def read_csv(path):
""" Read a csv file as a DataFrame
Parameters
----------
path : str
path of the file
Returns
-------
DataFrame
"""
table = csv_weld.Table(path)
new_columns = {}
for column_name in table.columns:
column = table.columns[column_name]
weld_obj, weld_input_name = LazyResult.generate_placeholder_weld_object(column.data_id, column.encoder, column.decoder)
new_columns[column_name] = LazyResult(weld_obj, numpy_to_weld_type(column.dtype), 1)
random_column = new_columns[new_columns.keys()[0]]
index_weld_obj = weld_range(0, 'len({})'.format(random_column.expr.weld_code), 1)
index_weld_obj.update(random_column.expr)
return DataFrame(new_columns, Index(index_weld_obj, np.dtype(np.int64)))
def _create_variables(self):
variables = OrderedDict()
for kv in self.ds.variables.items():
# generate a data_id to act as placeholder to the data
data_id = LazyResult.generate_data_id(kv[0])
weld_obj, weld_input_id = LazyResult.generate_placeholder_weld_object(
data_id, Variable.encoder, Variable.decoder)
variable = Variable(self.file_id, kv[0], kv[1].dimensions,
kv[1].shape, kv[1].__dict__, weld_obj,
kv[1].dtype)
LazyResult.register_lazy_data(weld_input_id, variable)
variables[kv[0]] = variable
return variables
