraph(f"Suitability Score: <font size=14 color='{prob_color.hexval()}'>{acceptance_prob:.2f}%</font>", 
+        story.append(Paragraph(f"Suitability Score: <font size=14 color='{prob_color.hexval()}'><b>{acceptance_prob:.2f}%</b></font>",
                              ParagraphStyle(name='Prob', fontSize=10, spaceAfter=8, alignment=1, fontName='Helvetica-Bold')))
         if acceptance_prob >= 80:
             story.append(Paragraph("<b>HR Verdict:</b> Outstanding candidate, recommended for immediate advancement.", body_text))
@@ -540,9 +541,9 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
         participants = sorted([p for p in set(u['speaker'] for u in analysis_data['transcript']) if p != 'Unknown'])
         table_data = [
             ['Metric', 'Value'],
-            ['Interview Duration', f"{analysis_data['text_analysis']['total_duration']:.1f} seconds"],
+            ['Interview Duration', f"{analysis_data['text_analysis']['total_duration']:.2f} seconds"],
             ['Speaker Turns', f"{analysis_data['text_analysis']['speaker_turns']}"],
-            ['Participants', f"{', '.join(participants)}"],
+            ['Participants', ', '.join(participants)],
         ]
         table = Table(table_data, colWidths=[2.2*inch, 3.8*inch])
         table.setStyle(TableStyle([
@@ -554,7 +555,7 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
             ('FONTSIZE', (0,0), (-1,-1), 8),
             ('BOTTOMPADDING', (0,0), (-1,0), 6),
             ('TOPPADDING', (0,0), (-1,0), 6),
-            ('BACKGROUND', (0,1), (-1,-1), colors.HexColor('#F5F6FA'),),
+            ('BACKGROUND', (0,1), (-1,-1), colors.HexColor('#F5F6FA')),
             ('GRID', (0,0), (-1,-1), 0.4, colors.HexColor('#DDE4EB')),
         ]))
         story.append(table)
@@ -565,41 +566,41 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
         # Detailed Analysis
         story.append(Paragraph("Detailed Candidate Evaluation", h1))
         
-        # Communication and Speech
+        # Communication and Vocal Dynamics
         story.append(Paragraph("1. Communication & Vocal Dynamics", h2))
         voice_analysis = analysis_data.get('voice_analysis', {})
-        if voice_analysis' and 'error' not in voice_analysis:
+        if voice_analysis and 'error' not in voice_analysis:
             table_data = [
                 ['Metric', 'Value', 'HR Insight'],
                 ['Speaking Rate', f"{voice_analysis.get('speaking_rate', 0):.2f} words/sec", 'Benchmark: 2.0-3.0 wps; impacts clarity'],
-                ['Filler Words', f"{voice_analysis.get('filler_ratio', 0) * 100:.1f}%', 'High usage reduces credibility'],
+                ['Filler Words', f"{voice_analysis.get('filler_ratio', 0) * 100:.1f}%", 'High usage reduces credibility'],
                 ['Anxiety', voice_analysis.get('interpretation', {}).get('anxiety_level', 'N/A'), f"Score: {voice_analysis.get('composite_scores', {}).get('anxiety', 0):.3f}"],
                 ['Confidence', voice_analysis.get('interpretation', {}).get('confidence_level', 'N/A'), f"Score: {voice_analysis.get('composite_scores', {}).get('confidence', 0):.3f}"],
                 ['Fluency', voice_analysis.get('interpretation', {}).get('fluency_level', 'N/A'), 'Drives engagement'],
             ]
             table = Table(table_data, colWidths=[1.5*inch, 1.3*inch, 3.2*inch])
             table.setStyle(TableStyle([
-                ('BACKGROUND', (0,0), (-1,0)), colors.HexColor('#0050BC')),
-                ('TEXTCOLOR', (0,0), (-1,-0)), colors.white),
+                ('BACKGROUND', (0,0), (-1,0), colors.HexColor('#0050BC')),
+                ('TEXTCOLOR', (0,0), (-1,0), colors.white),
                 ('ALIGN', (0,0), (-1,-1), 'LEFT'),
                 ('VALIGN', (0,0), (-1,-1), 'MIDDLE'),
-                ('FONTNAME', (0,0), (-1,-0)), 'Helvetica-Bold'),
+                ('FONTNAME', (0,0), (-1,0), 'Helvetica-Bold'),
                 ('FONTSIZE', (0,0), (-1,-1), 8),
-                ('BOTTOMPADDING', (0,0), (-1,-0)), 6),
-                ('TOPPADDING', (0,0), (0,-1), 6),
-                ('BACKGROUND', (0,1), (-1,-1), colors.HexColor('#F5F6FA'))),
-                ('GRID', (0,0), (-1,-1), 0.4, colors.HexColor('#DDE4EB'))),
+                ('BOTTOMPADDING', (0,0), (-1,0), 6),
+                ('TOPPADDING', (0,0), (-1,0), 6),
+                ('BACKGROUND', (0,1), (-1,-1), colors.HexColor('#F5F6FA')),
+                ('GRID', (0,0), (-1,-1), 0.4, colors.HexColor('#DDE4EB')),
             ]))
             story.append(table)
             story.append(Spacer(1, 0.15*inch))
             chart_buffer = io.BytesIO()
-            generate_anxiety_chart(voice_analysis.get('composite_scores', {}), chart_buffer)
+            generate_anxiety_confidence_chart(voice_analysis.get('composite_scores', {}), chart_buffer)
             chart_buffer.seek(0)
             img = Image(chart_buffer, width=4.2*inch, height=2.8*inch)
             img.hAlign = 'CENTER'
             story.append(img)
         else:
-            story.append(Paragraph("Voice analysis unavailable.", body_text))
+            story.append(Paragraph(f"Voice analysis unavailable: {voice_analysis.get('error', 'Unknown error')}", body_text))
         story.append(Spacer(1, 0.15*inch))
 
         # Parse Gemini Report
@@ -615,7 +616,8 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
         lines = gemini_report_text.split('\n')
         for line in lines:
             line = line.strip()
-            if not line: continue
+            if not line:
+                continue
             if line.startswith('**') and line.endswith('**'):
                 section_title = line.strip('**').strip()
                 if section_title.startswith(('1.', '2.', '3.', '4.', '5.')):
@@ -637,10 +639,11 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
                     current_subsection = None
             elif line.startswith('-') and current_section:
                 clean_line = line.lstrip('-').strip()
-                if not clean_line: continue
-                clean_line = re.sub(r'[()]', '', clean_line)
+                if not clean_line:
+                    continue
+                clean_line = re.sub(r'[()]+', '', clean_line)
                 if current_section == 'Competency':
-                    if any(k in clean_line.lower() for k in ['leader', 'leadership', 'problem', 'commun', 'adapt', 'strength']):
+                    if any(k in clean_line.lower() for k in ['leader', 'problem', 'commun', 'adapt', 'strength']):
                         current_subsection = 'Strengths'
                     elif any(k in clean_line.lower() for k in ['improv', 'grow', 'depth']):
                         current_subsection = 'Growth Areas'
@@ -717,10 +720,14 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
         return False
 
 def convert_to_serializable(obj):
-    if isinstance(obj, np.generic): return obj.item()
-    if isinstance(obj, dict): return {k: convert_to_serializable(v) for k, v in obj.items()}
-    if isinstance(obj, list): return [convert_to_serializable(item) for item in obj]
-    if isinstance(obj, np.ndarray): return obj.tolist()
+    if isinstance(obj, np.generic):
+        return obj.item()
+    if isinstance(obj, dict):
+        return {k: convert_to_serializable(v) for k, v in obj.items()}
+    if isinstance(obj, list):
+        return [convert_to_serializable(item) for item in obj]
+    if isinstance(obj, np.ndarray):
+        return obj.tolist()
     return obj
 
 def process_interview(audio_url: str) -> Dict:
@@ -800,6 +807,6 @@ def process_interview(audio_url: str) -> Dict:
         if is_downloaded and local_audio_path and os.path.exists(local_audio_path):
             try:
                 os.remove(local_audio_path)
-                logger.info(f"Cleaned up temporary audio file: {local_audio_path}")
+                logger.info(f"Cleaned up temporary file: {local_audio_path}")
             except Exception as e:
                 logger.error(f"Failed to clean up local audio file {local_audio_path}: {str(e)}")