def add_column_to_workflow(
user,
workflow: models.Workflow,
column: models.Column,
column_initial_value: Any,
action_column_event: Optional[str] = None,
action: Optional[models.Action] = None,
):
"""Add a new column to the workflow.
:param user: User executing the operation
:param workflow: Used workflow
:param column: Column to insert
:param column_initial_value: Initial value for the column
:param action_column_event: Event to record if the action/column needs to
be stored
:param action: If the column is a question, this is the action in which it
is being used.
:return: Nothing. Column added to Wflow and DB
"""
# Catch the special case of integer type and no initial value. Pandas
# encodes it as NaN but a cycle through the database transforms it into
# a string. To avoid this case, integer + empty value => double
if column.data_type == 'integer' and column_initial_value is None:
column.data_type = 'double'
# Fill in the remaining fields in the column
column.workflow = workflow
column.is_key = False
# Update the positions of the appropriate columns
workflow.reposition_columns(workflow.ncols + 1, column.position)
# Save column, refresh workflow, and increase number of columns
column.save()
workflow.refresh_from_db()
workflow.ncols += 1
workflow.set_query_builder_ops()
workflow.save()
# Add the new column to the DB
try:
sql.add_column_to_db(
workflow.get_data_frame_table_name(),
column.name,
column.data_type,
initial=column_initial_value)
except Exception as exc:
raise services.OnTaskWorkflowAddColumn(
message=_('Unable to add element: {0}').format(str(exc)),
to_delete=[column])
if action_column_event:
acc, __ = models.ActionColumnConditionTuple.objects.get_or_create(
action=action,
column=column,
condition=None)
acc.log(user, action_column_event)
column.log(user, models.Log.COLUMN_ADD)
def add_formula_column(
user,
workflow: models.Workflow,
column: models.Column,
operation: str,
selected_columns: List[models.Column],
):
"""Add the formula column to the workflow.
:param user: User making the request
:param workflow: Workflow to add the column
:param column: Column being added
:param operation: string denoting the operation
:param selected_columns: List of columns selected for the operation.
:return: Column is added to the workflow
"""
# Save the column object attached to the form and add additional fields
column.workflow = workflow
column.is_key = False
# Save the instance
column.save()
# Update the data frame
df = pandas.load_table(workflow.get_data_frame_table_name())
# Add the column with the appropriate computation
cnames = [col.name for col in selected_columns]
df[column.name] = _op_distrib[operation](df[cnames])
# Populate the column type
column.data_type = pandas.datatype_names.get(
df[column.name].dtype.name)
# Update the positions of the appropriate columns
workflow.reposition_columns(workflow.ncols + 1, column.position)
column.save()
workflow.refresh_from_db()
# Store the df to DB
try:
pandas.store_dataframe(df, workflow)
except Exception as exc:
raise services.OnTaskWorkflowAddColumn(
message=_('Unable to add column: {0}').format(str(exc)),
to_delete=[column])
workflow.ncols = workflow.columns.count()
workflow.save()
column.log(user, models.Log.COLUMN_ADD_FORMULA)
def add_random_column(
user,
workflow: models.Workflow,
column: models.Column,
data_frame: pd.DataFrame,
):
"""Add the formula column to the workflow.
:param user: User making the request
:param workflow: Workflow to add the column
:param column: Column being added
:param data_frame: Data frame of the current workflow
:return: Column is added to the workflow
"""
# Save the column object attached to the form and add additional fields
column.workflow = workflow
column.is_key = False
# Detect the case of a single integer as initial value so that it is
# expanded
try:
int_value = int(column.categories[0])
if int_value <= 1:
raise services.OnTaskWorkflowIntegerLowerThanOne(
field_name='values',
message=_('The integer value has to be larger than 1'))
column.set_categories([idx + 1 for idx in range(int_value)])
except (ValueError, TypeError, IndexError):
pass
column.save()
# Empty new column
new_column = [None] * workflow.nrows
# Create the random partitions
partitions = _partition([idx for idx in range(workflow.nrows)],
len(column.categories))
# Assign values to partitions
for idx, indexes in enumerate(partitions):
for col_idx in indexes:
new_column[col_idx] = column.categories[idx]
# Assign the new column to the data frame
data_frame[column.name] = new_column
# Update the positions of the appropriate columns
workflow.reposition_columns(workflow.ncols + 1, column.position)
workflow.refresh_from_db()
# Store the df to DB
try:
pandas.store_dataframe(data_frame, workflow)
except Exception as exc:
raise services.OnTaskWorkflowStoreError(
message=_('Unable to add the column: {0}').format(str(exc)),
to_delete=[column])
workflow.ncols = workflow.columns.count()
workflow.save()
# Log the event
column.log(user, models.Log.COLUMN_ADD_RANDOM)