From 7fda59e673103815d54135e13475721fec061e5d Mon Sep 17 00:00:00 2001
From: Justin Reese <justaddcoffee+github@gmail.com>
Date: Sun, 3 May 2020 13:15:06 -0700
Subject: [PATCH 1/2] Remove old HPO ingest

---
 kg_covid_19/transform_utils/hpo/__init__.py |  5 --
 kg_covid_19/transform_utils/hpo/hpo.py      | 98 ---------------------
 2 files changed, 103 deletions(-)
 delete mode 100644 kg_covid_19/transform_utils/hpo/__init__.py
 delete mode 100644 kg_covid_19/transform_utils/hpo/hpo.py

diff --git a/kg_covid_19/transform_utils/hpo/__init__.py b/kg_covid_19/transform_utils/hpo/__init__.py
deleted file mode 100644
index 18ac8db5..00000000
--- a/kg_covid_19/transform_utils/hpo/__init__.py
+++ /dev/null
@@ -1,5 +0,0 @@
-from .hpo import HpoTransform
-
-__all__ = [
-    "HpoTransform"
-]
diff --git a/kg_covid_19/transform_utils/hpo/hpo.py b/kg_covid_19/transform_utils/hpo/hpo.py
deleted file mode 100644
index 1d9ace1a..00000000
--- a/kg_covid_19/transform_utils/hpo/hpo.py
+++ /dev/null
@@ -1,98 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-import os
-from typing import Optional
-
-import obonet  # type: ignore
-from typing.io import TextIO  # type: ignore
-
-from kg_covid_19.transform_utils.transform import Transform
-from kg_covid_19.utils import write_node_edge_item
-from kg_covid_19.utils.transform_utils import get_item_by_priority, data_to_dict, \
-    ItemInDictNotFound
-
-"""Ingest Human Phenotype Ontology (no annotations for now, just the ontology)
-
-Dataset location: https://raw.githubusercontent.com/obophenotype/human-phenotype-ontology/master/hp.obo
-GitHub Issue: https://github.com/Knowledge-Graph-Hub/kg-covid-19/issues/48
-
-"""
-
-
-class HpoTransform(Transform):
-
-    def __init__(self, input_dir: str = None, output_dir: str = None):
-        source_name = "hpo"
-        super().__init__(source_name, input_dir, output_dir)
-
-    def run(self, data_file: Optional[str] = None):
-        self.node_header.extend(["comments", "description"])
-        hpo_node_type = "biolink:PhenotypicFeature"
-        hpo_edge_label = "rdfs:subClassOf"
-        hpo_ro_relation = "RO:0002351"
-        hpo_obo_file = os.path.join(self.input_base_dir, "hp.obo")
-
-        # transform data, something like:
-        with open(self.output_node_file, 'w') as node, \
-             open(self.output_edge_file, 'w') as edge:
-
-            # write headers (change default node/edge headers if necessary
-            node.write("\t".join(self.node_header) + "\n")
-            edge.write("\t".join(self.edge_header) + "\n")
-
-            graph = obonet.read_obo(hpo_obo_file)
-
-            for id_, data in graph.nodes(data=True):
-
-                # Write HPO nodes
-                self.write_hpo_node(node, id_, data, hpo_node_type)
-
-                # if we see is_a relationship(s), write parent-child edge(s)
-                if 'is_a' in data:
-                    for parent in data['is_a']:
-                        self.write_hpo_edge(edge,
-                                            id_,
-                                            hpo_edge_label,
-                                            parent,
-                                            hpo_ro_relation)
-
-
-    def write_hpo_node(self, fh: TextIO, id: str, data: dict, node_type: str) -> None:
-        # Try to get comments/def in case this is useful for ML
-        try:
-            comment_field = get_item_by_priority(data, ['comment'])
-        except ItemInDictNotFound:
-            comment_field = ""
-
-        try:
-            description = get_item_by_priority(data, ['def'])
-        except ItemInDictNotFound:
-            description = ""
-
-        try:
-            name_field = get_item_by_priority(data, ['name'])
-        except ItemInDictNotFound:
-            name_field = ""
-
-        write_node_edge_item(fh=fh, header=self.node_header,
-                             data=[id,
-                                   name_field,
-                                   node_type,
-                                   comment_field,
-                                   description
-                                   ])
-
-    def write_hpo_edge(self,
-                       fh: TextIO,
-                       subject: str,
-                       edge_label: str,
-                       object: str,
-                       relation: str) -> None:
-
-        # ['subject', 'edge_label', 'object', 'relation', 'publications']
-        write_node_edge_item(fh=fh, header=self.edge_header,
-                             data=[subject,
-                                   edge_label,
-                                   object,
-                                   relation,
-                                   ""])

From aed13ae82b722ecd764fd1ce996798b2c22ec1fb Mon Sep 17 00:00:00 2001
From: Justin Reese <justaddcoffee+github@gmail.com>
Date: Sun, 3 May 2020 13:15:32 -0700
Subject: [PATCH 2/2] Remove unused import

---
 kg_covid_19/transform.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kg_covid_19/transform.py b/kg_covid_19/transform.py
index 9a721c28..fc8095f3 100644
--- a/kg_covid_19/transform.py
+++ b/kg_covid_19/transform.py
@@ -4,7 +4,6 @@
 from typing import List
 
 from kg_covid_19.transform_utils.drug_central.drug_central import DrugCentralTransform
-from kg_covid_19.transform_utils.hpo.hpo import HpoTransform
 from kg_covid_19.transform_utils.intact.intact import IntAct
 from kg_covid_19.transform_utils.ontology import OntologyTransform
 from kg_covid_19.transform_utils.ontology.ontology_transform import ONTOLOGIES