PyOPIA 2.10.0__tar.gz → 2.12.0__tar.gz

{pyopia-2.10.0 → pyopia-2.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyOPIA
-Version: 2.10.0
+Version: 2.12.0
 Summary: A Python Ocean Particle Image Analysis toolbox.
 Project-URL: Repository, https://github.com/sintef/pyopia
 Project-URL: Documentation, https://pyopia.readthedocs.io
@@ -25,6 +25,7 @@ Requires-Dist: nbconvert<8,>=7.16.4
 Requires-Dist: numpy>=1.24.0
 Requires-Dist: pandas[computation]<3,>=2.1.1
 Requires-Dist: poetry-version-plugin<0.3,>=0.2.0
+Requires-Dist: pydantic>=2.11.7
 Requires-Dist: pytest-error-for-skips<3,>=2.0.2
 Requires-Dist: pytest>=7.2.0
 Requires-Dist: readthedocs-sphinx-search<0.4,>=0.3.2
@@ -54,10 +55,15 @@ A Python Ocean Particle Image Analysis toolbox
 # Quick tryout of PyOPIA
 
 1) Install [uv](https://docs.astral.sh/uv/getting-started/installation)
-2) Run PyOPIA classification tests on database particles
+2) Initialize PyOPIA project with a small example image dataset and run processing
 ```bash
-uv run --python 3.12 --with git+https://github.com/SINTEF/pyopia --with tensorflow==2.16.2 --with keras==3.5.0 python -m pyopia.tests.test_classify
+uvx --python 3.12 --from pyopia[classification] pyopia --init-project pyopiatest --example-data
+cd pyopiatest
+uvx --python 3.12 --from pyopia[classification] pyopia process config.toml
 ```
+3) Inspect the processed particle statistics in the processed/ folder
+
+See the documentation for more information on how to install and use PyOPIA.
 
 # Documentation:
 

{pyopia-2.10.0 → pyopia-2.12.0}/README.md

@@ -6,10 +6,15 @@ A Python Ocean Particle Image Analysis toolbox
 # Quick tryout of PyOPIA
 
 1) Install [uv](https://docs.astral.sh/uv/getting-started/installation)
-2) Run PyOPIA classification tests on database particles
+2) Initialize PyOPIA project with a small example image dataset and run processing
 ```bash
-uv run --python 3.12 --with git+https://github.com/SINTEF/pyopia --with tensorflow==2.16.2 --with keras==3.5.0 python -m pyopia.tests.test_classify
+uvx --python 3.12 --from pyopia[classification] pyopia --init-project pyopiatest --example-data
+cd pyopiatest
+uvx --python 3.12 --from pyopia[classification] pyopia process config.toml
 ```
+3) Inspect the processed particle statistics in the processed/ folder
+
+See the documentation for more information on how to install and use PyOPIA.
 
 # Documentation:
 

pyopia-2.12.0/pyopia/__init__.py

@@ -0,0 +1 @@
+__version__ = "2.12.0"

pyopia-2.12.0/pyopia/auxillarydata.py

@@ -0,0 +1,106 @@
+import pandas as pd
+import logging
+import xarray as xr
+
+logger = logging.getLogger()
+
+AUXILLARY_DATA_FILE_TEMPLATE = """% COMMENT LINE: PLEASE UPDATE THIS FILE WITH PROJECT RELEVANT DATA. EACH COLUMN WILL BECOME A NETCDF VARIABLE.
+% COMMENT LINE: ONE LINE PER MEASUREMENT, TIME IS INTERPOLATED TO IMAGE DATA TIMES IN PYOPIA. FOLLOWING LINES ARE UNITS, DESCRIPTION AND VARIABLE NAME.
+,metres,degC
+Time of measurement,Depth at measurement location,Temperature at measurement location
+time,depth,temperature
+2022-06-08T18:40:00.00000,0.0,5.0
+2022-06-08T18:41:00.00000,5.0,6.0
+2022-06-08T18:42:00.00000,10.0,7.0
+2022-06-08T18:43:00.00000,20.0,8.0
+"""  # noqa: E501
+
+
+class AuxillaryData:
+    """
+    Handle auxillary data for PyOPIA particle statistics file.
+
+    Auxillary data variables may include (image) depth, longitude, latitude, etc.
+    This class parses a well-defined defined .csv input format, see example below.
+
+    Parameters
+    ----------
+    auxillary_data_path : str
+        Path to auxillary data files .csv creates by the enduser
+
+
+    Example of auxillary data file
+    ------------------------------
+    % COMMENT LINE:
+    % COMMENT LINE:
+    ,m,degC,psu
+    Time of measurement,Depth at measurement location,Temperature at measurement location
+    time,depth,temperature,salinity
+    2025-03-19T16:59:29.950729,0.0,5.0,34
+    2025-03-19T17:59:29.950729,0.0,5.0,34
+
+
+    Note
+    ----
+    Each column will become a netCDF variable
+    The two first lines are comments, and are ignored
+    Note that the third and fourth rows contain units and description for each variable
+    """
+
+    def __init__(self, auxillary_data_path=None):
+        self.auxillary_data_path = auxillary_data_path
+
+        # Create empty dataframe for cases where no file was specified, or an error occured reading it
+        self.auxillary_data = pd.DataFrame(index=pd.Index([], name="time")).to_xarray()
+        if auxillary_data_path is not None:
+            try:
+                self.auxillary_data = self.load_auxillary_data(auxillary_data_path)
+            except RuntimeError as e:
+                print(f"Failed to load auxillary data from file: {self.auxillary_data}")
+                logging.error(
+                    f"Failed to load auxillary data from file: {self.auxillary_data}"
+                )
+                logging.error(e)
+
+    def load_auxillary_data(self, auxillary_data_path):
+        """Load and format uxillary data from .csv file"""
+
+        # Load in the auxillary data file
+        auxillary_data = pd.read_csv(auxillary_data_path, skiprows=4)
+
+        # Load units and description rows
+        units = pd.read_csv(auxillary_data_path, skiprows=2, nrows=0).columns
+        long_names = pd.read_csv(auxillary_data_path, skiprows=3, nrows=0).columns
+
+        # Set time as the index and make sure its type is datetime64[ns]
+        auxillary_data["time"] = auxillary_data["time"].astype("datetime64[ns]")
+        auxillary_data = auxillary_data.set_index("time")
+
+        # Transform into xarray, add units
+        auxillary_data = auxillary_data.to_xarray()
+        for i, col in enumerate(auxillary_data.data_vars):  # Iterate over each column
+            auxillary_data[col].attrs["units"] = units[i + 1]
+            auxillary_data[col].attrs["long_name"] = long_names[i + 1]
+
+        logging.info(auxillary_data)
+
+        return auxillary_data
+
+    def add_auxillary_data_to_xstats(self, xstats):
+        """Add auxillary data to a PyOPIA xstats object"""
+        logging.info("Adding auxillary data to xstats and storing to new file")
+
+        # Add each auxillary data variable to xstats, interpolated to xstats times
+        for (
+            data_var
+        ) in self.auxillary_data.data_vars:  # Iterate over each data variable
+            xstats[data_var] = xr.DataArray(
+                data=self.auxillary_data[data_var]
+                .astype(float)
+                .interp(time=xstats["timestamp"]),
+                dims=xstats.dims,
+                coords=xstats.coords,
+                attrs=self.auxillary_data[data_var].attrs,
+            )
+
+        return xstats

{pyopia-2.10.0 → pyopia-2.12.0}/pyopia/cf_metadata.json

@@ -1,49 +1,49 @@
 {"major_axis_length": {
     "standard_name": "major_axis_length",
     "long_name": "The length of the major axis of the ellipse that has the same normalized second central moments as the region",
-    "units": "micrometer",
+    "units": "Pixels",
     "calculation_method": "Computed using skimage.measure.regionprops (axis_major_length)",
     "pyopia_process_level": 1},
 "minor_axis_length": {
 "standard_name": "minor_axis_length",
     "long_name": "The length of the minor axis of the ellipse that has the same normalized second central moments as the region",
-    "units": "micrometer",
+    "units": "Pixels",
     "calculation_method": "Computed using skimage.measure.regionprops (axis_minor_length)",
     "pyopia_process_level": 1},
 "equivalent_diameter": {
     "standard_name": "equivalent_circular_diameter",
     "long_name": "Diameter of a circle with the same area as the particle",
-    "units": "micrometer",
+    "units": "Pixels",
     "calculation_method": "Computed using skimage.measure.regionprops (equivalent_diameter)",
     "pyopia_process_level": 1},
 "minr": {
     "standard_name": "minimum_row_index",
     "long_name": "Minimum row index of the particle bounding box",
-    "units": "pixels",
+    "units": "Pixels",
     "calculation_method": "Extracted from skimage.measure.regionprops (bbox[0])",
     "pyopia_process_level": 1},
 "maxr": {
     "standard_name": "maximum_row_index",
     "long_name": "Maximum row index of the particle bounding box",
-    "units": "pixels",
+    "units": "Pixels",
     "calculation_method": "Extracted from skimage.measure.regionprops (bbox[2])",
     "pyopia_process_level": 1},
 "minc": {
     "standard_name": "minimum_column_index",
     "long_name": "Minimum column index of the particle bounding box",
-    "units": "pixels",
+    "units": "Pixels",
     "calculation_method": "Extracted from skimage.measure.regionprops (bbox[1])",
     "pyopia_process_level": 1},
 "maxc": {
     "standard_name": "maximum_column_index",
     "long_name": "Maximum column index of the particle bounding box",
-    "units": "pixels",
+    "units": "Pixels",
     "calculation_method": "Extracted from skimage.measure.regionprops (bbox[3])",
     "pyopia_process_level": 1},
 "saturation": {
     "standard_name": "image_saturation",
     "long_name": "Percentage saturation of the image",
-    "units": "percent",
+    "units": "Percent",
     "calculation_method": "Computed as the percentage of the image covered by particles relative to the maximum acceptable coverage",
     "pyopia_process_level": 1},
 "index": {
@@ -58,11 +58,6 @@
     "units": "",
     "calculation_method": "Generated during particle export",
     "pyopia_process_level": 1},
-"time": {
-    "standard_name": "time",
-    "long_name": "Time of particle observation",
-    "calculation_method": "Extracted from the timestamp of the observation",
-    "pyopia_process_level": 0},
 "timestamp": {
     "standard_name": "timestamp",
     "long_name": "Timestamp of particle observation",

{pyopia-2.10.0 → pyopia-2.12.0}/pyopia/classify.py

@@ -3,6 +3,7 @@ Module containing tools for classifying particle ROIs
 """
 
 import os
+import hashlib
 import numpy as np
 import pandas as pd
 import logging
@@ -125,6 +126,11 @@ class Classify:
         path, filename = os.path.split(model_path)
         self.model = keras.models.load_model(model_path)
 
+        # Create a hash of the model weights file
+        with open(model_path, "rb") as f:
+            digest = hashlib.file_digest(f, "sha256")
+        self.model_hash = digest.hexdigest()
+
         # Try to create model output class name list from last model layer name
         class_labels = None
         try: