From 857458c37c618863dbf198de86a5e54cc4a994d3 Mon Sep 17 00:00:00 2001
From: Hari Subbaraj <hari.subbaraj@gmail.com>
Date: Sat, 5 May 2018 21:25:42 -0700
Subject: [PATCH] [DataFrame] Implemented prod, product, added test suite
 (#1994)

* implemented prod/product, modified declaration for sum, added pandas test suite

* fixed tests

* removed test_analytics file

* implemented nunique, skew

* fixed requested changes

* added nunique, skew

* fixed tests in request

* added newline back

* fixed newlines hopefully

* fixed flake8 issues

* more flake8 issues

* fixed test for prod
---
 python/ray/dataframe/dataframe.py           | 49 ++++++++++++++++-----
 python/ray/dataframe/test/test_dataframe.py | 20 ++++-----
 2 files changed, 49 insertions(+), 20 deletions(-)

diff --git a/python/ray/dataframe/dataframe.py b/python/ray/dataframe/dataframe.py
index 4b640875a..b886691d5 100644
--- a/python/ray/dataframe/dataframe.py
+++ b/python/ray/dataframe/dataframe.py
@@ -646,7 +646,8 @@ class DataFrame(object):
         return DataFrameGroupBy(self, by, axis, level, as_index, sort,
                                 group_keys, squeeze, **kwargs)
 
-    def sum(self, axis=None, skipna=True, level=None, numeric_only=None):
+    def sum(self, axis=None, skipna=True, level=None, numeric_only=None,
+            min_count=1, **kwargs):
         """Perform a sum across the DataFrame.
 
         Args:
@@ -658,7 +659,8 @@ class DataFrame(object):
         """
         def remote_func(df):
             return df.sum(axis=axis, skipna=skipna, level=level,
-                          numeric_only=numeric_only)
+                          numeric_only=numeric_only, min_count=min_count,
+                          **kwargs)
 
         return self._arithmetic_helper(remote_func, axis, level)
 
@@ -3040,16 +3042,43 @@ class DataFrame(object):
                                      fill_value)
 
     def prod(self, axis=None, skipna=None, level=None, numeric_only=None,
-             min_count=0, **kwargs):
-        raise NotImplementedError(
-            "To contribute to Pandas on Ray, please visit "
-            "github.com/ray-project/ray.")
+             min_count=1, **kwargs):
+        """Return the product of the values for the requested axis
+
+        Args:
+            axis : {index (0), columns (1)}
+            skipna : boolean, default True
+            level : int or level name, default None
+            numeric_only : boolean, default None
+            min_count : int, default 1
+
+        Returns:
+            prod : Series or DataFrame (if level specified)
+        """
+        def remote_func(df):
+            return df.prod(axis=axis, skipna=skipna, level=level,
+                           numeric_only=numeric_only, min_count=min_count,
+                           **kwargs)
+
+        return self._arithmetic_helper(remote_func, axis, level)
 
     def product(self, axis=None, skipna=None, level=None, numeric_only=None,
-                min_count=0, **kwargs):
-        raise NotImplementedError(
-            "To contribute to Pandas on Ray, please visit "
-            "github.com/ray-project/ray.")
+                min_count=1, **kwargs):
+        """Return the product of the values for the requested axis
+
+        Args:
+            axis : {index (0), columns (1)}
+            skipna : boolean, default True
+            level : int or level name, default None
+            numeric_only : boolean, default None
+            min_count : int, default 1
+
+        Returns:
+            product : Series or DataFrame (if level specified)
+        """
+        return self.prod(axis=axis, skipna=skipna, level=level,
+                         numeric_only=numeric_only, min_count=min_count,
+                         **kwargs)
 
     def quantile(self, q=0.5, axis=0, numeric_only=True,
                  interpolation='linear'):
diff --git a/python/ray/dataframe/test/test_dataframe.py b/python/ray/dataframe/test/test_dataframe.py
index bf7e17daf..43d11b6b4 100644
--- a/python/ray/dataframe/test/test_dataframe.py
+++ b/python/ray/dataframe/test/test_dataframe.py
@@ -212,6 +212,8 @@ def test_int_dataframe():
 
     test_copy(ray_df)
     test_sum(ray_df, pandas_df)
+    test_prod(ray_df, pandas_df)
+    test_product(ray_df, pandas_df)
     test_abs(ray_df, pandas_df)
     test_keys(ray_df, pandas_df)
     test_transpose(ray_df, pandas_df)
@@ -376,6 +378,8 @@ def test_float_dataframe():
 
     test_copy(ray_df)
     test_sum(ray_df, pandas_df)
+    test_prod(ray_df, pandas_df)
+    test_product(ray_df, pandas_df)
     test_abs(ray_df, pandas_df)
     test_keys(ray_df, pandas_df)
     test_transpose(ray_df, pandas_df)
@@ -2347,18 +2351,14 @@ def test_pow():
     test_inter_df_math("pow", simple=False)
 
 
-def test_prod():
-    ray_df = create_test_dataframe()
-
-    with pytest.raises(NotImplementedError):
-        ray_df.prod(None)
+@pytest.fixture
+def test_prod(ray_df, pandas_df):
+    assert(ray_df.prod().equals(pandas_df.prod()))
 
 
-def test_product():
-    ray_df = create_test_dataframe()
-
-    with pytest.raises(NotImplementedError):
-        ray_df.product()
+@pytest.fixture
+def test_product(ray_df, pandas_df):
+    assert(ray_df.product().equals(pandas_df.product()))
 
 
 @pytest.fixture