-
Notifications
You must be signed in to change notification settings - Fork 2
/
docker-compose-app.yml
178 lines (176 loc) · 6.36 KB
/
docker-compose-app.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
version: "2.1"
services:
#############
# RDF Layer #
#############
triples-reader:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.rdf.TripleReader"
#SPARK_APPLICATION_ARGS: "--input /data/rdf.nt"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/rdf.nt"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
triple-ops:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.rdf.TripleOps"
#SPARK_APPLICATION_ARGS: "--input /data/rdf.nt"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/rdf.nt"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
triples-writer:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.rdf.TripleWriter"
#SPARK_APPLICATION_ARGS: "--input /data/rdf.nt --out /output/rdf_layer/triples_writer"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/rdf.nt --out hdfs://namenode:8020/output/rdf_layer/triples_writer"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
- ./output:/output
rdf-stats:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.rdf.RDFStats"
#SPARK_APPLICATION_ARGS: "--input /data/rdf.nt --out /output/rdf_layer/rdf_stats"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/rdf.nt --out hdfs://namenode:8020/output/rdf_layer/rdf_stats"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
- ./output:/output
pagerank:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.rdf.PageRank"
#SPARK_APPLICATION_ARGS: "--input /data/rdf.nt"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/rdf.nt"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
#####################
# Inferencing Layer #
#####################
inferencing:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.inference.RDFGraphInference"
#SPARK_APPLICATION_ARGS: "--input /data/rdf.nt --out /output/inferencing_layer/inferencing --profile rdfs"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/rdf.nt --out hdfs://namenode:8020/output/inferencing_layer/inferencing --profile rdfs"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./output:/output
- ./examples/data:/data
###############
# Query Layer #
###############
# Fails because file name is too long
sparklify:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.query.Sparklify"
#SPARK_APPLICATION_ARGS: "--input /data/rdf.nt"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/rdf.nt"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./output:/output
- ./examples/data:/data
#############
# OWL Layer #
#############
owl-reader-manchester:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.owl.OWLReaderRDD"
#SPARK_APPLICATION_ARGS: "--input /data/ont_manchester.owl --syntax manch"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/ont_manchester.owl --syntax manch"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
# Fails because of an UnsupportedOperationException
owl-reader-functional:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.owl.OWLReaderRDD"
#SPARK_APPLICATION_ARGS: "--input /data/ont_functional.owl --syntax fun"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/ont_functional.owl --syntax fun"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
owl-dataset-reader-manchester:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.owl.OWLReaderDataset"
#SPARK_APPLICATION_ARGS: "--input /data/ont_manchester.owl --syntax manch"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/ont_manchester.owl --syntax manch"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
# Fails because of an UnsupportedOperationException
owl-dataset-reader-functional:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.owl.OWLReaderDataset"
#SPARK_APPLICATION_ARGS: "--input /data/ont_functional.owl --syntax fun"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/ont_functional.owl --syntax fun"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./examples/data:/data
############
# ML Layer #
############
clustering:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.ml.clustering.RDFByModularityClustering"
#SPARK_APPLICATION_ARGS: "--input /data/Clustering_sampledata.nt --output /output/ml_layer/clustering --numIterations 10"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/Clustering_sampledata.nt --output hdfs://namenode:8020/output/ml_layer/clustering --numIterations 10"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./output:/output
- ./examples/data:/data
# Generated file is empty
rule-mining:
build: ./examples
networks:
- spark-net
environment:
SPARK_APPLICATION_MAIN_CLASS: "net.sansa_stack.examples.spark.ml.mining.MineRules"
#SPARK_APPLICATION_ARGS: "--input /data/MineRules_sampledata.tsv --out /output/ml_layer/rule_mining"
SPARK_APPLICATION_ARGS: "--input hdfs://namenode:8020/data/MineRules_sampledata.tsv --out hdfs://namenode:8020/output/ml_layer/rule_mining"
ENABLE_INIT_DAEMON: "false"
volumes:
- ./output:/output
- ./examples/data:/data
networks:
- spark-net
networks:
spark-net:
external:
name: spark-net