Merge dev into samukweku/refactor_expand_grid

janitor/functions/__init__.py

@@ -2,18 +2,18 @@
 # General Functions
 
 pyjanitor's general-purpose data cleaning functions.
+"""
 
-NOTE: Instructions for future contributors:
+# NOTE: Instructions for future contributors:
 
-1. Place the source code of the functions in a file named after the function.
-2. Place utility functions in the same file.
-3. If you use a utility function from another source file,
-please refactor it out to `janitor.functions.utils`.
-4. Import the function into this file so that it shows up in the top-level API.
-5. Sort the imports in alphabetical order.
-6. Try to group related functions together (e.g. see `convert_date.py`)
-7. Never import utils.
-"""
+# 1. Place the source code of the functions in a file named after the function.
+# 2. Place utility functions in the same file.
+# 3. If you use a utility function from another source file,
+# please refactor it out to `janitor.functions.utils`.
+# 4. Import the function into this file so that it shows up in the top-level API.
+# 5. Sort the imports in alphabetical order.
+# 6. Try to group related functions together (e.g. see `convert_date.py`)
+# 7. Never import utils.
 
 from .add_columns import add_columns
 from .also import also
@@ -65,7 +65,14 @@
 from .reorder_columns import reorder_columns
 from .round_to_fraction import round_to_fraction
 from .row_to_names import row_to_names
-from .select import select, select_columns, select_rows
+from .select import (
+    DropLabel,
+    get_columns,
+    get_index_labels,
+    select,
+    select_columns,
+    select_rows,
+)
 from .shuffle import shuffle
 from .sort_column_value_order import sort_column_value_order
 from .sort_naturally import sort_naturally
@@ -77,11 +84,6 @@
 from .truncate_datetime import truncate_datetime_dataframe
 from .update_where import update_where
 from .utils import (
-    DropLabel,
-    col,
-    get_columns,
-    get_index_labels,
-    patterns,
     unionize_dataframe_categories,
 )
 
@@ -158,10 +160,8 @@
     "transform_columns",
     "truncate_datetime_dataframe",
     "update_where",
-    "patterns",
     "unionize_dataframe_categories",
     "DropLabel",
     "get_index_labels",
-    "col",
     "get_columns",
 ]

janitor/functions/clean_names.py

@@ -9,7 +9,8 @@
 from pandas.api.types import is_scalar
 
 from janitor.errors import JanitorError
-from janitor.functions.utils import _is_str_or_cat, get_index_labels
+from janitor.functions.select import get_index_labels
+from janitor.functions.utils import _is_str_or_cat
 from janitor.utils import deprecated_alias
 
 

janitor/functions/coalesce.py

@@ -5,7 +5,7 @@
 import pandas as pd
 import pandas_flavor as pf
 
-from janitor.functions.utils import _select_index
+from janitor.functions.select import _select_index
 from janitor.utils import check, deprecated_alias
 
 

janitor/functions/collapse_levels.py

@@ -1,7 +1,5 @@
 """Implementation of the `collapse_levels` function."""
 
-from typing import Union
-
 import pandas as pd
 import pandas_flavor as pf
 from pandas.api.types import is_string_dtype
@@ -12,9 +10,9 @@
 @pf.register_dataframe_method
 def collapse_levels(
     df: pd.DataFrame,
-    sep: Union[str, None] = None,
-    glue: Union[str, None] = None,
-    axis="columns",
+    sep: str = None,
+    glue: str = None,
+    axis: str = "columns",
 ) -> pd.DataFrame:
     """Flatten multi-level index/column dataframe to a single level.
 

janitor/functions/conditional_join.py

@@ -19,7 +19,6 @@
     _generic_func_cond_join,
     _JoinOperator,
     _keep_output,
-    col,
     greater_than_join_types,
     less_than_join_types,
 )
@@ -72,8 +71,6 @@ def conditional_join(
     label from `df`, `right_on` is the column label from `right`,
     while `op` is the operator.
 
-    The `col` class is also supported in the `conditional_join` syntax.
-
     For multiple conditions, the and(`&`)
     operator is used to combine the results of the individual conditions.
 
@@ -133,24 +130,11 @@ def conditional_join(
         3        4         3         5
         4        4         3         6
 
-        Use the `col` class:
-        >>> df1.conditional_join(
-        ...     df2,
-        ...     col("value_1") > col("value_2A"),
-        ...     col("value_1") < col("value_2B")
-        ... )
-           value_1  value_2A  value_2B
-        0        2         1         3
-        1        5         3         6
-        2        3         2         4
-        3        4         3         5
-        4        4         3         6
-
         Select specific columns, after the join:
         >>> df1.conditional_join(
         ...     df2,
-        ...     col("value_1") > col("value_2A"),
-        ...     col("value_1") < col("value_2B"),
+        ...     ("value_1", "value_2A", ">"),
+        ...     ("value_1", "value_2B", "<"),
         ...     right_columns='value_2B',
         ...     how='left'
         ... )
@@ -168,8 +152,8 @@ def conditional_join(
         ...  .rename(columns={'value_1':'left_column'})
         ...  .conditional_join(
         ...      df2,
-        ...      ("left_column", "value_2A", ">"),
-        ...      ("left_column", "value_2B", "<"),
+        ...     ("left_column", "value_2A", ">"),
+        ...     ("left_column", "value_2B", "<"),
         ...      right_columns='value_2B',
         ...      how='outer')
         ... )
@@ -189,8 +173,8 @@ def conditional_join(
         Get the first match:
         >>> df1.conditional_join(
         ...     df2,
-        ...     col("value_1") > col("value_2A"),
-        ...     col("value_1") < col("value_2B"),
+        ...     ("value_1", "value_2A", ">"),
+        ...     ("value_1", "value_2B", "<"),
         ...     keep='first'
         ... )
            value_1  value_2A  value_2B
@@ -202,8 +186,8 @@ def conditional_join(
         Get the last match:
         >>> df1.conditional_join(
         ...     df2,
-        ...     col("value_1") > col("value_2A"),
-        ...     col("value_1") < col("value_2B"),
+        ...     ("value_1", "value_2A", ">"),
+        ...     ("value_1", "value_2B", "<"),
         ...     keep='last'
         ... )
            value_1  value_2A  value_2B
@@ -245,6 +229,8 @@ def conditional_join(
             - Numba support for equi join
         - 0.27.0
             - Added support for timedelta dtype.
+        - 0.28.0
+            - `col` class deprecated.
 
     Args:
         df: A pandas DataFrame.
@@ -355,10 +341,6 @@ def _conditional_join_preliminary_checks(
     if not conditions:
         raise ValueError("Kindly provide at least one join condition.")
 
-    conditions = [
-        cond.join_args if isinstance(cond, col) else cond
-        for cond in conditions
-    ]
     for condition in conditions:
         check("condition", condition, [tuple])
         len_condition = len(condition)

janitor/functions/encode_categorical.py

@@ -7,7 +7,7 @@
 import pandas_flavor as pf
 from pandas.api.types import is_list_like
 
-from janitor.functions.utils import get_index_labels
+from janitor.functions.select import get_index_labels
 from janitor.utils import check_column, deprecated_alias, find_stack_level
 
 

janitor/functions/impute.py

@@ -6,7 +6,7 @@
 import pandas as pd
 import pandas_flavor as pf
 
-from janitor.functions.utils import get_index_labels
+from janitor.functions.select import get_index_labels
 from janitor.utils import deprecated_alias
 
 

janitor/functions/move.py

@@ -6,7 +6,7 @@
 import pandas as pd
 import pandas_flavor as pf
 
-from janitor.functions.utils import _index_converter, _select_index
+from janitor.functions.select import _index_converter, _select_index
 
 
 @pf.register_dataframe_method

janitor/functions/pivot.py

@@ -14,7 +14,7 @@
 from pandas.api.types import is_extension_array_dtype, is_list_like
 from pandas.core.dtypes.concat import concat_compat
 
-from janitor.functions.utils import (
+from janitor.functions.select import (
     _index_converter,
     _select_index,
     get_index_labels,