viseda 1.0.0__tar.gz

viseda-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 VisEDA Contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

viseda-1.0.0/PKG-INFO

@@ -0,0 +1,266 @@
+Metadata-Version: 2.4
+Name: viseda
+Version: 1.0.0
+Summary: Visual Exploratory Data Analysis for image, video, hyperspectral, point-cloud, and text/NLP datasets
+Author: Isaac Osei Agyemang, Daniel Acheampong, Adu Asare Baffour, Isaac Adjei-Mensah
+License-Expression: MIT
+Keywords: EDA,exploratory data analysis,image,video,hyperspectral,point cloud,LiDAR,text,NLP,computer vision,remote sensing
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Classifier: Topic :: Scientific/Engineering :: Visualization
+Classifier: Topic :: Scientific/Engineering :: GIS
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.23
+Requires-Dist: matplotlib>=3.6
+Requires-Dist: scikit-learn>=1.2
+Requires-Dist: scikit-image>=0.20
+Requires-Dist: opencv-python>=4.7
+Provides-Extra: hyperspectral
+Requires-Dist: scipy>=1.10; extra == "hyperspectral"
+Requires-Dist: spectral>=0.23; extra == "hyperspectral"
+Requires-Dist: rasterio>=1.3; extra == "hyperspectral"
+Provides-Extra: pointcloud
+Requires-Dist: laspy[lazrs]>=2.3; extra == "pointcloud"
+Provides-Extra: all
+Requires-Dist: scipy>=1.10; extra == "all"
+Requires-Dist: spectral>=0.23; extra == "all"
+Requires-Dist: rasterio>=1.3; extra == "all"
+Requires-Dist: laspy[lazrs]>=2.3; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4; extra == "dev"
+Requires-Dist: pytest-cov>=4.1; extra == "dev"
+Requires-Dist: build>=1.0; extra == "dev"
+Requires-Dist: twine>=5.0; extra == "dev"
+Dynamic: license-file
+
+# VisEDA — Visual Exploratory Data Analysis
+
+VisEDA is a Python toolkit for exploratory data analysis of **image, video,
+hyperspectral, point-cloud, and text/NLP datasets**. It provides numerical
+summaries, dataset-level visualisations, per-sample diagnostics, duplicate or
+similarity analysis where applicable, command-line workflows, and
+self-contained HTML reports.
+
+## Modules
+
+- **ImageEDA** — spatial, pixel, quality, colour, texture, frequency, duplicate,
+  class-balance, and normalisation analysis.
+- **VideoEDA** — spatial, temporal, motion, blur, scene-change, colour, and
+  video-similarity analysis.
+- **HyperspectralEDA** — per-band statistics, SNR/noise, spectral quality,
+  vegetation/water indices, PCA, false-colour, texture, and spectral-diversity analysis.
+- **PointCloudEDA** — geometry, density, height, duplicate/outlier,
+  nearest-neighbour, PCA shape-descriptor, and attribute analysis.
+- **TextEDA** — length, vocabulary, lexical diversity, symbols, readability,
+  writing scripts, duplicates, TF-IDF document distances, and label analysis.
+
+## Installation
+
+```bash
+pip install viseda
+```
+
+Optional file-format support:
+
+```bash
+# MATLAB/ENVI/GeoTIFF hyperspectral files
+pip install "viseda[hyperspectral]"
+
+# LAS/LAZ point clouds
+pip install "viseda[pointcloud]"
+
+# All optional file-format dependencies
+pip install "viseda[all]"
+```
+
+Python 3.9 or later is required.
+
+## Quick start
+
+### ImageEDA
+
+```python
+from viseda import ImageEDA
+
+eda = ImageEDA(verbose=True)
+eda.load("path/to/images", label_from_parent=True)
+
+summary = eda.summary()
+print(summary["inventory"])
+print(summary["quality"])
+
+eda.plot(save_path="image_dashboard.png")
+eda.report("image_report.html")
+```
+
+In-memory images are supported through `load_arrays()`.
+
+### VideoEDA
+
+```python
+from viseda import VideoEDA
+
+eda = VideoEDA(verbose=True, frame_sample_rate=5)
+eda.load("path/to/videos", label_from_parent=True)
+
+print(eda.summary()["temporal"])
+eda.plot_dataset(save_path="video_dashboard.png")
+eda.report("video_report.html")
+```
+
+NumPy video arrays can be loaded with `load_arrays()`.
+
+### HyperspectralEDA
+
+```python
+import numpy as np
+from viseda import HyperspectralEDA
+
+cube = np.random.default_rng(0).random((128, 128, 103)).astype("float32")
+wavelengths = np.linspace(400, 1500, cube.shape[2])
+
+np.save("scene.npy", cube)
+
+eda = HyperspectralEDA(
+    wavelengths=wavelengths,
+    compute_glcm=False,
+    compute_pca=True,
+)
+eda.load("scene.npy")
+
+print(eda.summary()["spectral_quality"])
+ndvi = eda.compute_index(cube_index=0, index_name="ndvi")
+scores, variance_ratio = eda.pca_scores(cube_index=0, n_components=3)
+
+eda.plot(save_path="hyper_dashboard.png")
+eda.report("hyper_report.html")
+```
+
+The `hyperspectral` extra adds support for MATLAB `.mat`, ENVI, and
+multi-band GeoTIFF files.
+
+### PointCloudEDA
+
+```python
+import numpy as np
+from viseda import PointCloudEDA
+
+points = np.random.default_rng(0).random((10000, 3)).astype("float32")
+
+eda = PointCloudEDA(
+    max_points_per_cloud=200000,
+    compute_neighbors=True,
+    compute_geometry=True,
+)
+eda.load_arrays([points], labels=["sample"])
+
+print(eda.summary()["geometry"])
+eda.plot_dataset(save_path="pointcloud_dashboard.png")
+eda.report("pointcloud_report.html")
+```
+
+The `pointcloud` extra adds LAS/LAZ support. NPY, NPZ, TXT, CSV, XYZ, PTS,
+and ASCII PLY are supported by the base installation.
+
+### TextEDA
+
+```python
+from viseda import TextEDA
+
+eda = TextEDA()
+eda.load_texts(
+    [
+        "Exploratory data analysis is useful before model training.",
+        "TextEDA summarises vocabulary, length, readability and duplicates.",
+    ],
+    labels=["eda", "eda"],
+)
+
+print(eda.summary()["lexical"])
+print(eda.vocabulary(top_n=10))
+
+eda.plot_dataset(save_path="text_dashboard.png")
+eda.report("text_report.html")
+```
+
+TextEDA also loads TXT, Markdown, HTML, CSV, TSV, JSON, JSONL and NDJSON
+datasets through `load()`.
+
+## Command line
+
+The package installs the `viseda` command:
+
+```bash
+viseda --help
+```
+
+Available subcommands are:
+
+```text
+viseda image ...
+viseda hyper ...
+viseda cloud ...
+viseda video ...
+viseda text ...
+```
+
+Examples:
+
+```bash
+viseda image "C:/datasets/images" --label-from-parent --plot --report image_report.html
+
+viseda video "C:/datasets/videos" --label-from-parent --plot --report video_report.html
+
+viseda hyper "C:/datasets/hyper" --label-from-parent --plot --dataset-plot \
+  --report hyper_report.html
+
+viseda cloud "C:/datasets/pointclouds" --label-from-parent --plot \
+  --report pointcloud_report.html
+
+viseda text "C:/datasets/text" --label-from-parent --plot \
+  --report text_report.html
+```
+
+Use `viseda <subcommand> --help` for the options of a particular modality.
+
+## Supported input formats
+
+| Module | Main file inputs |
+|---|---|
+| ImageEDA | JPG/JPEG, PNG, BMP, TIFF and other formats accepted by the current image loader |
+| VideoEDA | MP4, AVI, MOV, MKV, WEBM, MPEG/MPG, M4V |
+| HyperspectralEDA | MAT, NPY, NPZ, ENVI HDR/BIL/BIP/BSQ/ENVI, TIF/TIFF |
+| PointCloudEDA | NPY, NPZ, TXT, CSV, XYZ, PTS, ASCII PLY, LAS/LAZ |
+| TextEDA | TXT/TEXT, MD, RST, LOG, HTML/HTM, CSV/TSV, JSON, JSONL/NDJSON |
+
+Some file formats require the optional extras described above.
+
+## Development
+
+Install the project in editable mode with development tools:
+
+```bash
+python -m pip install -e ".[dev]"
+pytest
+```
+
+Build and validate a release:
+
+```bash
+python -m pip install --upgrade build twine
+python -m build
+python -m twine check dist/*
+```
+
+## License
+
+MIT. See `LICENSE`.

viseda-1.0.0/README.md

@@ -0,0 +1,222 @@
+# VisEDA — Visual Exploratory Data Analysis
+
+VisEDA is a Python toolkit for exploratory data analysis of **image, video,
+hyperspectral, point-cloud, and text/NLP datasets**. It provides numerical
+summaries, dataset-level visualisations, per-sample diagnostics, duplicate or
+similarity analysis where applicable, command-line workflows, and
+self-contained HTML reports.
+
+## Modules
+
+- **ImageEDA** — spatial, pixel, quality, colour, texture, frequency, duplicate,
+  class-balance, and normalisation analysis.
+- **VideoEDA** — spatial, temporal, motion, blur, scene-change, colour, and
+  video-similarity analysis.
+- **HyperspectralEDA** — per-band statistics, SNR/noise, spectral quality,
+  vegetation/water indices, PCA, false-colour, texture, and spectral-diversity analysis.
+- **PointCloudEDA** — geometry, density, height, duplicate/outlier,
+  nearest-neighbour, PCA shape-descriptor, and attribute analysis.
+- **TextEDA** — length, vocabulary, lexical diversity, symbols, readability,
+  writing scripts, duplicates, TF-IDF document distances, and label analysis.
+
+## Installation
+
+```bash
+pip install viseda
+```
+
+Optional file-format support:
+
+```bash
+# MATLAB/ENVI/GeoTIFF hyperspectral files
+pip install "viseda[hyperspectral]"
+
+# LAS/LAZ point clouds
+pip install "viseda[pointcloud]"
+
+# All optional file-format dependencies
+pip install "viseda[all]"
+```
+
+Python 3.9 or later is required.
+
+## Quick start
+
+### ImageEDA
+
+```python
+from viseda import ImageEDA
+
+eda = ImageEDA(verbose=True)
+eda.load("path/to/images", label_from_parent=True)
+
+summary = eda.summary()
+print(summary["inventory"])
+print(summary["quality"])
+
+eda.plot(save_path="image_dashboard.png")
+eda.report("image_report.html")
+```
+
+In-memory images are supported through `load_arrays()`.
+
+### VideoEDA
+
+```python
+from viseda import VideoEDA
+
+eda = VideoEDA(verbose=True, frame_sample_rate=5)
+eda.load("path/to/videos", label_from_parent=True)
+
+print(eda.summary()["temporal"])
+eda.plot_dataset(save_path="video_dashboard.png")
+eda.report("video_report.html")
+```
+
+NumPy video arrays can be loaded with `load_arrays()`.
+
+### HyperspectralEDA
+
+```python
+import numpy as np
+from viseda import HyperspectralEDA
+
+cube = np.random.default_rng(0).random((128, 128, 103)).astype("float32")
+wavelengths = np.linspace(400, 1500, cube.shape[2])
+
+np.save("scene.npy", cube)
+
+eda = HyperspectralEDA(
+    wavelengths=wavelengths,
+    compute_glcm=False,
+    compute_pca=True,
+)
+eda.load("scene.npy")
+
+print(eda.summary()["spectral_quality"])
+ndvi = eda.compute_index(cube_index=0, index_name="ndvi")
+scores, variance_ratio = eda.pca_scores(cube_index=0, n_components=3)
+
+eda.plot(save_path="hyper_dashboard.png")
+eda.report("hyper_report.html")
+```
+
+The `hyperspectral` extra adds support for MATLAB `.mat`, ENVI, and
+multi-band GeoTIFF files.
+
+### PointCloudEDA
+
+```python
+import numpy as np
+from viseda import PointCloudEDA
+
+points = np.random.default_rng(0).random((10000, 3)).astype("float32")
+
+eda = PointCloudEDA(
+    max_points_per_cloud=200000,
+    compute_neighbors=True,
+    compute_geometry=True,
+)
+eda.load_arrays([points], labels=["sample"])
+
+print(eda.summary()["geometry"])
+eda.plot_dataset(save_path="pointcloud_dashboard.png")
+eda.report("pointcloud_report.html")
+```
+
+The `pointcloud` extra adds LAS/LAZ support. NPY, NPZ, TXT, CSV, XYZ, PTS,
+and ASCII PLY are supported by the base installation.
+
+### TextEDA
+
+```python
+from viseda import TextEDA
+
+eda = TextEDA()
+eda.load_texts(
+    [
+        "Exploratory data analysis is useful before model training.",
+        "TextEDA summarises vocabulary, length, readability and duplicates.",
+    ],
+    labels=["eda", "eda"],
+)
+
+print(eda.summary()["lexical"])
+print(eda.vocabulary(top_n=10))
+
+eda.plot_dataset(save_path="text_dashboard.png")
+eda.report("text_report.html")
+```
+
+TextEDA also loads TXT, Markdown, HTML, CSV, TSV, JSON, JSONL and NDJSON
+datasets through `load()`.
+
+## Command line
+
+The package installs the `viseda` command:
+
+```bash
+viseda --help
+```
+
+Available subcommands are:
+
+```text
+viseda image ...
+viseda hyper ...
+viseda cloud ...
+viseda video ...
+viseda text ...
+```
+
+Examples:
+
+```bash
+viseda image "C:/datasets/images" --label-from-parent --plot --report image_report.html
+
+viseda video "C:/datasets/videos" --label-from-parent --plot --report video_report.html
+
+viseda hyper "C:/datasets/hyper" --label-from-parent --plot --dataset-plot \
+  --report hyper_report.html
+
+viseda cloud "C:/datasets/pointclouds" --label-from-parent --plot \
+  --report pointcloud_report.html
+
+viseda text "C:/datasets/text" --label-from-parent --plot \
+  --report text_report.html
+```
+
+Use `viseda <subcommand> --help` for the options of a particular modality.
+
+## Supported input formats
+
+| Module | Main file inputs |
+|---|---|
+| ImageEDA | JPG/JPEG, PNG, BMP, TIFF and other formats accepted by the current image loader |
+| VideoEDA | MP4, AVI, MOV, MKV, WEBM, MPEG/MPG, M4V |
+| HyperspectralEDA | MAT, NPY, NPZ, ENVI HDR/BIL/BIP/BSQ/ENVI, TIF/TIFF |
+| PointCloudEDA | NPY, NPZ, TXT, CSV, XYZ, PTS, ASCII PLY, LAS/LAZ |
+| TextEDA | TXT/TEXT, MD, RST, LOG, HTML/HTM, CSV/TSV, JSON, JSONL/NDJSON |
+
+Some file formats require the optional extras described above.
+
+## Development
+
+Install the project in editable mode with development tools:
+
+```bash
+python -m pip install -e ".[dev]"
+pytest
+```
+
+Build and validate a release:
+
+```bash
+python -m pip install --upgrade build twine
+python -m build
+python -m twine check dist/*
+```
+
+## License
+
+MIT. See `LICENSE`.

viseda-1.0.0/pyproject.toml

@@ -0,0 +1,88 @@
+[build-system]
+requires = ["setuptools>=77", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "viseda"
+version = "1.0.0"
+description = "Visual Exploratory Data Analysis for image, video, hyperspectral, point-cloud, and text/NLP datasets"
+readme = "README.md"
+requires-python = ">=3.9"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+  { name = "Isaac Osei Agyemang, Daniel Acheampong, Adu Asare Baffour, Isaac Adjei-Mensah" },
+]
+keywords = [
+  "EDA",
+  "exploratory data analysis",
+  "image",
+  "video",
+  "hyperspectral",
+  "point cloud",
+  "LiDAR",
+  "text",
+  "NLP",
+  "computer vision",
+  "remote sensing",
+]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Science/Research",
+  "Intended Audience :: Developers",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Topic :: Scientific/Engineering :: Image Processing",
+  "Topic :: Scientific/Engineering :: Visualization",
+  "Topic :: Scientific/Engineering :: GIS",
+]
+
+dependencies = [
+  "numpy>=1.23",
+  "matplotlib>=3.6",
+  "scikit-learn>=1.2",
+  "scikit-image>=0.20",
+  "opencv-python>=4.7",
+]
+
+[project.optional-dependencies]
+hyperspectral = [
+  "scipy>=1.10",
+  "spectral>=0.23",
+  "rasterio>=1.3",
+]
+
+pointcloud = [
+  "laspy[lazrs]>=2.3",
+]
+
+all = [
+  "scipy>=1.10",
+  "spectral>=0.23",
+  "rasterio>=1.3",
+  "laspy[lazrs]>=2.3",
+]
+
+dev = [
+  "pytest>=7.4",
+  "pytest-cov>=4.1",
+  "build>=1.0",
+  "twine>=5.0",
+]
+
+[project.scripts]
+viseda = "viseda.cli:main"
+
+[tool.setuptools]
+include-package-data = false
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["viseda*"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q"

viseda-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+