From 4cec1bb37e9e085a34cae56bc6fc77982dfed182 Mon Sep 17 00:00:00 2001
From: Shaun Verch <Shaun.M.Verch@omb.eop.gov>
Date: Thu, 13 Jan 2022 13:17:30 -0500
Subject: [PATCH] Install and run pandas-vet (#1119)

* Install and run pandas-vet

This doesn't fix the errors, but it can give us a starting point for the
discussion of which of these errors we care about.

* Ignore the errors for now

* Ignore eeoc.gov in link checker

Sometimes it seems down from the perspective of github actions.
---
 data/data-pipeline/.flake8        | 11 +++++++++--
 data/data-pipeline/poetry.lock    | 18 +++++++++++++++++-
 data/data-pipeline/pyproject.toml |  1 +
 3 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/data/data-pipeline/.flake8 b/data/data-pipeline/.flake8
index b88df142..f217b57d 100644
--- a/data/data-pipeline/.flake8
+++ b/data/data-pipeline/.flake8
@@ -1,7 +1,14 @@
 [flake8]
 ignore =
   E266,  # to many leading '#' for block comment
-  W503  # line break before binary operator
+  W503,  # line break before binary operator
+  # TODO: Uncomment and fix the issues here that we care about, see
+  # https://github.com/usds/justice40-tool/issues/1123
+  PD002,
+  PD003,
+  PD004,
+  PD010,
+  PD901
 max-line-length = 150
 max-complexity = 18
-select = B,C,E,F,W,T4,B9
+select = B,C,E,F,W,T4,B9,PD
diff --git a/data/data-pipeline/poetry.lock b/data/data-pipeline/poetry.lock
index 5b5f0988..690b7932 100644
--- a/data/data-pipeline/poetry.lock
+++ b/data/data-pipeline/poetry.lock
@@ -1050,6 +1050,18 @@ pytz = ">=2017.3"
 [package.extras]
 test = ["hypothesis (>=3.58)", "pytest (>=6.0)", "pytest-xdist"]
 
+[[package]]
+name = "pandas-vet"
+version = "0.2.2"
+description = "A flake8 plugin to lint pandas in an opinionated way"
+category = "dev"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+attrs = "*"
+flake8 = ">3.0.0"
+
 [[package]]
 name = "pandocfilters"
 version = "1.5.0"
@@ -1700,7 +1712,7 @@ testing = ["pytest (>=4.6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytes
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.7.1"
-content-hash = "f832db8cb99fd9f868d6e03c7536b7679bfdc0228693ba796ae2a4028b641a28"
+content-hash = "208cadba99466a38822740b0b78e5be94c4bf728eb79eda4c40cfd0d22901907"
 
 [metadata.files]
 appnope = [
@@ -2365,6 +2377,10 @@ pandas = [
     {file = "pandas-1.3.4-cp39-cp39-win_amd64.whl", hash = "sha256:a51528192755f7429c5bcc9e80832c517340317c861318fea9cea081b57c9afd"},
     {file = "pandas-1.3.4.tar.gz", hash = "sha256:a2aa18d3f0b7d538e21932f637fbfe8518d085238b429e4790a35e1e44a96ffc"},
 ]
+pandas-vet = [
+    {file = "pandas-vet-0.2.2.tar.gz", hash = "sha256:0a316c3edaaa1bcd772bfaea0e8d2b2aa409b740198746a2b60f2007b313f42e"},
+    {file = "pandas_vet-0.2.2-py3-none-any.whl", hash = "sha256:961235064ebe5b38ca9c3f45961fdce61796a01aea1f07b06b67f6b359aabea2"},
+]
 pandocfilters = [
     {file = "pandocfilters-1.5.0-py2.py3-none-any.whl", hash = "sha256:33aae3f25fd1a026079f5d27bdd52496f0e0803b3469282162bafdcbdf6ef14f"},
     {file = "pandocfilters-1.5.0.tar.gz", hash = "sha256:0b679503337d233b4339a817bfc8c50064e2eff681314376a47cb582305a7a38"},
diff --git a/data/data-pipeline/pyproject.toml b/data/data-pipeline/pyproject.toml
index 490ab806..fcb538b5 100644
--- a/data/data-pipeline/pyproject.toml
+++ b/data/data-pipeline/pyproject.toml
@@ -37,6 +37,7 @@ safety = "^1.10.3"
 tox = "^3.24.0"
 pytest-mock = "^3.6.1"
 tox-poetry = "^0.4.1"
+pandas-vet = "^0.2.2"
 
 [build-system]
 build-backend = "poetry.core.masonry.api"