From 12d030b2932c30e8c30f6732a3dfac05c6f85250 Mon Sep 17 00:00:00 2001
From: Peter Veerman <peterkangveerman@gmail.com>
Date: Thu, 3 May 2018 10:06:48 -0700
Subject: [PATCH 1/3] Implement df.as_matrix

---
 python/ray/dataframe/dataframe.py           | 13 +++++++---
 python/ray/dataframe/test/test_dataframe.py | 27 ++++++++++++++++++---
 2 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/python/ray/dataframe/dataframe.py b/python/ray/dataframe/dataframe.py
index 5abd98f361bf..23cc43178e96 100644
--- a/python/ray/dataframe/dataframe.py
+++ b/python/ray/dataframe/dataframe.py
@@ -1189,9 +1189,16 @@ def as_blocks(self, copy=True):
             "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
+        """
+        return to_pandas(self).as_matrix(columns)
 
     def asfreq(self, freq, method=None, how=None, normalize=False,
                fill_value=None):
diff --git a/python/ray/dataframe/test/test_dataframe.py b/python/ray/dataframe/test/test_dataframe.py
index 7660b5366447..0e7f821453ba 100644
--- a/python/ray/dataframe/test/test_dataframe.py
+++ b/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()
+
+    frameCols = frame.columns
+    for i, row in enumerate(mat):
+        for j, value in enumerate(row):
+            col = frameCols[j]
+            if np.isnan(value):
+                assert np.isnan(frame[col][i])
+            else:
+                assert value == frame[col][i]
 
-    with pytest.raises(NotImplementedError):
-        ray_df.as_matrix()
+    # 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():

From 490b889d01e00379202010e0299001fcb055b55e Mon Sep 17 00:00:00 2001
From: Devin Petersohn <devin.petersohn@gmail.com>
Date: Sun, 6 May 2018 11:48:58 -0700
Subject: [PATCH 2/3] Addressing comments

---
 python/ray/dataframe/dataframe.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/python/ray/dataframe/dataframe.py b/python/ray/dataframe/dataframe.py
index 23cc43178e96..0aff85c7e3cc 100644
--- a/python/ray/dataframe/dataframe.py
+++ b/python/ray/dataframe/dataframe.py
@@ -1198,6 +1198,7 @@ def as_matrix(self, columns=None):
         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,
@@ -4595,8 +4596,8 @@ def __round__(self, decimals=0):
             "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(

From 6ec0bbae757f95a076b122962b187a8e7b38048a Mon Sep 17 00:00:00 2001
From: Devin Petersohn <devin.petersohn@gmail.com>
Date: Sun, 6 May 2018 18:53:15 -0700
Subject: [PATCH 3/3] Addressing comments

---
 python/ray/dataframe/test/test_dataframe.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/python/ray/dataframe/test/test_dataframe.py b/python/ray/dataframe/test/test_dataframe.py
index 0e7f821453ba..81cf5882cb08 100644
--- a/python/ray/dataframe/test/test_dataframe.py
+++ b/python/ray/dataframe/test/test_dataframe.py
@@ -998,10 +998,10 @@ def test_as_matrix():
     frame = rdf.DataFrame(test_data.frame)
     mat = frame.as_matrix()
 
-    frameCols = frame.columns
+    frame_columns = frame.columns
     for i, row in enumerate(mat):
         for j, value in enumerate(row):
-            col = frameCols[j]
+            col = frame_columns[j]
             if np.isnan(value):
                 assert np.isnan(frame[col][i])
             else: