cleanup comments in various funcs

Author: joshuabmoore

pyhctsa/operations/correlation.py

@@ -1719,7 +1719,7 @@ def _stat_av(y: ArrayLike, window_stat: str = 'mean', num_seg: int = 5, inc_move
         logging.warning(f"Time-series of length {len(y)} is too short for {num_seg} windows")
         return np.nan
     inc = np.floor(win_length/inc_move) # increment to move at each step
-    # if incrment rounded down to zero, prop it up
+    # if increment rounded down to zero, prop it up
     if inc == 0:
         inc = 1
 
@@ -1829,7 +1829,7 @@ def autocorr_shape(y: ArrayLike, stop_when: Union[int, str] = 'pos_drown') -> di
 
     # Check for good behavior
     if np.any(np.isnan(acf)):
-        # This is an anomalous time series (e.g., all constant, or conatining NaNs)
+        # This is an anomalous time series (e.g., all constant, or containing NaNs)
         out = np.nan
 
     out = {}

pyhctsa/operations/information.py

@@ -403,7 +403,7 @@ def automutual_info(
     for k, delay in enumerate(time_delay):
         # check enough samples to compute automutual info
         if delay > n - min_samples:
-            # time sereis too short - keep the remaining values as NaNs
+            # time series too short - keep the remaining values as NaNs
             break
 
         # form the time-delay vectors y1 and y2
@@ -679,7 +679,7 @@ def _rm_info(*args):
         return
 
     # some initial tests on the input arguments
-    x = np.array(args[0])  # make sure the imputs are in numpy array form
+    x = np.array(args[0])  # make sure the inputs are in numpy array form
     y = np.array(args[1])
 
     x_shape = x.shape
@@ -915,7 +915,7 @@ def _rm_histogram_2(*args):
         logging.warning("Invalid number of cells in Y dimension")
 
     if upperx <= lowerx:
-        logging.warning("Ivalid bounds in X dimension")
+        logging.warning("Invalid bounds in X dimension")
 
     if uppery <= lowery:
         logging.warning("Invalid bounds in Y dimension")

pyhctsa/operations/medical.py

@@ -271,7 +271,6 @@ def pol_var(x: ArrayLike, d: float = 1, D: int = 6) -> float:
     i = 0
     pc = 0
 
-    # seqcnt = 0
     while i <= (N-D):
         x_seq = x_sym[i:(i+D)]
         if np.array_equal(x_seq, z_seq) or np.array_equal(x_seq, o_seq):

pyhctsa/operations/model_fit.py

@@ -307,7 +307,7 @@ def local_simple(y: ArrayLike, forecast_meth: str = 'mean',
     Returns
     -------
     dict
-        Dictionary containing output statistics on the residuals of the simple fortecasting method. 
+        Dictionary containing output statistics on the residuals of the simple forecasting method. 
 
     """
     y = np.asarray(y)
@@ -316,7 +316,7 @@ def local_simple(y: ArrayLike, forecast_meth: str = 'mean',
     if train_length == 'ac':
         lp = first_crossing(y, 'ac', 0, 'discrete')
     else:
-        #the e length of the subsegment preceeding to use to predict the subsequent value
+        #the e length of the subsegment preceding to use to predict the subsequent value
         lp = train_length 
     evalr = np.arange(lp, N) #range over which to evaluate the forecast
     if np.size(evalr) == 0:

pyhctsa/operations/stationarity.py

@@ -55,14 +55,11 @@ def local_distributions(y: ArrayLike, num_segs: int = 5, each_or_par: str = 'par
         start_idx = i * lseg
         end_idx = (i + 1) * lseg
         segment_data = y[start_idx:end_idx]
-        #kde = KDEUnivariate(segment_data)
         kde = gaussian_kde(segment_data, bw_method="scott")
-        #kde.fit(bw="scott") # tune bw adjustment factor empiricially?
         dns[:, i] = kde.evaluate(r)
     # Compare the local distributions
     if each_or_par in ["par", "parent"]:
         #Compares each subdistribtuion to the parent (full signal) distribution
-        #kde = KDEUnivariate(y).fit(bw="scott")
         kde = gaussian_kde(y, bw_method="scott")
         pardn = kde.evaluate(r)
         divs = np.zeros(num_segs)
@@ -551,7 +548,7 @@ def range_evolve(y: ArrayLike) -> dict:
 
     fullr = np.ptp(y)
 
-    # return number of unqiue entries in a vector, x
+    # return number of unique entries in a vector, x
     lunique = lambda x : len(np.unique(x))
     out['totnuq'] = lunique(cums)
 
@@ -1081,7 +1078,7 @@ def sliding_window(y: ArrayLike, window_stat: str = 'mean', across_win_stat: str
     return out
 
 def _get_window(step_ind, inc, win_length):
-    # helper funtion to convert a step index (stepInd) to a range of indices corresponding to that window
+    # helper function to convert a step index (stepInd) to a range of indices corresponding to that window
     start_idx = (step_ind) * inc
     end_idx = (step_ind) * inc + win_length
 

pyhctsa/operations/symbolic.py

@@ -85,7 +85,7 @@ def surprise(y: ArrayLike, what_prior: str = 'dist', memory: float = 0.2, num_gr
             store[i] = p
         elif what_prior == 'T1':
             # uses one-point correlations in memory to inform the next point
-            # estimate transition probabilites from data in memory
+            # estimate transition probabilities from data in memory
             # find where in memory this has been observbed before, and preceded it
             memory_data = yth[rs[0, i] - memory:rs[0, i]]
             inmem = np.where(memory_data[:-1] == yth[rs[0, i] - 1])[0]
@@ -124,7 +124,7 @@ def surprise(y: ArrayLike, what_prior: str = 'dist', memory: float = 0.2, num_gr
         out['min'] = np.nan
 
     # Calculate statistics
-    out['max'] = np.max(store) # maximum amount of information you cna gain in this way
+    out['max'] = np.max(store) # maximum amount of information you can gain in this way
     out['mean'] = np.mean(store)
     out['sum'] = np.sum(store)
     out['median'] = np.median(store)
@@ -587,7 +587,7 @@ def transition_matrix(y: ArrayLike, how_to_cg: str = 'quantile',
     num_groups : int, optional
         number of groups in the course-graining. Default is 2.
     tau : int or str, optional
-        analyze transition matricies corresponding to this lag. We
+        analyze transition matrices corresponding to this lag. We
         could either downsample the time series at this lag and then do the
         discretization as normal, or do the discretization and then just
         look at this dicrete lag. Here we do the former. Can also set tau to 'ac'