Merge final release (#1)

* adding initial skeleton * updating .gitignore * updating dev dependencies * adding report.py * updating notes * adding prospector.yaml * updating beam to install gcp extras * adding documentation * adding data exploration report + code * adding latest beam pipeline code * adding latest beam pipeline code * adding debug.py * adding latesty beam pipeline code * adding latest beam pipeline code * adding latest beam pipeline code * updating .gitignore * updating folder structure for data input/output * updating prospector.yaml * adding latest beam pipeline code * updating prospector.yaml * migrate beam pipeline to main.py * updating .gitignore * updating .gitignore * adding download script for data set * adding initial docs * moving inputs/outputs to use pathlib * removing shard_name_template from output file * adding pyenv 3.7.9 * removing requirements.txt for documentation * updating README.md * updating download data script for new location in GCS * adding latest beam pipeline code for dataflow * adding latest beam pipeline code for dataflow * adding latest beam pipeline code for dataflow * moving dataflow notes * updating prospector.yaml * adding latest beam pipeline code for dataflow * updating beam pipeline to use GroupByKey * updating download_data script with new bucket * update prospector.yaml * update dataflow documentation with new commands for vpc * adding latest beam pipeline code for dataflow with group optimisation * updating dataflow documentation * adding latest beam pipeline code for dataflow with group optimisation * updating download_data script with pp-2020 dataset * adding temporary notes * updating dataflow notes * adding latest beam pipeline code * updating dataflow notes * adding latest beam pipeline code for dataflow * adding debug print * moving panda-profiling report into docs * updating report.py * adding entrypoint command * adding initial docs * adding commands.md to notes * commenting out debug imports * updating documentation * updating latest beam pipeline with default inputs * updating poetry * adding requirements.txt * updating documentation
2025-12-22 20:05:45 +00:00 · 2021-09-28 00:31:09 +01:00
parent 8a22bfebe1
commit 80376a662e
34 changed files with 5667 additions and 1 deletions
--- a/prospector.yaml
+++ b/prospector.yaml
@@ -0,0 +1,80 @@
+# This will enable almost every single warning
+output-format: vscode
+doc-warnings: true
+# allow-shorthand: false
+strictness: none
+
+ignore-patterns:
+  - (^|/)\..+
+
+pylint:
+  run: true
+  disable:
+    - fixme
+    - bad-continuation
+    - missing-module-docstring
+    - logging-fstring-interpolation
+    - missing-function-docstring
+    - abstract-method
+    - missing-class-docstring
+    - super-init-not-called
+    - arguments-differ
+    - inconsistent-return-statements
+    - expression-not-assigned
+    - line-too-long
+  enable:
+
+  options:
+    max-locals: 15
+    max-returns: 6
+    max-branches: 12
+    max-statements: 50
+    # max-parents: 7
+    max-attributes: 20
+    min-public-methods: 0
+    max-public-methods: 25
+    max-module-lines: 1000
+    max-line-length: 88
+
+mccabe:
+  run: true
+  options:
+    max-complexity: 10
+
+pep8:
+  run: true
+  options:
+    max-line-length: 88
+    single-line-if-stmt: n
+  disable:
+    - E501 # line too long
+
+pyroma:
+  run: false
+  disable:
+    - PYR19
+    - PYR16
+
+pep257:
+  disable:
+    - D000
+    - D203
+    # - D213
+    - D212 # multiline docstrings on first line only.
+    - D404
+    - D100
+    - D407 # numpy docstring format
+    - D107 # missing docstring in __init__
+    # Docstrings ending with newlines and : in Returns block.
+    - D413
+    - D406
+    - D103
+    - D101 # missing docstring in public class
+    - D102 # missing docstring in public method
+
+pyflakes:
+  disable:
+    - F401 # unused import
+
+dodgy:
+  run: true