Merge pull request #8369 from anntzer/hist-reuses-_reshape_2D

dstansby · web-flow · commit 73d2ea019a14 · 2017-03-25T15:51:49.000Z
Use cbook._reshape_2D in hist.
diff --git a/lib/matplotlib/axes/_axes.py b/lib/matplotlib/axes/_axes.py
@@ -6109,41 +6109,6 @@ def hist(self, x, bins=None, range=None, normed=False, weights=None,
         bin_range = range
         del range
 
-        def _normalize_input(inp, ename='input'):
-            """Normalize 1 or 2d input into list of np.ndarray or
-            a single 2D np.ndarray.
-
-            Parameters
-            ----------
-            inp : iterable
-            ename : str, optional
-                Name to use in ValueError if `inp` can not be normalized
-
-            """
-            if (isinstance(x, np.ndarray) or
-                    not iterable(cbook.safe_first_element(inp))):
-                # TODO: support masked arrays;
-                inp = np.asarray(inp)
-                if inp.ndim == 2:
-                    # 2-D input with columns as datasets; switch to rows
-                    inp = inp.T
-                elif inp.ndim == 1:
-                    # new view, single row
-                    inp = inp.reshape(1, inp.shape[0])
-                else:
-                    raise ValueError(
-                        "{ename} must be 1D or 2D".format(ename=ename))
-                if inp.shape[1] < inp.shape[0]:
-                    warnings.warn(
-                        '2D hist input should be nsamples x nvariables;\n '
-                        'this looks transposed '
-                        '(shape is %d x %d)' % inp.shape[::-1])
-            else:
-                # multiple hist with data of different length
-                inp = [np.asarray(xi) for xi in inp]
-
-            return inp
-
         if not self._hold:
             self.cla()
 
@@ -6178,20 +6143,18 @@ def _normalize_input(inp, ename='input'):
         binsgiven = (cbook.iterable(bins) or bin_range is not None)
 
         # basic input validation
-        flat = np.ravel(x)
-
-        input_empty = len(flat) == 0
+        input_empty = np.size(x) == 0
 
         # Massage 'x' for processing.
         if input_empty:
             x = np.array([[]])
         else:
-            x = _normalize_input(x, 'x')
+            x = cbook._reshape_2D(x, 'x')
         nx = len(x)  # number of datasets
 
         # We need to do to 'weights' what was done to 'x'
         if weights is not None:
-            w = _normalize_input(weights, 'weights')
+            w = cbook._reshape_2D(weights, 'weights')
         else:
             w = [None]*nx
 
diff --git a/lib/matplotlib/cbook/__init__.py b/lib/matplotlib/cbook/__init__.py
@@ -1744,7 +1744,7 @@ def _compute_conf_interval(data, med, iqr, bootstrap):
     bxpstats = []
 
     # convert X to a list of lists
-    X = _reshape_2D(X)
+    X = _reshape_2D(X, "X")
 
     ncols = len(X)
     if labels is None:
@@ -1974,14 +1974,16 @@ def _check_1d(x):
             return np.atleast_1d(x)
 
 
-def _reshape_2D(X):
+def _reshape_2D(X, name):
     """
-    Converts a non-empty list or an ndarray of two or fewer dimensions
-    into a list of iterable objects so that in
+    Use Fortran ordering to convert ndarrays and lists of iterables to lists of
+    1D arrays.
 
-        for v in _reshape_2D(X):
+    Lists of iterables are converted by applying `np.asarray` to each of their
+    elements.  1D ndarrays are returned in a singleton list containing them.
+    2D ndarrays are converted to the list of their *columns*.
 
-    v is iterable and can be used to instantiate a 1D array.
+    *name* is used to generate the error message for invalid inputs.
     """
     # Iterate over columns for ndarrays, over rows otherwise.
     X = X.T if isinstance(X, np.ndarray) else np.asarray(X)
@@ -1992,7 +1994,7 @@ def _reshape_2D(X):
         # 2D array, or 1D array of iterables: flatten them first.
         return [np.reshape(x, -1) for x in X]
     else:
-        raise ValueError("input `X` must have 2 or fewer dimensions")
+        raise ValueError("{} must have 2 or fewer dimensions".format(name))
 
 
 def violin_stats(X, method, points=100):
@@ -2039,7 +2041,7 @@ def violin_stats(X, method, points=100):
     vpstats = []
 
     # Want X to be a list of data sequences
-    X = _reshape_2D(X)
+    X = _reshape_2D(X, "X")
 
     for x in X:
         # Dictionary of results for this distribution
