tree: 6bf63d03bdc0644ed61f8eee5c6417a6418c93fa [path history] [tgz]
  1. ctr-score-generator/
  2. inventory-updater/
  3. pf-service/
  4. README.md
Processes/performance-forecasting/README.md

What is performance forecasting?

performance forecasting is an offline process to check the performance of forecasting traffic inventory.

Prerequisites

Cluster: Spark 2.3/HDFS 2.7/YARN 2.3/MapReduce 2.7/Hive 1.2 Driver: Python 3.6, Spark Client 2.3

Install and Run

  1. Download the bluemarlin-services/performance-forecasting project
  2. Transfer the performance-forecasting directory to bluemarlin-services/performance-forecasting on a machine which also has Spark Client.
  3. cd performance-forecasting
  4. cd sub-project directory
  5. python setup install (to install performance-forecasting sub project package).
  6. Run run.sh.

Documentation

Documentation is provided through comments in config.yml and README files