Skip to content

Commit 88244d1

Browse files
tom-dyartom-dyar
committed
Final framework updates: add DNA similarity demo runner and README updates
1 parent dc8893b commit 88244d1

File tree

2 files changed

+272
-0
lines changed

2 files changed

+272
-0
lines changed

‎README.md‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -71,6 +71,9 @@ python run_fraud_detection_demo.py
7171

7272
# Sales Forecasting with hybrid models
7373
python run_sales_forecasting_demo.py
74+
75+
# DNA Similarity Analysis with sequence classification
76+
python run_dna_similarity_demo.py
7477
```
7578

7679
### Alternative: Standalone Installation
@@ -227,6 +230,7 @@ open http://localhost:8080 # Application API
227230
python run_credit_risk_demo.py
228231
python run_fraud_detection_demo.py
229232
python run_sales_forecasting_demo.py
233+
python run_dna_similarity_demo.py
230234
```
231235

232236
**🚀 What's New in This Release:**

‎run_dna_similarity_demo.py‎

Lines changed: 268 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,268 @@
1+
#!/usr/bin/env python3
2+
"""
3+
DNA Similarity Demo - End-to-End Implementation with IntegratedML Framework
4+
5+
This script demonstrates DNA sequence classification and similarity search using
6+
the IntegratedML Flexible Model Integration Framework.
7+
"""
8+
9+
import os
10+
import sys
11+
import logging
12+
import time
13+
from pathlib import Path
14+
15+
# Add project root to path
16+
project_root = Path(__file__).parent
17+
sys.path.insert(0, str(project_root))
18+
19+
# Configure logging
20+
logging.basicConfig(
21+
level=logging.INFO,
22+
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
23+
)
24+
logger = logging.getLogger(__name__)
25+
26+
27+
def print_banner(text):
28+
"""Print a formatted banner."""
29+
print("\n" + "=" * 80)
30+
print(f" {text}")
31+
print("=" * 80)
32+
33+
34+
def print_step(step_num, description):
35+
"""Print a formatted step."""
36+
print(f"\n🧬 Step {step_num}: {description}")
37+
print("-" * 60)
38+
39+
40+
def wait_for_user():
41+
"""Wait for user input to continue."""
42+
input("\nPress Enter to continue...")
43+
44+
45+
def main():
46+
"""Run the complete DNA Similarity demo."""
47+
print_banner("INTEGRATEDML DNA SIMILARITY & CLASSIFICATION DEMO")
48+
print("This demo showcases DNA sequence classification and similarity search")
49+
print("using the IntegratedML Flexible Model Integration Framework.")
50+
51+
try:
52+
# Step 1: Framework Introduction
53+
print_step(1, "IntegratedML Framework Introduction")
54+
55+
print("🎯 This demo demonstrates how the IntegratedML framework solves")
56+
print(" the original DNA similarity project challenges:")
57+
print()
58+
print(" Challenge #1: Hardcoded Vectorization")
59+
print(" ✓ Solution: Configurable vectorization strategies")
60+
print()
61+
print(" Challenge #2: Hardcoded Algorithm Selection")
62+
print(" ✓ Solution: Pluggable algorithms via YAML configuration")
63+
print()
64+
print(" Challenge #3: Mixed Database Logic")
65+
print(" ✓ Solution: Clean database abstraction layer")
66+
67+
wait_for_user()
68+
69+
# Step 2: Demo Setup and Configuration
70+
print_step(2, "Demo Setup and Configuration")
71+
72+
print("🔧 Initializing DNA similarity demo...")
73+
74+
# Check if demo files exist
75+
demo_dir = project_root / "demos" / "dna_similarity"
76+
config_path = demo_dir / "config" / "dna_model_config.yaml"
77+
demo_script = demo_dir / "dna_demo.py"
78+
79+
if not demo_dir.exists():
80+
logger.error("❌ DNA similarity demo directory not found!")
81+
print("Please ensure the demos/dna_similarity directory exists.")
82+
return False
83+
84+
if not config_path.exists():
85+
logger.error("❌ DNA demo configuration file not found!")
86+
print(f"Please ensure {config_path} exists.")
87+
return False
88+
89+
if not demo_script.exists():
90+
logger.error("❌ DNA demo script not found!")
91+
print(f"Please ensure {demo_script} exists.")
92+
return False
93+
94+
print("✅ Demo directory structure verified")
95+
print(f"📁 Demo location: {demo_dir}")
96+
print(f"⚙️ Configuration: {config_path.name}")
97+
print(f"🐍 Demo script: {demo_script.name}")
98+
99+
wait_for_user()
100+
101+
# Step 3: Import and Initialize Demo Components
102+
print_step(3, "Loading Demo Components")
103+
104+
print("📦 Importing DNA similarity demo modules...")
105+
106+
try:
107+
# Import the demo runner
108+
sys.path.insert(0, str(demo_dir))
109+
from dna_demo import DNADemoRunner
110+
111+
print("✅ DNA demo modules imported successfully")
112+
113+
# Initialize demo runner
114+
print("🧬 Initializing DNA demo runner...")
115+
demo_runner = DNADemoRunner(str(config_path))
116+
117+
print("✅ DNA demo runner initialized")
118+
print(f"📊 Configuration loaded from: {config_path.name}")
119+
120+
except ImportError as e:
121+
logger.error(f"❌ Failed to import DNA demo modules: {e}")
122+
print("Please ensure all required dependencies are installed:")
123+
print(" pip install pandas scikit-learn sentence-transformers pyyaml numpy")
124+
return False
125+
except Exception as e:
126+
logger.error(f"❌ Failed to initialize demo runner: {e}")
127+
print(f"Error: {e}")
128+
return False
129+
130+
wait_for_user()
131+
132+
# Step 4: Run Vectorization Strategy Demonstration
133+
print_step(4, "Vectorization Strategy Demonstration")
134+
135+
print("🔬 Demonstrating multiple vectorization approaches...")
136+
print("This addresses Challenge #1: Hardcoded Vectorization")
137+
print()
138+
139+
try:
140+
# Create sample data for demonstrations
141+
sample_data = demo_runner._create_sample_data()
142+
print(f"✅ Created sample dataset with {len(sample_data)} DNA sequences")
143+
print(f"📊 Classes represented: {sample_data['class'].nunique()}")
144+
145+
# Run vectorization demonstration
146+
demo_runner.demonstrate_vectorization_strategies(sample_data)
147+
148+
except Exception as e:
149+
logger.error(f"❌ Vectorization demonstration failed: {e}")
150+
print(f"Error during vectorization demo: {e}")
151+
152+
wait_for_user()
153+
154+
# Step 5: Run Algorithm Selection Demonstration
155+
print_step(5, "Algorithm Selection Demonstration")
156+
157+
print("🤖 Demonstrating pluggable algorithm selection...")
158+
print("This addresses Challenge #2: Hardcoded Algorithm Selection")
159+
print()
160+
161+
try:
162+
# Run algorithm demonstration
163+
demo_runner.demonstrate_algorithm_selection(sample_data)
164+
165+
except Exception as e:
166+
logger.error(f"❌ Algorithm demonstration failed: {e}")
167+
print(f"Error during algorithm demo: {e}")
168+
169+
wait_for_user()
170+
171+
# Step 6: Database Integration Demonstration
172+
print_step(6, "Database Integration Demonstration")
173+
174+
print("🗃️ Demonstrating clean IRIS database integration...")
175+
print("This addresses Challenge #3: Mixed Database Logic")
176+
print()
177+
178+
try:
179+
# Run database integration demonstration
180+
demo_runner.demonstrate_iris_integration()
181+
182+
except Exception as e:
183+
logger.error(f"❌ Database integration demonstration failed: {e}")
184+
print(f"Error during database demo: {e}")
185+
186+
wait_for_user()
187+
188+
# Step 7: Similarity Search Demonstration
189+
print_step(7, "DNA Similarity Search Demonstration")
190+
191+
print("🔍 Demonstrating vector-based DNA similarity search...")
192+
print("This shows advanced framework capabilities for sequence analysis")
193+
print()
194+
195+
try:
196+
# Run similarity search demonstration
197+
demo_runner.demonstrate_similarity_search(sample_data)
198+
199+
except Exception as e:
200+
logger.error(f"❌ Similarity search demonstration failed: {e}")
201+
print(f"Error during similarity search demo: {e}")
202+
203+
wait_for_user()
204+
205+
# Step 8: Complete Framework Demonstration
206+
print_step(8, "Complete Framework Integration")
207+
208+
print("🚀 Running complete IntegratedML framework demonstration...")
209+
print("This shows all components working together seamlessly")
210+
print()
211+
212+
try:
213+
# Run the complete demo
214+
print("=" * 60)
215+
print("RUNNING COMPLETE DNA SIMILARITY FRAMEWORK DEMO")
216+
print("=" * 60)
217+
218+
# Execute the full demo
219+
demo_runner.run_complete_demo()
220+
221+
print("=" * 60)
222+
print("DNA SIMILARITY FRAMEWORK DEMO COMPLETED")
223+
print("=" * 60)
224+
225+
except Exception as e:
226+
logger.error(f"❌ Complete demo failed: {e}")
227+
print(f"Error during complete demo: {e}")
228+
229+
wait_for_user()
230+
231+
# Final summary
232+
print_banner("DNA SIMILARITY DEMO COMPLETED! 🎉")
233+
print("Key accomplishments:")
234+
print("✅ Demonstrated configurable vectorization strategies")
235+
print("✅ Showed pluggable algorithm selection")
236+
print("✅ Illustrated clean database abstraction")
237+
print("✅ Performed DNA sequence classification")
238+
print("✅ Executed vector-based similarity search")
239+
print("✅ Showcased framework flexibility and extensibility")
240+
print()
241+
print("🧬 Framework Benefits Demonstrated:")
242+
print(" 📊 Configuration-driven development")
243+
print(" 🔧 Clean separation of concerns")
244+
print(" 🚀 Enterprise-ready deployment")
245+
print(" 🎯 Improved developer productivity")
246+
print()
247+
print("This demo shows how the IntegratedML framework transforms")
248+
print("hardcoded bioinformatics solutions into flexible, maintainable,")
249+
print("and production-ready applications!")
250+
251+
return True
252+
253+
except Exception as e:
254+
logger.error(f"❌ Demo failed with error: {e}")
255+
print(f"Demo execution failed: {e}")
256+
print()
257+
print("💡 Troubleshooting tips:")
258+
print(" 1. Ensure all dependencies are installed:")
259+
print(" pip install pandas scikit-learn sentence-transformers pyyaml numpy")
260+
print(" 2. Verify demo files exist in demos/dna_similarity/")
261+
print(" 3. Check that configuration file is present")
262+
print(" 4. Run from the project root directory")
263+
return False
264+
265+
266+
if __name__ == "__main__":
267+
success = main()
268+
sys.exit(0 if success else 1)

0 commit comments

Comments
 (0)