87 lines
3.6 KiB
Markdown
87 lines
3.6 KiB
Markdown
# Project Structure
|
|
|
|
## Root Directory (Minimal & Clean)
|
|
|
|
```
|
|
Simulated_Assessment_Engine/
|
|
├── README.md # Complete documentation (all-in-one)
|
|
├── .gitignore # Git ignore rules
|
|
├── .env # API key (create this, not in git)
|
|
│
|
|
├── main.py # Simulation engine (Step 2)
|
|
├── config.py # Configuration
|
|
├── check_api.py # API connection test
|
|
├── run_complete_pipeline.py # Master orchestrator (all 3 steps)
|
|
│
|
|
├── data/ # Data files
|
|
│ ├── AllQuestions.xlsx # Question mapping (1,297 questions)
|
|
│ ├── merged_personas.xlsx # Merged personas (3,000 students, 79 columns)
|
|
│ └── demo_answers/ # Demo output examples
|
|
│
|
|
├── support/ # Support files (required for Step 1)
|
|
│ ├── 3000-students.xlsx # Student demographics
|
|
│ ├── 3000_students_output.xlsx # Student CPIDs from database
|
|
│ └── fixed_3k_personas.xlsx # Persona enrichment (22 columns)
|
|
│
|
|
├── scripts/ # Utility scripts
|
|
│ ├── prepare_data.py # Step 1: Persona preparation
|
|
│ ├── comprehensive_post_processor.py # Step 3: Post-processing
|
|
│ ├── final_production_verification.py # Production verification
|
|
│ └── [other utility scripts]
|
|
│
|
|
├── services/ # Core services
|
|
│ ├── data_loader.py # Load personas and questions
|
|
│ ├── simulator.py # LLM simulation engine
|
|
│ └── cognition_simulator.py # Cognition test simulation
|
|
│
|
|
├── output/ # Generated output (gitignored)
|
|
│ ├── full_run/ # Production output (34 files)
|
|
│ └── dry_run/ # Test output (5 students)
|
|
│
|
|
└── docs/ # Additional documentation
|
|
├── README.md # Documentation index
|
|
├── DEPLOYMENT_GUIDE.md # Deployment instructions
|
|
├── WORKFLOW_GUIDE.md # Complete workflow guide
|
|
├── PROJECT_STRUCTURE.md # This file
|
|
└── [other documentation]
|
|
```
|
|
|
|
## Key Files
|
|
|
|
### Core Scripts
|
|
- **`main.py`** - Main simulation engine (processes all students)
|
|
- **`config.py`** - Configuration (API keys, settings, paths)
|
|
- **`run_complete_pipeline.py`** - Orchestrates all 3 steps
|
|
- **`check_api.py`** - Tests API connection
|
|
|
|
### Data Files
|
|
- **`data/AllQuestions.xlsx`** - All 1,297 questions with metadata
|
|
- **`data/merged_personas.xlsx`** - Unified persona file (79 columns, 3,000 rows)
|
|
- **`support/3000-students.xlsx`** - Student demographics
|
|
- **`support/3000_students_output.xlsx`** - Student CPIDs from database
|
|
- **`support/fixed_3k_personas.xlsx`** - Persona enrichment data
|
|
|
|
### Services
|
|
- **`services/data_loader.py`** - Loads personas and questions
|
|
- **`services/simulator.py`** - LLM-based response generation
|
|
- **`services/cognition_simulator.py`** - Math-based cognition test simulation
|
|
|
|
### Scripts
|
|
- **`scripts/prepare_data.py`** - Step 1: Merge personas
|
|
- **`scripts/comprehensive_post_processor.py`** - Step 3: Post-processing
|
|
- **`scripts/final_production_verification.py`** - Verify standalone status
|
|
|
|
## Documentation
|
|
|
|
- **`README.md`** - Complete documentation (beginner to expert)
|
|
- **`docs/`** - Additional documentation (deployment, workflow, etc.)
|
|
|
|
## Output
|
|
|
|
- **`output/full_run/`** - Production output (34 Excel files)
|
|
- **`output/dry_run/`** - Test output (5 students)
|
|
|
|
---
|
|
|
|
**Note**: Root directory contains only essential files. All additional documentation is in `docs/` folder.
|