Remove debugging prints and add a test for prints (#768)

* Remove debugging prints and add a test for prints

* No longer should we merge PRs that contain debugging prints
* Cleans up several test files where prints were left
* Add a test `grep`ing for print statements

Fix bash script

Update script

Remove travis file

* Add print check to lint testing

* Only check package files (non-stress test files) for prints

.github/workflows/ci.yml

@@ -25,8 +25,8 @@ jobs:
         with:
           python-version: '3.7.x'
           architecture: 'x64'
-      - run: pip install flake8
-      - run: flake8 .
+      - run: pip install flake8 flake8-print
+      - run: flake8 --enable=T modin
   test-all:
     needs: [lint-flake8, lint-black]
     runs-on: ubuntu-latest

modin/pandas/base.py

@@ -3280,7 +3280,6 @@ def compute_offset(value):
             if key.start is None:
                 return self.head(compute_offset(key.stop))
             elif key.stop is None:
-                print(compute_offset(-key.start))
                 return self.tail(compute_offset(-key.start))
             return self.head(compute_offset(key.stop)).tail(compute_offset(-key.start))
         # We convert to a RangeIndex because getitem_row_array is expecting a list

modin/pandas/test/performance-tests/test_performance.py

@@ -25,7 +25,6 @@
 # def test_read_csv(benchmark):
 #     path = "~/Downloads/201710k.csv"
 #     result = benchmark(pd.read_csv, path)
-#     print(result)
 
 
 def test_sum(benchmark):

modin/pandas/test/test_api.py

@@ -82,7 +82,6 @@ def test_dataframe_api_equality():
     ignore = ["timetuple"]
     missing_from_modin = set(pandas_dir) - set(modin_dir)
     assert not len(missing_from_modin - set(ignore))
-
     assert not len(set(modin_dir) - set(pandas_dir))
 
     # These have to be checked manually
@@ -134,15 +133,13 @@ def test_series_api_equality():
     ignore = ["timetuple"]
     missing_from_modin = set(pandas_dir) - set(modin_dir)
     assert not len(missing_from_modin - set(ignore)), missing_from_modin
-
     assert not len(set(modin_dir) - set(pandas_dir)), set(modin_dir) - set(pandas_dir)
 
     # These have to be checked manually
     allowed_different = ["to_hdf", "hist"]
     difference = []
 
     for m in modin_dir:
-        print(m)
         if m in allowed_different:
             continue
         try:
@@ -174,6 +171,4 @@ def test_series_api_equality():
                     difference.append(append_val)
             except IndexError:
                 pass
-
-    print(difference)
     assert not len(difference), "Differences found in API: {}".format(difference)

modin/pandas/test/test_series.py

@@ -1685,7 +1685,6 @@ def test_loc(data):
     modin_series, pandas_series = create_test_series(data)
     for v in modin_series.index:
         df_equals(modin_series.loc[v], pandas_series.loc[v])
-        print(v)
         df_equals(modin_series.loc[v:], pandas_series.loc[v:])
 
     indices = [True if i % 3 == 0 else False for i in range(len(modin_series.index))]

modin/pandas/test/utils.py

@@ -348,8 +348,6 @@ def df_equals(df1, df2):
         assert df1.dtypes == df2.dtypes
     else:
         if df1 != df2:
-            print(df1)
-            print(df2)
             np.testing.assert_almost_equal(df1, df2)
 
 

modin/sql/connection.py

@@ -30,7 +30,7 @@ def execute(self, query):
             self._insert_into(split_query)
         else:
             raise NotImplementedError(
-                "This API is for demonstration purposes " "only. Coming Soon!"
+                "This API is for demonstration purposes only. Coming Soon!"
             )
 
     def _create_table(self, split_query):
@@ -45,7 +45,6 @@ def _insert_into(self, split_query):
         values = " ".join(split_query[4:]).replace("(", "").replace(")", "").split(", ")
         to_append = Series([eval(i) for i in values], index=table.columns)
         self._tables[split_query[2]] = table.append(to_append, ignore_index=True)
-        print(self._tables[split_query[2]])
 
 
 def connect(name):