{"name": "dzetsaka : AI-Powered Remote Sensing Classification", "package_name": "dzetsaka", "version": "5.1.1", "experimental": false, "qgis_min": "3.0.0", "qgis_max": "4.99.0", "downloads": 1382, "uploaded_by": null, "upload_datetime": "2026-10-01T07:05:38.981616", "changelog": "5.1.1\n* FIX: Recipe accuracy tier parsing crashed with NameError (missing 're' import)\n* FIX: Code-quality findings from the plugins.qgis.org scan (try/except/pass, redefined wrapper names, unused global)\n5.1.0\n* FIX: QGIS 4 / PyQt6 crash when opening the Recipe Hub (unscoped Qt enums)\n* FIX: Optuna/SHAP/SMOTE toggles never offered to install missing dependencies on PyQt6\n* FIX: Plugin reload kept serving stale dashboard code\n* FIX: Plugin version read as 'unknown' and missing processing provider icon\n* FIX: Recipe dropdown list ran off-screen; it now scrolls and opens upward when needed\n* PERF: Prediction with a confidence map runs the model once per block (up to 4x faster, identical output)\n* PERF: Dynamic block size uses available system RAM (up to 4 GB) instead of hardcoded 512 MB limit\n* UX: Newly installed dependencies work without restarting QGIS, with a progress window while installing\n* UX: Browse Hub looks like a regular button; recipe selector is a plain list; dashboard can be narrower\n* FIX: QgisLogger now feeds QGIS log messages into issue-report buffer (logs were missing from bug reports)\n* UX: Success dialog after classification shows output filename, confidence map, and elapsed duration\n5.0.11\n* FIX: Fix confusion matrix CSV transposed relative to HTML report (issue #53)\n* REFACTOR: Convert optional-dependencies to PEP 735 dependency-groups\n5.0.10\n* FIX: Fix UnboundLocalError on 'xt' with separate validation vector (issue #52)\n* TEST: Add regression tests for vector_test_path code path\n5.0.9\n* FIX: Fix split rounding crash with odd sample counts and hardcoded shapefile driver\n* FIX: Fix training failures from undefined SVM variable and missing relative import\n* FIX: Fix duplicate dock widget on plugin reload\n* REFACTOR: Extract constants, remove ~4200 lines of dead code\n* TEST: Add unit tests for classifier_config, accuracy_index, validation_metrics, label_encoders\n5.0.8\n* FIX: Replace all sync dependency installer calls with async QgsTask to prevent macOS ARM64 crash (issue #48)\n* FIX: Fix StratifiedKFold not iterable with scikit-learn 1.x (issue #51)\n* CI: Gate release on cross-platform tests (Ubuntu, macOS ARM64, macOS Intel)\n5.0.7\n* FIX: Fix UnboundLocalError for cvDistance when using Polygon Group CV mode (issue #49)\n* FIX: QGIS 4.x / PyQt6 compatibility - scoped enum fixes, exec() migration\n* ADD: Declare QGIS 4.x support (qgisMaximumVersion=4.99)\n5.0.6\n* FIX: Defer all GUI calls from QgsTask callbacks via QTimer.singleShot to prevent macOS ARM64 SIGABRT crash (issue #48)\n* FIX: Add thread-identity diagnostic logging for dependency install task debugging\n5.0.5\n* FIX: Prevent QGIS crash on macOS ARM64 during dependency auto-install by using a main-thread callback instead of cross-thread signals (issue #48)\n* FIX: Handle missing legacy GDT_* constants in GDAL 4.x to prevent AttributeError at import time\n* FIX: Remove pkexec apt fallback that requested admin password on Linux\n* FIX: Add --break-system-packages for PEP 668 compatibility (Debian 13+, Ubuntu 24+)\n5.0.4\n* CHORE: Bump plugin metadata version to provide a unique QGIS Plugin Repository release number\n5.0.3\n* FIX: Prefer QGIS bundled Python on macOS arm64 in dependency autoinstaller to avoid selecting Xcode/system Python (issue #47)\n5.0.2\n* FIX: Harden dependency installer runtime constraints to avoid NumPy conflicts with QGIS bundled stack (issue #46)\n5.0.1\n* FIX: Import QAction from QtWidgets instead of QtGui, which crashed QGIS 3.28+ at startup (issue #45)\n* FIX: Qt5/Qt6 compatibility: exec_() fallback, enum aliases, matplotlib backend detection\n5.0.0\n* NEW: 11 classifiers with Optuna search and SHAP explanations\n* NEW: Guided wizard, compact dashboard, Smart Defaults, algorithm comparison, and recipes\n* NEW: HTML report with diagnostics\n* PERF: Faster training and prediction\nFull history: https://github.com/nkarasiak/dzetsaka/blob/main/CHANGELOG.md", "external_deps": null, "download_url": "https://plugins.qgis.org/plugins/dzetsaka/version/5.1.1/download/"}