Merge pull request #82 from oscarbranson/dev

0.3.31 - Minor fixes for python updates

.github/workflows/tests.yml

@@ -10,20 +10,23 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
-        os: [windows-latest, ubuntu-latest, macos-latest]
+        python-version: ["3.9", "3.10", "3.11"]
+        os: [windows-latest, ubuntu-latest]
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
 
     - name: Setup python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
 
-    - name: ${{ matrix.os }} python ${{ matrix.python-version }}
+    - name: Install Python dependencies
       shell: bash -l {0}
       run: |
         python3 -m pip install -r requirements.txt
         python3 -m pip install -e . --no-deps --force-reinstall
+    
+    - name: Run tests
+      run: |
         python3 -m unittest

CHANGELOG.md

@@ -1,7 +1,7 @@
 # Changelog
 All significant changes to the software will be documented here.
 
-## [0.3.30-dev] - LIVE
+## [0.3.31-dev] - LIVE
 
 ### TODO
 - implement different analyte lists for different stages (raw, ratios, mass_fractions), OR improve analyte_checker functionality. This has to propagate throught to filter assignment.

latools/__init__.py

@@ -17,7 +17,7 @@
 from .helpers import chemistry
 from . import preprocessing
 
-VERSION = '0.3.30'
+VERSION = '0.3.31'
 
 def cite(output='text'):
     """

latools/latools.py

@@ -67,7 +67,11 @@
 # TODO: Add 'smooth all' function.
 
 class analyse(object):
-    """
+    def __init__(self, data_path, errorhunt=False, config='DEFAULT',
+                 dataformat=None, extension='.csv', srm_identifier='STD',
+                 cmap=None, time_format=None, internal_standard='Ca43',
+                 file_structure='multi', names='file_names', srm_file=None, pbar=None, split_kwargs={}):
+        """
     For processing and analysing whole LA - ICPMS datasets.
 
     Parameters
@@ -156,14 +160,6 @@ class analyse(object):
     cmaps : dict
         An analyte - specific colour map, used for plotting.
     """
-
-    def __init__(self, data_path, errorhunt=False, config='DEFAULT',
-                 dataformat=None, extension='.csv', srm_identifier='STD',
-                 cmap=None, time_format=None, internal_standard='Ca43',
-                 file_structure='multi', names='file_names', srm_file=None, pbar=None, split_kwargs={}):
-        """
-        For processing and analysing whole LA - ICPMS datasets.
-        """
         # initialise log
         params = {k: v for k, v in locals().items() if k not in ['self', 'pbar']}
         self.log = ['__init__ :: args=() kwargs={}'.format(str(params))]
@@ -279,7 +275,9 @@ def __init__(self, data_path, errorhunt=False, config='DEFAULT',
         data.sort(key=lambda d: d.uTime[0])
 
         # process sample names
-        if (names == 'file_names') | (names == 'metadata_names'):
+        if file_structure == 'long':
+            samples = np.array([s.sample for s in data], dtype=object)  
+        elif (names == 'file_names') | (names == 'metadata_names'):
             samples = np.array([s.sample.replace(' ', '') for s in data], dtype=object)  # get all sample names
             # if duplicates, rename them
             usamples, ucounts = np.unique(samples, return_counts=True)
@@ -292,8 +290,6 @@ def __init__(self, data_path, errorhunt=False, config='DEFAULT',
                     samples[ind] = new  # rename in samples
                     for s, ns in zip([data[i] for i in np.where(ind)[0]], new):
                         s.sample = ns  # rename in D objects
-        elif file_structure == 'long':
-            samples = np.array([s.sample for s in data], dtype=object)
         else:
             samples = np.arange(len(data))  # assign a range of numbers
             for i, s in enumerate(samples):

latools/preprocessing/split.py

@@ -185,7 +185,7 @@ def long_file(data_file, dataformat, sample_list, analyte='total_counts', savedi
             srm_replace.append(s)
         sample_list = srm_replace
 
-    dataformat = read_dataformat(dataformat, silent=False)
+    dataformat = read_dataformat(dataformat, silent=True)
 
     _, _, dat, meta = read_data(data_file, dataformat=dataformat, name_mode='file')
 
@@ -211,6 +211,10 @@ def long_file(data_file, dataformat, sample_list, analyte='total_counts', savedi
     n = int(max(ns))
 
     nsamples = len(sample_list)
+
+    print('\n*** Starting Long File Split ***')
+    print(f'There are {nsamples} in the sample list.')
+    print(f'With initial settings, we have found {n} ablations in the data.')
 
     # deal with wildcards
     if nsamples <= n and mode != 'strict':
@@ -249,20 +253,21 @@ def long_file(data_file, dataformat, sample_list, analyte='total_counts', savedi
                     ns[sig] = np.cumsum((sig ^ np.roll(sig, 1)) & sig)[sig]
                     n = int(max(ns))
                 print('       (Removed data fragments < {} points long)'.format(min_points))
-        elif isinstance(min_points, (int, float)):
-            # minimum point filter
-            sig = sig & np.roll(sig, min_points)
-            ns = np.zeros(sig.size)
-            ns[sig] = np.cumsum((sig ^ np.roll(sig, 1)) & sig)[sig]
-            n = int(max(ns))
+        # elif isinstance(min_points, (int, float)):
+        #     print('  -> There are more ablations than samples...')
+        #     # minimum point filter
+        #     sig = sig & np.roll(sig, min_points)
+        #     ns = np.zeros(sig.size)
+        #     ns[sig] = np.cumsum((sig ^ np.roll(sig, 1)) & sig)[sig]
+        #     n = int(max(ns))
         else:
             print('  -> There are more samples than ablations...')
             print('     Check your sample list is correct. If so, consider')
             print('     adding autorange_params to change the signal detection.')
             return
 
     minn = min([len(sample_list), n])
-
+    
     # calculate split boundaries
     bounds = []
     lower = 0
@@ -307,7 +312,7 @@ def long_file(data_file, dataformat, sample_list, analyte='total_counts', savedi
 
     # save output
     if passthrough:
-        print(f"Success! {n} ablations identified.")
+        print(f"*** Success! {n} ablations identified. ***\n")
         for sample, sdat in sections.items():
 
             sanalytes = list(sdat['rawdata'].keys())

old_setup.py

@@ -0,0 +1,45 @@
+from setuptools import setup, find_packages
+
+# bcause TravisCI was being a jerK
+try:
+  from latools import __version__
+except:
+  __version__ = "version_missing"
+
+with open("README.md", "r") as fh:
+    long_description = fh.read()
+
+setup(name='latools',
+      version=__version__,
+      description='Tools for LA-ICPMS data analysis.',
+      long_description=long_description,
+      long_description_content_type="text/markdown",
+      url='https://github.com/oscarbranson/latools',
+      author='Oscar Branson',
+      author_email='[email protected]',
+      license='MIT',
+      packages=find_packages(),
+      classifiers=['Development Status :: 4 - Beta',
+                   'Intended Audience :: Science/Research',
+                   'Topic :: Scientific/Engineering',
+                   'Programming Language :: Python :: 2',
+                   'Programming Language :: Python :: 3',
+                   ],
+      python_requires='>3.6',
+      install_requires=['numpy',
+                        'pandas',
+                        'matplotlib',
+                        'uncertainties',
+                        'scikit-learn',
+                        'scipy',
+                        'Ipython',
+                        'configparser',
+                        'tqdm'
+                        ],
+      package_data={
+        'latools': ['latools.cfg',
+                    'resources/*',
+                    'resources/data_formats/*',
+                    'resources/test_data/*'],
+      },
+      zip_safe=False)