This commit is contained in:
WaylonWalker 2020-02-28 08:16:44 -06:00
commit 24e604ab32
44 changed files with 2338 additions and 0 deletions

50
conf/base/catalog.yml Normal file
View file

@ -0,0 +1,50 @@
# Here you can define all your data sets by using simple YAML syntax.
#
# Documentation for this file format can be found in "The Data Catalog"
# Link: https://kedro.readthedocs.io/en/stable/04_user_guide/04_data_catalog.html
#
# We support interacting with a variety of data stores including local file systems, cloud, network and HDFS
#
# An example data set definition can look as follows:
#
#bikes:
# type: pandas.CSVDataSet
# filepath: "data/01_raw/bikes.csv"
#
#weather:
# type: spark.SparkDataSet
# filepath: s3a://your_bucket/data/01_raw/weather*
# file_format: csv
# credentials: dev_s3
# load_args:
# header: True
# inferSchema: True
# save_args:
# sep: '|'
# header: True
#
#scooters:
# type: pandas.SQLTableDataSet
# credentials: scooters_credentials
# table_name: scooters
# load_args:
# index_col: ['name']
# columns: ['name', 'gear']
# save_args:
# if_exists: 'replace'
# # if_exists: 'fail'
# # if_exists: 'append'
#
# The Data Catalog supports being able to reference the same file using two different DataSet implementations
# (transcoding), templating and a way to reuse arguments that are frequently repeated. See more here:
# https://kedro.readthedocs.io/en/stable/04_user_guide/04_data_catalog.html
#
# This is a data set used by the "Hello World" example pipeline provided with the project
# template. Please feel free to remove it once you remove the example pipeline.
example_iris_data:
type: CSVLocalDataSet
filepath: data/01_raw/iris.csv

66
conf/base/logging.yml Normal file
View file

@ -0,0 +1,66 @@
version: 1
disable_existing_loggers: False
formatters:
simple:
format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
json_formatter:
format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
class: pythonjsonlogger.jsonlogger.JsonFormatter
handlers:
console:
class: logging.StreamHandler
level: INFO
formatter: simple
stream: ext://sys.stdout
info_file_handler:
class: logging.handlers.RotatingFileHandler
level: INFO
formatter: simple
filename: logs/info.log
maxBytes: 10485760 # 10MB
backupCount: 20
encoding: utf8
delay: True
error_file_handler:
class: logging.handlers.RotatingFileHandler
level: ERROR
formatter: simple
filename: logs/errors.log
maxBytes: 10485760 # 10MB
backupCount: 20
encoding: utf8
delay: True
journal_file_handler:
class: kedro.versioning.journal.JournalFileHandler
level: INFO
base_dir: logs/journals
formatter: json_formatter
loggers:
anyconfig:
level: WARNING
handlers: [console, info_file_handler, error_file_handler]
propagate: no
kedro.io:
level: INFO
handlers: [console, info_file_handler, error_file_handler]
propagate: no
kedro.pipeline:
level: INFO
handlers: [console, info_file_handler, error_file_handler]
propagate: no
kedro.journal:
level: INFO
handlers: [journal_file_handler]
propagate: no
root:
level: INFO
handlers: [console, info_file_handler, error_file_handler]

8
conf/base/parameters.yml Normal file
View file

@ -0,0 +1,8 @@
# Parameters for the example pipeline. Feel free to delete these once you
# remove the example pipeline from pipeline.py and the example nodes in
# `src/pipelines/`
example_test_data_ratio: 0.2
example_num_train_iter: 10000
example_learning_rate: 0.01