Add codespell support (config, workflow to detect/not fix) and make it fix few typos

.codespellrc

@@ -0,0 +1,6 @@
+[codespell]
+# Ref: https://github.com/codespell-project/codespell#using-a-config-file
+skip = .git*,*.css,.codespellrc
+check-hidden = true
+ignore-regex = ^\s*"image/\S+": ".*
+ignore-words-list = idel,dum,sav,alph

.github/workflows/codespell.yml

@@ -0,0 +1,25 @@
+# Codespell configuration is within .codespellrc
+---
+name: Codespell
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Annotate locations with typos
+        uses: codespell-project/codespell-problem-matcher@v1
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

analyses/RunLength_2017_04_08/InstallMex.m

@@ -193,7 +193,7 @@
    Flags = cat(2, Flags, {'-compatibleArrayDims'});
 end
 
-% Define endianess directive:
+% Define endianness directive:
 if isLittleEndian
    Flags = cat(2, Flags, {'-D_LITTLE_ENDIAN'});
 else  % Does Matlab run on a big endian machine currently?!

analyses/RunLength_2017_04_08/RunLength.c

@@ -310,7 +310,7 @@ void mexFunction(int nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[])
 
      // Create 3rd output as post-processing: ----------------------------------
      // Collecting the indices on the fly might be faster, but doing this
-     // afterwards allowes to allocate the correct number of elements directly:
+     // afterwards allows to allocate the correct number of elements directly:
      if (nlhs == 3) {
         if (isColumn) {
            plhs[2] = mxCreateDoubleMatrix(nb, 1, mxREAL);

analyses/RunLength_2017_04_08/RunLength_M.m

@@ -137,11 +137,11 @@
 
    if vectorized                  % Vectorized: --------------------------------
       len   = length(n);          % Number of bins
-      d     = cumsum(n);          % Cummulated run lengths
+      d     = cumsum(n);          % Cumulated run lengths
       index = zeros(1, d(len));   % Pre-allocate
       index(d(1:len-1)+1) = 1;    % Get the indices where the value changes
       index(1)            = 1;    % First element is treated as "changed" also
-      index = cumsum(index);      % Cummulated indices
+      index = cumsum(index);      % Cumulated indices
       x     = b(index);
 
    else                           % Loop: --------------------------------------

analyses/RunLength_2017_04_08/uTest_RunLength.m

@@ -140,7 +140,7 @@ function uTest_RunLength(doSpeed)
       end
    end
 
-   % Test coding with limitting counter to 255:
+   % Test coding with limiting counter to 255:
    for k = [1,2,3, 250:260, 500:520, 750:800]  % Around multiples of 255
       x0     = myCast(ones(1, k), aType);
       [b, n] = RunLength(x0, 'byte');

analyses/getkin.m

@@ -7,7 +7,7 @@
 %     BOUT_LENRH,BOUT_SPEEDRH,BOUT_LENLH,BOUT_SPEEDLH] = GETKIN(MSRAWDATA,LABELS,GROUP_NUM,FPS)
 %
 %   INPUTS:
-%   MSRAWDATA    Matrix of the positons of the 6-body parts outlining the rodent over time videotaped from the bottom looking up. 
+%   MSRAWDATA    Matrix of the positions of the 6-body parts outlining the rodent over time videotaped from the bottom looking up. 
 %                Rows represents time.
 %                Columns 1 & 2 tracks snout; columns 3 to 6 tracks the two front paws; Columns 7 to 10 tracks the two hind paws;
 %                Columns 11 & 12 tracks the base of the tail. Tested on tracking data generated by DeepLabCut 2.0.

bsoid/action_gif2.m

@@ -4,7 +4,7 @@
 %   
 %   [T,B,B_EX] = ACTION_GIF2(PNGPATH,GRP,N,N_LEN,FILEPATHOUTRESULTS) outputs classified behaviors based on DeepLabCut analysis
 %   PNGPATH    The path to frame-by-frame video from FFmpeg.
-%   GRP    Statistically different gropus based on unsupervised GMM model fitting of action space data. This is the output from BSOID.
+%   GRP    Statistically different groups based on unsupervised GMM model fitting of action space data. This is the output from BSOID.
 %   N    Number of sampled video you desire. Default 3. 
 %   N_LEN    Lower bound for consecutive frames (10fps, 50ms each) for which the video will be generated from. Default 6 (300ms).
 %   X    X times speed. Default 0.5.

bsoid/bsoid_assign.m

@@ -14,7 +14,7 @@
 %           Otherwise, set it to 0 for individual segmentation/.csv file. Default is 1. 
 %   SMTH_HSTRY    BOXCAR smoothing using number of frames from before. Default ~40ms before.
 %   SMTH_FUTR    BOXCAR smoothing using number of frames from after. Default ~40ms after.
-%   KCLASS    Maximum number of assigment classes that the Gaussian Mixture Model will try to parse out. Default 50.
+%   KCLASS    Maximum number of assignment classes that the Gaussian Mixture Model will try to parse out. Default 50.
 %
 %   OUTPUTS:
 %   F_10FPS    Compiled features that were used to cluster, 10fps temporal resolution.

bsoid/bsoid_fsml.m

@@ -4,7 +4,7 @@
 %   [LABELS_FSALL,F_10FPS_FS] = BSOID_FSML(DATA,BEHV_MDL,FPS,SMTH_HSTRY,SMTH_FUTR) outputs classified behaviors matching your camera's frame-rate
 %
 %   INPUTS:
-%   DATA_TEST    Matrix of the positons of the 6-body parts outlining the rodent over time videotaped from the bottom looking up. 
+%   DATA_TEST    Matrix of the positions of the 6-body parts outlining the rodent over time videotaped from the bottom looking up. 
 %                Rows represents time.
 %                Columns 1 & 2 tracks snout; columns 3 to 6 tracks the two front paws; Columns 7 to 10 tracks the two hind paws;
 %                Columns 11 & 12 tracks the base of the tail. Tested on tracking data generated by DeepLabCut 2.0.

bsoid/bsoid_mdl2.m

@@ -10,7 +10,7 @@
 %   CV_IT    Number of times to run cross-validation on. Default is 30.
 %   
 %   OUTPUTS:
-%   BEHV_MDL    Trained Multi-Class Support Vector Machine (SVM) classifier, based on Guassian kernels.
+%   BEHV_MDL    Trained Multi-Class Support Vector Machine (SVM) classifier, based on Gaussian kernels.
 %   CV_AMEAN    Cross-validated accuracy mean.
 %   CV_ASEM    Cross-validated accuracy standard error of the mean.
 %   ACC_FIG    Accuracy box plot figure showing all the cross validated data points.

bsoid/bsoid_svm.m

@@ -4,7 +4,7 @@
 %   [LABELS,F_10FPS_TEST] = BSOID_SVM(DATA_TEST,FPS,MDL) outputs classified behaviors using the output from bsoid_mdl.
 %
 %   INPUTS:
-%   DATA_TEST    Matrix of the positons of the 6-body parts outlining the rodent over time videotaped from the bottom looking up. 
+%   DATA_TEST    Matrix of the positions of the 6-body parts outlining the rodent over time videotaped from the bottom looking up. 
 %                Rows represents time.
 %                Columns 1 & 2 tracks snout; columns 3 to 6 tracks the two front paws; Columns 7 to 10 tracks the two hind paws;
 %                Columns 11 & 12 tracks the base of the tail. Tested on tracking data generated by DeepLabCut 2.0.

bsoid_app/bsoid_analysis.py

@@ -15,7 +15,7 @@ def streamlit_run(pyfile):
                    layout='wide', initial_sidebar_state='auto')
 local_css("./bsoid_app/bsoid_utilities/style.css")
 title = "<div> <span class='bold'><span class='h1'>B-SOID</span></span> " \
-        "   <span class='h2'>anaylsis 📊</span></span> </div>"
+        "   <span class='h2'>analysis 📊</span></span> </div>"
 st.markdown(title, unsafe_allow_html=True)
 st.markdown('Step 1: Pick the directory and workspace to analyze.')
 st.markdown('Step 2: Once input, select the type of results to analyze using the sidebar modules.')

bsoid_figs/figS4.py

@@ -2,7 +2,7 @@
 import subprocess
 
 
-print('\n \n \n FRAMSHIFT NEURAL DIFFERNCES \n \n \n')
+print('\n \n \n FRAMSHIFT NEURAL DIFFERENCES \n \n \n')
 path = '/Volumes/Elements/Manuscripts/B-SOiD/bsoid_natcomm/workspace/neuralbehavior_durs.mat'
 fig_format = 'png'
 outpath = '/Volumes/Elements/Manuscripts/B-SOiD/bsoid_natcomm/figure_panels/neural_data/'

bsoid_figs/subroutines/utilities/detect_peaks.py

@@ -39,7 +39,7 @@ def detect_peaks(x, mph=None, mpd=1, threshold=0, edge='rising',
     Returns
     -------
     ind : 1D array_like
-        indeces of the peaks in `x`.
+        indices of the peaks in `x`.
 
     Notes
     -----

bsoid_py/config/GLOBAL_CONFIG.py

@@ -1,4 +1,4 @@
-################### THINGS YOU PROBABLY DONT'T WANT TO CHANGE ###################
+################### THINGS YOU PROBABLY DON'T WANT TO CHANGE ###################
 
 import logging
 import sys

bsoid_py/train.py

@@ -26,7 +26,7 @@ def bsoid_tsne(data: list, bodyparts=BODYPARTS, fps=FPS, comp=COMP):
     :param fps: scalar, argument specifying camera frame-rate in LOCAL_CONFIG
     :param comp: boolean (0 or 1), argument to compile data or not in LOCAL_CONFIG
     :return f_10fps: 2D array, features
-    :retrun f_10fps_sc: 2D array, standardized features
+    :return f_10fps_sc: 2D array, standardized features
     :return trained_tsne: 2D array, trained t-SNE space
     """
     win_len = np.int(np.round(0.05 / (1 / fps)) * 2 - 1)

bsoid_py/utils/likelihoodprocessing.py

@@ -133,7 +133,7 @@ def main(folders: list):
     :param folders: list, data folders
     :return filenames: list, data filenames
     :return data: list, filtered data list
-    :retrun perc_rect: 1D array, percent filtered per BODYPART
+    :return perc_rect: 1D array, percent filtered per BODYPART
     """
     filenames, data, perc_rect = import_folders(folders)
     return filenames, data, perc_rect

bsoid_umap/config/GLOBAL_CONFIG.py

@@ -1,4 +1,4 @@
-################### THINGS YOU PROBABLY DONT'T WANT TO CHANGE ###################
+################### THINGS YOU PROBABLY DON'T WANT TO CHANGE ###################
 
 import logging
 import sys

bsoid_umap/utils/likelihoodprocessing.py

@@ -133,7 +133,7 @@ def main(folders: list):
     :param folders: list, data folders
     :return filenames: list, data filenames
     :return data: list, filtered data list
-    :retrun perc_rect: 1D array, percent filtered per BODYPART
+    :return perc_rect: 1D array, percent filtered per BODYPART
     """
     filenames, data, perc_rect = import_folders(folders)
     return filenames, data, perc_rect

docs/bsoid_mdl.md

@@ -29,7 +29,7 @@ function [OF_mdl,CV_amean,CV_asem,acc_fig] = bsoid_mdl(f_10fps,grp,hldout,cv_it,
 
 - `CV_AMEAN`    Cross-validated accuracy mean.
 
-- `CV_ASEM`    Cross-validated accuracy standard error fo the mean.
+- `CV_ASEM`    Cross-validated accuracy standard error of the mean.
 
 - `ACC_FIG`    Box plot showing classifier performance with individual data points representing a randomly subsampled test set from the hold out portion.
 

googlecolab/bsoid_v1_2_1.ipynb

@@ -367,7 +367,7 @@
         "    :param folders: list, data folders\n",
         "    :return filenames: list, data filenames\n",
         "    :return data: list, filtered data list\n",
-        "    :retrun perc_rect: 1D array, percent filtered per BODYPART\n",
+        "    :return perc_rect: 1D array, percent filtered per BODYPART\n",
         "    \"\"\"\n",
         "    filenames, data, perc_rect = import_folders(folders)\n",
         "    return filenames, data, perc_rect\n",
@@ -774,7 +774,7 @@
         "    :param fps: scalar, argument specifying camera frame-rate in LOCAL_CONFIG\n",
         "    :param comp: boolean (0 or 1), argument to compile data or not in LOCAL_CONFIG\n",
         "    :return f_10fps: 2D array, features\n",
-        "    :retrun f_10fps_sc: 2D array, standardized features\n",
+        "    :return f_10fps_sc: 2D array, standardized features\n",
         "    :return trained_tsne: 2D array, trained t-SNE space\n",
         "    \"\"\"\n",
         "    win_len = np.int(np.round(0.05 / (1 / fps)) * 2 - 1)\n",