MRG: implementing / testing get_fdata

nibabel/dataobj_images.py

@@ -41,6 +41,7 @@ def __init__(self, dataobj, header=None, extra=None, file_map=None):
         super(DataobjImage, self).__init__(header=header, extra=extra,
                                            file_map=file_map)
         self._dataobj = dataobj
+        self._fdata_cache = None
         self._data_cache = None
 
     @property
@@ -55,7 +56,19 @@ def _data(self):
         return self._dataobj
 
     def get_data(self, caching='fill'):
-        """ Return image data from image with any necessary scalng applied
+        """ Return image data from image with any necessary scaling applied
+
+        .. WARNING::
+
+            We recommend you use the ``get_fdata`` method instead of the
+            ``get_data`` method, because it is easier to predict the return
+            data type.  We will deprecate the ``get_data`` method around April
+            2018, and remove it around April 2020.
+
+            If you don't care about the predictability of the return data type,
+            and you want the minimum possible data size in memory, you can
+            replicate the array that would be returned by ``img.get_data()`` by
+            using ``np.asanyarray(img.dataobj)``.
 
         The image ``dataobj`` property can be an array proxy or an array.  An
         array proxy is an object that knows how to load the image data from
@@ -125,7 +138,7 @@ def get_data(self, caching='fill'):
         (no reference to the array).  If the cache is full, "unchanged" leaves
         the cache full and returns the cached array reference.
 
-        The cache can effect the behavior of the image, because if the cache is
+        The cache can affect the behavior of the image, because if the cache is
         full, or you have an array image, then modifying the returned array
         will modify the result of future calls to ``get_data()``.  For example
         you might do this:
@@ -191,11 +204,160 @@ def get_data(self, caching='fill'):
             self._data_cache = data
         return data
 
+    def get_fdata(self, caching='fill', dtype=np.float64):
+        """ Return floating point image data with necessary scaling applied
+
+        The image ``dataobj`` property can be an array proxy or an array.  An
+        array proxy is an object that knows how to load the image data from
+        disk.  An image with an array proxy ``dataobj`` is a *proxy image*; an
+        image with an array in ``dataobj`` is an *array image*.
+
+        The default behavior for ``get_fdata()`` on a proxy image is to read
+        the data from the proxy, and store in an internal cache.  Future calls
+        to ``get_fdata`` will return the cached array.  This is the behavior
+        selected with `caching` == "fill".
+
+        Once the data has been cached and returned from an array proxy, if you
+        modify the returned array, you will also modify the cached array
+        (because they are the same array).  Regardless of the `caching` flag,
+        this is always true of an array image.
+
+        Parameters
+        ----------
+        caching : {'fill', 'unchanged'}, optional
+            See the Notes section for a detailed explanation.  This argument
+            specifies whether the image object should fill in an internal
+            cached reference to the returned image data array. "fill" specifies
+            that the image should fill an internal cached reference if
+            currently empty.  Future calls to ``get_fdata`` will return this
+            cached reference.  You might prefer "fill" to save the image object
+            from having to reload the array data from disk on each call to
+            ``get_fdata``.  "unchanged" means that the image should not fill in
+            the internal cached reference if the cache is currently empty.  You
+            might prefer "unchanged" to "fill" if you want to make sure that
+            the call to ``get_fdata`` does not create an extra (cached)
+            reference to the returned array.  In this case it is easier for
+            Python to free the memory from the returned array.
+        dtype : numpy dtype specifier
+            A numpy dtype specifier specifying a floating point type.  Data is
+            returned as this floating point type.  Default is ``np.float64``.
+
+        Returns
+        -------
+        fdata : array
+            Array of image data of data type `dtype`.
+
+        See also
+        --------
+        uncache: empty the array data cache
+
+        Notes
+        -----
+        All images have a property ``dataobj`` that represents the image array
+        data.  Images that have been loaded from files usually do not load the
+        array data from file immediately, in order to reduce image load time
+        and memory use.  For these images, ``dataobj`` is an *array proxy*; an
+        object that knows how to load the image array data from file.
+
+        By default (`caching` == "fill"), when you call ``get_fdata`` on a
+        proxy image, we load the array data from disk, store (cache) an
+        internal reference to this array data, and return the array.  The next
+        time you call ``get_fdata``, you will get the cached reference to the
+        array, so we don't have to load the array data from disk again.
+
+        Array images have a ``dataobj`` property that already refers to an
+        array in memory, so there is no benefit to caching, and the `caching`
+        keywords have no effect.
+
+        For proxy images, you may not want to fill the cache after reading the
+        data from disk because the cache will hold onto the array memory until
+        the image object is deleted, or you use the image ``uncache`` method.
+        If you don't want to fill the cache, then always use
+        ``get_fdata(caching='unchanged')``; in this case ``get_fdata`` will not
+        fill the cache (store the reference to the array) if the cache is empty
+        (no reference to the array).  If the cache is full, "unchanged" leaves
+        the cache full and returns the cached array reference.
+
+        The cache can effect the behavior of the image, because if the cache is
+        full, or you have an array image, then modifying the returned array
+        will modify the result of future calls to ``get_fdata()``.  For example
+        you might do this:
+
+        >>> import os
+        >>> import nibabel as nib
+        >>> from nibabel.testing import data_path
+        >>> img_fname = os.path.join(data_path, 'example4d.nii.gz')
+
+        >>> img = nib.load(img_fname) # This is a proxy image
+        >>> nib.is_proxy(img.dataobj)
+        True
+
+        The array is not yet cached by a call to "get_fdata", so:
+
+        >>> img.in_memory
+        False
+
+        After we call ``get_fdata`` using the default `caching` == 'fill', the
+        cache contains a reference to the returned array ``data``:
+
+        >>> data = img.get_fdata()
+        >>> img.in_memory
+        True
+
+        We modify an element in the returned data array:
+
+        >>> data[0, 0, 0, 0]
+        0.0
+        >>> data[0, 0, 0, 0] = 99
+        >>> data[0, 0, 0, 0]
+        99.0
+
+        The next time we call 'get_fdata', the method returns the cached
+        reference to the (modified) array:
+
+        >>> data_again = img.get_fdata()
+        >>> data_again is data
+        True
+        >>> data_again[0, 0, 0, 0]
+        99.0
+
+        If you had *initially* used `caching` == 'unchanged' then the returned
+        ``data`` array would have been loaded from file, but not cached, and:
+
+        >>> img = nib.load(img_fname)  # a proxy image again
+        >>> data = img.get_fdata(caching='unchanged')
+        >>> img.in_memory
+        False
+        >>> data[0, 0, 0] = 99
+        >>> data_again = img.get_fdata(caching='unchanged')
+        >>> data_again is data
+        False
+        >>> data_again[0, 0, 0, 0]
+        0.0
+        """
+        if caching not in ('fill', 'unchanged'):
+            raise ValueError('caching value should be "fill" or "unchanged"')
+        dtype = np.dtype(dtype)
+        if not issubclass(dtype.type, np.inexact):
+            raise ValueError('{} should be floating point type'.format(dtype))
+        # Return cache if cache present and of correct dtype.
+        if self._fdata_cache is not None:
+            if self._fdata_cache.dtype.type == dtype.type:
+                return self._fdata_cache
+        data = np.asanyarray(self._dataobj).astype(dtype)
+        if caching == 'fill':
+            self._fdata_cache = data
+        return data
+
     @property
     def in_memory(self):
-        """ True when array data is in memory
+        """ True when any array data is in memory cache
+
+        There are separate caches for `get_data` reads and `get_fdata` reads.
+        This property is True if either of those caches are set.
         """
         return (isinstance(self._dataobj, np.ndarray) or
+                self._fdata_cache is not None or
                 self._data_cache is not None)
 
     def uncache(self):
@@ -206,23 +368,24 @@ def uncache(self):
         * *array images* where the data ``img.dataobj`` is an array
         * *proxy images* where the data ``img.dataobj`` is a proxy object
 
-        If you call ``img.get_data()`` on a proxy image, the result of reading
+        If you call ``img.get_fdata()`` on a proxy image, the result of reading
         from the proxy gets cached inside the image object, and this cache is
-        what gets returned from the next call to ``img.get_data()``.  If you
+        what gets returned from the next call to ``img.get_fdata()``.  If you
         modify the returned data, as in::
 
-            data = img.get_data()
+            data = img.get_fdata()
             data[:] = 42
 
-        then the next call to ``img.get_data()`` returns the modified array,
+        then the next call to ``img.get_fdata()`` returns the modified array,
         whether the image is an array image or a proxy image::
 
-            assert np.all(img.get_data() == 42)
+            assert np.all(img.get_fdata() == 42)
 
         When you uncache an array image, this has no effect on the return of
-        ``img.get_data()``, but when you uncache a proxy image, the result of
-        ``img.get_data()`` returns to its original value.
+        ``img.get_fdata()``, but when you uncache a proxy image, the result of
+        ``img.get_fdata()`` returns to its original value.
         """
+        self._fdata_cache = None
         self._data_cache = None
 
     @property

nibabel/tests/test_filebasedimages.py

@@ -29,6 +29,9 @@ def shape(self):
     def get_data(self):
         return self.arr
 
+    def get_fdata(self):
+        return self.arr.astype(np.float64)
+
     @classmethod
     def from_file_map(klass, file_map):
         with file_map['image'].get_prepare_fileobj('rb') as fobj: