datapruning 1.0.8__tar.gz → 1.0.9__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {datapruning-1.0.8/datapruning.egg-info → datapruning-1.0.9}/PKG-INFO +1 -1
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/engine/strategy_display.py +5 -5
- {datapruning-1.0.8 → datapruning-1.0.9/datapruning.egg-info}/PKG-INFO +1 -1
- {datapruning-1.0.8 → datapruning-1.0.9}/pyproject.toml +1 -1
- {datapruning-1.0.8 → datapruning-1.0.9}/LICENSE +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/MANIFEST.in +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/README.md +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/build_src/_core.c +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/__init__.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/algorithms/__init__.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/algorithms/base.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/algorithms/cluster_centroids.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/algorithms/density_pruner.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/algorithms/duplicate_aware.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/algorithms/instance_hardness.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/algorithms/random_undersampler.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/algorithms/registry.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/engine/__init__.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/engine/benchmark.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/engine/explainability.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/engine/intelligence.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/engine/optimizer.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/engine/scanner.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/engine/strategy_selector.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/pipeline.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/reports/__init__.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/reports/exporter.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning/sdk.py +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning.egg-info/SOURCES.txt +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning.egg-info/dependency_links.txt +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning.egg-info/requires.txt +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/datapruning.egg-info/top_level.txt +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/setup.cfg +0 -0
- {datapruning-1.0.8 → datapruning-1.0.9}/setup.py +0 -0
|
@@ -17,7 +17,7 @@ STRATEGY_DISPLAY = {
|
|
|
17
17
|
},
|
|
18
18
|
"iht": {
|
|
19
19
|
"display_name": "Boundary Optimization",
|
|
20
|
-
"icon": "\
|
|
20
|
+
"icon": "\U0001F3AF",
|
|
21
21
|
"description": "Preserves difficult-to-classify examples near decision boundaries.",
|
|
22
22
|
"best_for": "Fraud detection, rare event prediction, imbalanced classification",
|
|
23
23
|
"advantages": [
|
|
@@ -32,7 +32,7 @@ STRATEGY_DISPLAY = {
|
|
|
32
32
|
},
|
|
33
33
|
"cluster": {
|
|
34
34
|
"display_name": "Representative Compression",
|
|
35
|
-
"icon": "\
|
|
35
|
+
"icon": "\U0001F4CA",
|
|
36
36
|
"description": "Creates a compact representative subset by clustering the dataset.",
|
|
37
37
|
"best_for": "Very large datasets needing maximum compression",
|
|
38
38
|
"advantages": [
|
|
@@ -46,7 +46,7 @@ STRATEGY_DISPLAY = {
|
|
|
46
46
|
},
|
|
47
47
|
"density": {
|
|
48
48
|
"display_name": "Structural Optimization",
|
|
49
|
-
"icon": "\
|
|
49
|
+
"icon": "\U0001F9E9",
|
|
50
50
|
"description": "Removes redundant samples in high-density regions while preserving structure.",
|
|
51
51
|
"best_for": "General tabular datasets with clear structure",
|
|
52
52
|
"advantages": [
|
|
@@ -60,7 +60,7 @@ STRATEGY_DISPLAY = {
|
|
|
60
60
|
},
|
|
61
61
|
"duplicate_aware": {
|
|
62
62
|
"display_name": "Duplicate Cleanup",
|
|
63
|
-
"icon": "\
|
|
63
|
+
"icon": "\U0001F9F9",
|
|
64
64
|
"description": "Identifies and removes duplicate or near-duplicate records.",
|
|
65
65
|
"best_for": "Datasets with many repeated or near-identical records",
|
|
66
66
|
"advantages": [
|
|
@@ -78,7 +78,7 @@ STRATEGY_DISPLAY = {
|
|
|
78
78
|
def get_strategy_display(key: str) -> dict:
|
|
79
79
|
return dict(STRATEGY_DISPLAY.get(key, {
|
|
80
80
|
"display_name": key.replace("_", " ").title(),
|
|
81
|
-
"icon": "\
|
|
81
|
+
"icon": "\U0001F527",
|
|
82
82
|
"description": "",
|
|
83
83
|
"best_for": "",
|
|
84
84
|
"advantages": [],
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|