gn_crossmap 3.3.1 → 4.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +4 -0
- data/README.md +2 -1
- data/lib/gn_crossmap/resolver.rb +11 -6
- data/lib/gn_crossmap/resolver_job.rb +1 -1
- data/lib/gn_crossmap/stats.rb +2 -2
- data/lib/gn_crossmap/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 17c1750e71b66ba0d13b76a4acaa110f00b7cdd0
|
4
|
+
data.tar.gz: 96f3b4d6955c10724f78749c99d9c0414da21278
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 874afab0ba3e3c7e847ebcb8a86c439bcdcc56ab84ae86b0d5dc1912cd7dd8dff7fefa5bc0d031a082b9b854c11714879db44568edf79bcc698ba8337a633b9e
|
7
|
+
data.tar.gz: 4cff3ac93255cd203ef4c2e9083ff1da6babb94a6367afb244c38e743c23be620fb154aad8e7deed818c16ada4f7ad0b78643123b72dd2c54798cafa8f70728e
|
data/CHANGELOG.md
CHANGED
data/README.md
CHANGED
@@ -163,7 +163,8 @@ end
|
|
163
163
|
|resolution_stop |time when resolution of names stopped |
|
164
164
|
|resolution_span |time of intermediate checkpoint of resolving names |
|
165
165
|
|resolved_records |number of names already processed |
|
166
|
-
|
|
166
|
+
|speed |weighted speed average |
|
167
|
+
|current_speed |speed of resolution for the last batch |
|
167
168
|
|matches |Distribution of processed data by match type (see below) |
|
168
169
|
|errors |First 0-10 errors found during the csv file processing |
|
169
170
|
|
data/lib/gn_crossmap/resolver.rb
CHANGED
@@ -14,6 +14,7 @@ module GnCrossmap
|
|
14
14
|
@count = 0
|
15
15
|
@jobs = []
|
16
16
|
@batch = 200
|
17
|
+
@smoothing = 0.05
|
17
18
|
end
|
18
19
|
|
19
20
|
def resolve(data)
|
@@ -87,10 +88,13 @@ module GnCrossmap
|
|
87
88
|
# rubocop:disable Metrics/AbcSize
|
88
89
|
def update_stats(job_stats)
|
89
90
|
s = @stats.stats
|
90
|
-
s[:
|
91
|
-
s[:
|
91
|
+
s[:current_speed] = job_stats.stats[:current_speed]
|
92
|
+
s[:speed] = s[:current_speed] * @threads unless s[:speed]
|
93
|
+
s[:speed] = s[:speed] * (1 - @smoothing) +
|
94
|
+
s[:current_speed] * @smoothing * @threads
|
92
95
|
s[:resolution_span] = Time.now - s[:resolution_start]
|
93
96
|
s[:resolved_records] += job_stats.stats[:resolved_records]
|
97
|
+
s[:eta] = (s[:total_records] - s[:resolved_records]) / s[:speed]
|
94
98
|
s[:matches][7] += job_stats.stats[:matches][7]
|
95
99
|
end
|
96
100
|
# rubocop:enable all
|
@@ -121,13 +125,14 @@ module GnCrossmap
|
|
121
125
|
end
|
122
126
|
|
123
127
|
def with_log
|
128
|
+
yield
|
124
129
|
s = @count + 1
|
125
130
|
@count += @batch
|
126
131
|
e = [@count, @stats.stats[:total_records]].min
|
127
|
-
|
128
|
-
|
129
|
-
|
130
|
-
|
132
|
+
msg = format("Resolve %s-%s/%s records %d rec/s; eta: %d", s, e,
|
133
|
+
@stats.stats[:total_records], @stats.stats[:speed],
|
134
|
+
@stats.stats[:eta].to_i + Time.now.to_i)
|
135
|
+
GnCrossmap.log(msg)
|
131
136
|
end
|
132
137
|
end
|
133
138
|
end
|
data/lib/gn_crossmap/stats.rb
CHANGED
@@ -10,8 +10,8 @@ module GnCrossmap
|
|
10
10
|
resolved_records: 0, ingestion_span: nil,
|
11
11
|
resolution_span: nil, ingestion_start: nil,
|
12
12
|
resolution_start: nil, resolution_stop: nil,
|
13
|
-
|
14
|
-
errors: [] }
|
13
|
+
speed: nil, current_speed: nil, eta: nil,
|
14
|
+
matches: match_types, errors: [] }
|
15
15
|
end
|
16
16
|
|
17
17
|
private
|
data/lib/gn_crossmap/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: gn_crossmap
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 4.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dmitry Mozzherin
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-09-
|
11
|
+
date: 2017-09-13 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: biodiversity
|