Skip to content

Commit 0d33fd2

Browse files
cmungallcmungall
authored
Merge pull request #16 from linkml/patch-utils
Adding filesystem handler.
2 parents 0872233 + 633acc2 commit 0d33fd2

24 files changed

+3246
-1291
lines changed

‎.github/workflows/qc.yml

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
name: linkml-data-browser QC
1+
name: linkml-store QC
22

33
on:
44
push:
@@ -12,6 +12,7 @@ jobs:
1212
strategy:
1313
matrix:
1414
python-version: [ "3.8", "3.11" ]
15+
mongodb-version: ['7.0']
1516

1617
steps:
1718
- uses: actions/checkout@v3.0.2
@@ -33,5 +34,10 @@ jobs:
3334
- name: Check code quality with flake8
3435
run: poetry run tox -e lint
3536

37+
- name: Start MongoDB
38+
uses: supercharge/mongodb-github-action@1.11.0
39+
with:
40+
mongodb-version: ${{ matrix.mongodb-version }}
41+
3642
- name: Test with pytest and generate coverage file
3743
run: poetry run pytest

‎docs/how-to/Query-Existing-MongoDB.ipynb

Lines changed: 156 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,156 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"id": "initial_id",
7+
"metadata": {
8+
"collapsed": true,
9+
"ExecuteTime": {
10+
"end_time": "2024-06-23T01:39:45.566588Z",
11+
"start_time": "2024-06-23T01:39:44.203426Z"
12+
}
13+
},
14+
"outputs": [],
15+
"source": [
16+
"from linkml_store import Client\n",
17+
"\n",
18+
"client = Client()"
19+
]
20+
},
21+
{
22+
"cell_type": "code",
23+
"execution_count": 2,
24+
"outputs": [],
25+
"source": [
26+
"db = client.attach_database(\"mongodb://localhost:27017/nmdc\")"
27+
],
28+
"metadata": {
29+
"collapsed": false,
30+
"ExecuteTime": {
31+
"end_time": "2024-06-23T01:39:45.571778Z",
32+
"start_time": "2024-06-23T01:39:45.566759Z"
33+
}
34+
},
35+
"id": "73685fd7e60f63b2"
36+
},
37+
{
38+
"cell_type": "code",
39+
"execution_count": 3,
40+
"outputs": [
41+
{
42+
"data": {
43+
"text/plain": "['nmdc_schema_version',\n 'ids_nmdc_gfs0',\n 'nom_analysis_activity_set',\n 'read_qc_analysis_activity_set',\n 'roles']"
44+
},
45+
"execution_count": 3,
46+
"metadata": {},
47+
"output_type": "execute_result"
48+
}
49+
],
50+
"source": [
51+
"db.list_collection_names()[0:5]"
52+
],
53+
"metadata": {
54+
"collapsed": false,
55+
"ExecuteTime": {
56+
"end_time": "2024-06-23T01:39:45.605798Z",
57+
"start_time": "2024-06-23T01:39:45.572040Z"
58+
}
59+
},
60+
"id": "46fac5899adf5b7e"
61+
},
62+
{
63+
"cell_type": "code",
64+
"execution_count": 4,
65+
"outputs": [],
66+
"source": [
67+
"collection = db.get_collection(\"biosample_set\")\n"
68+
],
69+
"metadata": {
70+
"collapsed": false,
71+
"ExecuteTime": {
72+
"end_time": "2024-06-23T01:39:45.608722Z",
73+
"start_time": "2024-06-23T01:39:45.605907Z"
74+
}
75+
},
76+
"id": "fdc7d9bbd7a1ecae"
77+
},
78+
{
79+
"cell_type": "code",
80+
"execution_count": 5,
81+
"outputs": [],
82+
"source": [
83+
"qr = collection.find({}, limit=5)"
84+
],
85+
"metadata": {
86+
"collapsed": false,
87+
"ExecuteTime": {
88+
"end_time": "2024-06-23T01:39:45.711560Z",
89+
"start_time": "2024-06-23T01:39:45.609722Z"
90+
}
91+
},
92+
"id": "ed5a741307293cfa"
93+
},
94+
{
95+
"cell_type": "code",
96+
"execution_count": 6,
97+
"outputs": [
98+
{
99+
"data": {
100+
"text/plain": " id name \\\n0 gold:Gb0115231 Sand microcosm microbial communities from a hy... \n1 gold:Gb0115220 Sand microcosm microbial communities from a hy... \n2 gold:Gb0115221 Sand microcosm microbial communities from a hy... \n3 gold:Gb0115228 Sand microcosm microbial communities from a hy... \n4 gold:Gb0115225 Sand microcosm microbial communities from a hy... \n\n description \\\n0 Sterilized sand packs were incubated back in t... \n1 Sterilized sand packs were incubated back in t... \n2 Sterilized sand packs were incubated back in t... \n3 Sterilized sand packs were incubated back in t... \n4 Sterilized sand packs were incubated back in t... \n\n env_broad_scale \\\n0 {'has_raw_value': 'ENVO:01000253', 'term': {'i... \n1 {'has_raw_value': 'ENVO:01000253', 'term': {'i... \n2 {'has_raw_value': 'ENVO:01000253', 'term': {'i... \n3 {'has_raw_value': 'ENVO:01000253', 'term': {'i... \n4 {'has_raw_value': 'ENVO:01000253', 'term': {'i... \n\n env_local_scale \\\n0 {'has_raw_value': 'ENVO:01000621', 'term': {'i... \n1 {'has_raw_value': 'ENVO:01000621', 'term': {'i... \n2 {'has_raw_value': 'ENVO:01000621', 'term': {'i... \n3 {'has_raw_value': 'ENVO:01000621', 'term': {'i... \n4 {'has_raw_value': 'ENVO:01000621', 'term': {'i... \n\n env_medium type \\\n0 {'has_raw_value': 'ENVO:01000017', 'term': {'i... nmdc:Biosample \n1 {'has_raw_value': 'ENVO:01000017', 'term': {'i... nmdc:Biosample \n2 {'has_raw_value': 'ENVO:01000017', 'term': {'i... nmdc:Biosample \n3 {'has_raw_value': 'ENVO:01000017', 'term': {'i... nmdc:Biosample \n4 {'has_raw_value': 'ENVO:01000017', 'term': {'i... nmdc:Biosample \n\n collection_date \\\n0 {'has_raw_value': '2014-11-25'} \n1 {'has_raw_value': '2014-09-23'} \n2 {'has_raw_value': '2014-11-25'} \n3 {'has_raw_value': '2014-05-21'} \n4 {'has_raw_value': '2014-08-12'} \n\n depth \\\n0 {'has_raw_value': '0.5', 'has_numeric_value': ... \n1 {'has_raw_value': '0.5', 'has_numeric_value': ... \n2 {'has_raw_value': '0.5', 'has_numeric_value': ... \n3 {'has_raw_value': '0.5', 'has_numeric_value': ... \n4 {'has_raw_value': '0.5', 'has_numeric_value': ... \n\n geo_loc_name ... habitat \\\n0 {'has_raw_value': 'USA: Columbia River, Washin... ... sand microcosm \n1 {'has_raw_value': 'USA: Columbia River, Washin... ... sand microcosm \n2 {'has_raw_value': 'USA: Columbia River, Washin... ... sand microcosm \n3 {'has_raw_value': 'USA: Columbia River, Washin... ... sand microcosm \n4 {'has_raw_value': 'USA: Columbia River, Washin... ... sand microcosm \n\n location mod_date \\\n0 groundwater-surface water interaction zone in ... 2021-06-17 \n1 groundwater-surface water interaction zone in ... 2021-06-17 \n2 groundwater-surface water interaction zone in ... 2021-06-17 \n3 groundwater-surface water interaction zone in ... 2021-06-17 \n4 groundwater-surface water interaction zone in ... 2021-06-17 \n\n ncbi_taxonomy_name sample_collection_site part_of \\\n0 sediment metagenome sand microcosm [gold:Gs0114663] \n1 sediment metagenome sand microcosm [gold:Gs0114663] \n2 sediment metagenome sand microcosm [gold:Gs0114663] \n3 sediment metagenome sand microcosm [gold:Gs0114663] \n4 sediment metagenome sand microcosm [gold:Gs0114663] \n\n alternative_identifiers insdc_biosample_identifiers samp_name \\\n0 [img.taxon:3300042754] [biosample:SAMN06343877] GW-RW T4_25-Nov-14 \n1 [img.taxon:3300042744] [biosample:SAMN06343866] GW-RW T3_23-Sept-14 \n2 [img.taxon:3300042791] [biosample:SAMN06343867] GW-RW T3_25-Nov-14 \n3 [img.taxon:3300042751] [biosample:SAMN06343874] GW-RW T4_21-May-14 \n4 [img.taxon:3300042748] [biosample:SAMN06343871] GW-RW T4_12-Aug-14 \n\n gold_biosample_identifiers \n0 [gold:Gb0115231] \n1 [gold:Gb0115220] \n2 [gold:Gb0115221] \n3 [gold:Gb0115228] \n4 [gold:Gb0115225] \n\n[5 rows x 28 columns]",
101+
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>id</th>\n <th>name</th>\n <th>description</th>\n <th>env_broad_scale</th>\n <th>env_local_scale</th>\n <th>env_medium</th>\n <th>type</th>\n <th>collection_date</th>\n <th>depth</th>\n <th>geo_loc_name</th>\n <th>...</th>\n <th>habitat</th>\n <th>location</th>\n <th>mod_date</th>\n <th>ncbi_taxonomy_name</th>\n <th>sample_collection_site</th>\n <th>part_of</th>\n <th>alternative_identifiers</th>\n <th>insdc_biosample_identifiers</th>\n <th>samp_name</th>\n <th>gold_biosample_identifiers</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>gold:Gb0115231</td>\n <td>Sand microcosm microbial communities from a hy...</td>\n <td>Sterilized sand packs were incubated back in t...</td>\n <td>{'has_raw_value': 'ENVO:01000253', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000621', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000017', 'term': {'i...</td>\n <td>nmdc:Biosample</td>\n <td>{'has_raw_value': '2014-11-25'}</td>\n <td>{'has_raw_value': '0.5', 'has_numeric_value': ...</td>\n <td>{'has_raw_value': 'USA: Columbia River, Washin...</td>\n <td>...</td>\n <td>sand microcosm</td>\n <td>groundwater-surface water interaction zone in ...</td>\n <td>2021-06-17</td>\n <td>sediment metagenome</td>\n <td>sand microcosm</td>\n <td>[gold:Gs0114663]</td>\n <td>[img.taxon:3300042754]</td>\n <td>[biosample:SAMN06343877]</td>\n <td>GW-RW T4_25-Nov-14</td>\n <td>[gold:Gb0115231]</td>\n </tr>\n <tr>\n <th>1</th>\n <td>gold:Gb0115220</td>\n <td>Sand microcosm microbial communities from a hy...</td>\n <td>Sterilized sand packs were incubated back in t...</td>\n <td>{'has_raw_value': 'ENVO:01000253', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000621', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000017', 'term': {'i...</td>\n <td>nmdc:Biosample</td>\n <td>{'has_raw_value': '2014-09-23'}</td>\n <td>{'has_raw_value': '0.5', 'has_numeric_value': ...</td>\n <td>{'has_raw_value': 'USA: Columbia River, Washin...</td>\n <td>...</td>\n <td>sand microcosm</td>\n <td>groundwater-surface water interaction zone in ...</td>\n <td>2021-06-17</td>\n <td>sediment metagenome</td>\n <td>sand microcosm</td>\n <td>[gold:Gs0114663]</td>\n <td>[img.taxon:3300042744]</td>\n <td>[biosample:SAMN06343866]</td>\n <td>GW-RW T3_23-Sept-14</td>\n <td>[gold:Gb0115220]</td>\n </tr>\n <tr>\n <th>2</th>\n <td>gold:Gb0115221</td>\n <td>Sand microcosm microbial communities from a hy...</td>\n <td>Sterilized sand packs were incubated back in t...</td>\n <td>{'has_raw_value': 'ENVO:01000253', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000621', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000017', 'term': {'i...</td>\n <td>nmdc:Biosample</td>\n <td>{'has_raw_value': '2014-11-25'}</td>\n <td>{'has_raw_value': '0.5', 'has_numeric_value': ...</td>\n <td>{'has_raw_value': 'USA: Columbia River, Washin...</td>\n <td>...</td>\n <td>sand microcosm</td>\n <td>groundwater-surface water interaction zone in ...</td>\n <td>2021-06-17</td>\n <td>sediment metagenome</td>\n <td>sand microcosm</td>\n <td>[gold:Gs0114663]</td>\n <td>[img.taxon:3300042791]</td>\n <td>[biosample:SAMN06343867]</td>\n <td>GW-RW T3_25-Nov-14</td>\n <td>[gold:Gb0115221]</td>\n </tr>\n <tr>\n <th>3</th>\n <td>gold:Gb0115228</td>\n <td>Sand microcosm microbial communities from a hy...</td>\n <td>Sterilized sand packs were incubated back in t...</td>\n <td>{'has_raw_value': 'ENVO:01000253', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000621', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000017', 'term': {'i...</td>\n <td>nmdc:Biosample</td>\n <td>{'has_raw_value': '2014-05-21'}</td>\n <td>{'has_raw_value': '0.5', 'has_numeric_value': ...</td>\n <td>{'has_raw_value': 'USA: Columbia River, Washin...</td>\n <td>...</td>\n <td>sand microcosm</td>\n <td>groundwater-surface water interaction zone in ...</td>\n <td>2021-06-17</td>\n <td>sediment metagenome</td>\n <td>sand microcosm</td>\n <td>[gold:Gs0114663]</td>\n <td>[img.taxon:3300042751]</td>\n <td>[biosample:SAMN06343874]</td>\n <td>GW-RW T4_21-May-14</td>\n <td>[gold:Gb0115228]</td>\n </tr>\n <tr>\n <th>4</th>\n <td>gold:Gb0115225</td>\n <td>Sand microcosm microbial communities from a hy...</td>\n <td>Sterilized sand packs were incubated back in t...</td>\n <td>{'has_raw_value': 'ENVO:01000253', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000621', 'term': {'i...</td>\n <td>{'has_raw_value': 'ENVO:01000017', 'term': {'i...</td>\n <td>nmdc:Biosample</td>\n <td>{'has_raw_value': '2014-08-12'}</td>\n <td>{'has_raw_value': '0.5', 'has_numeric_value': ...</td>\n <td>{'has_raw_value': 'USA: Columbia River, Washin...</td>\n <td>...</td>\n <td>sand microcosm</td>\n <td>groundwater-surface water interaction zone in ...</td>\n <td>2021-06-17</td>\n <td>sediment metagenome</td>\n <td>sand microcosm</td>\n <td>[gold:Gs0114663]</td>\n <td>[img.taxon:3300042748]</td>\n <td>[biosample:SAMN06343871]</td>\n <td>GW-RW T4_12-Aug-14</td>\n <td>[gold:Gb0115225]</td>\n </tr>\n </tbody>\n</table>\n<p>5 rows × 28 columns</p>\n</div>"
102+
},
103+
"execution_count": 6,
104+
"metadata": {},
105+
"output_type": "execute_result"
106+
}
107+
],
108+
"source": [
109+
"qr.rows_dataframe"
110+
],
111+
"metadata": {
112+
"collapsed": false,
113+
"ExecuteTime": {
114+
"end_time": "2024-06-23T01:39:45.731557Z",
115+
"start_time": "2024-06-23T01:39:45.714621Z"
116+
}
117+
},
118+
"id": "643c81991a449525"
119+
},
120+
{
121+
"cell_type": "code",
122+
"execution_count": 6,
123+
"outputs": [],
124+
"source": [],
125+
"metadata": {
126+
"collapsed": false,
127+
"ExecuteTime": {
128+
"end_time": "2024-06-23T01:39:45.731830Z",
129+
"start_time": "2024-06-23T01:39:45.728994Z"
130+
}
131+
},
132+
"id": "bb27cf2adebbc0da"
133+
}
134+
],
135+
"metadata": {
136+
"kernelspec": {
137+
"display_name": "Python 3",
138+
"language": "python",
139+
"name": "python3"
140+
},
141+
"language_info": {
142+
"codemirror_mode": {
143+
"name": "ipython",
144+
"version": 2
145+
},
146+
"file_extension": ".py",
147+
"mimetype": "text/x-python",
148+
"name": "python",
149+
"nbconvert_exporter": "python",
150+
"pygments_lexer": "ipython2",
151+
"version": "2.7.6"
152+
}
153+
},
154+
"nbformat": 4,
155+
"nbformat_minor": 5
156+
}

0 commit comments

Comments
 (0)