initial draft

.gitignore

@@ -0,0 +1,151 @@
+##########################
+# KEDRO PROJECT
+
+# ignore all local configuration
+conf/local/**
+!conf/local/.gitkeep
+
+# ignore potentially sensitive credentials files
+conf/**/*credentials*
+
+# ignore everything in the following folders
+data/**
+
+# except their sub-folders
+!data/**/
+
+# also keep all .gitkeep files
+!.gitkeep
+
+# keep also the example dataset
+!data/01_raw/*
+
+
+##########################
+# Common files
+
+# IntelliJ
+.idea/
+*.iml
+out/
+.idea_modules/
+
+### macOS
+*.DS_Store
+.AppleDouble
+.LSOverride
+.Trashes
+
+# Vim
+*~
+.*.swo
+.*.swp
+
+# emacs
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# C extensions
+*.so
+
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+.static_storage/
+.media/
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/

.telemetry

@@ -0,0 +1 @@
+consent: false

conf/README.md

@@ -0,0 +1,20 @@
+# What is this for?
+
+This folder should be used to store configuration files used by Kedro or by separate tools.
+
+This file can be used to provide users with instructions for how to reproduce local configuration with their own credentials. You can edit the file however you like, but you may wish to retain the information below and add your own section in the section titled **Instructions**.
+
+## Local configuration
+
+The `local` folder should be used for configuration that is either user-specific (e.g. IDE configuration) or protected (e.g. security keys).
+
+> *Note:* Please do not check in any local configuration to version control.
+
+## Base configuration
+
+The `base` folder is for shared configuration, such as non-sensitive and project-related configuration that may be shared across team members.
+
+WARNING: Please do not put access credentials in the base configuration folder.
+
+## Find out more
+You can find out more about configuration from the [user guide documentation](https://docs.kedro.org/en/stable/configuration/configuration_basics.html).

conf/base/catalog.yml

@@ -0,0 +1,104 @@
+# 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/data/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/data/data_catalog.html
+
+companies:
+  type: pandas.CSVDataset
+  filepath: data/01_raw/companies.csv
+
+reviews:
+  type: pandas.CSVDataset
+  filepath: data/01_raw/reviews.csv
+
+shuttles:
+  type: pandas.ExcelDataset
+  filepath: data/01_raw/shuttles.xlsx
+  load_args:
+    engine: openpyxl
+
+preprocessed_companies:
+  type: pandas.ParquetDataset
+  filepath: data/02_intermediate/preprocessed_companies.pq
+
+preprocessed_shuttles:
+  type: pandas.ParquetDataset
+  filepath: data/02_intermediate/preprocessed_shuttles.pq
+
+model_input_table:
+  type: pandas.ParquetDataset
+  filepath: data/03_primary/model_input_table.pq
+
+regressor:
+  type: pickle.PickleDataset
+  filepath: data/06_models/regressor.pickle
+  versioned: true
+
+metrics:
+  type: tracking.MetricsDataset
+  filepath: data/09_tracking/metrics.json
+
+companies_columns:
+  type: tracking.JSONDataset
+  filepath: data/09_tracking/companies_columns.json
+
+shuttle_passenger_capacity_plot_exp:
+  type: plotly.PlotlyDataset
+  filepath: data/08_reporting/shuttle_passenger_capacity_plot_exp.json
+  versioned: true
+  plotly_args:
+    type: bar
+    fig:
+      x: shuttle_type
+      y: passenger_capacity
+      orientation: h
+    layout:
+      xaxis_title: Shuttles
+      yaxis_title: Average passenger capacity
+      title: Shuttle Passenger capacity
+
+shuttle_passenger_capacity_plot_go:
+  type: plotly.JSONDataset
+  filepath: data/08_reporting/shuttle_passenger_capacity_plot_go.json
+  versioned: true
+
+dummy_confusion_matrix:
+  type: matplotlib.MatplotlibWriter
+  filepath: data/08_reporting/dummy_confusion_matrix.png
+  versioned: true

conf/base/parameters_data_science.yml

@@ -0,0 +1,12 @@
+model_options:
+  test_size: 0.2
+  random_state: 3
+  features:
+    - engines
+    - passenger_capacity
+    - crew
+    - d_check_complete
+    - moon_clearance_complete
+    - iata_approved
+    - company_rating
+    - review_scores_rating

conf/logging.yml

@@ -0,0 +1,43 @@
+# To enable this custom logging configuration, set KEDRO_LOGGING_CONFIG to the path of this file.
+# More information available at https://docs.kedro.org/en/stable/logging/logging.html
+version: 1
+
+disable_existing_loggers: False
+
+formatters:
+  simple:
+    format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+
+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: info.log
+    maxBytes: 10485760 # 10MB
+    backupCount: 20
+    encoding: utf8
+    delay: True
+
+  rich:
+    class: kedro.logging.RichHandler
+    rich_tracebacks: True
+    # Advance options for customisation.
+    # See https://docs.kedro.org/en/stable/logging/logging.html#project-side-logging-configuration
+    # tracebacks_show_locals: False
+
+loggers:
+  kedro:
+    level: INFO
+
+  spaceflights_pandas_viz:
+    level: INFO
+
+root:
+  handlers: [rich, info_file_handler]