Added doc blocks to the cell steps classes (#1204)

Added docblocks to steps classes

frictionless/steps/cell/cell_convert.py

@@ -11,20 +11,123 @@
 
 @attrs.define(kw_only=True)
 class cell_convert(Step):
-    """Convert cell"""
+    """Convert cell
+
+    Converts cell values of one or more fields using arbitrary functions, method
+    invocations or dictionary translations. 
+
+    Parameters
+    ----------
+        type  : step identifier
+        value : value to replace in cells.
+        function : arbitrary function, data method or dictionary translations.
+        field_name : field name to apply function to.
+
+    Methods
+    -------
+        transform_resource(resource):
+            converts cell value of a resource using arbitrary function, data method 
+            or dictionary translations
+
+    Examples
+    --------
+    >>> from frictionless import Resource, Pipeline, steps
+    >>> source = Resource(path="data/transform.csv")
+        +----+-----------+------------+
+        | id | name      | population |
+        +====+===========+============+
+        |  1 | 'germany' |         83 |
+        +----+-----------+------------+
+        |  2 | 'france'  |         66 |
+        +----+-----------+------------+
+        |  3 | 'spain'   |         47 |
+        +----+-----------+------------+
+    >>> # replacing value
+    >>> pipeline = Pipeline(
+            steps=[
+                steps.cell_convert(field_name='population', value="100"),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view()) 
+        +----+-----------+------------+
+        | id | name      | population |
+        +====+===========+============+
+        |  1 | 'germany' |        100 |
+        +----+-----------+------------+
+        |  2 | 'france'  |        100 |
+        +----+-----------+------------+
+        |  3 | 'spain'   |        100 |
+        +----+-----------+------------+
+
+    >>> # using lamda function
+    >>> pipeline = Pipeline(
+            steps=[
+                steps.cell_convert(function=lambda v: v*2, field_name='population'),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view())
+        +----+-----------+------------+
+        | id | name      | population |
+        +====+===========+============+
+        |  1 | 'germany' |     100100 |
+        +----+-----------+------------+
+        |  2 | 'france'  |     100100 |
+        +----+-----------+------------+
+        |  3 | 'spain'   |     100100 |
+        +----+-----------+------------+
+
+    >>> # using method of data value
+    >>> pipeline = Pipeline(
+            steps=[
+                steps.cell_convert(function='upper', field_name='name'),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view())
+        +----+-----------+------------+
+        | id | name      | population |
+        +====+===========+============+
+        |  1 | 'GERMANY' |     100100 |
+        +----+-----------+------------+
+        |  2 | 'FRANCE'  |     100100 |
+        +----+-----------+------------+
+        |  3 | 'SPAIN'   |     100100 |
+        +----+-----------+------------+
+
+    >>> # using a dictionary
+    >>> pipeline = Pipeline(
+            steps=[
+                steps.cell_convert(field_name='name', function = {'GERMANY': 'Z', 'B': 'Y'}),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view())
+        +----+----------+------------+-----------------+
+        | id | name     | population | avg_age         |
+        +====+==========+============+=================+
+        |  1 | 'Z'      |     100100 | Decimal('30.5') |
+        +----+----------+------------+-----------------+
+        |  2 | 'FRANCE' |     100100 | Decimal('30.0') |
+        +----+----------+------------+-----------------+
+        |  3 | 'SPAIN'  |     100100 | Decimal('40.0') |
+        +----+----------+------------+-----------------+
+
+    """
 
     type = "cell-convert"
 
     # State
 
     value: Optional[Any] = None
-    """TODO: add docs"""
+    """Value to replace in the field cell"""
 
     function: Optional[Any] = None
-    """TODO: add docs"""
+    """Function/Data method/Dictionary to apply to the column"""
 
     field_name: Optional[str] = None
-    """TODO: add docs"""
+    """Name of the field to apply the function"""
 
     # Transform
 

frictionless/steps/cell/cell_fill.py

@@ -11,20 +11,129 @@
 
 @attrs.define(kw_only=True)
 class cell_fill(Step):
-    """Fill cell"""
+    """Fill cell
+
+    Replaces missing values with non-missing values from the adjacent row/column. 
+
+    Parameters
+    ----------
+        type : step identifier
+        value : value to replace in cells.        
+        field_name : field name to apply function to.
+        direction: column/row direction from where to copy the non-missing value.
+                   for column cells, it also checks for the field types and only works 
+                   if the two columns are of same types.
+
+
+    Methods
+    -------
+        transform_resource(resource):
+            replaces cell value of a resource using adjacent row/column value or using
+            user defined value.
+
+    Examples
+    --------
+    >>> from frictionless import Resource, Pipeline, steps
+    >>> source = Resource(path="data/transform-missing.csv")
+        +----+-----------+-----------+-----------------+-----------------+
+        | id | name      | title     | population      | avg_age         |
+        +====+===========+===========+=================+=================+
+        |  1 | 'germany' | 'germany' | Decimal('30.5') | None            |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  2 | None      | 'italy'   |   Decimal('66') | Decimal('35.0') |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  3 | 'spain'   | 'spain'   | Decimal('50.0') | None            |
+        +----+-----------+-----------+-----------------+-----------------+
+    >>> # replacing missing values by user defined value
+    >>> pipeline = Pipeline(
+            steps=[
+                steps.table_normalize(),
+                steps.cell_fill(field_name="name", value="france"),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view()) 
+        +----+-----------+-----------+-----------------+-----------------+
+        | id | name      | title     | population      | avg_age         |
+        +====+===========+===========+=================+=================+
+        |  1 | 'germany' | 'germany' | Decimal('30.5') | None            |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  2 | 'france'  | 'italy'   |   Decimal('66') | Decimal('35.0') |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  3 | 'spain'   | 'spain'   | Decimal('50.0') | None            |
+        +----+-----------+-----------+-----------------+-----------------+
+
+    >>> # using non-missing value from the row above
+    >>> pipeline = pipeline = Pipeline(
+            steps=[
+                steps.table_normalize(),
+                steps.cell_fill(direction="down"),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view())
+        +----+-----------+-----------+-----------------+-----------------+
+        | id | name      | title     | population      | avg_age         |
+        +====+===========+===========+=================+=================+
+        |  1 | 'germany' | 'germany' | Decimal('30.5') | None            |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  2 | 'france'  | 'italy'   |   Decimal('66') | Decimal('35.0') |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  3 | 'spain'   | 'spain'   | Decimal('50.0') | Decimal('35.0') |
+        +----+-----------+-----------+-----------------+-----------------+
+
+    >>> # using non-missing value from the right column
+    >>> pipeline = Pipeline(
+            steps=[
+                steps.table_normalize(),
+                steps.cell_fill(direction="left"),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view())
+        +----+-----------+-----------+-----------------+-----------------+
+        | id | name      | title     | population      | avg_age         |
+        +====+===========+===========+=================+=================+
+        |  1 | 'germany' | 'germany' | Decimal('30.5') | None            |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  2 | 'france'  | 'italy'   |   Decimal('66') | Decimal('35.0') |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  3 | 'spain'   | 'spain'   | Decimal('50.0') | Decimal('35.0') |
+        +----+-----------+-----------+-----------------+-----------------+
+
+    >>> # using non-missing value from the left column
+    >>> pipeline = Pipeline(
+            steps=[
+                steps.table_normalize(),
+                steps.cell_fill(direction="right"),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view())
+        +----+-----------+-----------+-----------------+-----------------+
+        | id | name      | title     | population      | avg_age         |
+        +====+===========+===========+=================+=================+
+        |  1 | 'germany' | 'germany' | Decimal('30.5') | Decimal('30.5') |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  2 | 'france'  | 'italy'   |   Decimal('66') | Decimal('35.0') |
+        +----+-----------+-----------+-----------------+-----------------+
+        |  3 | 'spain'   | 'spain'   | Decimal('50.0') | Decimal('35.0') |
+        +----+-----------+-----------+-----------------+-----------------+
+
+    """
 
     type = "cell-fill"
 
     # State
 
     value: Optional[Any] = None
-    """TODO: add docs"""
+    """Value to replace in the field cell with missing value"""
 
     field_name: Optional[str] = None
-    """TODO: add docs"""
+    """Name of the field to replace the missing value cells"""
 
     direction: Optional[str] = None
-    """TODO: add docs"""
+    """Directions to read the non missing value from(left/right/above)"""
 
     # Transform
 

frictionless/steps/cell/cell_format.py

@@ -11,17 +11,82 @@
 
 @attrs.define(kw_only=True)
 class cell_format(Step):
-    """Format cell"""
+    """Format cell
+
+    Formats all values in the given or all string fields using the `template` format string. 
+
+    Parameters
+    ----------
+        type : step identifier
+        template: template to apply format string.        
+        field_name : field name to apply the format.
+
+    Methods
+    -------
+        transform_resource(resource):
+            format cells of given or all string fields using user defined template.
+
+    Examples
+    --------
+    >>> from frictionless import Resource, Pipeline, steps
+    >>> source = Resource(path="data/transform-string.csv")
+    >>> print(source.to_view())
+        +-----------+--------------+--------------+
+        | name      | country_code | city         |
+        +===========+==============+==============+
+        | 'germany' | 'DE'         | 'berlin'     |
+        +-----------+--------------+--------------+
+        | 'denmark' | 'DK'         | 'copenhagen' |
+        +-----------+--------------+--------------+
+        | 'spain'   | 'ES'         | 'Andalusia'  |
+        +-----------+--------------+--------------+
+    >>> # apply format to a specific field
+    >>> pipeline = Pipeline(
+            steps=[
+                steps.cell_format(template="Prefix: {0}", field_name="name"),
+            ],
+        )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view()) 
+        +-------------------+--------------+--------------+
+        | name              | country_code | city         |
+        +===================+==============+==============+
+        | 'Prefix: germany' | 'DE'         | 'berlin'     |
+        +-------------------+--------------+--------------+
+        | 'Prefix: denmark' | 'DK'         | 'copenhagen' |
+        +-------------------+--------------+--------------+
+        | 'Prefix: spain'   | 'ES'         | 'Andalusia'  |
+        +-------------------+--------------+--------------+
+
+    >>> # apply format to all fields
+    >>> pipeline = Pipeline(
+        steps=[
+            steps.cell_format(template="Prefix: {0}"),
+        ],
+    )
+    >>> target = source.transform(pipeline)
+    >>> print(target.to_view())
+        +-------------------+--------------+----------------------+
+        | name              | country_code | city                 |
+        +===================+==============+======================+
+        | 'Prefix: germany' | 'Prefix: DE' | 'Prefix: berlin'     |
+        +-------------------+--------------+----------------------+
+        | 'Prefix: denmark' | 'Prefix: DK' | 'Prefix: copenhagen' |
+        +-------------------+--------------+----------------------+
+        | 'Prefix: spain'   | 'Prefix: ES' | 'Prefix: Andalusia'  |
+        +-------------------+--------------+----------------------+
+
+    """
 
     type = "cell-format"
 
     # State
 
     template: str
-    """TODO: add docs"""
+    """format string to apply to cells"""
 
     field_name: Optional[str] = None
-    """TODO: add docs"""
+    """field name to apply template format"""
 
     # Transform