rohdesamuel commented on a change in pull request #10915: [BEAM-8335] Add PCollection to DataFrame logic for InteractiveRunner. URL: https://github.com/apache/beam/pull/10915#discussion_r384892102
########## File path: sdks/python/apache_beam/runners/interactive/utils.py ########## @@ -0,0 +1,112 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +"""Utilities to be used in Interactive Beam. +""" + +from __future__ import absolute_import + +import pandas as pd + +from apache_beam.typehints import typehints as th +from apache_beam.utils.windowed_value import WindowedValue + +COLUMN_PREFIX = 'el' + + +def parse_row_(el, element_type, depth): + elements = [] + columns = [] + + # Recurse if there are a known length of columns to parse into. + if isinstance(element_type, (th.TupleHint.TupleConstraint)): + for index, t in enumerate(element_type._inner_types()): + underlying_columns, underlying_elements = parse_row_(el[index], t, + depth + 1) + column = '[{}]'.format(index) + if underlying_columns: + columns += [column + c for c in underlying_columns] + else: + columns += [column] + elements += underlying_elements + + # Don't make new columns for variable length types. + elif isinstance( + element_type, + (th.ListHint.ListConstraint, th.TupleHint.TupleSequenceConstraint)): + elements = [pd.array(el)] + + # For any other types, try to parse as a namedtuple, otherwise pass element + # through. + else: + fields = getattr(el, '_fields', None) Review comment: Unfortunately this is the way to check if it is a named tuple. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
