Skip to content

Columns

toolbox_pyspark.columns 🔗

Summary

The columns module is used to fetch columns from a given DataFrame using convenient syntax.

get_columns 🔗

get_columns(
    dataframe: psDataFrame,
    columns: Optional[Union[str, str_collection]] = None,
) -> str_list

Summary

Get a list of column names from a DataFrame based on optional filter criteria.

Parameters:

Name Type Description Default
dataframe DataFrame

The DataFrame from which to retrieve column names.

 required
columns Optional[Union[str, str_collection]]

Optional filter criteria for selecting columns.
If a string is provided, it can be one of the following options:

Value Description
"all" Return all columns in the DataFrame.
"all_str" Return columns of string type.
"all_int" Return columns of integer type.
"all_numeric" Return columns of numeric types (integers and floats).
"all_datetime" or "all_timestamp" Return columns of datetime or timestamp type.
"all_date" Return columns of date type.
Any other string Return columns matching the provided exact column name.

If a list or tuple of column names is provided, return only those columns.
Defaults to None (which returns all columns).

 None

Raises:

Type Description
TypeError

If any of the inputs parsed to the parameters of this function are not the correct type. Uses the @typeguard.typechecked decorator.

Returns:

Type Description
str_list

The selected column names from the DataFrame.
Examples

Set up
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
>>> # Imports
>>> from pprint import pprint
>>> import pandas as pd
>>> from pyspark.sql import SparkSession, functions as F
>>> from toolbox_pyspark.columns import get_columns
>>>
>>> # Instantiate Spark
>>> spark = SparkSession.builder.getOrCreate()
>>>
>>> # Create data
>>> df = (
...     spark
...     .createDataFrame(
...         pd.DataFrame(
...             {
...                 "a": (0, 1, 2, 3),
...                 "b": ["a", "b", "c", "d"],
...             }
...         )
...     )
...     .withColumns(
...         {
...             "c": F.lit("1").cast("int"),
...             "d": F.lit("2").cast("string"),
...             "e": F.lit("1.1").cast("float"),
...             "f": F.lit("1.2").cast("double"),
...             "g": F.lit("2022-01-01").cast("date"),
...             "h": F.lit("2022-02-01 01:00:00").cast("timestamp"),
...         }
...     )
... )
>>>
>>> # Check
>>> df.show()
>>> print(df.dtypes)
Terminal
+---+---+---+---+-----+-----+------------+---------------------+
| a | b | c | d |   e |   f |          g |                   h |
+---+---+---+---+-----+-----+------------+---------------------+
| 0 | a | 1 | 2 | 1.1 | 1.2 | 2022-01-01 | 2022-02-01 01:00:00 |
| 1 | b | 1 | 2 | 1.1 | 1.2 | 2022-01-01 | 2022-02-01 01:00:00 |
| 2 | c | 1 | 2 | 1.1 | 1.2 | 2022-01-01 | 2022-02-01 01:00:00 |
| 3 | d | 1 | 2 | 1.1 | 1.2 | 2022-01-01 | 2022-02-01 01:00:00 |
+---+---+---+---+-----+-----+------------+---------------------+
Terminal
[
    ("a", "bigint"),
    ("b", "string"),
    ("c", "int"),
    ("d", "string"),
    ("e", "float"),
    ("f", "double"),
    ("g", "date"),
    ("h", "timestamp"),
]

Example 1: Default params
1
>>> print(get_columns(df).columns)
Terminal
["a", "b", "c", "d", "e", "f", "g", "h"]

Conclusion: Success.

Example 2: Specific columns
1
>>> print(get_columns(df, ["a", "b", "c"]).columns)
Terminal
["a", "b", "c"]

Conclusion: Success.

Example 3: Single column as list
1
>>> print(get_columns(df, ["a"]).columns)
Terminal
["a"]

Conclusion: Success.

Example 4: Single column as string
1
>>> print(get_columns(df, "a").columns)
Terminal
["a"]

Conclusion: Success.

Example 5: All columns
1
>>> print(get_columns(df, "all").columns)
Terminal
["a", "b", "c", "d", "e", "f", "g", "h"]

Conclusion: Success.

Example 6: All str
1
>>> print(get_columns(df, "all_str").columns)
Terminal
["b", "d"]

Conclusion: Success.

Example 7: All int
1
>>> print(get_columns(df, "all int").columns)
Terminal
["c"]

Conclusion: Success.

Example 8: All float
1
>>> print(get_columns(df, "all_decimal").columns)
Terminal
["e", "f"]

Conclusion: Success.

Example 9: All numeric
1
>>> print(get_columns(df, "all_numeric").columns)
Terminal
["c", "e", "f"]

Conclusion: Success.

Example 10: All date
1
>>> print(get_columns(df, "all_date").columns)
Terminal
["g"]

Conclusion: Success.

Example 11: All datetime
1
>>> print(get_columns(df, "all_datetime").columns)
Terminal
["h"]

Conclusion: Success.

Source code in src/toolbox_pyspark/columns.py 
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
@typechecked
def get_columns(
    dataframe: psDataFrame,
    columns: Optional[Union[str, str_collection]] = None,
) -> str_list:
    """
    !!! note "Summary"
        Get a list of column names from a DataFrame based on optional filter criteria.

    Params:
        dataframe (psDataFrame):
            The DataFrame from which to retrieve column names.
        columns (Optional[Union[str, str_collection]], optional):
            Optional filter criteria for selecting columns.<br>
            If a string is provided, it can be one of the following options:

            | Value | Description |
            |-------|-------------|
            | `#!py "all"` | Return all columns in the DataFrame.
            | `#!py "all_str"` | Return columns of string type.
            | `#!py "all_int"` | Return columns of integer type.
            | `#!py "all_numeric"` | Return columns of numeric types (integers and floats).
            | `#!py "all_datetime"` or `#!py "all_timestamp"` | Return columns of datetime or timestamp type.
            | `#!py "all_date"` | Return columns of date type.
            | Any other string | Return columns matching the provided exact column name.

            If a list or tuple of column names is provided, return only those columns.<br>
            Defaults to `#!py None` (which returns all columns).

    Raises:
        TypeError:
            If any of the inputs parsed to the parameters of this function are not the correct type. Uses the [`@typeguard.typechecked`](https://typeguard.readthedocs.io/en/stable/api.html#typeguard.typechecked) decorator.

    Returns:
        (str_list):
            The selected column names from the DataFrame.

    ???+ example "Examples"

        ```{.py .python linenums="1" title="Set up"}
        >>> # Imports
        >>> from pprint import pprint
        >>> import pandas as pd
        >>> from pyspark.sql import SparkSession, functions as F
        >>> from toolbox_pyspark.columns import get_columns
        >>>
        >>> # Instantiate Spark
        >>> spark = SparkSession.builder.getOrCreate()
        >>>
        >>> # Create data
        >>> df = (
        ...     spark
        ...     .createDataFrame(
        ...         pd.DataFrame(
        ...             {
        ...                 "a": (0, 1, 2, 3),
        ...                 "b": ["a", "b", "c", "d"],
        ...             }
        ...         )
        ...     )
        ...     .withColumns(
        ...         {
        ...             "c": F.lit("1").cast("int"),
        ...             "d": F.lit("2").cast("string"),
        ...             "e": F.lit("1.1").cast("float"),
        ...             "f": F.lit("1.2").cast("double"),
        ...             "g": F.lit("2022-01-01").cast("date"),
        ...             "h": F.lit("2022-02-01 01:00:00").cast("timestamp"),
        ...         }
        ...     )
        ... )
        >>>
        >>> # Check
        >>> df.show()
        >>> print(df.dtypes)
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+---+---+-----+-----+------------+---------------------+
        | a | b | c | d |   e |   f |          g |                   h |
        +---+---+---+---+-----+-----+------------+---------------------+
        | 0 | a | 1 | 2 | 1.1 | 1.2 | 2022-01-01 | 2022-02-01 01:00:00 |
        | 1 | b | 1 | 2 | 1.1 | 1.2 | 2022-01-01 | 2022-02-01 01:00:00 |
        | 2 | c | 1 | 2 | 1.1 | 1.2 | 2022-01-01 | 2022-02-01 01:00:00 |
        | 3 | d | 1 | 2 | 1.1 | 1.2 | 2022-01-01 | 2022-02-01 01:00:00 |
        +---+---+---+---+-----+-----+------------+---------------------+
        ```
        ```{.sh .shell title="Terminal"}
        [
            ("a", "bigint"),
            ("b", "string"),
            ("c", "int"),
            ("d", "string"),
            ("e", "float"),
            ("f", "double"),
            ("g", "date"),
            ("h", "timestamp"),
        ]
        ```
        </div>

        ```{.py .python linenums="1" title="Example 1: Default params"}
        >>> print(get_columns(df).columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["a", "b", "c", "d", "e", "f", "g", "h"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 2: Specific columns"}
        >>> print(get_columns(df, ["a", "b", "c"]).columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["a", "b", "c"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 3: Single column as list"}
        >>> print(get_columns(df, ["a"]).columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["a"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 4: Single column as string"}
        >>> print(get_columns(df, "a").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["a"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 5: All columns"}
        >>> print(get_columns(df, "all").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["a", "b", "c", "d", "e", "f", "g", "h"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 6: All str"}
        >>> print(get_columns(df, "all_str").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["b", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 7: All int"}
        >>> print(get_columns(df, "all int").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["c"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 8: All float"}
        >>> print(get_columns(df, "all_decimal").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["e", "f"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 9: All numeric"}
        >>> print(get_columns(df, "all_numeric").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["c", "e", "f"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 10: All date"}
        >>> print(get_columns(df, "all_date").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["g"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 11: All datetime"}
        >>> print(get_columns(df, "all_datetime").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["h"]
        ```
        !!! success "Conclusion: Success."
        </div>
    """
    if columns is None:
        return dataframe.columns
    elif is_type(columns, str):
        if "all" in columns:
            if "str" in columns:
                return [col for col, typ in dataframe.dtypes if typ in ("str", "string")]
            elif "int" in columns:
                return [col for col, typ in dataframe.dtypes if typ in ("int", "integer")]
            elif "numeric" in columns:
                return [
                    col
                    for col, typ in dataframe.dtypes
                    if typ in ("int", "integer", "float", "double", "long") or "decimal" in typ
                ]
            elif "float" in columns or "double" in columns or "decimal" in columns:
                return [
                    col
                    for col, typ in dataframe.dtypes
                    if typ in ("float", "double", "long") or "decimal" in typ
                ]
            elif "datetime" in columns or "timestamp" in columns:
                return [
                    col for col, typ in dataframe.dtypes if typ in ("datetime", "timestamp")
                ]
            elif "date" in columns:
                return [col for col, typ in dataframe.dtypes if typ in ["date"]]
            else:
                return dataframe.columns
        else:
            return [columns]
    else:
        return list(columns)

get_columns_by_likeness 🔗

get_columns_by_likeness(
    dataframe: psDataFrame,
    starts_with: Optional[str] = None,
    contains: Optional[str] = None,
    ends_with: Optional[str] = None,
    match_case: bool = False,
    operator: Literal[
        "and", "or", "and not", "or not"
    ] = "and",
) -> str_list

Summary

Extract the column names from a given dataframe based on text that the column name contains.

Details

You can use any combination of startswith, contains, and endswith. Under the hood, these will be implemented with a number of internal lambda functions to determine matches.

The operator parameter determines how the conditions (starts_with, contains, ends_with) are combined:

Value Description
"and" All conditions must be true.
"or" At least one condition must be true.
"and not" The first condition must be true and the second condition must be false.
"or not" At least one condition must be true, but not all.

Parameters:

Name Type Description Default
dataframe DataFrame

The dataframe from which to extract the column names.

 required
starts_with Optional[str]

Extract any columns that starts with this str.
Determined by using the str.startswith() method.
Defaults to None.

 None
contains Optional[str]

Extract any columns that contains this str anywhere within it.
Determined by using the in keyword.
Defaults to None.

 None
ends_with Optional[str]

Extract any columns that ends with this str.
Determined by using the str.endswith() method.
Defaults to None.

 None
match_case bool

If you want to ensure an exact match for the columns, set this to True, else if you want to match the exact case for the columns, set this to False.
Defaults to False.

 False
operator Literal['and', 'or', 'and not', 'or not']

The logical operator to place between the functions.
Only used when there are multiple values parsed to the parameters: starts_with, contains: ends_with.
Defaults to and.

 'and'

Returns:

Type Description
str_list

The list of columns which match the criteria specified.
Examples

Set up
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
>>> # Imports
>>> import pandas as pd
>>> from pyspark.sql import SparkSession
>>> from toolbox_pyspark.columns import get_columns_by_likeness
>>>
>>> # Instantiate Spark
>>> spark = SparkSession.builder.getOrCreate()
>>>
>>> # Create data
>>> values = list(range(1, 6))
>>> df = spark.createDataFrame(
...     pd.DataFrame(
...         {
...             "aaa": values,
...             "aab": values,
...             "aac": values,
...             "afa": values,
...             "afb": values,
...             "afc": values,
...             "bac": values,
...         }
...     )
... )
>>>
>>> # Check
>>> df.show()
Terminal
+-----+-----+-----+-----+-----+-----+-----+
| aaa | aab | aac | afa | afb | afc | bac |
+-----+-----+-----+-----+-----+-----+-----+
|   1 |   1 |   1 |   1 |   1 |   1 |   1 |
|   2 |   2 |   2 |   2 |   2 |   2 |   2 |
|   3 |   3 |   3 |   3 |   3 |   3 |   3 |
|   4 |   4 |   4 |   4 |   4 |   4 |   4 |
|   5 |   5 |   5 |   5 |   5 |   5 |   5 |
+-----+-----+-----+-----+-----+-----+-----+

Example 1: Starts With
1
>>> print(get_columns_by_likeness(df, starts_with="a"))
Terminal
["aaa", "aab", "aac", "afa", "afb", "afc"]

Conclusion: Success.

Example 2: Contains
1
>>> print(get_columns_by_likeness(df, contains="f"))
Terminal
["afa", "afb", "afc"]

Conclusion: Success.

Example 3: Ends With
1
>>> print(get_columns_by_likeness(df, ends_with="c"))
Terminal
["aac", "afc", "bac"]

Conclusion: Success.

Example 4: Starts With and Contains
1
>>> print(get_columns_by_likeness(df, starts_with="a", contains="c"))
Terminal
["aac", "afc"]

Conclusion: Success.

Example 5: Starts With and Ends With
1
>>> print(get_columns_by_likeness(df, starts_with="a", ends_with="b"))
Terminal
["aab", "afb"]

Conclusion: Success.

Example 6: Contains and Ends With
1
>>> print(get_columns_by_likeness(df, contains="f", ends_with="b"))
Terminal
["afb"]

Conclusion: Success.

Example 7: Starts With and Contains and Ends With
1
>>> print(get_columns_by_likeness(df, starts_with="a", contains="f", ends_with="b"))
Terminal
["afb"]

Conclusion: Success.

Example 8: Using 'or' Operator
1
>>> print(get_columns_by_likeness(df, starts_with="a", operator="or", contains="f"))
Terminal
["aaa", "aab", "aac", "afa", "afb", "afc"]

Conclusion: Success.

Example 9: Using 'and not' Operator
1
>>> print(get_columns_by_likeness(df, starts_with="a", operator="and not", contains="f"))
Terminal
["aaa", "aab", "aac"]

Conclusion: Success.

Example 10: Error Example 1
1
>>> print(get_columns_by_likeness(df, starts_with=123))
Terminal
TypeError: `starts_with` must be a `string` or `None`.

Conclusion: Error.

Example 11: Error Example 2
1
>>> print(get_columns_by_likeness(df, operator="xor"))
Terminal
ValueError: `operator` must be one of 'and', 'or', 'and not', 'or not'

Conclusion: Error.

Source code in src/toolbox_pyspark/columns.py 
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
@typechecked
def get_columns_by_likeness(
    dataframe: psDataFrame,
    starts_with: Optional[str] = None,
    contains: Optional[str] = None,
    ends_with: Optional[str] = None,
    match_case: bool = False,
    operator: Literal["and", "or", "and not", "or not"] = "and",
) -> str_list:
    """
    !!! note "Summary"
        Extract the column names from a given `dataframe` based on text that the column name contains.

    ???+ abstract "Details"
        You can use any combination of `startswith`, `contains`, and `endswith`. Under the hood, these will be implemented with a number of internal `#!py lambda` functions to determine matches.

        The `operator` parameter determines how the conditions (`starts_with`, `contains`, `ends_with`) are combined:

        | Value | Description |
        |-------|-------------|
        | `"and"` | All conditions must be true.
        | `"or"` | At least one condition must be true.
        | `"and not"` | The first condition must be true and the second condition must be false.
        | `"or not"` | At least one condition must be true, but not all.

    Params:
        dataframe (psDataFrame):
            The `dataframe` from which to extract the column names.
        starts_with (Optional[str], optional):
            Extract any columns that starts with this `#!py str`.<br>
            Determined by using the `#!py str.startswith()` method.<br>
            Defaults to `#!py None`.
        contains (Optional[str], optional):
            Extract any columns that contains this `#!py str` anywhere within it.<br>
            Determined by using the `#!py in` keyword.<br>
            Defaults to `#!py None`.
        ends_with (Optional[str], optional):
            Extract any columns that ends with this `#!py str`.<br>
            Determined by using the `#!py str.endswith()` method.<br>
            Defaults to `#!py None`.
        match_case (bool, optional):
            If you want to ensure an exact match for the columns, set this to `#!py True`, else if you want to match the exact case for the columns, set this to `#!py False`.<br>
            Defaults to `#!py False`.
        operator (Literal["and", "or", "and not", "or not"], optional):
            The logical operator to place between the functions.<br>
            Only used when there are multiple values parsed to the parameters: `#!py starts_with`, `#!py contains`: `#!py ends_with`.<br>
            Defaults to `#!py and`.

    Returns:
        (str_list):
            The list of columns which match the criteria specified.

    ???+ example "Examples"

        ```{.py .python linenums="1" title="Set up"}
        >>> # Imports
        >>> import pandas as pd
        >>> from pyspark.sql import SparkSession
        >>> from toolbox_pyspark.columns import get_columns_by_likeness
        >>>
        >>> # Instantiate Spark
        >>> spark = SparkSession.builder.getOrCreate()
        >>>
        >>> # Create data
        >>> values = list(range(1, 6))
        >>> df = spark.createDataFrame(
        ...     pd.DataFrame(
        ...         {
        ...             "aaa": values,
        ...             "aab": values,
        ...             "aac": values,
        ...             "afa": values,
        ...             "afb": values,
        ...             "afc": values,
        ...             "bac": values,
        ...         }
        ...     )
        ... )
        >>>
        >>> # Check
        >>> df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +-----+-----+-----+-----+-----+-----+-----+
        | aaa | aab | aac | afa | afb | afc | bac |
        +-----+-----+-----+-----+-----+-----+-----+
        |   1 |   1 |   1 |   1 |   1 |   1 |   1 |
        |   2 |   2 |   2 |   2 |   2 |   2 |   2 |
        |   3 |   3 |   3 |   3 |   3 |   3 |   3 |
        |   4 |   4 |   4 |   4 |   4 |   4 |   4 |
        |   5 |   5 |   5 |   5 |   5 |   5 |   5 |
        +-----+-----+-----+-----+-----+-----+-----+
        ```
        </div>

        ```{.py .python linenums="1" title="Example 1: Starts With"}
        >>> print(get_columns_by_likeness(df, starts_with="a"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["aaa", "aab", "aac", "afa", "afb", "afc"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 2: Contains"}
        >>> print(get_columns_by_likeness(df, contains="f"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["afa", "afb", "afc"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 3: Ends With"}
        >>> print(get_columns_by_likeness(df, ends_with="c"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["aac", "afc", "bac"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 4: Starts With and Contains"}
        >>> print(get_columns_by_likeness(df, starts_with="a", contains="c"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["aac", "afc"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 5: Starts With and Ends With"}
        >>> print(get_columns_by_likeness(df, starts_with="a", ends_with="b"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["aab", "afb"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 6: Contains and Ends With"}
        >>> print(get_columns_by_likeness(df, contains="f", ends_with="b"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["afb"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 7: Starts With and Contains and Ends With"}
        >>> print(get_columns_by_likeness(df, starts_with="a", contains="f", ends_with="b"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["afb"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 8: Using 'or' Operator"}
        >>> print(get_columns_by_likeness(df, starts_with="a", operator="or", contains="f"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["aaa", "aab", "aac", "afa", "afb", "afc"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 9: Using 'and not' Operator"}
        >>> print(get_columns_by_likeness(df, starts_with="a", operator="and not", contains="f"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["aaa", "aab", "aac"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 10: Error Example 1"}
        >>> print(get_columns_by_likeness(df, starts_with=123))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        TypeError: `starts_with` must be a `string` or `None`.
        ```
        !!! failure "Conclusion: Error."
        </div>

        ```{.py .python linenums="1" title="Example 11: Error Example 2"}
        >>> print(get_columns_by_likeness(df, operator="xor"))
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ValueError: `operator` must be one of 'and', 'or', 'and not', 'or not'
        ```
        !!! failure "Conclusion: Error."
        </div>
    """

    # Columns
    cols: str_list = dataframe.columns
    if not match_case:
        cols = [col.upper() for col in cols]
        starts_with = starts_with.upper() if starts_with is not None else None
        contains = contains.upper() if contains is not None else None
        ends_with = ends_with.upper() if ends_with is not None else None

    # Parameters
    o_: Literal["and", "or", "and not", "or not"] = operator
    s_: bool = starts_with is not None
    c_: bool = contains is not None
    e_: bool = ends_with is not None

    # Functions
    _ops = {
        "and": lambda x, y: x and y,
        "or": lambda x, y: x or y,
        "and not": lambda x, y: x and not y,
        "or not": lambda x, y: x or not y,
    }
    _s = lambda col, s: col.startswith(s)
    _c = lambda col, c: c in col
    _e = lambda col, e: col.endswith(e)
    _sc = lambda col, s, c: _ops[o_](_s(col, s), _c(col, c))
    _se = lambda col, s, e: _ops[o_](_s(col, s), _e(col, e))
    _ce = lambda col, c, e: _ops[o_](_c(col, c), _e(col, e))
    _sce = lambda col, s, c, e: _ops[o_](_ops[o_](_s(col, s), _c(col, c)), _e(col, e))

    # Logic
    if s_ and not c_ and not e_:
        return [col for col in cols if _s(col, starts_with)]
    elif c_ and not s_ and not e_:
        return [col for col in cols if _c(col, contains)]
    elif e_ and not s_ and not c_:
        return [col for col in cols if _e(col, ends_with)]
    elif s_ and c_ and not e_:
        return [col for col in cols if _sc(col, starts_with, contains)]
    elif s_ and e_ and not c_:
        return [col for col in cols if _se(col, starts_with, ends_with)]
    elif c_ and e_ and not s_:
        return [col for col in cols if _ce(col, contains, ends_with)]
    elif s_ and c_ and e_:
        return [col for col in cols if _sce(col, starts_with, contains, ends_with)]
    else:
        return cols

rename_columns 🔗

rename_columns(
    dataframe: psDataFrame,
    columns: Optional[Union[str, str_collection]] = None,
    string_function: str = "upper",
) -> psDataFrame

Summary

Use one of the common Python string functions to be applied to one or multiple columns.

Details

The string_function must be a valid string method. For more info on available functions, see: https://docs.python.org/3/library/stdtypes.html#string-methods

Parameters:

Name Type Description Default
dataframe DataFrame

The DataFrame to be updated.

 required
columns Optional[Union[str, str_collection]]

The columns to be updated.
Must be a valid column on dataframe.
If not provided, will be applied to all columns.
It is also possible to parse the values "all", which will also apply this function to all columns in dataframe.
Defaults to None.

 None
string_function str

The string function to be applied. Defaults to "upper".

 'upper'

Returns:

Type Description
DataFrame

The updated DataFrame.
Examples

Set up
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
>>> # Import
>>> import pandas as pd
>>> from pyspark.sql import SparkSession
>>> from toolbox_pyspark.columns import rename_columns
>>>
>>> # Instantiate Spark
>>> spark = SparkSession.builder.getOrCreate()
>>>
>>> # Create data
>>> df = spark.createDataFrame(
...     pd.DataFrame(
...         {
...             "a": [0, 1, 2, 3],
...             "b": ["a", "b", "c", "d"],
...             "c": ["c", "c", "c", "c"],
...             "d": ["d", "d", "d", "d"],
...         }
...     )
... )
>>>
>>> # Check
>>> df.show()
Terminal
+---+---+---+---+
| a | b | c | d |
+---+---+---+---+
| 0 | a | c | d |
| 1 | b | c | d |
| 2 | c | c | d |
| 3 | d | c | d |
+---+---+---+---+

Example 1: Single column, default params
1
>>> print(rename_columns(df, "a").columns)
Terminal
["A", "b", "c", "d"]

Conclusion: Success.

Example 2: Single column, simple function
1
>>> print(rename_columns(df, "a", "upper").columns)
Terminal
["A", "b", "c", "d"]

Conclusion: Success.

Example 3: Single column, complex function
1
>>> print(rename_columns(df, "a", "replace('b', 'test')").columns)
Terminal
["a", "test", "c", "d"]

Conclusion: Success.

Example 4: Multiple columns
1
>>> print(rename_columns(df, ["a", "b"]).columns)
Terminal
["A", "B", "c", "d"]

Conclusion: Success.

Example 5: Default function over all columns
1
>>> print(rename_columns(df).columns)
Terminal
["A", "B", "C", "D"]

Conclusion: Success.

Example 6: Complex function over multiple columns
1
>>> print(rename_columns(df, ["a", "b"], "replace('b', 'test')").columns)
Terminal
["a", "test", "c", "d"]

Conclusion: Success.

See Also
Source code in src/toolbox_pyspark/columns.py 
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
@typechecked
def rename_columns(
    dataframe: psDataFrame,
    columns: Optional[Union[str, str_collection]] = None,
    string_function: str = "upper",
) -> psDataFrame:
    """
    !!! note "Summary"
        Use one of the common Python string functions to be applied to one or multiple columns.

    ???+ abstract "Details"
        The `string_function` must be a valid string method. For more info on available functions, see: https://docs.python.org/3/library/stdtypes.html#string-methods

    Params:
        dataframe (psDataFrame):
            The DataFrame to be updated.
        columns (Optional[Union[str, str_collection]], optional):
            The columns to be updated.<br>
            Must be a valid column on `dataframe`.<br>
            If not provided, will be applied to all columns.<br>
            It is also possible to parse the values `"all"`, which will also apply this function to all columns in `dataframe`.<br>
            Defaults to `None`.
        string_function (str, optional):
            The string function to be applied. Defaults to `"upper"`.

    Returns:
        (psDataFrame):
            The updated DataFrame.

    ???+ example "Examples"

        ```{.py .python linenums="1" title="Set up"}
        >>> # Import
        >>> import pandas as pd
        >>> from pyspark.sql import SparkSession
        >>> from toolbox_pyspark.columns import rename_columns
        >>>
        >>> # Instantiate Spark
        >>> spark = SparkSession.builder.getOrCreate()
        >>>
        >>> # Create data
        >>> df = spark.createDataFrame(
        ...     pd.DataFrame(
        ...         {
        ...             "a": [0, 1, 2, 3],
        ...             "b": ["a", "b", "c", "d"],
        ...             "c": ["c", "c", "c", "c"],
        ...             "d": ["d", "d", "d", "d"],
        ...         }
        ...     )
        ... )
        >>>
        >>> # Check
        >>> df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+---+---+
        | a | b | c | d |
        +---+---+---+---+
        | 0 | a | c | d |
        | 1 | b | c | d |
        | 2 | c | c | d |
        | 3 | d | c | d |
        +---+---+---+---+
        ```
        </div>

        ```{.py .python linenums="1" title="Example 1: Single column, default params"}
        >>> print(rename_columns(df, "a").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["A", "b", "c", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 2: Single column, simple function"}
        >>> print(rename_columns(df, "a", "upper").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["A", "b", "c", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 3: Single column, complex function"}
        >>> print(rename_columns(df, "a", "replace('b', 'test')").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["a", "test", "c", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 4: Multiple columns"}
        >>> print(rename_columns(df, ["a", "b"]).columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["A", "B", "c", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 5: Default function over all columns"}
        >>> print(rename_columns(df).columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["A", "B", "C", "D"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 6: Complex function over multiple columns"}
        >>> print(rename_columns(df, ["a", "b"], "replace('b', 'test')").columns)
        ```
        <div class="result" markdown>
        ```{.sh .shell title="Terminal"}
        ["a", "test", "c", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

    ??? tip "See Also"
        - [`assert_columns_exists()`][toolbox_pyspark.checks.assert_columns_exists]
        - [`assert_column_exists()`][toolbox_pyspark.checks.assert_column_exists]
    """
    columns = get_columns(dataframe, columns)
    assert_columns_exists(dataframe=dataframe, columns=columns, match_case=True)
    cols_exprs: dict[str, str] = {
        col: eval(
            f"'{col}'.{string_function}{'()' if not string_function.endswith(')') else ''}"
        )
        for col in columns
    }
    return dataframe.withColumnsRenamed(cols_exprs)

reorder_columns 🔗

reorder_columns(
    dataframe: psDataFrame,
    new_order: Optional[str_collection] = None,
    missing_columns_last: bool = True,
    key_columns_position: Optional[
        Literal["first", "last"]
    ] = "first",
) -> psDataFrame

Summary

Reorder the columns in a given DataFrame in to a custom order, or to put the key_ columns at the end (that is, to the far right) of the dataframe.

Details

The decision flow chart is as follows:

graph TD
    a([begin])
    z([end])
    b{{new_order}}
    c{{missing_cols_last}}
    d{{key_cols_position}}
    g[cols = dataframe.columns]
    h[cols = new_order]
    i[cols += missing_cols]
    j[cols = non_key_cols + key_cols]
    k[cols = key_cols + non_key_cols]
    l["return dataframe.select(cols)"]
    a --> b
    b --is not None--> h --> c
    b --is None--> g --> d
    c --False--> l
    c --True--> i ----> l
    d --"first"--> k ---> l
    d --"last"---> j --> l
    d --None--> l
    l --> z

Parameters:

Name Type Description Default
dataframe DataFrame

The DataFrame to update

 required
new_order Optional[Union[str, str_list, str_tuple, str_set]]

The custom order for the columns on the order.
Defaults to None.

 None
missing_columns_last bool

For any columns existing on dataframes.columns, but missing from new_order, if missing_columns_last=True, then include those missing columns to the right of the dataframe, in the same order that they originally appear.
Defaults to True.

 True
key_columns_position Optional[Literal['first', 'last']]

Where should the "key_*" columns be located?.

  • If "first", then they will be relocated to the start of the dataframe, before all other columns.
  • If "last", then they will be relocated to the end of the dataframe, after all other columns.
  • If None, they they will remain their original order.

Regardless of their position, their original order will be maintained. Defaults to "first".

 'first'

Raises:

Type Description
TypeError

If any of the inputs parsed to the parameters of this function are not the correct type. Uses the @typeguard.typechecked decorator.

Returns:

Type Description
DataFrame

The updated DataFrame.
Examples

Set up
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
>>> # Imports
>>> import pandas as pd
>>> from pyspark.sql import SparkSession
>>> from toolbox_pyspark.columns import reorder_columns
>>>
>>> # Instantiate Spark
>>> spark = SparkSession.builder.getOrCreate()
>>>
>>> # Create data
>>> df = spark.createDataFrame(
...     pd.DataFrame(
...         {
...             "a": [0, 1, 2, 3],
...             "b": ["a", "b", "c", "d"],
...             "key_a": ["0", "1", "2", "3"],
...             "c": ["1", "1", "1", "1"],
...             "d": ["2", "2", "2", "2"],
...             "key_c": ["1", "1", "1", "1"],
...             "key_e": ["3", "3", "3", "3"],
...         }
...     )
... )
>>>
>>> # Check
>>> df.show()
Terminal
+---+---+-------+---+---+-------+-------+
| a | b | key_a | c | d | key_c | key_e |
+---+---+-------+---+---+-------+-------+
| 0 | a |     0 | 1 | 2 |     1 |     3 |
| 1 | b |     1 | 1 | 2 |     1 |     3 |
| 2 | c |     2 | 1 | 2 |     1 |     3 |
| 3 | d |     3 | 1 | 2 |     1 |     3 |
+---+---+-------+---+---+-------+-------+

Example 1: Default config
1
2
>>> new_df = reorder_columns(dataframe=df)
>>> new_df.show()
Terminal
+-------+-------+-------+---+---+---+---+
| key_a | key_c | key_e | a | b | c | d |
+-------+-------+-------+---+---+---+---+
|     0 |     1 |     3 | 0 | a | 1 | 2 |
|     1 |     1 |     3 | 1 | b | 1 | 2 |
|     2 |     1 |     3 | 2 | c | 1 | 2 |
|     3 |     1 |     3 | 3 | d | 1 | 2 |
+-------+-------+-------+---+---+---+---+

Conclusion: Success.

Example 2: Custom order
1
2
3
4
5
>>> new_df = reorder_columns(
...     dataframe=df,
...     new_order=["key_a", "key_c", "b", "key_e", "a", "c", "d"],
... )
>>> new_df.show()
Terminal
+-------+-------+---+-------+---+---+---+
| key_a | key_c | b | key_e | a | c | d |
+-------+-------+---+-------+---+---+---+
|     0 |     1 | a |     3 | 0 | 1 | 2 |
|     1 |     1 | b |     3 | 1 | 1 | 2 |
|     2 |     1 | c |     3 | 2 | 1 | 2 |
|     3 |     1 | d |     3 | 3 | 1 | 2 |
+-------+-------+---+-------+---+---+---+

Conclusion: Success.

Example 3: Custom order, include missing columns
1
2
3
4
5
6
>>> new_df = reorder_columns(
...     dataframe=df,
...     new_order=["key_a", "key_c", "a", "b"],
...     missing_columns_last=True,
...     )
>>> new_df.show()
Terminal
+-------+-------+---+---+-------+---+---+
| key_a | key_c | a | b | key_e | c | d |
+-------+-------+---+---+-------+---+---+
|     0 |     1 | 0 | a |     3 | 1 | 2 |
|     1 |     1 | 1 | b |     3 | 1 | 2 |
|     2 |     1 | 2 | c |     3 | 1 | 2 |
|     3 |     1 | 3 | d |     3 | 1 | 2 |
+-------+-------+---+---+-------+---+---+

Conclusion: Success.

Example 4: Custom order, exclude missing columns
1
2
3
4
5
6
>>> new_df = reorder_columns(
...     dataframe=df,
...     new_order=["key_a", "key_c", "a", "b"],
...     missing_columns_last=False,
... )
>>> new_df.show()
Terminal
+-------+-------+---+---+
| key_a | key_c | a | b |
+-------+-------+---+---+
|     0 |     1 | 0 | a |
|     1 |     1 | 1 | b |
|     2 |     1 | 2 | c |
|     3 |     1 | 3 | d |
+-------+-------+---+---+

Conclusion: Success.

Example 5: Keys last
1
2
3
4
5
>>> new_df = reorder_columns(
...     dataframe=df,
...     key_columns_position="last",
... )
>>> new_df.show()
Terminal
+---+---+---+---+-------+-------+-------+
| a | b | c | d | key_a | key_c | key_e |
+---+---+---+---+-------+-------+-------+
| 0 | a | 1 | 2 |     0 |     1 |     3 |
| 1 | b | 1 | 2 |     1 |     1 |     3 |
| 2 | c | 1 | 2 |     2 |     1 |     3 |
| 3 | d | 1 | 2 |     3 |     1 |     3 |
+---+---+---+---+-------+-------+-------+

Conclusion: Success.

Example 6: Keys first
1
2
3
4
5
>>> new_df = reorder_columns(
...     dataframe=df,
...     key_columns_position="first",
... )
>>> new_df.show()
Terminal
+-------+-------+-------+---+---+---+---+
| key_a | key_c | key_e | a | b | c | d |
+-------+-------+-------+---+---+---+---+
|     0 |     1 |     3 | 0 | a | 1 | 2 |
|     1 |     1 |     3 | 1 | b | 1 | 2 |
|     2 |     1 |     3 | 2 | c | 1 | 2 |
|     3 |     1 |     3 | 3 | d | 1 | 2 |
+-------+-------+-------+---+---+---+---+

Conclusion: Success.

Source code in src/toolbox_pyspark/columns.py 
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
@typechecked
def reorder_columns(
    dataframe: psDataFrame,
    new_order: Optional[str_collection] = None,
    missing_columns_last: bool = True,
    key_columns_position: Optional[Literal["first", "last"]] = "first",
) -> psDataFrame:
    """
    !!! note "Summary"
        Reorder the columns in a given DataFrame in to a custom order, or to put the `key_` columns at the end (that is, to the far right) of the dataframe.

    ???+ abstract "Details"
        The decision flow chart is as follows:

        ```mermaid
        graph TD
            a([begin])
            z([end])
            b{{new_order}}
            c{{missing_cols_last}}
            d{{key_cols_position}}
            g[cols = dataframe.columns]
            h[cols = new_order]
            i[cols += missing_cols]
            j[cols = non_key_cols + key_cols]
            k[cols = key_cols + non_key_cols]
            l["return dataframe.select(cols)"]
            a --> b
            b --is not None--> h --> c
            b --is None--> g --> d
            c --False--> l
            c --True--> i ----> l
            d --"first"--> k ---> l
            d --"last"---> j --> l
            d --None--> l
            l --> z
        ```

    Params:
        dataframe (psDataFrame):
            The DataFrame to update
        new_order (Optional[Union[str, str_list, str_tuple, str_set]], optional):
            The custom order for the columns on the order.<br>
            Defaults to `#!py None`.
        missing_columns_last (bool, optional):
            For any columns existing on `#!py dataframes.columns`, but missing from `#!py new_order`, if `#!py missing_columns_last=True`, then include those missing columns to the right of the dataframe, in the same order that they originally appear.<br>
            Defaults to `#!py True`.
        key_columns_position (Optional[Literal["first", "last"]], optional):
            Where should the `#!py "key_*"` columns be located?.<br>

            - If `#!py "first"`, then they will be relocated to the start of the dataframe, before all other columns.
            - If `#!py "last"`, then they will be relocated to the end of the dataframe, after all other columns.
            - If `#!py None`, they they will remain their original order.

            Regardless of their position, their original order will be maintained.
            Defaults to `#!py "first"`.

    Raises:
        TypeError:
            If any of the inputs parsed to the parameters of this function are not the correct type. Uses the [`@typeguard.typechecked`](https://typeguard.readthedocs.io/en/stable/api.html#typeguard.typechecked) decorator.

    Returns:
        (psDataFrame):
            The updated DataFrame.

    ???+ example "Examples"

        ```{.py .python linenums="1" title="Set up"}
        >>> # Imports
        >>> import pandas as pd
        >>> from pyspark.sql import SparkSession
        >>> from toolbox_pyspark.columns import reorder_columns
        >>>
        >>> # Instantiate Spark
        >>> spark = SparkSession.builder.getOrCreate()
        >>>
        >>> # Create data
        >>> df = spark.createDataFrame(
        ...     pd.DataFrame(
        ...         {
        ...             "a": [0, 1, 2, 3],
        ...             "b": ["a", "b", "c", "d"],
        ...             "key_a": ["0", "1", "2", "3"],
        ...             "c": ["1", "1", "1", "1"],
        ...             "d": ["2", "2", "2", "2"],
        ...             "key_c": ["1", "1", "1", "1"],
        ...             "key_e": ["3", "3", "3", "3"],
        ...         }
        ...     )
        ... )
        >>>
        >>> # Check
        >>> df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+-------+---+---+-------+-------+
        | a | b | key_a | c | d | key_c | key_e |
        +---+---+-------+---+---+-------+-------+
        | 0 | a |     0 | 1 | 2 |     1 |     3 |
        | 1 | b |     1 | 1 | 2 |     1 |     3 |
        | 2 | c |     2 | 1 | 2 |     1 |     3 |
        | 3 | d |     3 | 1 | 2 |     1 |     3 |
        +---+---+-------+---+---+-------+-------+
        ```
        </div>

        ```{.py .python linenums="1" title="Example 1: Default config"}
        >>> new_df = reorder_columns(dataframe=df)
        >>> new_df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +-------+-------+-------+---+---+---+---+
        | key_a | key_c | key_e | a | b | c | d |
        +-------+-------+-------+---+---+---+---+
        |     0 |     1 |     3 | 0 | a | 1 | 2 |
        |     1 |     1 |     3 | 1 | b | 1 | 2 |
        |     2 |     1 |     3 | 2 | c | 1 | 2 |
        |     3 |     1 |     3 | 3 | d | 1 | 2 |
        +-------+-------+-------+---+---+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 2: Custom order"}
        >>> new_df = reorder_columns(
        ...     dataframe=df,
        ...     new_order=["key_a", "key_c", "b", "key_e", "a", "c", "d"],
        ... )
        >>> new_df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +-------+-------+---+-------+---+---+---+
        | key_a | key_c | b | key_e | a | c | d |
        +-------+-------+---+-------+---+---+---+
        |     0 |     1 | a |     3 | 0 | 1 | 2 |
        |     1 |     1 | b |     3 | 1 | 1 | 2 |
        |     2 |     1 | c |     3 | 2 | 1 | 2 |
        |     3 |     1 | d |     3 | 3 | 1 | 2 |
        +-------+-------+---+-------+---+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 3: Custom order, include missing columns"}
        >>> new_df = reorder_columns(
        ...     dataframe=df,
        ...     new_order=["key_a", "key_c", "a", "b"],
        ...     missing_columns_last=True,
        ...     )
        >>> new_df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +-------+-------+---+---+-------+---+---+
        | key_a | key_c | a | b | key_e | c | d |
        +-------+-------+---+---+-------+---+---+
        |     0 |     1 | 0 | a |     3 | 1 | 2 |
        |     1 |     1 | 1 | b |     3 | 1 | 2 |
        |     2 |     1 | 2 | c |     3 | 1 | 2 |
        |     3 |     1 | 3 | d |     3 | 1 | 2 |
        +-------+-------+---+---+-------+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 4: Custom order, exclude missing columns"}
        >>> new_df = reorder_columns(
        ...     dataframe=df,
        ...     new_order=["key_a", "key_c", "a", "b"],
        ...     missing_columns_last=False,
        ... )
        >>> new_df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +-------+-------+---+---+
        | key_a | key_c | a | b |
        +-------+-------+---+---+
        |     0 |     1 | 0 | a |
        |     1 |     1 | 1 | b |
        |     2 |     1 | 2 | c |
        |     3 |     1 | 3 | d |
        +-------+-------+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 5: Keys last"}
        >>> new_df = reorder_columns(
        ...     dataframe=df,
        ...     key_columns_position="last",
        ... )
        >>> new_df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+---+---+-------+-------+-------+
        | a | b | c | d | key_a | key_c | key_e |
        +---+---+---+---+-------+-------+-------+
        | 0 | a | 1 | 2 |     0 |     1 |     3 |
        | 1 | b | 1 | 2 |     1 |     1 |     3 |
        | 2 | c | 1 | 2 |     2 |     1 |     3 |
        | 3 | d | 1 | 2 |     3 |     1 |     3 |
        +---+---+---+---+-------+-------+-------+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 6: Keys first"}
        >>> new_df = reorder_columns(
        ...     dataframe=df,
        ...     key_columns_position="first",
        ... )
        >>> new_df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +-------+-------+-------+---+---+---+---+
        | key_a | key_c | key_e | a | b | c | d |
        +-------+-------+-------+---+---+---+---+
        |     0 |     1 |     3 | 0 | a | 1 | 2 |
        |     1 |     1 |     3 | 1 | b | 1 | 2 |
        |     2 |     1 |     3 | 2 | c | 1 | 2 |
        |     3 |     1 |     3 | 3 | d | 1 | 2 |
        +-------+-------+-------+---+---+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>
    """
    df_cols: str_list = dataframe.columns
    if new_order is not None:
        cols: str_list = get_columns(dataframe, new_order)
        if missing_columns_last:
            cols += [col for col in df_cols if col not in new_order]
    else:
        non_key_cols: str_list = [col for col in df_cols if not col.lower().startswith("key_")]
        key_cols: str_list = [col for col in df_cols if col.lower().startswith("key_")]
        if key_columns_position == "first":
            cols = key_cols + non_key_cols
        elif key_columns_position == "last":
            cols = non_key_cols + key_cols
        else:
            cols = df_cols
    return dataframe.select(cols)

delete_columns 🔗

delete_columns(
    dataframe: psDataFrame,
    columns: Union[str, str_collection],
    missing_column_handler: Literal[
        "raise", "warn", "pass"
    ] = "pass",
) -> psDataFrame

Summary

For a given dataframe, delete the columns listed in columns.

Details

You can use missing_columns_handler to specify how to handle missing columns.

Parameters:

Name Type Description Default
dataframe DataFrame

The dataframe from which to delete the columns

 required
columns Union[str, str_collection]

The list of columns to delete.

 required
missing_column_handler Literal['raise', 'warn', 'pass']

How to handle any columns which are missing from dataframe.columns.

If any columns in columns are missing from dataframe.columns, then the following will happen for each option:

Option Result
"raise" An ColumnDoesNotExistError exception will be raised
"warn" An ColumnDoesNotExistWarning warning will be raised
"pass" Nothing will be raised

Defaults to "pass".

 'pass'

Raises:

Type Description
TypeError

If any of the inputs parsed to the parameters of this function are not the correct type. Uses the @typeguard.typechecked decorator.
ColumnDoesNotExistError

If any of the columns do not exist within dataframe.columns.

Returns:

Type Description
DataFrame

The updated dataframe, with the columns listed in columns having been removed.
Examples

Set up
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
>>> # Imports
>>> import pandas as pd
>>> from pyspark.sql import SparkSession
>>> from toolbox_pyspark.columns import delete_columns
>>>
>>> # Instantiate Spark
>>> spark = SparkSession.builder.getOrCreate()
>>>
>>> # Create data
>>> df = spark.createDataFrame(
...     pd.DataFrame(
...         {
...             "a": [0, 1, 2, 3],
...             "b": ["a", "b", "c", "d"],
...             "c": ["c", "c", "c", "c"],
...             "d": ["d", "d", "d", "d"],
...         }
...     )
... )
>>>
>>> # Check
>>> df.show()
Terminal
+---+---+---+---+
| a | b | c | d |
+---+---+---+---+
| 0 | a | c | d |
| 1 | b | c | d |
| 2 | c | c | d |
| 3 | d | c | d |
+---+---+---+---+

Example 1: Single column
1
>>> df.transform(delete_columns, "a").show()
Terminal
+---+---+---+
| b | c | d |
+---+---+---+
| a | c | d |
| b | c | d |
| c | c | d |
| d | c | d |
+---+---+---+

Conclusion: Success.

Example 2: Multiple columns
1
>>> df.transform(delete_columns, ["a", "b"]).show()
Terminal
+---+---+
| c | d |
+---+---+
| c | d |
| c | d |
| c | d |
| c | d |
+---+---+

Conclusion: Success.

Example 3: Single column missing, raises error
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns="z",
...         missing_column_handler="raise",
...     )
...     .show()
... )
Terminal
ColumnDoesNotExistError: Columns ["z"] do not exist in "dataframe".
Try one of: ["a", "b", "c", "d"]

Conclusion: Success.

Example 4: Multiple columns, one missing, raises error
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns=["a", "b", "z"],
...         missing_column_handler="raise",
...     )
...     .show()
... )
Terminal
ColumnDoesNotExistError: Columns ["z"] do not exist in "dataframe".
Try one of: ["a", "b", "c", "d"]

Conclusion: Success.

Example 5: Multiple columns, all missing, raises error
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns=["x", "y", "z"],
...         missing_column_handler="raise",
...     )
...     .show()
... )
Terminal
ColumnDoesNotExistError: Columns ["x", "y", "z"] do not exist in "dataframe".
Try one of: ["a", "b", "c", "d"]

Conclusion: Success.

Example 6: Single column missing, raises warning
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns="z",
...         missing_column_handler="warn",
...     )
...     .show()
... )
Terminal
ColumnDoesNotExistWarning: Columns missing from "dataframe": ["z"].
Will still proceed to delete columns that do exist.
Terminal
+---+---+---+---+
| a | b | c | d |
+---+---+---+---+
| 0 | a | c | d |
| 1 | b | c | d |
| 2 | c | c | d |
| 3 | d | c | d |
+---+---+---+---+

Conclusion: Success.

Example 7: Multiple columns, one missing, raises warning
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns=["a", "b", "z"],
...         missing_column_handler="warn",
...     )
...     .show()
... )
Terminal
ColumnDoesNotExistWarning: Columns missing from "dataframe": ["z"].
Will still proceed to delete columns that do exist.
Terminal
+---+---+
| c | d |
+---+---+
| c | d |
| c | d |
| c | d |
| c | d |
+---+---+

Conclusion: Success.

Example 8: Multiple columns, all missing, raises warning
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns=["x", "y", "z"],
...         missing_column_handler="warn",
...     )
...     .show()
... )
Terminal
ColumnDoesNotExistWarning: Columns missing from "dataframe": ["x", "y", "z"].
Will still proceed to delete columns that do exist.
Terminal
+---+---+---+---+
| a | b | c | d |
+---+---+---+---+
| 0 | a | c | d |
| 1 | b | c | d |
| 2 | c | c | d |
| 3 | d | c | d |
+---+---+---+---+

Conclusion: Success.

Example 9: Single column missing, nothing raised
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns="z",
...         missing_column_handler="pass",
...     )
...     .show()
... )
Terminal
+---+---+---+---+
| a | b | c | d |
+---+---+---+---+
| 0 | a | c | d |
| 1 | b | c | d |
| 2 | c | c | d |
| 3 | d | c | d |
+---+---+---+---+

Conclusion: Success.

Example 10: Multiple columns, one missing, nothing raised
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns=["a", "b", "z"],
...         missing_column_handler="pass",
...     )
...     .show()
... )
Terminal
+---+---+
| c | d |
+---+---+
| c | d |
| c | d |
| c | d |
| c | d |
+---+---+

Conclusion: Success.

Example 11: Multiple columns, all missing, nothing raised
1
2
3
4
5
6
7
8
>>> (
...     df.transform(
...         delete_columns,
...         columns=["x", "y", "z"],
...         missing_column_handler="pass",
...     )
...     .show()
... )
Terminal
+---+---+---+---+
| a | b | c | d |
+---+---+---+---+
| 0 | a | c | d |
| 1 | b | c | d |
| 2 | c | c | d |
| 3 | d | c | d |
+---+---+---+---+

Conclusion: Success.

Source code in src/toolbox_pyspark/columns.py 
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
@typechecked
def delete_columns(
    dataframe: psDataFrame,
    columns: Union[str, str_collection],
    missing_column_handler: Literal["raise", "warn", "pass"] = "pass",
) -> psDataFrame:
    """
    !!! note "Summary"
        For a given `#!py dataframe`, delete the columns listed in `columns`.

    ???+ abstract "Details"
        You can use `#!py missing_columns_handler` to specify how to handle missing columns.

    Params:
        dataframe (psDataFrame):
            The dataframe from which to delete the columns
        columns (Union[str, str_collection]):
            The list of columns to delete.
        missing_column_handler (Literal["raise", "warn", "pass"], optional):
            How to handle any columns which are missing from `#!py dataframe.columns`.

            If _any_ columns in `columns` are missing from `#!py dataframe.columns`, then the following will happen for each option:

            | Option | Result |
            |--------|--------|
            | `#!py "raise"` | An `#!py ColumnDoesNotExistError` exception will be raised
            | `#!py "warn"` | An `#!py ColumnDoesNotExistWarning` warning will be raised
            | `#!py "pass"` | Nothing will be raised

            Defaults to `#!py "pass"`.

    Raises:
        TypeError:
            If any of the inputs parsed to the parameters of this function are not the correct type. Uses the [`@typeguard.typechecked`](https://typeguard.readthedocs.io/en/stable/api.html#typeguard.typechecked) decorator.
        ColumnDoesNotExistError:
            If any of the `#!py columns` do not exist within `#!py dataframe.columns`.

    Returns:
        (psDataFrame):
            The updated `#!py dataframe`, with the columns listed in `#!py columns` having been removed.

    ???+ example "Examples"

        ```{.py .python linenums="1" title="Set up"}
        >>> # Imports
        >>> import pandas as pd
        >>> from pyspark.sql import SparkSession
        >>> from toolbox_pyspark.columns import delete_columns
        >>>
        >>> # Instantiate Spark
        >>> spark = SparkSession.builder.getOrCreate()
        >>>
        >>> # Create data
        >>> df = spark.createDataFrame(
        ...     pd.DataFrame(
        ...         {
        ...             "a": [0, 1, 2, 3],
        ...             "b": ["a", "b", "c", "d"],
        ...             "c": ["c", "c", "c", "c"],
        ...             "d": ["d", "d", "d", "d"],
        ...         }
        ...     )
        ... )
        >>>
        >>> # Check
        >>> df.show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+---+---+
        | a | b | c | d |
        +---+---+---+---+
        | 0 | a | c | d |
        | 1 | b | c | d |
        | 2 | c | c | d |
        | 3 | d | c | d |
        +---+---+---+---+
        ```
        </div>

        ```{.py .python linenums="1" title="Example 1: Single column"}
        >>> df.transform(delete_columns, "a").show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+---+
        | b | c | d |
        +---+---+---+
        | a | c | d |
        | b | c | d |
        | c | c | d |
        | d | c | d |
        +---+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 2: Multiple columns"}
        >>> df.transform(delete_columns, ["a", "b"]).show()
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+
        | c | d |
        +---+---+
        | c | d |
        | c | d |
        | c | d |
        | c | d |
        +---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 3: Single column missing, raises error"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns="z",
        ...         missing_column_handler="raise",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        ColumnDoesNotExistError: Columns ["z"] do not exist in "dataframe".
        Try one of: ["a", "b", "c", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 4: Multiple columns, one missing, raises error"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns=["a", "b", "z"],
        ...         missing_column_handler="raise",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        ColumnDoesNotExistError: Columns ["z"] do not exist in "dataframe".
        Try one of: ["a", "b", "c", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 5: Multiple columns, all missing, raises error"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns=["x", "y", "z"],
        ...         missing_column_handler="raise",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        ColumnDoesNotExistError: Columns ["x", "y", "z"] do not exist in "dataframe".
        Try one of: ["a", "b", "c", "d"]
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 6: Single column missing, raises warning"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns="z",
        ...         missing_column_handler="warn",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        ColumnDoesNotExistWarning: Columns missing from "dataframe": ["z"].
        Will still proceed to delete columns that do exist.
        ```
        ```{.txt .text title="Terminal"}
        +---+---+---+---+
        | a | b | c | d |
        +---+---+---+---+
        | 0 | a | c | d |
        | 1 | b | c | d |
        | 2 | c | c | d |
        | 3 | d | c | d |
        +---+---+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 7: Multiple columns, one missing, raises warning"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns=["a", "b", "z"],
        ...         missing_column_handler="warn",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        ColumnDoesNotExistWarning: Columns missing from "dataframe": ["z"].
        Will still proceed to delete columns that do exist.
        ```
        ```{.txt .text title="Terminal"}
        +---+---+
        | c | d |
        +---+---+
        | c | d |
        | c | d |
        | c | d |
        | c | d |
        +---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 8: Multiple columns, all missing, raises warning"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns=["x", "y", "z"],
        ...         missing_column_handler="warn",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        ColumnDoesNotExistWarning: Columns missing from "dataframe": ["x", "y", "z"].
        Will still proceed to delete columns that do exist.
        ```
        ```{.txt .text title="Terminal"}
        +---+---+---+---+
        | a | b | c | d |
        +---+---+---+---+
        | 0 | a | c | d |
        | 1 | b | c | d |
        | 2 | c | c | d |
        | 3 | d | c | d |
        +---+---+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 9: Single column missing, nothing raised"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns="z",
        ...         missing_column_handler="pass",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+---+---+
        | a | b | c | d |
        +---+---+---+---+
        | 0 | a | c | d |
        | 1 | b | c | d |
        | 2 | c | c | d |
        | 3 | d | c | d |
        +---+---+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 10: Multiple columns, one missing, nothing raised"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns=["a", "b", "z"],
        ...         missing_column_handler="pass",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+
        | c | d |
        +---+---+
        | c | d |
        | c | d |
        | c | d |
        | c | d |
        +---+---+
        ```
        !!! success "Conclusion: Success."
        </div>

        ```{.py .python linenums="1" title="Example 11: Multiple columns, all missing, nothing raised"}
        >>> (
        ...     df.transform(
        ...         delete_columns,
        ...         columns=["x", "y", "z"],
        ...         missing_column_handler="pass",
        ...     )
        ...     .show()
        ... )
        ```
        <div class="result" markdown>
        ```{.txt .text title="Terminal"}
        +---+---+---+---+
        | a | b | c | d |
        +---+---+---+---+
        | 0 | a | c | d |
        | 1 | b | c | d |
        | 2 | c | c | d |
        | 3 | d | c | d |
        +---+---+---+---+
        ```
        !!! success "Conclusion: Success."
        </div>
    """
    columns = get_columns(dataframe, columns)
    if missing_column_handler == "raise":
        assert_columns_exists(dataframe=dataframe, columns=columns)
    elif missing_column_handler == "warn":
        warn_columns_missing(dataframe=dataframe, columns=columns)
    elif missing_column_handler == "pass":
        pass
    return dataframe.select([col for col in dataframe.columns if col not in columns])