Spaces:
Running
on
Zero
Running
on
Zero
File size: 13,379 Bytes
0ccf2f0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 |
"""
Test suite for 8D FractalStat Integration
Tests 8D FractalStat coordinate computation, hybrid scoring, and resonance calculations
Now upgraded from 7D FractalStat to 8D FractalStat with alignment dimension.
"""
import pytest
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent))
from warbler_cda.retrieval_api import RetrievalAPI, RetrievalQuery, RetrievalMode
from warbler_cda.embeddings import EmbeddingProviderFactory
from warbler_cda.fractalstat_entity import FractalStatCoordinates, Realm, Horizon, Polarity, Alignment
class TestFractalStatCoordinateComputation:
"""Test FractalStat coordinate computation from embeddings."""
def setup_method(self):
"""Setup for each test."""
try:
from warbler_cda.embeddings.sentence_transformer_provider import (
SentenceTransformerEmbeddingProvider,
)
self.provider = SentenceTransformerEmbeddingProvider()
self.skip = False
except ImportError:
self.skip = True
def test_fractalstat_from_embedding(self):
"""Test FractalStat coordinate computation from embedding."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
text = "Test document for FractalStat coordinates"
embedding = self.provider.embed_text(text)
fractalstat = self.provider.compute_fractalstat_from_embedding(embedding)
assert "lineage" in fractalstat
assert "adjacency" in fractalstat
assert "luminosity" in fractalstat
assert "polarity" in fractalstat
assert "dimensionality" in fractalstat
assert "horizon" in fractalstat
assert "realm" in fractalstat
def test_fractalstat_values_in_range(self):
"""Test that FractalStat values are in expected ranges."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
text = "Test text"
embedding = self.provider.embed_text(text)
fractalstat = self.provider.compute_fractalstat_from_embedding(embedding)
# Verify expected ranges for different dimensions:
# lineage: unbounded positive (energy-based, generation/passage)
# adjacency: [-1, 1] (semantic connectivity)
# luminosity: [0, 100] (activity/coherence level)
# polarity: [-1, 1] (resonance balance)
# dimensionality: [1, 8] (complexity depth)
assert fractalstat["lineage"] >= 0.0, "lineage should be non-negative"
assert -1.0 <= fractalstat["adjacency"] <= 1.0, "adjacency should be between -1 and 1"
assert 0.0 <= fractalstat["luminosity"] <= 100.0, "luminosity should be between 0 and 100"
assert -1.0 <= fractalstat["polarity"] <= 1.0, "polarity should be between -1 and 1"
assert 1 <= fractalstat["dimensionality"] <= 8, "dimensionality should be between 1 and 8"
def test_different_texts_produce_different_fractalstat(self):
"""Test that different texts produce different FractalStat coordinates."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
text1 = "This is about performance and optimization"
text2 = "This is completely different about philosophy"
emb1 = self.provider.embed_text(text1)
emb2 = self.provider.embed_text(text2)
fractalstat_1 = self.provider.compute_fractalstat_from_embedding(emb1)
fractalstat_2 = self.provider.compute_fractalstat_from_embedding(emb2)
differences = [
abs(fractalstat_1[key] - fractalstat_2[key])
for key in ["lineage", "adjacency", "luminosity", "polarity", "dimensionality"]
]
assert any(
diff > 0.1 for diff in differences
), "Different texts should produce different FractalStat"
class TestFractalStatHybridScoring:
"""Test FractalStat hybrid scoring in retrieval."""
def setup_method(self):
"""Setup for each test."""
try:
from warbler_cda.embeddings.sentence_transformer_provider import (
SentenceTransformerEmbeddingProvider,
)
self.provider = SentenceTransformerEmbeddingProvider()
self.skip = False
except ImportError:
self.skip = True
self.api = RetrievalAPI(
embedding_provider=(
self.provider if not self.skip else EmbeddingProviderFactory.get_default_provider()
),
config={"enable_fractalstat_hybrid": True},
)
def test_hybrid_scoring_combines_semantic_and_fractalstat(self):
"""Test that hybrid scoring combines semantic and FractalStat components."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
self.api.add_document("doc_1", "Semantic embeddings for document retrieval")
self.api.add_document("doc_2", "FractalStat hybrid scoring approach")
self.api.add_document("doc_3", "Machine learning and embeddings")
query = RetrievalQuery(
query_id="test_hybrid",
mode=RetrievalMode.SEMANTIC_SIMILARITY,
semantic_query="embeddings and scoring",
max_results=3,
fractalstat_hybrid=True,
weight_semantic=0.6,
weight_fractalstat=0.4,
)
assembly = self.api.retrieve_context(query)
assert assembly is not None
for result in assembly.results:
assert hasattr(result, "semantic_similarity")
assert hasattr(result, "fractalstat_resonance")
assert hasattr(result, "relevance_score")
def test_fractalstat_resonance_calculation(self):
"""Test FractalStat resonance calculation."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
doc_fractalstat = {
"lineage": 0.5,
"adjacency": 0.6,
"luminosity": 0.7,
"polarity": 0.5,
"dimensionality": 0.4,
"horizon": "scene",
"realm": {"type": "semantic", "label": "test"},
}
query_fractalstat = {
"lineage": 0.5,
"adjacency": 0.5,
"luminosity": 0.7,
"polarity": 0.5,
"dimensionality": 0.4,
"horizon": "scene",
"realm": {"type": "semantic", "label": "test"},
}
resonance = self.api._calculate_fractalstat_resonance(doc_fractalstat, query_fractalstat)
assert 0.0 <= resonance <= 1.0
assert resonance > 0.7, "Similar FractalStat coordinates should have high resonance"
def test_fractalstat_resonance_with_different_coordinates(self):
"""Test FractalStat resonance with very different coordinates."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
doc_fractalstat = {
"lineage": 0.1,
"adjacency": 0.2,
"luminosity": 0.1,
"polarity": 0.2,
"dimensionality": 0.1,
}
query_fractalstat = {
"lineage": 0.9,
"adjacency": 0.8,
"luminosity": 0.9,
"polarity": 0.8,
"dimensionality": 0.9,
}
resonance = self.api._calculate_fractalstat_resonance(doc_fractalstat, query_fractalstat)
assert 0.0 <= resonance <= 1.0
assert resonance < 0.4, "Very different FractalStat coordinates should have low resonance"
class TestFractalStatDocumentEnrichment:
"""Test document enrichment with FractalStat coordinates."""
def setup_method(self):
"""Setup for each test."""
try:
from warbler_cda.embeddings.sentence_transformer_provider import (
SentenceTransformerEmbeddingProvider,
)
self.provider = SentenceTransformerEmbeddingProvider()
self.skip = False
except ImportError:
self.skip = True
self.api = RetrievalAPI(
embedding_provider=self.provider if not self.skip else None,
config={"enable_fractalstat_hybrid": True},
)
def test_document_enriched_with_embedding(self):
"""Test that documents are enriched with embeddings."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
self.api.add_document("doc_1", "Test document content")
stored_doc = self.api._context_store["doc_1"]
assert "embedding" in stored_doc
assert isinstance(stored_doc["embedding"], list)
def test_document_enriched_with_fractalstat(self):
"""Test that documents are enriched with FractalStat coordinates."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
self.api.add_document("doc_1", "Test document for FractalStat")
stored_doc = self.api._context_store["doc_1"]
assert "fractalstat_coordinates" in stored_doc
fractalstat = stored_doc["fractalstat_coordinates"]
assert "lineage" in fractalstat
assert "adjacency" in fractalstat
assert "luminosity" in fractalstat
assert "polarity" in fractalstat
assert "dimensionality" in fractalstat
class TestFractalStatQueryAddressing:
"""Test FractalStat query addressing for multi-dimensional retrieval."""
def setup_method(self):
"""Setup for each test."""
try:
from warbler_cda.embeddings.sentence_transformer_provider import (
SentenceTransformerEmbeddingProvider,
)
self.provider = SentenceTransformerEmbeddingProvider()
self.skip = False
except ImportError:
self.skip = True
self.api = RetrievalAPI(
embedding_provider=(
self.provider if not self.skip else EmbeddingProviderFactory.get_default_provider()
),
config={"enable_fractalstat_hybrid": True},
)
def test_query_with_fractalstat_address(self):
"""Test query with explicit FractalStat address."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
self.api.add_document("doc_1", "Document about optimization")
self.api.add_document("doc_2", "Document about performance")
fractalstat_address = {
"realm": {"type": "technical", "label": "optimization"},
"lineage": 0.7,
"adjacency": 0.6,
"horizon": "scene",
"luminosity": 0.8,
"polarity": 0.6,
"dimensionality": 0.7,
}
query = RetrievalQuery(
query_id="test_fractalstat_query",
mode=RetrievalMode.SEMANTIC_SIMILARITY,
semantic_query="performance",
max_results=5,
fractalstat_hybrid=True,
fractalstat_address=fractalstat_address,
)
assembly = self.api.retrieve_context(query)
assert assembly is not None
def test_default_fractalstat_address_generated(self):
"""Test that default FractalStat address is generated if not provided."""
query = RetrievalQuery(
query_id="test_default_fractalstat",
mode=RetrievalMode.SEMANTIC_SIMILARITY,
semantic_query="test",
fractalstat_hybrid=True,
)
assert query.fractalstat_address is not None
assert "lineage" in query.fractalstat_address
assert "adjacency" in query.fractalstat_address
assert "luminosity" in query.fractalstat_address
assert "polarity" in query.fractalstat_address
class TestFractalStatDimensions:
"""Test FractalStat dimensional space properties."""
def setup_method(self):
"""Setup for each test."""
try:
from warbler_cda.embeddings.sentence_transformer_provider import (
SentenceTransformerEmbeddingProvider,
)
self.provider = SentenceTransformerEmbeddingProvider()
self.skip = False
except ImportError:
self.skip = True
def test_eight_dimensions_in_fractalstat(self):
"""Test that FractalStat provides 8 key dimensions."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
text = "Test for seven dimensions"
embedding = self.provider.embed_text(text)
fractalstat = self.provider.compute_fractalstat_from_embedding(embedding)
expected_dims = [
"lineage",
"adjacency",
"luminosity",
"polarity",
"dimensionality",
"horizon",
"realm",
]
for dim in expected_dims:
assert dim in fractalstat, f"FractalStat should contain {dim}"
def test_fractalstat_realm_structure(self):
"""Test that FractalStat realm has proper structure."""
if self.skip:
pytest.skip("SentenceTransformer not installed")
text = "Test"
embedding = self.provider.embed_text(text)
fractalstat = self.provider.compute_fractalstat_from_embedding(embedding)
realm = fractalstat["realm"]
assert isinstance(realm, dict)
assert "type" in realm
assert "label" in realm
if __name__ == "__main__":
pytest.main([__file__, "-v"])
|