Merge branch 'synthetics2021' of https://github.com/hyperiongeo/welly …

…into synthetics2021

.github/workflows/run-tests.yml

@@ -7,7 +7,7 @@ on:
   push:
     branches: [ develop, main ]
   pull_request:
-    branches: [ develop ]
+    branches: [ develop, main ]
 
 jobs:
   build:
@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
 
     steps:
     - uses: actions/checkout@v3
@@ -29,5 +29,4 @@ jobs:
         python -m pip install --upgrade pip
         python -m pip install .[test]
     - name: Test with pytest
-      run: |
-        python run_tests.py
+      run: pytest

pyproject.toml

@@ -1,11 +1,62 @@
 [build-system]
-requires = [
-    "setuptools>=48",
-    "setuptools_scm[toml] >= 4, <6",
-    "setuptools_scm_git_archive",
-    "wheel >= 0.29.0",
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "welly"
+dynamic = ["version"]
+authors = [{ name = "The Welly Authors", email = "[email protected]" }]
+description = "Tools for making and managing well data."
+readme = "README.md"
+readme-content-type = "text/markdown"
+homepage = "https://github.com/agilescientific/welly"
+classifiers = [
+    "Intended Audience :: Science/Research",
+    "Development Status :: 4 - Beta",
+    "Natural Language :: English",
+    "Programming Language :: Python :: 3.6",
+    "Programming Language :: Python :: 3.7",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent"
+]
+dependencies = [
+    "numpy",
+    "scipy",
+    "pandas",
+    "matplotlib",
+    "lasio",
+    "striplog",
+    "tqdm",
+    "wellpathpy",
+    "requests"
+]
+
+[project.optional-dependencies]
+docs = ["sphinx", "sphinxcontrib-apidoc", "myst_nb", "furo"]
+test = ["pytest", "pytest-cov", "pytest-mpl"]
+dev = ["build", "pytest", "pytest-cov", "pytest-mpl", "sphinx", "sphinxcontrib-apidoc", "myst_nb", "furo"]
+
+[tool.hatch.metadata]
+packages = ["welly"]
+
+[tool.hatch.version]
+source = "vcs"
+
+[tool.hatch.build.hooks.vcs]
+version-file = "_version.py"
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+addopts = [
+  "--cov=welly",
+  "--cov-config=pyproject.toml",
+  "--mpl",
+  "--mpl-baseline-path=tests/baseline",
 ]
-build-backend = "setuptools.build_meta"
+testpaths = ["tests"]
 
 [tool.setuptools_scm]
 write_to = "welly/_version.py"

tests/test_well.py

@@ -5,6 +5,8 @@
 import os
 from pathlib import Path
 
+import pandas as pd
+
 import welly
 from welly import Well
 
@@ -148,3 +150,11 @@ def test_iter_well(well):
     for curve in well:
         assert curve == well.data['CALI']
         break
+
+def test_df_object_cols(df):
+
+    df["Test object"] = "54"
+    df["test_str"] = '1z'
+    well = Well.from_df(df)
+    assert all(well.df()["Test object"] == 54)
+    assert all(well.df()["test_str"] == "1z")

welly/__init__.py

@@ -3,6 +3,8 @@
 welly
 ==================
 """
+import sys
+
 from .project import Project
 from .well import Well
 from .header import Header
@@ -67,17 +69,10 @@ def read_df(df, **kwargs):
           ]
 
 
-from pkg_resources import get_distribution, DistributionNotFound
-
-try:
-    VERSION = get_distribution(__name__).version
-except DistributionNotFound:
-    try:
-        from ._version import version as VERSION
-    except ImportError:
-        raise ImportError(
-            "Failed to find (autogenerated) _version.py. "
-            "This might be because you are installing from GitHub's tarballs, "
-            "use the PyPI ones."
-            )
-__version__ = VERSION
+if sys.version_info >= (3, 8):
+    from importlib import metadata
+else:
+    import importlib_metadata as metadata
+
+__version__ = metadata.version(__name__)
+

welly/curve.py

@@ -9,6 +9,8 @@
 
 import numpy as np
 import pandas as pd
+from pandas.api.types import is_any_real_numeric_dtype
+from pandas.api.types import is_numeric_dtype
 from scipy.interpolate import interp1d
 
 from welly.plot import plot_2d_curve, plot_curve, plot_kde_curve
@@ -367,15 +369,15 @@ def _repr_html_(self):
         # Curve preview.
         s = '<tr><th style="border-top: 2px solid #000;">Depth</th><th style="border-top: 2px solid #000;">Value</th></tr>'
         rows += s.format(self.start, self.df.values[0][0])
-        if self.dtypes[0] == float:
+        if self.dtypes.iloc[0] == float:
             s = '<tr><td>{:.4f}</td><td>{:.4f}</td></tr>'
         else:
             s = '<tr><td>{}</td><td>{}</td></tr>'
         for depth, value in self.df.iloc[:3].iterrows():
-            rows += s.format(depth, value[0])
+            rows += s.format(depth, value.iloc[0])
         rows += '<tr><td>⋮</td><td>⋮</td></tr>'
         for depth, value in self.df.iloc[-3:].iterrows():
-            rows += s.format(depth, value[0])
+            rows += s.format(depth, value.iloc[0])
 
         # Footer.
         # ...
@@ -509,7 +511,7 @@ def step(self):
             0. If the index is numeric and not equally sampled
             None. If the index is not numeric
         """
-        if self.df.index.is_numeric() and not self.df.index.empty:
+        if is_any_real_numeric_dtype(self.df.index) and not self.df.index.empty:
             return get_step_from_array(self.df.index.values)
         else:
             return None
@@ -969,7 +971,7 @@ def to_basis(self,
             Curve. The current instance in the new basis.
         """
         # category data type or a string in data defaults to 'nearest'
-        if pd.api.types.is_categorical_dtype(self.df.iloc[:, 0]) or pd.api.types.is_string_dtype(self.df.iloc[:, 0]):
+        if not is_numeric_dtype(self.df.iloc[:, 0]):
             interp_kind = 'nearest'
 
         new_curve = copy.deepcopy(self)

welly/las.py

@@ -420,7 +420,7 @@ def to_lasio(well,
         if basis:
             df_merged = df_merged.reindex(basis)
         try:
-            l.add_curve('DEPT', df_merged.index.values)
+            l.append_curve('DEPT', df_merged.index.values)
         except:
             raise Exception("Please provide an index.")
 
@@ -452,7 +452,7 @@ def to_lasio(well,
                     # take the series, reindex it and transform to np.array
                     new_data = curve.df[col].reindex(basis).values
                     descr = getattr(curve, 'description', '')
-                    l.add_curve(mnemonic=key_,
+                    l.append_curve(mnemonic=key_,
                                 data=new_data,
                                 unit=curve.units,
                                 descr=descr)

welly/plot.py

@@ -393,9 +393,14 @@ def plot_2d_curve(curve,
                                  x2=np.nanmin(curve_data),
                                  facecolor='none',
                                  **kwargs)
+
+        # Combine the paths into a single Path object
+        vertices = np.concatenate([p.vertices for p in paths._paths])
+        codes = np.concatenate([p.codes for p in paths._paths])
+        merged_paths = mpl.path.Path(vertices, codes)
 
         # Make the 'fill' mask and clip the background image with it.
-        patch = PathPatch(paths._paths[0], visible=False)
+        patch = PathPatch(merged_paths, visible=False)
         ax.add_artist(patch)
         im.set_clip_path(patch)
     else:

welly/well.py

@@ -632,17 +632,28 @@ def df(self,
             # swap MultiIndex levels
             df = df.swaplevel()
 
-        # I think this is the wrong place to do this.
-        # Anyway, use i not name just in case there are duplicate names.
-        for i, (_, column) in enumerate(df.iteritems()):
-            if is_object_dtype(column.dtype):
-                try:
-                    df.iloc[:, i] = column.astype(float)
-                except ValueError:
-                    pass
+        df = self._convert_object_cols_to_numeric(df)
 
         return df
 
+    def _convert_object_cols_to_numeric(self, df):
+        """
+        Convert object columns into numeric columns, if possible.
+
+        Args:
+            df (pd.DataFrame): dataframe to work
+        Returns:
+            pd.DataFrame. Whole dataframe with conversions
+        """
+        df_nonobject = df.select_dtypes(exclude="object")
+        df_object = df.select_dtypes(include="object")
+        for col in df_object.columns:
+            try:
+                df_object[col] = pd.to_numeric(df_object[col])
+            except ValueError:
+                pass
+        return pd.concat([df_nonobject, df_object], axis=1)
+
     def add_curves_from_las(self, fname, remap=None, funcs=None):
         """
         Given a LAS file, add curves from it to the current well instance.