Update app.py

app.py

@@ -98,8 +98,80 @@ if uploaded_file is not None:
 
     df_combined['Self_score'] = df_combined.apply(calculate_self_score, axis=1)
 
+     #Step 7 : Picking strengths and weaknesses
+    # List of keywords/phrases to capture
+    keywords = [
+        'Integrity/ Reliability', 'Appearance', 'Enthusiasm/Passion',
+        'Learning Motivation/ Self-Development', 'Ability to Adapt/Flexibility',
+        'Communication/Information', 'Cooperation/ Team spirit',
+        'Handling of Complex Situations', 'Coolness/Handling of Unclear Situations', 'Self-reliance/Initiative',
+        'Conflict Management', 'Ability to Assert Oneself/ Negotiation Skills',
+        'Tact and Sensitivity', 'Quality Orientation', 'Client Orientation',
+        'Specialized Knowledge', 'Methodology/ Didactics/ Language',
+        'Creativity/ Conceptional Skills', 'Project Management',
+        'Result Orientation', 'Leadership Skills', 'Coach and Advisor'
+    ]
+    
+    # Extract phrases between "Topics I would like to discuss... " and "Schedule for the follow-up meeting"
+    phrases_pattern = r"Please use the form at the end of the section to finalize your development planning\.\s*(.*?)\s*Schedule for the follow-up meeting"
+    phrases_matches = re.findall(phrases_pattern, pdf_text, re.DOTALL)
+    
+    # Extract the word after "The biggest strengths and room for improvements perceived by:"
+    label_pattern = r"The biggest strengths and room for improvements perceived by:\s*(\w+)"
+    labels = re.findall(label_pattern, pdf_text)
+    
+    # Process each match and extract only the required keywords
+    json_output = []
+    for i, phrases_text in enumerate(phrases_matches):
+        extracted_phrases = [
+            phrase for phrase in keywords if phrase in phrases_text
+        ]
+        if extracted_phrases:
+            label = labels[i] if i < len(labels) else f"Phrases_{i+1}"
+            json_output.append({label: extracted_phrases})
+    
+    # Convert to JSON format
+    json_output_str = json.dumps(json_output, indent=2)
+    
+    # Print the JSON result
+    #print(json_output_str)
+    
+    json_data = df.to_json(orient='records')
+    
+    data = []
+    for item in json_output:
+        for label, phrases in item.items():
+            for phrase in phrases:
+                data.append({'Label': label, 'Dimensions': phrase})
+    
+    df4 = pd.DataFrame(data)
+
+    #Step 9: Converting Streangths and Weaknesses with scores into json
+
+    # Filter dataframes based on 'Label' value
+    boss, direct, colleague, other_colleague = [df4[df4['Label'] == label].copy() for label in ['Boss', 'Direct', 'Colleagues', 'Colleague (o']]
+    
+    # Create mapping dictionaries from df3
+    mappings = {
+        'Boss_score': df_combined.set_index('Dimensions')['Boss_score'].to_dict(),
+        'Report_score': df_combined.set_index('Dimensions')['Report_score'].to_dict(),
+        'Colleague_score': df_combined.set_index('Dimensions')['Colleague_score'].to_dict(),
+        'Other_colleague_score': df_combined.set_index('Dimensions')['Colleague_other_score'].to_dict()
+    }
+    
+    # Map the values from df3 to the appropriate DataFrames
+    boss['Boss_score'] = boss['Dimensions'].map(mappings['Boss_score'])
+    direct['Report_score'] = direct['Dimensions'].map(mappings['Report_score'])
+    colleague['Colleague_score'] = colleague['Dimensions'].map(mappings['Colleague_score'])
+    other_colleague['Other_colleague_score'] = other_colleague['Dimensions'].map(mappings['Other_colleague_score'])
+
+    boss.sort_values(by = 'Boss_score', ascending = False)
+    boss_json = boss.iloc[3:,1:].to_dict(orient='records')
+    prompt = f"You are a corporate trainer who guides me how to behave in corporate settings. You will analyze the top 3 strengths and scores{boss_json} rated by my boss out of 6. You will generate a nudge for each dimension to improveupon these strengths." 
+        
     st.write("### Output:")
     st.write("#### 1. Extracted data: Dimensions Assessment of the leader by: Boss, Colleagues, Colleagues (other b.), Direct reports, Customers and All Raters")
     st.write("#### 2. Derived data: Self score")
     st.write("### Dataset Table")
     st.dataframe(df_combined)
+    st.write(f"#### {print(prompt)}")