Pyjedai

⚒️ **Fixed**
- Issue 19 , 20 , 21 ;
- Removed FALCONN and SCANN
- Refined dependencies
- Removed Optuna injection
- Fixed typos
- Reports

➕ **Added**
- New utilities to docs

⚠️ **Issues**
- None

**Full Changelog**: https://github.com/AI-team-UoA/pyJedAI/compare/0.1.6...0.1.7

---

**Authored by** Nikoletos-K

⚒️ **Fixed**
- Issue 16 ;
- Typos in clustering.py
- Datamodel gt initialization
- Imports in utils
- Bugs in NN-workflow
- Bugs and evaluation of simple Schema Clustering

➕ **Added**
- Dataframe memory consumption
- New Schema Clustering method for RDF data [Not final implementation - alpha version]

⚠️ **Issues**
- SCANN and FALCONN produce warnings

**Full Changelog**: https://github.com/AI-team-UoA/pyJedAI/compare/0.1.5...0.1.6

---

**Authored by** Nikoletos-K

⚒️ **Fixed**
- Schema Matching structure [ Nikoletos-K ]

➕ **Added**
- First working version of Schema Clustering [ Nikoletos-K ]
- vector_based_blocking component: SCANN/FAISS full functionality on Linux OS only! [ JacobMaciejewski ]
- RowColumnClustering: new clustering algorithm [ JacobMaciejewski ]

⚠️ **Issues**
- Minor changes in ProgressiveWorkFlow(PYJEDAIWorkFlow). [ JacobMaciejewski ]

⚒️ Fixed
- Correlation Clustering method.
- nltk.download('stopwords') download only when needed.
- Schema Matching component to align with the latest version of Valentine.

➕ Added
- datamodel.py: SchemaData for Schema Matching Component
- ‼️ New Component; **pyJedAI Spatial**, for **Interlinking geospatial RDF data**. [ IordanisT ]
- SCANN functionality, only available for Linux OS. [ JacobMaciejewski ]

⚠️ Issues
- None

⚒️ Fixed
- None

➕ Added
- Clustering algorithms: **[ Author: JacobMaciejewski 📌 ]**
- **EquivalenceCluster**
- **ExtendedSimilarityEdge**
- **Vertex**
- **RicochetCluster**
- **ExactClustering**
- **CenterClustering**
- **BestMatchClustering**
- **MergeCenterClustering**
- **CorrelationClustering**
- **CutClustering**
- **MarkovClustering**
- **KiralyMSMApproximateClustering**
- **RicochetSRClustering**

- Blocking:
- Statistics

⚠️ Issues
- None

⚒️ Fixed
- Fixed export methods. Use case of not providing a ground-truth
- Time of vectorization by saving and retrieving the distance matrix
- Bug resolution in PER indexing, Dirty ER
- Speed/Memory optimizations in NN Blocking & Join PER

➕ Added
- 'sqeuclidean' metric in matching step
- Valentine as a Schema Matching plugin
- Frequency Evaluator compatible with base ER matching

⚠️ Issues
- Vectorizers (tfidf, etc) don't support dirty er. Will be fixed in the next release.