Merge pull request #978 from nouiz/sparse

theano/sparse/__init__.py

@@ -13,6 +13,8 @@ except ImportError:
     sys.stderr.write("WARNING: scipy can't be imported."
             " We disable the sparse matrix code.")
 
+from type import *
+
 if enable_sparse:
     from basic import *
     import opt

theano/sparse/basic.py

@@ -19,6 +19,7 @@ from theano.gradient import DisconnectedType
 from theano.sparse.utils import hash_from_sparse
 import theano.tests.unittest_tools as utt
 from theano.gradient import grad_not_implemented
+from theano.sparse.type import SparseType, _is_sparse
 
 sparse_formats = ['csc', 'csr']
 
@@ -64,19 +65,6 @@ def _is_dense_variable(x):
     return isinstance(x.type, tensor.TensorType)
 
 
-def _is_sparse(x):
-    """
-    @rtype: boolean
-    @return: True iff x is a L{scipy.sparse.spmatrix} (and not a
-    L{numpy.ndarray})
-    """
-    if not isinstance(x, (scipy.sparse.spmatrix, numpy.ndarray)):
-        raise NotImplementedError("this function should only be called on "
-                                  "sparse.scipy.sparse.spmatrix or "
-                                  "numpy.ndarray, not,", x)
-    return isinstance(x, scipy.sparse.spmatrix)
-
-
 def _is_dense(x):
     """
     @rtype: boolean
@@ -396,130 +384,8 @@ class SparseConstant(gof.Constant, _sparse_py_operators):
         return str(self)
 
 
-class SparseType(gof.Type):
-    """
-    @type dtype: numpy dtype string such as 'int64' or 'float64' (among others)
-    @type format: string
-    @ivar format: The sparse storage strategy.
-
-    @note As far as I can tell, L{scipy.sparse} objects must be matrices, i.e.
-    have dimension 2.
-    """
-    format_cls = {'csr': scipy.sparse.csr_matrix,
-                  'csc': scipy.sparse.csc_matrix}
-    dtype_set = set(['int8', 'int16', 'int32', 'int64', 'float32',
-                     'uint8', 'uint16', 'uint32', 'uint64',
-                     'float64', 'complex64', 'complex128'])
-    ndim = 2
-
-    Variable = SparseVariable
-    Constant = SparseConstant
-
-    def __init__(self, format, dtype):
-        """
-        Fundamental way to create a sparse node.
-        @param dtype:   Type of numbers in the matrix.
-        @param format:  The sparse storage strategy.
-        @return         An empty SparseVariable instance.
-        """
-        dtype = str(dtype)
-        if dtype in self.dtype_set:
-            self.dtype = dtype
-        else:
-            raise NotImplementedError('unsupported dtype "%s" not in list' %
-                                      dtype, list(self.dtype_set))
-
-        assert isinstance(format, basestring)
-        if format in self.format_cls:
-            self.format = format
-        else:
-            raise NotImplementedError('unsupported format "%s" not in list' %
-                                      format, self.format_cls.keys())
-
-    def filter(self, value, strict=False, allow_downcast=None):
-        if isinstance(value, self.format_cls[self.format])\
-                and value.dtype == self.dtype:
-            return value
-        if strict:
-            raise TypeError("%s is not sparse, or not the right dtype (is %s, "
-                            "expected %s)" % (value, value.dtype, self.dtype))
-        # The input format could be converted here
-        if allow_downcast:
-            sp = self.format_cls[self.format](value, dtype=self.dtype)
-        else:
-            sp = self.format_cls[self.format](value)
-            if str(sp.dtype) != self.dtype:
-                raise NotImplementedError("Expected %s dtype but got %s" %
-                                          (self.dtype, str(sp.dtype)))
-        if sp.format != self.format:
-            raise NotImplementedError()
-        return sp
-
-    @staticmethod
-    def may_share_memory(a, b):
-        # This is Fred suggestion for a quick and dirty way of checking
-        # aliasing .. this can potentially be further refined (ticket #374)
-        if _is_sparse(a) and _is_sparse(b):
-            return (SparseType.may_share_memory(a, b.data) or
-                    SparseType.may_share_memory(a, b.indices) or
-                    SparseType.may_share_memory(a, b.indptr))
-        if _is_sparse(b) and isinstance(a, numpy.ndarray):
-            a, b = b, a
-        if _is_sparse(a) and isinstance(b, numpy.ndarray):
-            if (numpy.may_share_memory(a.data, b) or
-                numpy.may_share_memory(a.indices, b) or
-                numpy.may_share_memory(a.indptr, b)):
-                # currently we can't share memory with a.shape as it is a tuple
-                return True
-        return False
-
-    def make_variable(self, name=None):
-        return SparseVariable(self, name=name)
-
-    def __eq__(self, other):
-        return (type(self) == type(other) and other.dtype == self.dtype and
-                other.format == self.format)
-
-    def __hash__(self):
-        return hash(self.dtype) ^ hash(self.format)
-
-    def __str__(self):
-        return "Sparse[%s, %s]" % (str(self.dtype), str(self.format))
-
-    def __repr__(self):
-        return "Sparse[%s, %s]" % (str(self.dtype), str(self.format))
-
-    def values_eq_approx(self, a, b, eps=1e-6):
-        # WARNING: equality comparison of sparse matrices is not fast or easy
-        # we definitely do not want to be doing this un-necessarily during
-        # a FAST_RUN computation..
-        if not scipy.sparse.issparse(a) or not scipy.sparse.issparse(b):
-            return False
-        diff = abs(a - b)
-        if diff.nnz == 0:
-            return True
-        # Built-in max from python is not implemented for sparse matrix as a
-        # reduction. It returns a sparse matrix wich cannot be compared to a
-        # scalar. When comparing sparse to scalar, no exceptions is raised and
-        # the returning value is not consistent. That is why it is apply to a
-        # numpy.ndarray.
-        return max(diff.data) < eps
-
-    def values_eq(self, a, b):
-        # WARNING: equality comparison of sparse matrices is not fast or easy
-        # we definitely do not want to be doing this un-necessarily during
-        # a FAST_RUN computation..
-        return scipy.sparse.issparse(a) \
-                and scipy.sparse.issparse(b) \
-                and abs(a - b).sum() == 0.0
-
-    def is_valid_value(self, a):
-        return scipy.sparse.issparse(a) and (a.format == self.format)
-
-# Register CudaNdarrayType to the OutputGuard list of known types
-# to have OutputGuard generate C code for this type.
-theano.compile.mode.register_OutputGuard_c_code(SparseType)
-
+SparseType.Variable = SparseVariable
+SparseType.Constant = SparseConstant
 
 # for more dtypes, call SparseType(format, dtype)
 def matrix(format, name=None, dtype=None):

theano/sparse/type.py

+import numpy
+try:
+    import scipy
+    imported_scipy = True
+except ImportError:
+    imported_scipy = False
+
+import theano
+from theano import gof
+
+def _is_sparse(x):
+    """
+    @rtype: boolean
+    @return: True iff x is a L{scipy.sparse.spmatrix} (and not a
+    L{numpy.ndarray})
+    """
+    if not isinstance(x, (scipy.sparse.spmatrix, numpy.ndarray)):
+        raise NotImplementedError("this function should only be called on "
+                                  "sparse.scipy.sparse.spmatrix or "
+                                  "numpy.ndarray, not,", x)
+    return isinstance(x, scipy.sparse.spmatrix)
+
+
+class SparseType(gof.Type):
+    """
+    @type dtype: numpy dtype string such as 'int64' or 'float64' (among others)
+    @type format: string
+    @ivar format: The sparse storage strategy.
+
+    @note As far as I can tell, L{scipy.sparse} objects must be matrices, i.e.
+    have dimension 2.
+    """
+    if imported_scipy:
+        format_cls = {'csr': scipy.sparse.csr_matrix,
+                      'csc': scipy.sparse.csc_matrix}
+    dtype_set = set(['int8', 'int16', 'int32', 'int64', 'float32',
+                     'uint8', 'uint16', 'uint32', 'uint64',
+                     'float64', 'complex64', 'complex128'])
+    ndim = 2
+
+    # Will be set to SparseVariable SparseConstant later.
+    Variable = None
+    Constant = None
+
+    def __init__(self, format, dtype):
+        """
+        Fundamental way to create a sparse node.
+        @param dtype:   Type of numbers in the matrix.
+        @param format:  The sparse storage strategy.
+        @return         An empty SparseVariable instance.
+        """
+        if not imported_scipy:
+            raise Exception("You can't make SparseType object as SciPy"
+                            " is not available.")
+        dtype = str(dtype)
+        if dtype in self.dtype_set:
+            self.dtype = dtype
+        else:
+            raise NotImplementedError('unsupported dtype "%s" not in list' %
+                                      dtype, list(self.dtype_set))
+
+        assert isinstance(format, basestring)
+        if format in self.format_cls:
+            self.format = format
+        else:
+            raise NotImplementedError('unsupported format "%s" not in list' %
+                                      format, self.format_cls.keys())
+
+    def filter(self, value, strict=False, allow_downcast=None):
+        if isinstance(value, self.format_cls[self.format])\
+                and value.dtype == self.dtype:
+            return value
+        if strict:
+            raise TypeError("%s is not sparse, or not the right dtype (is %s, "
+                            "expected %s)" % (value, value.dtype, self.dtype))
+        # The input format could be converted here
+        if allow_downcast:
+            sp = self.format_cls[self.format](value, dtype=self.dtype)
+        else:
+            sp = self.format_cls[self.format](value)
+            if str(sp.dtype) != self.dtype:
+                raise NotImplementedError("Expected %s dtype but got %s" %
+                                          (self.dtype, str(sp.dtype)))
+        if sp.format != self.format:
+            raise NotImplementedError()
+        return sp
+
+    @staticmethod
+    def may_share_memory(a, b):
+        # This is Fred suggestion for a quick and dirty way of checking
+        # aliasing .. this can potentially be further refined (ticket #374)
+        if _is_sparse(a) and _is_sparse(b):
+            return (SparseType.may_share_memory(a, b.data) or
+                    SparseType.may_share_memory(a, b.indices) or
+                    SparseType.may_share_memory(a, b.indptr))
+        if _is_sparse(b) and isinstance(a, numpy.ndarray):
+            a, b = b, a
+        if _is_sparse(a) and isinstance(b, numpy.ndarray):
+            if (numpy.may_share_memory(a.data, b) or
+                numpy.may_share_memory(a.indices, b) or
+                numpy.may_share_memory(a.indptr, b)):
+                # currently we can't share memory with a.shape as it is a tuple
+                return True
+        return False
+
+    def make_variable(self, name=None):
+        return self.Variable(self, name=name)
+
+    def __eq__(self, other):
+        return (type(self) == type(other) and other.dtype == self.dtype and
+                other.format == self.format)
+
+    def __hash__(self):
+        return hash(self.dtype) ^ hash(self.format)
+
+    def __str__(self):
+        return "Sparse[%s, %s]" % (str(self.dtype), str(self.format))
+
+    def __repr__(self):
+        return "Sparse[%s, %s]" % (str(self.dtype), str(self.format))
+
+    def values_eq_approx(self, a, b, eps=1e-6):
+        # WARNING: equality comparison of sparse matrices is not fast or easy
+        # we definitely do not want to be doing this un-necessarily during
+        # a FAST_RUN computation..
+        if not scipy.sparse.issparse(a) or not scipy.sparse.issparse(b):
+            return False
+        diff = abs(a - b)
+        if diff.nnz == 0:
+            return True
+        # Built-in max from python is not implemented for sparse matrix as a
+        # reduction. It returns a sparse matrix wich cannot be compared to a
+        # scalar. When comparing sparse to scalar, no exceptions is raised and
+        # the returning value is not consistent. That is why it is apply to a
+        # numpy.ndarray.
+        return max(diff.data) < eps
+
+    def values_eq(self, a, b):
+        # WARNING: equality comparison of sparse matrices is not fast or easy
+        # we definitely do not want to be doing this un-necessarily during
+        # a FAST_RUN computation..
+        return scipy.sparse.issparse(a) \
+                and scipy.sparse.issparse(b) \
+                and abs(a - b).sum() == 0.0
+
+    def is_valid_value(self, a):
+        return scipy.sparse.issparse(a) and (a.format == self.format)
+
+# Register CudaNdarrayType to the OutputGuard list of known types
+# to have OutputGuard generate C code for this type.
+theano.compile.mode.register_OutputGuard_c_code(SparseType)