codespell: action, config + some typos fixed

.codespellrc

@@ -0,0 +1,3 @@
+[codespell]
+skip = .git,*.pdf,*.svg,LICENSE.md
+ignore-words-list = ans

.github/workflows/codespell.yml

@@ -0,0 +1,22 @@
+---
+name: Codespell
+
+on:
+  push:
+    branches: [release]
+  pull_request:
+    branches: [release]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

moseq2_viz/gui.py

@@ -106,7 +106,7 @@ def add_group(index_file, by='SessionName', value='default', group='default', ex
 
 def get_best_fit_model(progress_paths, output_file=None, plot_all=False, fps=30, ext='p', objective='duration (mean match)'):
     """
-    Return the best model in the model foder that is closest to model free changepoint in the given objective.
+    Return the best model in the model folder that is closest to model free changepoint in the given objective.
 
     Args:
     progress_paths (dict): Dictionary containing paths the to model directory and pc scores file

moseq2_viz/helpers/wrappers.py

@@ -204,7 +204,7 @@ def plot_syllable_stat_wrapper(model_fit, index_file, output_file, stat='usage',
     index_file (str): path to index file.
     output_file (str): filename for syllable usage graph.
     stat (str): syllable statistic to plot.
-    sort (bool): sort syllables by parameter specified in count paramter.
+    sort (bool): sort syllables by parameter specified in count parameter.
     count (str): method to compute syllable mean usage, either 'usage' or 'frames'. 
     group (tuple, list, None): tuple or list of groups to include in usage plot. (None to graph all groups)
     max_syllable (int): the index of the maximum number of syllables to include

moseq2_viz/info/util.py

@@ -55,7 +55,7 @@ def entropy_rate(labels, truncate_syllable=40, normalize='bigram',
     truncate_syllable (int): maximum number of labels to keep for this calculation.
     normalize (str): the type of transition matrix normalization to perform.
     smoothing (float): a constant as pseudocount added to label usages before normalization
-    tm_smoothing (float): a constant as pseudocount added to label transtition counts before normalization.
+    tm_smoothing (float): a constant as pseudocount added to label transition counts before normalization.
     relabel_by (str): how to re-order labels. Options are: 'usage', 'frames', or None.
 
     Returns:
@@ -111,7 +111,7 @@ def transition_entropy(labels, tm_smoothing=0, truncate_syllable=40, transition_
 
     Args:
     labels (list or np.ndarray): a list of label arrays, where each entry in the list is an array of labels for one session.
-    tm_smoothing (float): a constant as pseudocount added to label transtition counts before normalization.
+    tm_smoothing (float): a constant as pseudocount added to label transition counts before normalization.
     truncate_syllable (int): maximum number of relabeled syllable to keep for this calculation
     transition_type (str): can be either "incoming" or "outgoing" to compute the entropy of each incoming or outgoing syllable transition.
     relabel_by (str): how to re-order labels. Options are: 'usage', 'frames', or None.

moseq2_viz/io/video.py

@@ -76,7 +76,7 @@ def write_crowd_movie_info_file(model_path, model_fit, index_file, output_dir):
 
     Args:
     model_path (str): path to model used to generate movies
-    model_fit (dict): loaded ARHMM mdoel results
+    model_fit (dict): loaded ARHMM model results
     index_file (str): path to index file used with model
     output_dir (str): path to crowd movies directory to store file in.
     """

moseq2_viz/model/fingerprint_classifier.py

@@ -246,7 +246,7 @@ def classifier_fingerprint(summary, features=['MoSeq'], preprocessor=None, class
         preprocessor (sklearn.preprocessing object, optional): Scalar for scaling the data by feature. Defaults to None.
         target (list, optional): labels the classifier predicts. Defaults to ['group'].
         param_search (bool, optional): run GridSearchCV to find the regularization param for classifier. Defaults to True.
-        C_list (numpy.array, optional): list of C regularization paramters to search through. Defaults to None. If None, C_list will search through np.logspace(-6,3, 50)
+        C_list (numpy.array, optional): list of C regularization parameters to search through. Defaults to None. If None, C_list will search through np.logspace(-6,3, 50)
         model_type (str, optional): name of the linear classifier. 'lr' for logistic regression or 'svc' for linearSVC. Defaults to 'lr'.
         cv (str, optional): cross validation type. 'loo' for LeaveOneOut 'skf' for StratifiedKFold. Defaults to 'loo'.
         n_splits (int, optional): number of splits for StratifiedKFold. Defaults to 5.

moseq2_viz/model/stat.py

@@ -70,7 +70,7 @@ def ztest_vect(d1, d2):
 
 def bootstrap_group_means(df, group1, group2, statistic="usage", max_syllable=40):
     """
-    compute boostrapped group means
+    compute bootstrapped group means
 
     Args:
     df (pandas.DataFrame): dataframe that contains syllable statistics per session (mean_df/stats_df)
@@ -565,7 +565,7 @@ def ttest(df, group1, group2, statistic="usage", max_syllable=40, verbose=False,
 
 def get_sig_syllables(df_pvals, thresh=0.05, mc_method="fdr_bh", verbose=False):
     """
-    Runs multiple p-value comparisons test given a set alpha threshold with mutliple test correction.
+    Runs multiple p-value comparisons test given a set alpha threshold with multiple test correction.
 
     Args:
     df_pvals (pandas.DataFrame): dataframe listing raw p-values

moseq2_viz/model/util.py

@@ -887,7 +887,7 @@ def prepare_model_dataframe(model_path, pca_path):
 def simulate_ar_trajectory(ar_mat, init_points=None, sim_points=100):
     """
     Simulate auto-regressive trajectory matrices from
-    a set of initalized points.
+    a set of initialized points.
 
     Args:
     ar_mat (2D np.ndarray): numpy array representing the autoregressive matrix of a model state with shape (npcs, npcs * nlags + 1)

moseq2_viz/viz.py

@@ -29,8 +29,8 @@ def _validate_and_order_syll_stats_params(complete_df, stat='usage', ordering='s
     ordering (str, list, None): statistics for sorting syllables on or a list for syllable ordering.
     max_sylls (int): the index of the maximum number of syllables to include
     groups (list): list of groups to include in plot. If groups=None, all groups will be plotted.
-    ctrl_group (str): name of control group for computing usage difference beween two groups.
-    exp_group (str): name of experimental group for computing usage difference beween two groups.
+    ctrl_group (str): name of control group for computing usage difference between two groups.
+    exp_group (str): name of experimental group for computing usage difference between two groups.
     colors (list): list of user-selected colors to represent the data
     figsize (tuple): tuple value of length = 2, representing (height x width) of the plotted figure dimensions
 
@@ -160,10 +160,10 @@ def make_crowd_matrix(slices, nexamples=50, pad=30, raw_size=(512, 424), outmovi
     min_dur (int): minimum syllable duration.
     scale (int): mouse size scaling factor.
     center (bool): boolean flag that indicates whether mice are centered.
-    rotate (bool): boolean flag that indicates wehther to rotate mice and orient them.
-    select_median_duration_instances (bool): flag that indicates wehther to select examples with syallable duration closer to median.
+    rotate (bool): boolean flag that indicates whether to rotate mice and orient them.
+    select_median_duration_instances (bool): flag that indicates whether to select examples with syallable duration closer to median.
     min_height (int): minimum max height from floor to use.
-    legacy_jitter_fix (bool): flag that indicates wehther to apply jitter fix for K1 camera.
+    legacy_jitter_fix (bool): flag that indicates whether to apply jitter fix for K1 camera.
     kwargs (dict): extra keyword arguments
 
     Returns:
@@ -175,7 +175,7 @@ def make_crowd_matrix(slices, nexamples=50, pad=30, raw_size=(512, 424), outmovi
 
     rng = np.random.default_rng(seed)
 
-    # set up x, y value to crop out the mouse with respect to the mouse centriod
+    # set up x, y value to crop out the mouse with respect to the mouse centroid
     xc0, yc0 = crop_size[1] // 2, crop_size[0] // 2
     xc = np.arange(-xc0, xc0 + 1, dtype='int16')
     yc = np.arange(-yc0, yc0 + 1, dtype='int16')
@@ -287,7 +287,7 @@ def make_crowd_matrix(slices, nexamples=50, pad=30, raw_size=(512, 424), outmovi
 
             rot_mat = cv2.getRotationMatrix2D((xc0, yc0), angles[i], 1)
 
-            # add the new instance to the exisiting crowd matrix
+            # add the new instance to the existing crowd matrix
             old_frame = crowd_matrix[i]
             new_frame = np.zeros_like(old_frame)
 
@@ -616,7 +616,7 @@ def plot_cp_comparison(model_results, pc_cps, plot_all=False, best_model=None, b
     pc_cps (np.array): Computed PC changepoints
     plot_all (bool): Boolean flag that indicates whether to plot all model changepoints for all keys included in model_cps dict.
     best_model (str): key name to the model with the closest median syllable duration
-    bw_adjust (float): fraction to modify bandwith of kernel density estimate. (lower = higher definition)
+    bw_adjust (float): fraction to modify bandwidth of kernel density estimate. (lower = higher definition)
 
     Returns:
     fig (pyplot.figure): syllable usage ordered by frequency, 90% usage marked