From f420b0d56c0bad55464cebdf842fcfae6ab0421c Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Fri, 19 Jul 2019 19:48:33 -0400
Subject: [PATCH] Reorganize, update code, and add travis/tox

Closes #3. Begins #2
---
 .travis.yml                                   |  27 ++++
 LICENSE                                       |   2 +-
 setup.cfg                                     |   8 +-
 src/guilty_phewas/__init__.py                 |   6 -
 src/guilty_phewas/__main__.py                 |  14 --
 src/guilty_phewas/script.py                   |  22 ---
 src/guiltytargets_phewas/__init__.py          |   3 +
 .../constants.py                              |   4 +-
 .../network_phewas.py                         |  31 ++--
 .../pulearn.py                                |  25 ++--
 src/guiltytargets_phewas/script.py            |  28 ++++
 .../string_ppi_assembler.py                   |   6 +-
 .../utils.py                                  |  19 ++-
 tox.ini                                       | 138 ++++++++++++++++++
 14 files changed, 255 insertions(+), 78 deletions(-)
 create mode 100644 .travis.yml
 delete mode 100644 src/guilty_phewas/__init__.py
 delete mode 100644 src/guilty_phewas/__main__.py
 delete mode 100644 src/guilty_phewas/script.py
 create mode 100644 src/guiltytargets_phewas/__init__.py
 rename src/{guilty_phewas => guiltytargets_phewas}/constants.py (58%)
 rename src/{guilty_phewas => guiltytargets_phewas}/network_phewas.py (92%)
 rename src/{guilty_phewas => guiltytargets_phewas}/pulearn.py (89%)
 create mode 100644 src/guiltytargets_phewas/script.py
 rename src/{guilty_phewas => guiltytargets_phewas}/string_ppi_assembler.py (99%)
 rename src/{guilty_phewas => guiltytargets_phewas}/utils.py (97%)
 create mode 100644 tox.ini

diff --git a/.travis.yml b/.travis.yml
new file mode 100644
index 0000000..2c1558c
--- /dev/null
+++ b/.travis.yml
@@ -0,0 +1,27 @@
+sudo: false
+cache: pip
+language: python
+python:
+  - "3.6"
+stages:
+  - lint
+  - docs
+jobs:
+  include:
+    # lint stage
+    - stage: lint
+      env: TOXENV=manifest
+    - env: TOXENV=flake8
+    - env: TOXENV=xenon
+    # docs stage
+    - stage: docs
+      env: TOXENV=doc8
+    - env: TOXENV=readme
+    - env: TOXENV=docs
+matrix:
+  allow_failures:
+    - env: TOXENV=xenon
+install:
+  - pip install tox
+script:
+  - tox
diff --git a/LICENSE b/LICENSE
index 8b23445..682d4b7 100644
--- a/LICENSE
+++ b/LICENSE
@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2019 
+Copyright (c) GuiltyTargets Developers, 2019
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
diff --git a/setup.cfg b/setup.cfg
index 216a71d..f2fea4b 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -2,7 +2,7 @@
 # Setup.py Configuration #
 ##########################
 [metadata]
-name = guilty_reloaded
+name = guiltytargets_phewas
 version = 0.0.1-dev
 description = Change meeeeee
 long_description = file: README.rst
@@ -13,15 +13,17 @@ author_email = mauriciopl@gmail.com
 maintainer = Mauricio Pio de Lacerda
 maintainer_email = mauriciopl@gmail.com
 
+url = https://github.com/GuiltyTargets/phewas
+
 # License Information
-license = Apache 2.0 License
+license = MIT
 license_file = LICENSE
 
 # Search tags
 classifiers =
     Development Status :: 1 - Planning
     Intended Audience :: Developers
-    License :: OSI Approved :: Apache Software License
+    License :: OSI Approved :: MIT License
     Operating System :: OS Independent
     Programming Language :: Python
     Programming Language :: Python :: 3.6
diff --git a/src/guilty_phewas/__init__.py b/src/guilty_phewas/__init__.py
deleted file mode 100644
index e61fdc9..0000000
--- a/src/guilty_phewas/__init__.py
+++ /dev/null
@@ -1,6 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""A dream come true."""
-
-def get_version():
-    return ""
diff --git a/src/guilty_phewas/__main__.py b/src/guilty_phewas/__main__.py
deleted file mode 100644
index 65944d6..0000000
--- a/src/guilty_phewas/__main__.py
+++ /dev/null
@@ -1,14 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""Entrypoint module, in case you use ``python3 -m module_name``.
-
-Why does this file exist, and why ``__main__``? For more info, read:
-
-- https://www.python.org/dev/peps/pep-0338/
-- https://docs.python.org/3/using/cmdline.html#cmdoption-m
-"""
-
-from .cli import main
-
-if __name__ == '__main__':
-    main()
diff --git a/src/guilty_phewas/script.py b/src/guilty_phewas/script.py
deleted file mode 100644
index 7687fcd..0000000
--- a/src/guilty_phewas/script.py
+++ /dev/null
@@ -1,22 +0,0 @@
-from GAT2VEC.evaluation.classification import Classification
-from GAT2VEC.gat2vec import Gat2Vec
-from guiltytargets.constants import gat2vec_config
-
-dir_ = "C:/Users/Mauricio/Thesis/bel_data/alzh"  # windows
-# dir_ = "C:\\Users\\Mauricio\\Thesis\\git\\reproduction\\data\\lc"
-
-classifier = Classification(dir_, dir_, tr=gat2vec_config.training_ratio)
-
-g2v = Gat2Vec(dir_, dir_, label=False, tr=gat2vec_config.training_ratio)
-model = g2v.train_gat2vec(
-        gat2vec_config.num_walks,
-        gat2vec_config.walk_length,
-        gat2vec_config.dimension,
-        gat2vec_config.window_size,
-        output=True,
-    )
-
-classifier = Classification(dir_, dir_, tr=gat2vec_config.training_ratio)
-
-auc_df = classifier.evaluate(model, label=False, evaluation_scheme="cv")
-
diff --git a/src/guiltytargets_phewas/__init__.py b/src/guiltytargets_phewas/__init__.py
new file mode 100644
index 0000000..cd0040a
--- /dev/null
+++ b/src/guiltytargets_phewas/__init__.py
@@ -0,0 +1,3 @@
+# -*- coding: utf-8 -*-
+
+"""GuiltyTargets PheWAS Extension."""
\ No newline at end of file
diff --git a/src/guilty_phewas/constants.py b/src/guiltytargets_phewas/constants.py
similarity index 58%
rename from src/guilty_phewas/constants.py
rename to src/guiltytargets_phewas/constants.py
index e055fcc..69b83fd 100644
--- a/src/guilty_phewas/constants.py
+++ b/src/guiltytargets_phewas/constants.py
@@ -1,6 +1,8 @@
 # -*- coding: utf-8 -*-
 
+"""Constants for GuiltyTargets PheWAS."""
+
 data_dir = 'data'
 disease_abr = ['ad']
 disease_ids_efo = ['EFO_0000249']
-ot_file = 'ot_entrez.txt'
\ No newline at end of file
+ot_file = 'ot_entrez.txt'
diff --git a/src/guilty_phewas/network_phewas.py b/src/guiltytargets_phewas/network_phewas.py
similarity index 92%
rename from src/guilty_phewas/network_phewas.py
rename to src/guiltytargets_phewas/network_phewas.py
index b2a1d0c..1e421d5 100644
--- a/src/guilty_phewas/network_phewas.py
+++ b/src/guiltytargets_phewas/network_phewas.py
@@ -7,8 +7,13 @@
 
 import networkx as nx
 import numpy as np
-from ppi_network_annotation.model.gene import Gene
-from pybel.dsl import protein, rna, gene
+from pybel.dsl import gene, protein, rna
+
+from guiltytargets.ppi_network_annotation import Gene
+
+__all__ = [
+    'NetworkNx',
+]
 
 logger = logging.getLogger(__name__)
 
@@ -16,11 +21,13 @@
 class NetworkNx:
     """Encapsulate a PPI network with differential gene expression, phenotypes and disease association annotation."""
 
-    def __init__(self,
-                 ppi_graph: nx.Graph,
-                 max_adj_p: Optional[float] = None,
-                 max_l2fc: Optional[float] = None,
-                 min_l2fc: Optional[float] = None):
+    def __init__(
+            self,
+            ppi_graph: nx.Graph,
+            max_adj_p: Optional[float] = None,
+            max_l2fc: Optional[float] = None,
+            min_l2fc: Optional[float] = None,
+    ) -> None:
         """Initialize the network object.
 
         :param ppi_graph: A graph of protein interactions.
@@ -63,8 +70,11 @@ def filter_genes(self, relevant_entrez: list) -> None:
         logger.info("In filter_genes()")
         raise Exception('Not ready to filter genes using NetworkX')
 
-    def _add_vertex_attributes(self, genes: List[Gene],
-                               disease_associations: Optional[dict] = None) -> None:
+    def _add_vertex_attributes(
+            self,
+            genes: List[Gene],
+            disease_associations: Optional[dict] = None,
+    ) -> None:
         """Add attributes to vertices.
 
         :param genes: A list of genes containing attribute information.
@@ -158,8 +168,7 @@ def get_attribute_from_indices(self, indices: list, attribute_name: str):
         return list(np.array(self.graph.vs[attribute_name])[indices])
 
     def get_differentially_expressed_genes(self, diff_type: str) -> List:
-        """Get up regulated, down regulated, all differentially expressed or not
-        differentially expressed nodes.
+        """Get up regulated, down regulated, all differentially expressed or not differentially expressed nodes.
 
         :param diff_type: One of `not_diff_expressed`, `diff_expressed`, `up_regulated`, `down_regulated`
         :return: A list of nodes corresponding to diff_type.
diff --git a/src/guilty_phewas/pulearn.py b/src/guiltytargets_phewas/pulearn.py
similarity index 89%
rename from src/guilty_phewas/pulearn.py
rename to src/guiltytargets_phewas/pulearn.py
index ca39f68..f4d4a1b 100644
--- a/src/guilty_phewas/pulearn.py
+++ b/src/guiltytargets_phewas/pulearn.py
@@ -3,21 +3,22 @@
 from collections import defaultdict
 
 import pandas as pd
-from GAT2VEC import parsers, paths
-from GAT2VEC.evaluation.classification import Classification
 from sklearn import svm
 from sklearn.metrics import accuracy_score, f1_score, roc_auc_score
 from sklearn.model_selection import StratifiedKFold
 
+from guiltytargets.gat2vec import Classification, Gat2Vec, gat2vec_parsers, gat2vec_paths
 
-# TODO move to GAT2VEC (forked)?
+__all__ = [
+    'PULearn',
+]
 
 
+# TODO move to GAT2VEC (forked)?
 class PULearn(Classification):
-    """ """
 
     def evaluate(self, model, label=False, evaluation_scheme="tr", cost_p: float = None, cost_n: float = None):
-        """Evaluates the model according to the given evaluation scheme.
+        """Evaluate the model according to the given evaluation scheme.
 
         :param model:
         :param label:
@@ -30,7 +31,7 @@ def evaluate(self, model, label=False, evaluation_scheme="tr", cost_p: float = N
         clf = self.get_classifier()
 
         if not label:
-            embedding = parsers.get_embeddingDF(model)
+            embedding = gat2vec_parsers.get_embeddingDF(model)
 
         if evaluation_scheme == "bsvm":
             if cost_n and cost_p and cost_n > 0 and cost_p > 0:
@@ -44,9 +45,9 @@ def evaluate(self, model, label=False, evaluation_scheme="tr", cost_p: float = N
             for tr in self.TR:
                 print("TR ... ", tr)
                 if label:
-                    model = paths.get_embedding_path_wl(self.dataset_dir, self.output_dir, tr)
+                    model = gat2vec_paths.get_embedding_path_wl(self.dataset_dir, self.output_dir, tr)
                     if isinstance(model, str):
-                        embedding = parsers.get_embeddingDF(model)
+                        embedding = gat2vec_parsers.get_embeddingDF(model)
                 results.update(self.evaluate_tr(clf, embedding, tr))
 
         print("Training Finished")
@@ -89,9 +90,7 @@ def get_biased_predictions(clf, x_train, x_test, y_train, cost_p, cost_n):
         return clf.predict(x_test), clf.predict_proba(x_test)
 
 
-if __name__ == '__main__':
-    from GAT2VEC.gat2vec import Gat2Vec
-
+def main():
     dir_ = "C:/Users/Mauricio/Thesis/bel_data/alzh"
     g2v = Gat2Vec(dir_, dir_, label=False, tr=[0.1, 0.3, 0.5])
     walk_length = 4
@@ -111,3 +110,7 @@ def get_biased_predictions(clf, x_train, x_test, y_train, cost_p, cost_n):
     print('PU created.')
     auc_df = pul.evaluate(model, label=False, evaluation_scheme="bsvm")
     print(auc_df)
+
+
+if __name__ == '__main__':
+    main()
diff --git a/src/guiltytargets_phewas/script.py b/src/guiltytargets_phewas/script.py
new file mode 100644
index 0000000..b4ecbfb
--- /dev/null
+++ b/src/guiltytargets_phewas/script.py
@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-
+
+from guiltytargets.constants import gat2vec_config
+from guiltytargets.gat2vec import Classification, Gat2Vec
+
+
+def main():
+    dir_ = "C:/Users/Mauricio/Thesis/bel_data/alzh"  # windows
+    # dir_ = "C:\\Users\\Mauricio\\Thesis\\git\\reproduction\\data\\lc"
+
+    classifier = Classification(dir_, dir_, tr=gat2vec_config.training_ratio)
+
+    g2v = Gat2Vec(dir_, dir_, label=False, tr=gat2vec_config.training_ratio)
+    model = g2v.train_gat2vec(
+        gat2vec_config.num_walks,
+        gat2vec_config.walk_length,
+        gat2vec_config.dimension,
+        gat2vec_config.window_size,
+        output=True,
+    )
+
+    classifier = Classification(dir_, dir_, tr=gat2vec_config.training_ratio)
+
+    auc_df = classifier.evaluate(model, label=False, evaluation_scheme="cv")
+
+
+if __name__ == '__main__':
+    main()
diff --git a/src/guilty_phewas/string_ppi_assembler.py b/src/guiltytargets_phewas/string_ppi_assembler.py
similarity index 99%
rename from src/guilty_phewas/string_ppi_assembler.py
rename to src/guiltytargets_phewas/string_ppi_assembler.py
index 150fba7..1df7ea8 100644
--- a/src/guilty_phewas/string_ppi_assembler.py
+++ b/src/guiltytargets_phewas/string_ppi_assembler.py
@@ -68,6 +68,10 @@ def _get_ensembl_id_to_symbol_converter(self) -> Dict:
         return dict(data3[['protein_external_id', 'preferred_name']].values)
 
 
-if __name__ == '__main__':
+def main():
     assembler = StringAssembler()
     assembler.create_adj_file()
+
+
+if __name__ == '__main__':
+    main()
diff --git a/src/guilty_phewas/utils.py b/src/guiltytargets_phewas/utils.py
similarity index 97%
rename from src/guilty_phewas/utils.py
rename to src/guiltytargets_phewas/utils.py
index e259e7e..814960c 100644
--- a/src/guilty_phewas/utils.py
+++ b/src/guiltytargets_phewas/utils.py
@@ -6,13 +6,13 @@
 from typing import Dict, List, Optional
 
 import bio2bel_phewascatalog
-from guiltytargets.ppi_network_annotation.model.gene import Gene
 import mygene
-import pandas as pd
 import networkx as nx
+import pandas as pd
 from opentargets import OpenTargetsClient
 from pybel.dsl import BaseEntity, gene, protein, rna
 
+from guiltytargets.ppi_network_annotation.model.gene import Gene
 from .network_phewas import NetworkNx
 
 
@@ -67,9 +67,11 @@ def get_significantly_differentiated(gene_list: List[Gene], max_adjp: float):
     """Returns a dictionary only with significantly differentially expressed genes from the gene list."""
     max_adjp = max_adjp or 0.05
 
-    dge = {g.entrez_id or g.symbol: g.log2_fold_change 
-           for g in gene_list 
-           if g.padj < max_adjp}
+    dge = {
+        g.entrez_id or g.symbol: g.log2_fold_change
+        for g in gene_list
+        if g.padj < max_adjp
+    }
 
     return {k: v for k, v in dge.items() if k}
 
@@ -123,8 +125,10 @@ def get_association_scores(disease_id, outpath):
         fields=['association_scoreoverall', 'target.id']
     )
     assoc_simple = [
-        {'id': a['target']['id'],
-         'score': a['association_score']['overall']}
+        {
+            'id': a['target']['id'],
+            'score': a['association_score']['overall']
+        }
         for a in assoc
     ]
     ensembl_list = [a['id'] for a in assoc_simple]
@@ -305,4 +309,3 @@ def _add_attribute_values(value, att_mappings, indices):
         """
         for i in indices:
             att_mappings[i].append(value)
-
diff --git a/tox.ini b/tox.ini
new file mode 100644
index 0000000..e8f702b
--- /dev/null
+++ b/tox.ini
@@ -0,0 +1,138 @@
+[tox]
+envlist =
+    coverage-clean
+    manifest
+    flake8
+    readme
+    doc8
+    docs
+    py
+    coverage-report
+
+[testenv]
+commands = coverage run -p -m pytest tests {posargs}
+passenv = CI TRAVIS TRAVIS_*
+deps =
+    coverage
+    pytest
+whitelist_externals =
+    /bin/cat
+    /bin/cp
+    /bin/mkdir
+    /usr/bin/git
+    /usr/local/bin/hub
+
+[testenv:coverage-clean]
+deps = coverage
+skip_install = true
+commands = coverage erase
+
+[testenv:coverage-report]
+deps = coverage
+skip_install = true
+commands =
+    coverage combine
+    coverage report
+
+[testenv:manifest]
+deps = check-manifest
+commands = check-manifest
+skip_install = true
+
+[testenv:xenon]
+deps = xenon
+skip_install = true
+commands = xenon --max-average A --max-modules A --max-absolute B .
+description = Run the xenon tool to monitor code complexity.
+
+[testenv:mypy]
+deps = mypy
+skip_install = true
+commands = mypy --ignore-missing-imports src/guiltytargets_phewas/
+description = Run the mypy tool to check static typing on the project.
+
+[testenv:pyroma]
+deps =
+    pygments
+    pyroma
+skip_install = true
+commands = pyroma --min=10 .
+description = Run the pyroma tool to check the project's package friendliness.
+
+[testenv:docs]
+changedir = docs
+deps =
+    sphinx
+    sphinx-rtd-theme
+    sphinx-autodoc-typehints
+commands =
+    mkdir -p {envtmpdir}
+    cp -r source {envtmpdir}/source
+    sphinx-build -W -b html -d {envtmpdir}/build/doctrees {envtmpdir}/source {envtmpdir}/build/html
+    sphinx-build -W -b coverage -d {envtmpdir}/build/doctrees {envtmpdir}/source {envtmpdir}/build/coverage
+    cat {envtmpdir}/build/coverage/c.txt
+    cat {envtmpdir}/build/coverage/python.txt
+
+[testenv:readme]
+commands = rst-lint README.rst
+skip_install = true
+deps =
+    restructuredtext_lint
+    pygments
+
+[testenv:flake8]
+skip_install = true
+deps =
+    flake8
+    flake8-docstrings>=0.2.7
+    flake8-import-order>=0.9
+    pep8-naming
+    flake8-colors
+commands =
+    flake8 src/guiltytargets_phewas/ tests/ setup.py
+
+[testenv:doc8]
+skip_install = true
+deps =
+    sphinx
+    doc8
+commands =
+    doc8 docs/source/ README.rst
+
+####################
+# Deployment tools #
+####################
+
+[testenv:bumpversion]
+commands = bumpversion {posargs}
+skip_install = true
+deps =
+    bumpversion
+
+[testenv:build]
+skip_install = true
+deps =
+    wheel
+    setuptools
+commands =
+    python setup.py -q sdist bdist_wheel
+
+[testenv:release]
+skip_install = true
+deps =
+    {[testenv:build]deps}
+    twine >= 1.5.0
+commands =
+    {[testenv:build]commands}
+    twine upload --skip-existing dist/*
+
+[testenv:finish]
+skip_install = true
+deps =
+    {[testenv:release]deps}
+    bumpversion
+commands =
+    bumpversion release
+    {[testenv:release]commands}
+    git push
+    bumpversion patch