rename X_approx_distribution to X_approximate_distribution (#2337)

backend/common/compute/diffexp_generic.py

@@ -1,6 +1,6 @@
 import numpy as np
 from scipy import sparse, stats
-from backend.common.constants import XApproxDistribution
+from backend.common.constants import XApproximateDistribution
 
 
 def diffexp_ttest(adaptor, maskA, maskB, top_n=8, diffexp_lfc_cutoff=0.01):
@@ -30,13 +30,13 @@ def diffexp_ttest(adaptor, maskA, maskB, top_n=8, diffexp_lfc_cutoff=0.01):
     :return:  for top N genes, {"positive": for top N genes, [ varindex, foldchange, pval, pval_adj ], "negative": for top N genes, [ varindex, foldchange, pval, pval_adj ]}
     """
 
-    X_approx_distribution = adaptor.get_X_approx_distribution()
+    X_approximate_distribution = adaptor.get_X_approximate_distribution()
     dataA = adaptor.get_X_array(maskA, None)
     dataB = adaptor.get_X_array(maskB, None)
 
     # mean, variance, N - calculate for both selections
-    meanA, vA, nA = mean_var_n(dataA, X_approx_distribution)
-    meanB, vB, nB = mean_var_n(dataB, X_approx_distribution)
+    meanA, vA, nA = mean_var_n(dataA, X_approximate_distribution)
+    meanB, vB, nB = mean_var_n(dataB, X_approximate_distribution)
     res = diffexp_ttest_from_mean_var(meanA, vA, nA, meanB, vB, nB, top_n, diffexp_lfc_cutoff)
 
     return res
@@ -113,7 +113,7 @@ def diffexp_ttest_from_mean_var(meanA, varA, nA, meanB, varB, nB, top_n, diffexp
 
 
 # Convenience function which handles sparse data
-def mean_var_n(X, X_approx_distribution=XApproxDistribution.NORMAL):
+def mean_var_n(X, X_approximate_distribution=XApproximateDistribution.NORMAL):
     """
     Two-pass variance calculation.  Numerically (more) stable
     than naive methods (and same method used by numpy.var())
@@ -131,14 +131,14 @@ def mean_var_n(X, X_approx_distribution=XApproxDistribution.NORMAL):
     with np.errstate(divide="call", invalid="call", call=fp_err_set):
         n = X.shape[0]
         if sparse.issparse(X):
-            if X_approx_distribution == XApproxDistribution.COUNT:
+            if X_approximate_distribution == XApproximateDistribution.COUNT:
                 X = X.log1p()
             mean = X.mean(axis=0).A1
             dfm = X - mean
             sumsq = np.sum(np.multiply(dfm, dfm), axis=0).A1
             v = sumsq / (n - 1)
         else:
-            if X_approx_distribution == XApproxDistribution.COUNT:
+            if X_approximate_distribution == XApproximateDistribution.COUNT:
                 X = np.log1p(X)
             mean = X.mean(axis=0)
             dfm = X - mean

backend/common/compute/estimate_distribution.py

@@ -2,7 +2,7 @@ import numba
 import concurrent.futures
 import numpy as np
 from scipy import sparse
-from backend.common.constants import XApproxDistribution
+from backend.common.constants import XApproximateDistribution
 
 
 @numba.njit(fastmath=True, error_model="numpy", nogil=True)
@@ -29,7 +29,7 @@ def min_max(arr):
     return min_val, max_val
 
 
-def estimate_approximate_distribution(X) -> XApproxDistribution:
+def estimate_approximate_distribution(X) -> XApproximateDistribution:
     """
     Estimate the distribution (normal, count) of the X matrix.
 
@@ -59,4 +59,4 @@ def estimate_approximate_distribution(X) -> XApproxDistribution:
         min_val, max_val = min_max(Xdata)
 
     excess_range = (max_val - min_val) > 24
-    return XApproxDistribution.COUNT if excess_range else XApproxDistribution.NORMAL
+    return XApproximateDistribution.COUNT if excess_range else XApproximateDistribution.NORMAL

backend/common/constants.py

@@ -24,7 +24,7 @@ class DiffExpMode(AugmentedEnum):
     VAR_FILTER = "varFilter"
 
 
-class XApproxDistribution(AugmentedEnum):
+class XApproximateDistribution(AugmentedEnum):
     NORMAL = "normal"
     COUNT = "count"