Utils: Introduce common dense/sparse operations

Author: nikicc

Orange/data/util.py

@@ -2,9 +2,58 @@
 Data-manipulation utilities.
 """
 import numpy as np
+import scipy.sparse as sp
 import bottleneck as bn
 
 
+def _nan_min_max(x, axis=0, func=None):
+    if not sp.issparse(x):
+        return func(x, axis=axis)
+    else:
+        r = []
+        if axis == 0:
+            x = x.T
+
+        # TODO check & transform to correct format
+
+        for row in x:
+            values = row.data
+            have_zeros = np.prod(row.shape) != values.size
+            extreme = func(values)
+            if have_zeros:
+                extreme = func([0, extreme])
+            r.append(extreme)
+        return np.array(r)
+
+
+def nan_min(x, axis):
+    return _nan_min_max(x, axis, np.nanmin)
+
+
+def nan_max(x, axis):
+    return _nan_min_max(x, axis, np.nanmax)
+
+
+def nan_average(x):
+    if not sp.issparse(x):
+        return np.average(x)
+    else:
+        n_values = np.prod(x.shape) - np.sum(np.isnan(x.data))
+        return np.nansum(x.data) / n_values
+
+
+def unique(x, return_counts=True):
+    if not sp.issparse(x):
+        return np.unique(x, return_counts=return_counts)
+    else:
+        n_zeros = np.prod(x.shape) - x.data.size
+        r = np.unique(x.data, return_counts=return_counts)
+        if return_counts:
+            return np.insert(r[0], 0, 0), np.insert(r[1], 0, n_zeros)
+        else:
+            return np.insert(r, 0, 0)
+
+
 def one_hot(values, dtype=float):
     """Return a one-hot transform of values