[DataFrame] Implements df.as_matrix (#2001)

* Implement df.as_matrix

* Addressing comments

* Addressing comments

python/ray/dataframe/dataframe.py

@@ -1189,9 +1189,17 @@ class DataFrame(object):
             "github.com/ray-project/ray.")
 
     def as_matrix(self, columns=None):
-        raise NotImplementedError(
-            "To contribute to Pandas on Ray, please visit "
-            "github.com/ray-project/ray.")
+        """Convert the frame to its Numpy-array representation.
+
+        Args:
+            columns: If None, return all columns, otherwise,
+                returns specified columns.
+
+        Returns:
+            values: ndarray
+        """
+        # TODO this is very inneficient, also see __array__
+        return to_pandas(self).as_matrix(columns)
 
     def asfreq(self, freq, method=None, how=None, normalize=False,
                fill_value=None):
@@ -4633,8 +4641,8 @@ class DataFrame(object):
             "github.com/ray-project/ray.")
 
     def __array__(self, dtype=None):
-        # TODO: This is very inefficient and needs fix
-        return np.array(to_pandas(self))
+        # TODO: This is very inefficient and needs fix, also see as_matrix
+        return to_pandas(self).__array__(dtype=dtype)
 
     def __array_wrap__(self, result, context=None):
         raise NotImplementedError(

python/ray/dataframe/test/test_dataframe.py

@@ -994,10 +994,31 @@ def test_as_blocks():
 
 
 def test_as_matrix():
-    ray_df = create_test_dataframe()
+    test_data = TestData()
+    frame = rdf.DataFrame(test_data.frame)
+    mat = frame.as_matrix()
 
-    with pytest.raises(NotImplementedError):
-        ray_df.as_matrix()
+    frame_columns = frame.columns
+    for i, row in enumerate(mat):
+        for j, value in enumerate(row):
+            col = frame_columns[j]
+            if np.isnan(value):
+                assert np.isnan(frame[col][i])
+            else:
+                assert value == frame[col][i]
+
+    # mixed type
+    mat = rdf.DataFrame(test_data.mixed_frame).as_matrix(['foo', 'A'])
+    assert mat[0, 0] == 'bar'
+
+    df = rdf.DataFrame({'real': [1, 2, 3], 'complex': [1j, 2j, 3j]})
+    mat = df.as_matrix()
+    assert mat[0, 0] == 1j
+
+    # single block corner case
+    mat = rdf.DataFrame(test_data.frame).as_matrix(['A', 'B'])
+    expected = test_data.frame.reindex(columns=['A', 'B']).values
+    tm.assert_almost_equal(mat, expected)
 
 
 def test_asfreq():