Implement automatic spell check via Codespell and fix typos (#149)

* Apply spelling fix and configure codespell

* Add news

* [pre-commit.ci] auto fixes from pre-commit hooks

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: bobleesj

.codespell/ignore_lines.txt

@@ -0,0 +1,2 @@
+;; Please include filenames and explanations for each ignored line.
+;; See https://docs.openverse.org/meta/codespell.html for docs.

.codespell/ignore_words.txt

@@ -0,0 +1,11 @@
+;; Please include explanations for each ignored word (lowercase).
+;; See https://docs.openverse.org/meta/codespell.html for docs.
+
+;; abbreviation for "materials" often used in a journal title
+mater
+
+;; alternative use of socioeconomic
+socio-economic
+
+;; Frobenius norm used in np.linalg.norm
+fro

.pre-commit-config.yaml

@@ -44,3 +44,9 @@ repos:
         name: Prevent Commit to Main Branch
         args: ["--branch", "main"]
         stages: [pre-commit]
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+    - id: codespell
+      additional_dependencies:
+        - tomli

AUTHORS.rst

@@ -2,7 +2,7 @@ Authors
 =======
 
 Luke Granlund
-Billinge Group and community contibutors.
+Billinge Group and community contributors.
 
 Contributors
 ------------

README.rst

@@ -152,7 +152,7 @@ trying to commit again.
 
 Improvements and fixes are always appreciated.
 
-Before contribuing, please read our `Code of Conduct <https://github.com/diffpy/diffpy.srmise/blob/main/CODE_OF_CONDUCT.rst>`_.
+Before contributing, please read our `Code of Conduct <https://github.com/diffpy/diffpy.srmise/blob/main/CODE_OF_CONDUCT.rst>`_.
 
 Contact
 -------

doc/examples/README.rst

@@ -111,7 +111,7 @@ the copiously commented scripts helpful.
 * Peak extraction with initial peaks:
       extract_initial.py
 
-* Peak fitting with intial peaks:
+* Peak fitting with initial peaks:
       fit_initial.py
 
 * Querying SrMise results:
@@ -678,7 +678,7 @@ the baseline. The methods of greatest interest are as follows. ::
     # Get the correlation between two parameters
     cov.getcorrelation((i1,j1), (i2,j2))
 
-Suppose, for example, one wants to emperically estimate the number of silver
+Suppose, for example, one wants to empirically estimate the number of silver
 atoms contributing to each occupied coordination shell of the FCC structure,
 knowing that the coordination number (i.e. nearest neighbors) of an ideal FCC
 structure is exactly 12.  For a monoelemental material the intensity of a peak

doc/examples/multimodel_known_dG2.py

@@ -114,7 +114,7 @@ def run(plot=True):
     # with respect to the actual experiment when using a Nyquist-sampled PDF
     # with experimentally determined uncertainties.
     #
-    # The present PDF satisifes these conditions, so the rankings below reflect
+    # The present PDF satisfies these conditions, so the rankings below reflect
     # an AIC-based estimate of which of the tested models the data best support.
     print("\n--------- Model Rankings for dG = %f ---------" % dG)
     print("Rank  Model  Class  Free         AIC   Prob  File")

doc/examples/output/extract_single_peak.pwa

@@ -44,7 +44,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 2.90074809344 0.267213055365 9.84389058517 # 1

doc/examples/output/fit_initial.pwa

@@ -43,7 +43,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 1.44052045545 0.126922793092 35515.0466525 # 1

doc/examples/output/known_dG_m0.pwa

@@ -51,7 +51,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 11.2310491383 0.29009226516 19.2512559254 # 2

doc/examples/output/known_dG_m1.pwa

@@ -51,7 +51,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 11.2529285169 0.364905691879 35.069510576 # 2

doc/examples/output/known_dG_m12.pwa

@@ -51,7 +51,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 11.2573520325 0.373991203999 34.6040498151 # 2

doc/examples/output/known_dG_m8.pwa

@@ -51,7 +51,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 11.2506286561 0.370187490596 34.3566941925 # 2

doc/examples/output/parameter_summary.pwa

@@ -44,7 +44,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 1.9557575566 0.248658302944 2.57966649229 # 1

doc/examples/output/query_results.pwa

@@ -44,7 +44,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 2.90080420526 0.268377339284 9.93053286298 # 1

doc/examples/output/unknown_dG_m11.pwa

@@ -50,7 +50,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 1.44110805058 0.137450008306 36477.2666515 # 2

doc/examples/output/unknown_dG_m17.pwa

@@ -50,7 +50,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 1.44210250295 0.130428325915 35832.2439651 # 2

doc/examples/output/unknown_dG_m18.pwa

@@ -50,7 +50,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 1.44255991965 0.130976461359 35872.4728645 # 2

doc/examples/output/unknown_dG_m5.pwa

@@ -50,7 +50,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 1.44110346987 0.135456358948 36202.906939 # 2

doc/examples/output/unknown_dG_m7.pwa

@@ -50,7 +50,7 @@ ModelEvaluator=AIC
 ## Extracted Peaks
 # Parameters are given in the natural units of the data,
 # where width is measured as full-width at half maximum.
-# Each line is followd by a comment which gives the index
+# Each line is followed by a comment which gives the index
 # of the corresponding Peak Function.
 #L position fwhm area
 1.4417380998 0.13653359706 36320.7534683 # 2

doc/examples/query_results.py

@@ -10,7 +10,7 @@
 # See LICENSE.txt for license information.
 #
 ##############################################################################
-"""Example of extracting multiple peaks and accessing results programatically.
+"""Example of extracting multiple peaks and accessing results programmatically.
 
 This example shows how to extract a range of peaks from a simple crystalline
 PDF using a crystalline baseline obtained from an existing trial.  It shows

doc/source/extending.rst

@@ -22,7 +22,7 @@ functionality common to all SrMise baseline and peak functions, which are
 separately implemented in the ``diffpy.srmise.baselines`` and
 ``diffpy.srmise.peaks`` subpackages.  Specific baseline and peak functions
 inherit from the ``BaselineFunction`` and ``PeakFunction`` classes in those
-subpackges, as shown below.
+subpackages, as shown below.
 
 * .. py:class:: BaseFunction
 

news/codespell.rst

@@ -0,0 +1,23 @@
+**Added:**
+
+* Codespell for automatic spelling check, configured in pre-commit
+
+**Changed:**
+
+* <news item>
+
+**Deprecated:**
+
+* <news item>
+
+**Removed:**
+
+* <news item>
+
+**Fixed:**
+
+* Typos in the source code and documentation
+
+**Security:**
+
+* <news item>

pyproject.toml

@@ -57,6 +57,11 @@ namespaces = false  # to disable scanning PEP 420 namespaces (true by default)
 [tool.setuptools.dynamic]
 dependencies = {file = ["requirements/pip.txt"]}
 
+[tool.codespell]
+exclude-file = ".codespell/ignore_lines.txt"
+ignore-words = ".codespell/ignore_words.txt"
+skip = "*.cif,*.dat"
+
 [tool.black]
 line-length = 115
 include = '\.pyi?$'

src/diffpy/srmise/modelcluster.py

@@ -53,7 +53,7 @@ class ModelCovariance(object):
     """
 
     def __init__(self, *args, **kwds):
-        """Intialize object."""
+        """Initialize object."""
         self.cov = None  # The raw covariance matrix
         self.model = None  # ModelParts instance, so both peaks and baseline (if present)
 
@@ -430,7 +430,7 @@ class ModelCluster(object):
     """
 
     def __init__(self, model, *args, **kwds):
-        """Intialize explicitly, or from existing ModelCluster.
+        """Initialize explicitly, or from existing ModelCluster.
 
         Parameters
         ----------
@@ -978,7 +978,7 @@ def estimatepeak(self):
         # be estimating and fitting each possible peak type to the data
         # and seeing which works best, but for small clusters evaluating
         # model quality is generally unreliable, and most peak shapes will
-        # be approxiately equally good anyway.
+        # be approximately equally good anyway.
         if len(self.model) > 0:
             # throw some exception
             pass
@@ -1105,7 +1105,7 @@ def fit(
         # after a second peak could potentially explain its residual.
         #
         # This is a tricky point.  It is often the case while fitting that an
-        # intially good peak becomes less accurate due to greater overlap at
+        # initially good peak becomes less accurate due to greater overlap at
         # the edges of the cluster, even as its (calculated) quality improves.
         # This may make combining clusters later more difficult, and so test
         # if the degree by which the new fit is off could perhaps be adequately
@@ -1220,7 +1220,7 @@ def reduce_to(self, x, y):
         -------
         ModelEvaluator or None
             Return ModelEvaluator instance if fit changed, otherwise None."""
-        # No reduction neccessary
+        # No reduction necessary
         if self.model.value(x) < y:
             logger.debug("reduce_to: No reduction necessary.")
             return None

src/diffpy/srmise/modelevaluators/aicc.py

@@ -176,7 +176,7 @@ def akaikeweights(aics):
         Parameters
         ----------
         aics : array-like
-            The squence of AIC instances
+            The sequence of AIC instances
 
         Returns
         -------
@@ -195,7 +195,7 @@ def akaikeprobs(aics):
         Parameters
         ----------
         aics : array-like
-            The squence of AIC instances
+            The sequence of AIC instances
 
         Returns
         -------

src/diffpy/srmise/pdfdataset.py

@@ -295,7 +295,7 @@ def readStr(self, datastring):
         if res:
             self.metadata["doping"] = float(res.groups()[0])
 
-        # parsing gerneral metadata
+        # parsing general metadata
         if metadata:
             regexp = r"\b(\w+)\ *=\ *(%(f)s)\b" % rx
             while True:
@@ -458,7 +458,7 @@ def copy(self, other=None):
 
 
 class PDFDataFormatError(Exception):
-    """Exception class marking failure to proccess PDF data string."""
+    """Exception class marking failure to process PDF data string."""
 
     pass
 

src/diffpy/srmise/pdfpeakextraction.py

@@ -258,7 +258,7 @@ def resampledata(self, dr, **kwds):
         The effective error may be scaled if class member scale is True.
 
         The method for 'resampling' the uncertainties is interpolation, since insufficient
-        information exists in a PDFPeakExtraction object to propogate them correctly on the
+        information exists in a PDFPeakExtraction object to propagate them correctly on the
         new grid.
 
         Parameters
@@ -897,7 +897,7 @@ def writepwastr(self, comments):
         lines.append("## Extracted Peaks")
         lines.append("# Parameters are given in the natural units of the data,")
         lines.append("# where width is measured as full-width at half maximum.")
-        lines.append("# Each line is followd by a comment which gives the index")
+        lines.append("# Each line is followed by a comment which gives the index")
         lines.append("# of the corresponding Peak Function.")
         lines.append("#L position fwhm area")
         for p in self.extracted.model:

src/diffpy/srmise/peakextraction.py

@@ -442,7 +442,7 @@ def readstr(self, datastring):
             for s in res[1:]:
                 self.initial_peaks.append(Peak.factory(s, safepf))
 
-        #  Instantiating srmise metatdata
+        #  Instantiating srmise metadata
 
         # pf
         res = re.search(r"^pf=(.*)$", srmisemetadata, re.M)
@@ -1382,16 +1382,16 @@ def fit_single(self):
     err = np.ones(len(r))
     evaluator = AICc()
 
-    te = PeakExtraction()
-    te.setdata(r, y, None, err)
-    te.setvars(rng=[1.51, 10.0], pf=[pf], cres=0.1, effective_dy=1.5 * err)
-    te.extract_single()
+    peak_extraction = PeakExtraction()
+    peak_extraction.setdata(r, y, None, err)
+    peak_extraction.setvars(rng=[1.51, 10.0], pf=[pf], cres=0.1, effective_dy=1.5 * err)
+    peak_extraction.extract_single()
 
     print("--- Actual Peak parameters ---")
     print(ideal_peaks)
 
     print("\n--- After extraction ---")
-    print(te)
+    print(peak_extraction)
 
-    te.plot()
+    peak_extraction.plot()
     input()

src/diffpy/srmise/peaks/gaussian.py

@@ -135,7 +135,7 @@ def estimate_parameters(self, r, y):
                 )
             guesspars[1] = 0.5 * (sigma_right + sigma_left) * self.sigma2fwhm
         else:
-            # Procede cautiously if min_y == max_y.  Without other information
+            # Proceed cautiously if min_y == max_y.  Without other information
             # we choose the center of the cluster as the peak center, and make
             # sure the peak has died down by the time it reaches the edge of
             # the data.
@@ -261,7 +261,7 @@ def _jacobianraw(self, pars, r, free):
         if free[2]:
             # derivative with respect to peak area
             # abs'(x)=sign(x) for real x except at 0 where it is undetermined.  Since any real peak necessarily has
-            # non-zero area and the function is paramaterized such that values of either sign represent equivalent
+            # non-zero area and the function is parameterized such that values of either sign represent equivalent
             # curves I arbitrarily choose positive sign for pars[2]==0 in order to
             # push the system back into a realistic parameter space should this improbable scenario occur.
             #   jacobian[2] = sign(pars[2])*exp_p