def update_cell(self, identifier, column_id, row_id, value, datastore):
"""Update a cell in a given dataset.
Raises ValueError if no dataset with given identifier exists or if the
specified cell is outside of the current dataset ranges.
Parameters
----------
identifier : string
Unique dataset identifier
column_id: int
Unique column identifier for updated cell
row_id: int
Unique row identifier
value: string
New cell value
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# Get the index of the specified cell column
col_index = get_index_for_column(dataset, column_id)
# Raise exception if row id is not valid
# Create a view for the modified dataset
col_list = []
for i in range(len(dataset.columns)):
col = dataset.columns[i]
if i == col_index:
try:
val_stmt = col.to_sql_value(value)
col_sql = val_stmt + ' ELSE ' + col.name_in_rdb + ' END '
except ValueError:
col_sql = '\'' + str(
value
) + '\' ELSE CAST({{input}}.' + col.name_in_rdb + ' AS varchar) END '
rid_sql = MIMIR_ROWID_COL.to_sql_value(row_id)
stmt = 'CASE WHEN ' + ROW_ID + ' = ' + rid_sql + ' THEN '
stmt += col_sql
stmt += 'AS ' + col.name_in_rdb
col_list.append(stmt)
else:
col_list.append(col.name_in_rdb)
sql = 'SELECT ' + ','.join(
col_list) + ' FROM ' + dataset.table_name + ';'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
# Store updated dataset information with new identifier
ds = datastore.register_dataset(table_name=view_name,
columns=dataset.columns,
row_counter=dataset.row_counter,
annotations=dataset.annotations)
return VizualApiResult(ds)
def insert_column(self, identifier, position, name, datastore):
"""Insert column with given name at given position in dataset.
Raises ValueError if no dataset with given identifier exists, if the
specified column position is outside of the current schema bounds, or if
the column name is invalid.
Parameters
----------
identifier: string
Unique dataset identifier
position: int
Index position at which the column will be inserted
name: string, optional
New column name
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Raise ValueError if given colum name is invalid
if not is_valid_name(name):
raise ValueError('invalid column name \'' + str(name) + '\'')
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# Make sure that position is a valid column index in the new dataset
if position < 0 or position > len(dataset.columns):
raise ValueError('invalid column index \'' + str(position) + '\'')
# Get identifier for new column
col_id = dataset.max_column_id() + 1
# Insert new column into schema
schema = list(dataset.columns)
new_column = MimirDatasetColumn(col_id, name, name)
schema.insert(position, new_column)
# Create a view for the modified schema
col_list = []
for col in schema:
if col.identifier == new_column.identifier:
# Note: By no (April 2018) this requires Mimir to run with the
# XNULL option. Otherwise, in some scenarios setting the all
# values in the new column to NULL may cause an exception.
col_list.append(" CAST('' AS int) AS " + col.name_in_rdb)
else:
col_list.append(col.name_in_rdb)
sql = 'SELECT ' + ','.join(
col_list) + ' FROM ' + dataset.table_name + ';'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
# Store updated dataset information with new identifier
ds = datastore.register_dataset(table_name=view_name,
columns=schema,
row_counter=dataset.row_counter,
annotations=dataset.annotations)
return VizualApiResult(ds)
def compute_empty_dataset(self, args, context):
"""Execute empty dataset command.
Parameters
----------
args: vizier.viztrail.command.ModuleArguments
User-provided command arguments
context: vizier.engine.task.base.TaskContext
Context in which a task is being executed
Returns
-------
vizier.engine.task.processor.ExecResult
"""
outputs = ModuleOutputs()
default_columns = [("''", "unnamed_column")]
ds_name = args.get_value(pckg.PARA_NAME).lower()
if ds_name in context.datasets:
raise ValueError('dataset \'' + ds_name + '\' exists')
if not is_valid_name(ds_name):
raise ValueError('invalid dataset name \'' + ds_name + '\'')
try:
source = "SELECT {};".format(", ".join(
default_val + " AS " + col_name
for default_val, col_name in default_columns))
view_name, dependencies = mimir.createView(dict(), source)
columns = [
MimirDatasetColumn(identifier=col_id,
name_in_dataset=col_defn[1])
for col_defn, col_id in zip(default_columns,
range(len(default_columns)))
]
ds = context.datastore.register_dataset(table_name=view_name,
columns=columns,
row_counter=1)
provenance = ModuleProvenance(
write={
ds_name:
DatasetDescriptor(identifier=ds.identifier,
columns=ds.columns,
row_count=ds.row_count)
},
read=dict(
) # Need to explicitly declare a lack of dependencies.
)
outputs.stdout.append(
TextOutput("Empty dataset '{}' created".format(ds_name)))
except Exception as ex:
provenance = ModuleProvenance()
outputs.error(ex)
return ExecResult(is_success=(len(outputs.stderr) == 0),
outputs=outputs,
provenance=provenance)
def filter_columns(self, identifier, columns, names, datastore):
"""Dataset projection operator. Returns a copy of the dataset with the
given identifier that contains only those columns listed in columns.
The list of names contains optional new names for the filtered columns.
A value of None in names indicates that the name of the corresponding
column is not changed.
Raises ValueError if no dataset with given identifier exists or if any
of the filter columns are unknown.
Parameters
----------
identifier: string
Unique dataset identifier
columns: list(int)
List of column identifier for columns in the result.
names: list(string)
Optional new names for filtered columns.
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# The schema of the new dataset only contains the columns in the given
# list. A column might need to be renamed.
schema = list()
col_list = []
for i in range(len(columns)):
col_idx = get_index_for_column(dataset, columns[i])
col = dataset.columns[col_idx]
if not names[i] is None:
schema.append(
MimirDatasetColumn(identifier=col.identifier,
name_in_dataset=names[i],
name_in_rdb=col.name_in_rdb))
else:
schema.append(col)
col_list.append(col.name_in_rdb)
sql = 'SELECT ' + ','.join(
col_list) + ' FROM ' + dataset.table_name + ';'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
# Store updated dataset information with new identifier
ds = datastore.register_dataset(table_name=view_name,
columns=schema,
row_counter=dataset.row_counter,
annotations=dataset.annotations.filter(
columns=columns,
rows=dataset.row_ids))
return VizualApiResult(ds)
def sort_dataset(self, identifier: str, columns: List[int],
reversed: List[bool],
datastore: Datastore) -> VizualApiResult:
"""Sort the dataset with the given identifier according to the order by
statement. The order by statement is a pair of lists. The first list
contains the identifier of columns to sort on. The second list contains
boolean flags, one for each entry in columns, indicating whether sort
order is revered for the corresponding column or not.
Returns the number of rows in the dataset and the identifier of the
sorted dataset.
Raises ValueError if no dataset with given identifier exists or if any
of the columns in the order by clause are unknown.
Parameters
----------
identifier: string
Unique dataset identifier
columns: list(int)
List of column identifier for sort columns.
reversed: list(bool)
Flags indicating whether the sort order of the corresponding column
is reveresed.
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
assert (isinstance(dataset, MimirDatasetHandle))
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# Create order by clause based on columns and reversed flags
order_by_clause = list()
for i in range(len(columns)):
col_id = columns[i]
stmt = cast(MimirDatasetColumn,
dataset.column_by_id(col_id)).name_in_rdb
if reversed[i]:
stmt += ' DESC'
order_by_clause.append(stmt)
sql = 'SELECT * FROM ' + dataset.identifier + ' ORDER BY '
sql += ','.join(order_by_clause)
view_name, dependencies, schema, properties, functionDeps = mimir.createView(
datasets={dataset.identifier: dataset.identifier}, query=sql)
ds = MimirDatasetHandle.from_mimir_result(view_name, schema,
properties)
return VizualApiResult(ds)
def sort_dataset(self, identifier, columns, reversed, datastore):
"""Sort the dataset with the given identifier according to the order by
statement. The order by statement is a pair of lists. The first list
contains the identifier of columns to sort on. The second list contains
boolean flags, one for each entry in columns, indicating whether sort
order is revered for the corresponding column or not.
Returns the number of rows in the dataset and the identifier of the
sorted dataset.
Raises ValueError if no dataset with given identifier exists or if any
of the columns in the order by clause are unknown.
Parameters
----------
identifier: string
Unique dataset identifier
columns: list(int)
List of column identifier for sort columns.
reversed: list(bool)
Flags indicating whether the sort order of the corresponding column
is reveresed.
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# Create order by clause based on columns and reversed flags
order_by_clause = list()
for i in range(len(columns)):
col_id = columns[i]
stmt = dataset.column_by_id(col_id).name_in_rdb
if reversed[i]:
stmt += ' DESC'
order_by_clause.append(stmt)
sql = 'SELECT * FROM {{input}} ORDER BY '
sql += ','.join(order_by_clause) + ';'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
# Register new dataset with only a modified list of row identifier
ds = datastore.register_dataset(table_name=view_name,
columns=dataset.columns,
annotations=dataset.annotations)
return VizualApiResult(ds)
def insert_row(self, identifier, position, datastore):
"""Insert row at given position in a dataset.
Raises ValueError if no dataset with given identifier exists or if the
specified row psotion isoutside the dataset bounds.
Parameters
----------
identifier: string
Unique dataset identifier
position: int
Index position at which the row will be inserted
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# Make sure that position is a valid row index in the new dataset
if position < 0 or position > len(dataset.row_ids):
raise ValueError('invalid row index \'' + str(position) + '\'')
# Get unique id for new row
dataset.row_counter += 1
# Create a view for the modified schema
col_list = []
for col in dataset.columns:
col_list.append(col.name_in_rdb)
sql = 'SELECT ' + ','.join(col_list) + ' FROM ' + dataset.table_name
mimirSchema = mimir.getSchema(sql)
union_list = []
for col in mimirSchema[1:]:
union_list.append('CAST(NULL AS ' + col['baseType'] + ') AS ' +
col['name'])
sql = '(' + sql + ') UNION ALL (SELECT ' + ','.join(union_list) + ');'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
# Store updated dataset information with new identifier
ds = datastore.register_dataset(table_name=view_name,
columns=dataset.columns,
row_counter=dataset.row_counter,
annotations=dataset.annotations)
return VizualApiResult(ds)
def create_missing_key_view(dataset, lens_name, key_column):
""" Create a view for missing ROW_ID's on a MISSING_KEY lens.
Parameters
----------
dataset: vizier.datastore.mimir.MimirDatasetHandle
Descriptor for the dataset on which the lens was created
lens_name: string
Identifier of the created MISSING_KEY lens
key_column: vizier.datastore.mimir.MimirDatasetColumn
Name of the column for which the missing values where generated
Returns
-------
string, int
Returns the name of the created view and the adjusted counter for row
ids.
"""
# Select the rows that have missing row ids
key_col_name = key_column.name_in_rdb
sql = 'SELECT ' + key_col_name + ' FROM ' + lens_name
sql += ' WHERE ' + ROW_ID + ' IS NULL;'
rs = mimir.vistrailsQueryMimirJson(sql, False, False)
case_conditions = []
for row in rs['data']:
row_id = dataset.row_counter + len(case_conditions)
val = str(row[0])
# If the key colum is of type real then we need to convert val into
# something that looks like a real
if key_column.data_type.lower() == 'real':
val += '.0'
case_conditions.append('WHEN ' + key_col_name + ' = ' + val +
' THEN ' + str(row_id))
# If no new rows where inserted we are good to go with the existing lens
if len(case_conditions) == 0:
return lens_name, dataset.row_counter
# Create the view SQL statement
stmt = 'CASE ' + (' '.join(case_conditions)).strip()
stmt += ' ELSE ' + ROW_ID + ' END AS ' + ROW_ID
col_list = [stmt]
for column in dataset.columns:
col_list.append(column.name_in_rdb)
sql = 'SELECT ' + ','.join(col_list) + ' FROM ' + lens_name + ';'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
return view_name, dataset.row_counter + len(case_conditions)
def delete_column(self, identifier, column_id, datastore):
"""Delete a column in a given dataset.
Raises ValueError if no dataset with given identifier exists or if the
specified column is unknown.
Parameters
----------
identifier: string
Unique dataset identifier
column_id: int
Unique column identifier
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# Get the index of the specified column that is to be deleted.
col_index = get_index_for_column(dataset, column_id)
# Delete column from schema
schema = list(dataset.columns)
del schema[col_index]
# Create a view for the modified schema
col_list = []
for col in schema:
col_list.append(col.name_in_rdb)
sql = 'SELECT ' + ','.join(
col_list) + ' FROM ' + dataset.table_name + ';'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
# Store updated dataset information with new identifier
ds = datastore.register_dataset(table_name=view_name,
columns=schema,
row_counter=dataset.row_counter,
annotations=dataset.annotations)
return VizualApiResult(ds)
def delete_row(self, identifier, rowid, datastore):
"""Delete a row in a given dataset.
Raises ValueError if no dataset with given identifier exists or if the
specified row is not within the range of the dataset.
Parameters
----------
identifier: string
Unique dataset identifier
row_index: int
Row index for deleted row
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# Create a view for the modified dataset
col_list = []
for col in dataset.columns:
col_list.append(col.name_in_rdb)
sql = 'SELECT ' + ','.join(col_list) + ' FROM ' + dataset.table_name
sql += ' WHERE ' + ROW_ID + ' <> ' + MIMIR_ROWID_COL.to_sql_value(
roid) + ';'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
# Store updated dataset information with new identifier
ds = datastore.register_dataset(table_name=view_name,
columns=dataset.columns,
row_counter=dataset.row_counter - 1,
annotations=dataset.annotations)
return VizualApiResult(ds)
def execute_query(self, args: ModuleArguments,
context: TaskContext) -> ExecResult:
"""Execute a SQL query in the given context.
Parameters
----------
args: vizier.viztrail.command.ModuleArguments
User-provided command arguments
context: vizier.engine.task.base.TaskContext
Context in which a task is being executed
Returns
-------
vizier.engine.task.processor.ExecResult
"""
# Get SQL source code that is in this cell and the global
# variables
source = args.get_value(cmd.PARA_SQL_SOURCE)
if not source.endswith(';'):
source = source
ds_name = args.get_value(cmd.PARA_OUTPUT_DATASET, raise_error=False)
# Get mapping of datasets in the context to their respective table
# name in the Mimir backend
mimir_table_names = dict()
for ds_name_o in context.datasets:
dataset_id = context.datasets[ds_name_o].identifier
dataset = context.datastore.get_dataset(dataset_id)
if dataset is None:
raise ValueError('unknown dataset \'' + ds_name_o + '\'')
mimir_table_names[ds_name_o] = dataset.identifier
# Module outputs
outputs = ModuleOutputs()
is_success = True
functions = {
name: context.dataobjects[name].identifier
for name in context.dataobjects
if context.dataobjects[name].obj_type == ARTIFACT_TYPE_PYTHON
}
try:
# Create the view from the SQL source
view_name, dependencies, mimirSchema, properties, functionDeps = mimir.createView(
datasets=mimir_table_names,
query=source,
functions=dict(functions))
ds = MimirDatasetHandle.from_mimir_result(view_name, mimirSchema,
properties, ds_name)
print(mimirSchema)
if ds_name is None or ds_name == '':
ds_name = "TEMPORARY_RESULT"
from vizier.api.webservice import server
ds_output = server.api.datasets.get_dataset(
project_id=context.project_id,
dataset_id=ds.identifier,
offset=0,
limit=10)
if ds_output is None:
outputs.stderr.append(
TextOutput("Error displaying dataset {}".format(ds_name)))
else:
ds_output['name'] = ds_name
outputs.stdout.append(DatasetOutput(ds_output))
dependenciesDict: Dict[str, str] = {
dep_name.lower(): get_artifact_id(dep)
for dep_name, dep in [(
dep_name, context.datasets.get(dep_name.lower(), None))
for dep_name in dependencies]
if dep is not None
}
functionDepDict: Dict[str, str] = {
dep_name.lower(): get_artifact_id(dep)
for dep_name, dep in [(
dep_name, context.dataobjects.get(dep_name.lower(), None))
for dep_name in dependencies]
if dep is not None
}
# print("---- SQL DATASETS ----\n{}\n{}".format(context.datasets, dependencies))
provenance = ModuleProvenance(write={
ds_name:
DatasetDescriptor(identifier=ds.identifier,
name=ds_name,
columns=ds.columns)
},
read={
**dependenciesDict,
**functionDepDict
})
except Exception as ex:
provenance = ModuleProvenance()
outputs.error(ex)
is_success = False
# Return execution result
return ExecResult(is_success=is_success,
outputs=outputs,
provenance=provenance)
def rename_column(self, identifier, column_id, name, datastore):
"""Rename column in a given dataset.
Raises ValueError if no dataset with given identifier exists, if the
specified column is unknown, or if the given column name is invalid.
Parameters
----------
identifier: string
Unique dataset identifier
column_id: int
Unique column identifier
name: string
New column name
datastore : vizier.datastore.fs.base.FileSystemDatastore
Datastore to retireve and update datasets
Returns
-------
vizier.engine.packages.vizual.api.VizualApiResult
"""
# Raise ValueError if given colum name is invalid
if not is_valid_name(name):
raise ValueError('invalid column name \'' + str(name) + '\'')
# Get dataset. Raise exception if dataset is unknown
dataset = datastore.get_dataset(identifier)
if dataset is None:
raise ValueError('unknown dataset \'' + identifier + '\'')
# Get the specified column that is to be renamed and set the column name
# to the new name
columns = list()
schema = list(dataset.columns)
colIndex = get_index_for_column(dataset, column_id)
col = schema[colIndex]
# No need to do anything if the name hasn't changed
if col.name.lower() != name.lower():
sql = 'SELECT * FROM ' + dataset.table_name
mimirSchema = mimir.getSchema(sql)
# Create list of dataset columns
colSql = ''
idx = 0
for col in mimirSchema:
col_id = len(columns)
name_in_dataset = sanitize_column_name(col['name'].upper())
name_in_rdb = sanitize_column_name(col['name'].upper())
col = MimirDatasetColumn(identifier=col_id,
name_in_dataset=name_in_dataset,
name_in_rdb=name_in_rdb)
if idx == 0:
colSql = name_in_dataset + ' AS ' + name_in_rdb
elif idx == colIndex:
colSql = colSql + ', ' + name_in_dataset + ' AS ' + name
col.name = name
col.name_in_rdb = name
else:
colSql = colSql + ', ' + name_in_dataset + ' AS ' + name_in_rdb
columns.append(col)
idx = idx + 1
# Create view for loaded dataset
sql = 'SELECT ' + colSql + ' FROM {{input}};'
view_name, dependencies = mimir.createView(dataset.table_name, sql)
# There are no changes to the underlying database. We only need to
# change the column information in the dataset schema.
# Store updated dataset to get new identifier
ds = datastore.register_dataset(table_name=view_name,
columns=columns,
row_counter=dataset.row_counter,
annotations=dataset.annotations)
return VizualApiResult(ds)
else:
return VizualApiResult(dataset)
def execute_query(self, args, context):
"""Execute a SQL query in the given context.
Parameters
----------
args: vizier.viztrail.command.ModuleArguments
User-provided command arguments
context: vizier.engine.task.base.TaskContext
Context in which a task is being executed
Returns
-------
vizier.engine.task.processor.ExecResult
"""
# Get SQL source code that is in this cell and the global
# variables
source = args.get_value(cmd.PARA_SQL_SOURCE)
if not source.endswith(';'):
source = source + ';'
ds_name = args.get_value(cmd.PARA_OUTPUT_DATASET, raise_error=False)
# Get mapping of datasets in the context to their respective table
# name in the Mimir backend
mimir_table_names = dict()
for ds_name_o in context.datasets:
dataset_id = context.datasets[ds_name_o]
dataset = context.datastore.get_dataset(dataset_id)
if dataset is None:
raise ValueError('unknown dataset \'' + ds_name_o + '\'')
mimir_table_names[ds_name_o] = dataset.table_name
# Module outputs
outputs = ModuleOutputs()
try:
# Create the view from the SQL source
view_name, dependencies = mimir.createView(mimir_table_names,
source)
sql = 'SELECT * FROM ' + view_name
mimirSchema = mimir.getSchema(sql)
columns = list()
for col in mimirSchema:
col_id = len(columns)
name_in_dataset = col['name']
col = MimirDatasetColumn(identifier=col_id,
name_in_dataset=name_in_dataset)
columns.append(col)
row_count = mimir.countRows(view_name)
provenance = None
if ds_name is None or ds_name == '':
ds_name = "TEMPORARY_RESULT"
ds = context.datastore.register_dataset(table_name=view_name,
columns=columns,
row_counter=row_count)
ds_output = server.api.datasets.get_dataset(
project_id=context.project_id,
dataset_id=ds.identifier,
offset=0,
limit=10)
ds_output['name'] = ds_name
dependencies = dict((dep_name.lower(),
context.datasets.get(dep_name.lower(), None))
for dep_name in dependencies)
# print("---- SQL DATASETS ----\n{}\n{}".format(context.datasets, dependencies))
outputs.stdout.append(DatasetOutput(ds_output))
provenance = ModuleProvenance(write={
ds_name:
DatasetDescriptor(identifier=ds.identifier,
columns=ds.columns,
row_count=ds.row_count)
},
read=dependencies)
except Exception as ex:
provenance = ModuleProvenance()
outputs.error(ex)
# Return execution result
return ExecResult(is_success=(len(outputs.stderr) == 0),
outputs=outputs,
provenance=provenance)
def create_dataset(self,
columns,
rows,
human_readable_name=None,
annotations=None,
backend_options=[],
dependencies=[]):
"""Create a new dataset in the datastore. Expects at least the list of
columns and the rows for the dataset.
Parameters
----------
columns: list(vizier.datastore.dataset.DatasetColumn)
List of columns. It is expected that each column has a unique
identifier.
rows: list(vizier.datastore.dataset.DatasetRow)
List of dataset rows.
annotations: vizier.datastore.annotation.dataset.DatasetMetadata, optional
Annotations for dataset components
Returns
-------
vizier.datastore.dataset.DatasetDescriptor
"""
# Get unique identifier for new dataset
identifier = 'DS_' + get_unique_identifier()
# Write rows to temporary file in CSV format
tmp_file = os.path.abspath(self.base_path + identifier)
# Create a list of columns that contain the user-vizible column name and
# the name in the database
db_columns = list()
colSql = ''
for col in map(base.sanitize_column_name, columns):
db_columns.append(
MimirDatasetColumn(identifier=col.identifier,
name_in_dataset=col.name,
name_in_rdb=col.name))
if colSql == '':
colSql = col.name + ' AS ' + col.name
else:
colSql = colSql + ', ' + col.name + ' AS ' + col.name
# Create CSV file for load
with open(tmp_file, 'w') as f_out:
writer = csv.writer(f_out, quoting=csv.QUOTE_MINIMAL)
writer.writerow([col.name_in_rdb for col in db_columns])
for row in rows:
record = helper.encode_values(row.values)
writer.writerow(record)
# Load CSV file using Mimirs loadCSV method.
table_name = mimir.loadDataSource(
tmp_file,
True,
True,
human_readable_name=human_readable_name,
backend_options=backend_options,
dependencies=dependencies)
os.remove(tmp_file)
sql = 'SELECT ' + colSql + ' FROM {{input}};'
view_name, dependencies = mimir.createView(table_name, sql)
# Get number of rows in the view that was created in the backend
row_count = mimir.countRows(view_name)
# Insert the new dataset metadata information into the datastore
return self.register_dataset(table_name=view_name,
columns=db_columns,
row_counter=row_count,
annotations=annotations)
def load_dataset(self,
f_handle=None,
url=None,
detect_headers=True,
infer_types=True,
load_format='csv',
options=[],
human_readable_name=None):
"""Create a new dataset from a given file or url. Expects that either
the file handle or the url are not None. Raises ValueError if both are
None or not None.
Parameters
----------
f_handle : vizier.filestore.base.FileHandle, optional
handle for an uploaded file on the associated file server.
url: string, optional, optional
Url for the file source
detect_headers: bool, optional
Detect column names in loaded file if True
infer_types: bool, optional
Infer column types for loaded dataset if True
load_format: string, optional
Format identifier
options: list, optional
Additional options for Mimirs load command
human_readable_name: string, optional
Optional human readable name for the resulting table
Returns
-------
vizier.datastore.mimir.dataset.MimirDatasetHandle
"""
if f_handle is None and url is None:
raise ValueError('no load source given')
elif not f_handle is None and not url is None:
raise ValueError('too many load sources given')
elif url is None:
# os.path.abspath((r'%s' % os.getcwd().replace('\\','/') ) + '/' + f_handle.filepath)
abspath = f_handle.filepath
elif not url is None:
abspath = url
# Load dataset into Mimir
init_load_name = mimir.loadDataSource(abspath, infer_types,
detect_headers, load_format,
human_readable_name, options)
# Retrieve schema information for the created dataset
sql = 'SELECT * FROM ' + init_load_name
mimirSchema = mimir.getSchema(sql)
# Create list of dataset columns
columns = list()
colSql = ''
for col in mimirSchema:
col_id = len(columns)
name_in_dataset = base.sanitize_column_name(col['name'].upper())
name_in_rdb = base.sanitize_column_name(col['name'].upper())
col = MimirDatasetColumn(identifier=col_id,
name_in_dataset=name_in_dataset,
name_in_rdb=name_in_rdb)
if colSql == '':
colSql = name_in_dataset + ' AS ' + name_in_rdb
else:
colSql = colSql + ', ' + name_in_dataset + ' AS ' + name_in_rdb
columns.append(col)
# Create view for loaded dataset
sql = 'SELECT ' + colSql + ' FROM {{input}};'
view_name, dependencies = mimir.createView(init_load_name, sql)
# TODO: this is a hack to speed up this step a bit.
# we get the first row id and the count and take a range;
# this is fragile and should be made better
#
# NOTE: This does not work because ROW_ID appears to be a string.
# Thus, sorting not necessarily returns the smallest integer value
# first.
#
row_count = mimir.countRows(view_name)
return self.register_dataset(table_name=view_name,
columns=columns,
row_counter=row_count)
