removing additional override of built-in parameter 'columns' with 'column_schema'

Author: Transurgeon

doc/source/getting_started/comparison/comparison_with_r.rst

@@ -133,8 +133,8 @@ with a combination of the ``iloc`` indexer attribute and ``numpy.r_``.
 
    named = list("abcdefg")
    n = 30
-   columns = named + np.arange(len(named), n).tolist()
-   df = pd.DataFrame(np.random.randn(n, n), columns=columns)
+   column_schema = named + np.arange(len(named), n).tolist()
+   df = pd.DataFrame(np.random.randn(n, n), columns=column_schema)
 
    df.iloc[:, np.r_[:10, 24:30]]
 

doc/source/user_guide/categorical.rst

@@ -626,12 +626,12 @@ even if some categories are not present in the data:
 
 .. ipython:: python
 
-    columns = pd.Categorical(
+    column_schema = pd.Categorical(
         ["One", "One", "Two"], categories=["One", "Two", "Three"], ordered=True
     )
     df = pd.DataFrame(
         data=[[1, 2, 3], [4, 5, 6]],
-        columns=pd.MultiIndex.from_arrays([["A", "B", "B"], columns]),
+        columns=pd.MultiIndex.from_arrays([["A", "B", "B"], column_schema]),
     )
     df.groupby(axis=1, level=1).sum()
 

doc/source/user_guide/cookbook.rst

@@ -1171,9 +1171,9 @@ Option 2: read column names and then data
 .. ipython:: python
 
     pd.read_csv(StringIO(data), sep=";", header=10, nrows=10).columns
-    columns = pd.read_csv(StringIO(data), sep=";", header=10, nrows=10).columns
+    column_schema = pd.read_csv(StringIO(data), sep=";", header=10, nrows=10).columns
     pd.read_csv(
-        StringIO(data), sep=";", index_col=0, header=12, parse_dates=True, names=columns
+        StringIO(data), sep=";", index_col=0, header=12, parse_dates=True, names=column_schema
     )
 
 

doc/source/user_guide/indexing.rst

@@ -1581,8 +1581,8 @@ The name, if set, will be shown in the console display:
 .. ipython:: python
 
    index = pd.Index(list(range(5)), name='rows')
-   columns = pd.Index(['A', 'B', 'C'], name='cols')
-   df = pd.DataFrame(np.random.randn(5, 3), index=index, columns=columns)
+   column_schema = pd.Index(['A', 'B', 'C'], name='cols')
+   df = pd.DataFrame(np.random.randn(5, 3), index=index, columns=column_schema)
    df
    df['A']
 

doc/source/user_guide/reshaping.rst

@@ -179,7 +179,7 @@ processed individually.
 
 .. ipython:: python
 
-    columns = pd.MultiIndex.from_tuples(
+    column_schema = pd.MultiIndex.from_tuples(
         [
             ("A", "cat", "long"),
             ("B", "cat", "long"),
@@ -188,7 +188,7 @@ processed individually.
         ],
         names=["exp", "animal", "hair_length"],
     )
-    df = pd.DataFrame(np.random.randn(4, 4), columns=columns)
+    df = pd.DataFrame(np.random.randn(4, 4), columns=column_schema)
     df
 
     df.stack(level=["animal", "hair_length"])
@@ -212,7 +212,7 @@ calling :meth:`~DataFrame.sort_index`, of course). Here is a more complex exampl
 
 .. ipython:: python
 
-   columns = pd.MultiIndex.from_tuples(
+   column_schema = pd.MultiIndex.from_tuples(
        [
            ("A", "cat"),
            ("B", "dog"),
@@ -224,7 +224,7 @@ calling :meth:`~DataFrame.sort_index`, of course). Here is a more complex exampl
    index = pd.MultiIndex.from_product(
        [("bar", "baz", "foo", "qux"), ("one", "two")], names=["first", "second"]
    )
-   df = pd.DataFrame(np.random.randn(8, 4), index=index, columns=columns)
+   df = pd.DataFrame(np.random.randn(8, 4), index=index, columns=column_schema)
    df2 = df.iloc[[0, 1, 2, 4, 5, 7]]
    df2
 

doc/source/user_guide/scale.rst

@@ -73,15 +73,15 @@ Option 1 loads in all the data and then filters to what we need.
 
 .. ipython:: python
 
-   columns = ["id_0", "name_0", "x_0", "y_0"]
+   column_schema = ["id_0", "name_0", "x_0", "y_0"]
 
-   pd.read_parquet("timeseries_wide.parquet")[columns]
+   pd.read_parquet("timeseries_wide.parquet")[column_schema]
 
 Option 2 only loads the columns we request.
 
 .. ipython:: python
 
-   pd.read_parquet("timeseries_wide.parquet", columns=columns)
+   pd.read_parquet("timeseries_wide.parquet", columns=column_schema)
 
 .. ipython:: python
    :suppress: