timsaucer commented on code in PR #666: URL: https://github.com/apache/datafusion-python/pull/666#discussion_r1598479222
########## examples/tpch/q01_pricing_summary_report.py: ########## @@ -0,0 +1,90 @@ +# 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. + +""" +TPC-H Problem Statement Query 1: + +The Pricing Summary Report Query provides a summary pricing report for all lineitems shipped as of +a given date. The date is within 60 - 120 days of the greatest ship date contained in the database. +The query lists totals for extended price, discounted extended price, discounted extended price +plus tax, average quantity, average extended price, and average discount. These aggregates are +grouped by RETURNFLAG and LINESTATUS, and listed in ascending order of RETURNFLAG and LINESTATUS. +A count of the number of lineitems in each group is included. + +The above problem statement text is copyrighted by the Transaction Processing Performance Council +as part of their TPC Benchmark H Specification revision 2.18.0. +""" + +import pyarrow as pa +from datafusion import SessionContext, col, lit, functions as F + +ctx = SessionContext() + +df = ctx.read_parquet("data/lineitem.parquet") + +# It may be that the date can be hard coded, based on examples shown. +# This approach will work with any date range in the provided data set. + +greatest_ship_date = df.aggregate( + [], [F.max(col("l_shipdate")).alias("shipdate")] +).collect()[0]["shipdate"][0] + +# From the given problem, this is how close to the last date in the database we +# want to report results for. It should be between 60-120 days before the end. +DAYS_BEFORE_FINAL = 68 + +# Note: this is a hack on setting the values. It should be set differently once +# https://github.com/apache/datafusion-python/issues/665 is resolved. Review Comment: Done https://github.com/apache/datafusion-python/issues/665#issuecomment-2107580388 -- 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. To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
