common/Interview.py

from typing import List, Optional
from pydantic import BaseModel
import pandas as pd
from itertools import groupby


class QAEntry(BaseModel):
    Num: int
    Section: str
    Question: str
    Expected_Output: Optional[str]
    Respondent: Optional[str]
    Answer: Optional[str]

class InterviewReport(BaseModel):
    Entries: List[QAEntry]

    def __repr__(self):
        output = ""
        for section, entries in groupby(self.Entries, key=lambda entry: entry.Section):
            output += f"{section}:\n"
            for entry in entries:
                output += f"Q {entry.Num}: {entry.Question}\n"
                output += f"Expected Output: {entry.Expected_Output if entry.Expected_Output else 'No Expected Output'}\n"
                output += f"Respondent: {entry.Respondent if entry.Respondent else 'No Respondent'}\n"
                output += f"A: {entry.Answer if entry.Answer else 'No Answer'}\n"
        return output
      
    def get_respondent_responses(self,respondent):
        respondent_entries = [
          entry for entry in self.Entries 
          if entry.Respondent and entry.Respondent.lower() == respondent.lower()
        ]
        
        return respondent_entries

    @staticmethod
    def generate_interview_script(interview_file):
        df = pd.read_excel(interview_file)

        qa_entries = []
        for idx, row in enumerate(df.to_dict('records')):
            print(f"Processing row {idx}: {row}")  # Debug: show the full row being processed

            entry = QAEntry(
                Num              = row['Num'],
                Section          = row['Section'],
                Question         = row['Question'],
                Expected_Output  = row.get('Expected_Output') if pd.notna(row.get('Expected_Output')) else None,
                Respondent       = None,
                Answer           = None
            )
            qa_entries.append(entry)

        return InterviewReport(Entries = qa_entries)
      

    @staticmethod
    def generate_interview_report(interview_file):
        df = pd.read_excel(interview_file)

        qa_entries = [
            QAEntry(
                Num        = row['Num'],
                Section    = row['Section'],
                Question   = row['Question'],
                Expected_Output = row.get('Expected_Output') if pd.notna(row.get('Expected_Output')) else "No Expected Output Provided",
                Respondent = row.get('Respondent') if pd.notna(row.get('Respondent')) else "No Respondent Provided",
                Answer     = row.get('Answer') if pd.notna(row.get('Answer')) else "No Answer Provided"
            )
            for row in df.to_dict('records')
        ]

        return InterviewReport(Entries = qa_entries)