water-column-sonar-processing 0.0.9__tar.gz → 0.0.11__tar.gz

water_column_sonar_processing-0.0.11/.env-test

@@ -0,0 +1,18 @@
+# DOTENV Values used for Testing
+# See here for more information: <https://github.com/theskumar/python-dotenv>
+
+AWS_REGION="us-east-1"
+
+ACCESS_KEY_ID="ACCESS_KEY_ID_123"
+SECRET_ACCESS_KEY="SECRET_ACCESS_KEY_456"
+
+OUTPUT_BUCKET_ACCESS_KEY="OUTPUT_BUCKET_ACCESS_KEY_ABC"
+OUTPUT_BUCKET_SECRET_ACCESS_KEY="OUTPUT_BUCKET_SECRET_ACCESS_KEY_123"
+
+INPUT_BUCKET_NAME="test-input-bucket"
+
+OUTPUT_BUCKET_NAME="test-output-bucket"
+
+TABLE_NAME="test-table"
+
+TOPIC_ARN="arn:aws:sns:${AWS_REGION}:123456789012:test-topic"

water_column_sonar_processing-0.0.11/.github/workflows/test_action.yaml

@@ -0,0 +1,24 @@
+name: Python package
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          # Semantic version range syntax or exact version of a Python version
+          python-version: '3.10'
+          # Optional - x64 or x86 architecture, defaults to x64
+#          architecture: 'x64'
+          cache: 'pip'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements_dev.txt
+      - name: Run the tests
+        run: python -m pytest

water_column_sonar_processing-0.0.11/.gitignore

@@ -0,0 +1,195 @@
+#tests/*.zarr
+#tests/*.bot
+#tests/*.raw
+#tests/*.json
+*.geojson
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+dist*
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+__pycache__
+.DS_Store
+
+*.env-prod*
+*.zarr
+*.csv
+
+*.raw
+*.bot
+*.idx
+
+.idea
+.pytest_cache
+.coverage
+*.iml
+#.python-version
+target
+coverage.xml
+htmlcov
+dist
+build
+*.egg-info
+/setup.py
+*.spec
+

water_column_sonar_processing-0.0.11/.pre-commit-config.yaml

@@ -0,0 +1,36 @@
+repos:
+  - repo: local
+    hooks:
+      - id: trufflehog
+        name: TruffleHog
+        description: Detect secrets in your data.
+        entry: bash -c 'trufflehog git file://. --since-commit HEAD --no-verification --fail --no-update'
+        language: system
+        stages: [ "pre-commit", "pre-push" ]
+
+#  - repo: https://github.com/psf/black
+#    rev: 24.10.0
+#    hooks:
+#      - id: black
+
+#  - repo: https://github.com/PyCQA/flake8
+#    rev: 7.1.1
+#    hooks:
+#      - id: flake8
+
+#  - repo: https://github.com/astral-sh/ruff-pre-commit
+#    # Ruff version.
+#    rev: v0.7.2
+#    hooks:
+#      # Run the linter.
+#      - id: ruff
+#        args: [ --fix ]
+#      # Run the formatter.
+#      - id: ruff-format
+
+#  - repo: https://github.com/pycqa/isort
+#    rev: 5.13.2
+#    hooks:
+#      - id: isort
+#        name: isort (python)
+#        args: ["--profile", "black", "--filter-files"]

water_column_sonar_processing-0.0.11/.python-version

@@ -0,0 +1,2 @@
+3.10.12
+water-column-sonar-processing

{water_column_sonar_processing-0.0.9 → water_column_sonar_processing-0.0.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: water_column_sonar_processing
-Version: 0.0.9
+Version: 0.0.11
 Summary: A processing tool for water column sonar data.
 Author-email: Rudy Klucik <rudy.klucik@noaa.gov>
 Project-URL: Homepage, https://github.com/CI-CMG/water-column-sonar-processing
@@ -24,7 +24,7 @@ Requires-Dist: numcodecs==0.13.1
 Requires-Dist: numpy==1.26.4
 Requires-Dist: pandas==2.2.3
 Requires-Dist: pyarrow==18.1.0
-Requires-Dist: python-dotenv==1.0.0
+Requires-Dist: python-dotenv==1.0.1
 Requires-Dist: requests==2.32.3
 Requires-Dist: s3fs==2023.12.1
 Requires-Dist: scipy==1.14.1
@@ -114,6 +114,7 @@ python -m twine upload --repository pypi dist/*
 ```
 
 # Pre Commit Hook
+see here for installation: https://pre-commit.com/
 https://dev.to/rafaelherik/using-trufflehog-and-pre-commit-hook-to-prevent-secret-exposure-edo
 ```
 pre-commit install --allow-missing-config
@@ -132,3 +133,8 @@ https://colab.research.google.com/drive/1KiLMueXiz9WVB9o4RuzYeGjNZ6PsZU7a#scroll
 20241125
 5 failed, 35 passed, 3 skipped, 1 warning in 9.71s
 3 failed, 38 passed, 3 skipped, 1 warning in 7.24s
+
+
+# TODO:
+add https://pypi.org/project/setuptools-scm/
+for extracting the version

{water_column_sonar_processing-0.0.9 → water_column_sonar_processing-0.0.11}/README.md

@@ -78,6 +78,7 @@ python -m twine upload --repository pypi dist/*
 ```
 
 # Pre Commit Hook
+see here for installation: https://pre-commit.com/
 https://dev.to/rafaelherik/using-trufflehog-and-pre-commit-hook-to-prevent-secret-exposure-edo
 ```
 pre-commit install --allow-missing-config
@@ -95,4 +96,9 @@ https://colab.research.google.com/drive/1KiLMueXiz9WVB9o4RuzYeGjNZ6PsZU7a#scroll
 8 failed, 32 passed, 3 skipped, 1 warning in 6.92s
 20241125
 5 failed, 35 passed, 3 skipped, 1 warning in 9.71s
-3 failed, 38 passed, 3 skipped, 1 warning in 7.24s
+3 failed, 38 passed, 3 skipped, 1 warning in 7.24s
+
+
+# TODO:
+add https://pypi.org/project/setuptools-scm/
+for extracting the version

water_column_sonar_processing-0.0.11/open-science-data-federation/ml/autoencoder_example.py

@@ -0,0 +1,94 @@
+# https://keras.io/examples/vision/autoencoder/
+
+import numpy as np
+import matplotlib.pyplot as plt
+
+from keras import layers
+from keras.datasets import mnist
+from keras.models import Model
+
+
+def preprocess(array):
+    """Normalizes the supplied array and reshapes it."""
+    array = array.astype("float32") / 255.0
+    array = np.reshape(array, (len(array), 28, 28, 1))
+    return array
+
+
+def noise(array):
+    """Adds random noise to each image in the supplied array."""
+    noise_factor = 0.4
+    noisy_array = array + noise_factor * np.random.normal(
+        loc=0.0, scale=1.0, size=array.shape
+    )
+
+    return np.clip(noisy_array, 0.0, 1.0)
+
+
+def display(array1, array2):
+    """Displays ten random images from each array."""
+    n = 10
+    indices = np.random.randint(len(array1), size=n)
+    images1 = array1[indices, :]
+    images2 = array2[indices, :]
+
+    plt.figure(figsize=(20, 4))
+    for i, (image1, image2) in enumerate(zip(images1, images2)):
+        ax = plt.subplot(2, n, i + 1)
+        plt.imshow(image1.reshape(28, 28))
+        plt.gray()
+        ax.get_xaxis().set_visible(False)
+        ax.get_yaxis().set_visible(False)
+
+        ax = plt.subplot(2, n, i + 1 + n)
+        plt.imshow(image2.reshape(28, 28))
+        plt.gray()
+        ax.get_xaxis().set_visible(False)
+        ax.get_yaxis().set_visible(False)
+
+    plt.show()
+
+
+# Since we only need images from the dataset to encode and decode, we
+# won't use the labels.
+(train_data, _), (test_data, _) = mnist.load_data()
+
+# Normalize and reshape the data
+train_data = preprocess(train_data)
+test_data = preprocess(test_data)
+
+# Create a copy of the data with added noise
+noisy_train_data = noise(train_data)
+noisy_test_data = noise(test_data)
+
+# Display the train data and a version of it with added noise
+display(train_data, noisy_train_data)
+
+
+input = layers.Input(shape=(28, 28, 1))
+
+# Encoder
+x = layers.Conv2D(32, (3, 3), activation="relu", padding="same")(input)
+x = layers.MaxPooling2D((2, 2), padding="same")(x)
+x = layers.Conv2D(32, (3, 3), activation="relu", padding="same")(x)
+x = layers.MaxPooling2D((2, 2), padding="same")(x)
+
+# Decoder
+x = layers.Conv2DTranspose(32, (3, 3), strides=2, activation="relu", padding="same")(x)
+x = layers.Conv2DTranspose(32, (3, 3), strides=2, activation="relu", padding="same")(x)
+x = layers.Conv2D(1, (3, 3), activation="sigmoid", padding="same")(x)
+
+# Autoencoder
+autoencoder = Model(input, x)
+autoencoder.compile(optimizer="adam", loss="binary_crossentropy")
+autoencoder.summary()
+
+
+autoencoder.fit(
+    x=train_data,
+    y=train_data,
+    epochs=50,
+    batch_size=128,
+    shuffle=True,
+    validation_data=(test_data, test_data),
+)

water_column_sonar_processing-0.0.11/open-science-data-federation/osdf_examples/foo.ipynb

@@ -0,0 +1,65 @@
+{
+ "cells": [
+  {
+   "metadata": {},
+   "cell_type": "raw",
+   "source": "",
+   "id": "bd6b0dd9ea15dfe2"
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-14T16:07:00.035002Z",
+     "start_time": "2024-11-14T16:07:00.033231Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "",
+   "id": "1ac76554b86e9eb0",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-14T16:07:00.100948Z",
+     "start_time": "2024-11-14T16:07:00.098301Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "",
+   "id": "dbbb1a940f83f73c",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "7042e6cf142a6f09"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}