company-mapping 0.2.1 → 0.2.2
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/.idea/workspace.xml +44 -52
- data/lib/company/mapping/company_mapper.rb +7 -1
- data/lib/company/mapping/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 43a9909e539e32e5c6c1dae7e079407d3016a52d
|
|
4
|
+
data.tar.gz: 6a6c535a94f54131c243f9e07fb657da05e91955
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 127aa0c51e5bb34509bddd9bb224c8bf5757af535cfbc57ba5bb52f944db80e8fd7059d72e84944b54910b8083304950555b75f983baf46874df9bff02b48e3a
|
|
7
|
+
data.tar.gz: e7d028939d7a78b380dbe264b2a5749a9385291b192902faee307c236d78c1382e983857f6dde3313823a1b417017282149c7afa743ac875a4a3e91b7aee77cb
|
data/.idea/workspace.xml
CHANGED
|
@@ -37,11 +37,11 @@
|
|
|
37
37
|
</provider>
|
|
38
38
|
</entry>
|
|
39
39
|
</file>
|
|
40
|
-
<file leaf-file-name="
|
|
41
|
-
<entry file="file://$PROJECT_DIR$/lib/company/mapping/
|
|
40
|
+
<file leaf-file-name="text_document.rb" pinned="false" current-in-tab="false">
|
|
41
|
+
<entry file="file://$PROJECT_DIR$/lib/company/mapping/document_utils/text_document.rb">
|
|
42
42
|
<provider selected="true" editor-type-id="text-editor">
|
|
43
|
-
<state relative-caret-position="
|
|
44
|
-
<caret line="
|
|
43
|
+
<state relative-caret-position="544">
|
|
44
|
+
<caret line="32" column="7" lean-forward="false" selection-start-line="32" selection-start-column="7" selection-end-line="32" selection-end-column="7" />
|
|
45
45
|
<folding />
|
|
46
46
|
</state>
|
|
47
47
|
</provider>
|
|
@@ -70,13 +70,9 @@
|
|
|
70
70
|
<file leaf-file-name="company_mapper.rb" pinned="false" current-in-tab="false">
|
|
71
71
|
<entry file="file://$PROJECT_DIR$/lib/company/mapping/company_mapper.rb">
|
|
72
72
|
<provider selected="true" editor-type-id="text-editor">
|
|
73
|
-
<state relative-caret-position="
|
|
74
|
-
<caret line="
|
|
75
|
-
<folding
|
|
76
|
-
<marker date="1490107467162" expanded="true" signature="188:993" ph=" ... end" />
|
|
77
|
-
<marker date="1490107467162" expanded="true" signature="322:502" ph="##..." />
|
|
78
|
-
<marker date="1490107467162" expanded="true" signature="536:985" ph=" ... end" />
|
|
79
|
-
</folding>
|
|
73
|
+
<state relative-caret-position="226">
|
|
74
|
+
<caret line="19" column="32" lean-forward="false" selection-start-line="19" selection-start-column="32" selection-end-line="19" selection-end-column="32" />
|
|
75
|
+
<folding />
|
|
80
76
|
</state>
|
|
81
77
|
</provider>
|
|
82
78
|
</entry>
|
|
@@ -149,9 +145,9 @@
|
|
|
149
145
|
<option value="$PROJECT_DIR$/lib/company/mapping/tfidf/tf/term_frequency.rb" />
|
|
150
146
|
<option value="$PROJECT_DIR$/lib/company/mapping/tfidf/tfidf.rb" />
|
|
151
147
|
<option value="$PROJECT_DIR$/lib/company/mapping/vector_similarity/cosine_similarity.rb" />
|
|
152
|
-
<option value="$PROJECT_DIR$/lib/company/mapping/company_mapper.rb" />
|
|
153
148
|
<option value="$PROJECT_DIR$/lib/company/mapping.rb" />
|
|
154
149
|
<option value="$PROJECT_DIR$/lib/company/mapping/document_utils/company_corpus.rb" />
|
|
150
|
+
<option value="$PROJECT_DIR$/lib/company/mapping/company_mapper.rb" />
|
|
155
151
|
<option value="$PROJECT_DIR$/lib/company/mapping/version.rb" />
|
|
156
152
|
</list>
|
|
157
153
|
</option>
|
|
@@ -618,7 +614,7 @@
|
|
|
618
614
|
<updated>1490091405243</updated>
|
|
619
615
|
<workItem from="1490091406885" duration="1302000" />
|
|
620
616
|
<workItem from="1490093277867" duration="45000" />
|
|
621
|
-
<workItem from="1490093333788" duration="
|
|
617
|
+
<workItem from="1490093333788" duration="10658000" />
|
|
622
618
|
</task>
|
|
623
619
|
<task id="LOCAL-00001" summary=".gemspec updated">
|
|
624
620
|
<created>1490095337026</created>
|
|
@@ -669,7 +665,14 @@
|
|
|
669
665
|
<option name="project" value="LOCAL" />
|
|
670
666
|
<updated>1490106342128</updated>
|
|
671
667
|
</task>
|
|
672
|
-
<
|
|
668
|
+
<task id="LOCAL-00008" summary="check company type">
|
|
669
|
+
<created>1490108993452</created>
|
|
670
|
+
<option name="number" value="00008" />
|
|
671
|
+
<option name="presentableId" value="LOCAL-00008" />
|
|
672
|
+
<option name="project" value="LOCAL" />
|
|
673
|
+
<updated>1490108993452</updated>
|
|
674
|
+
</task>
|
|
675
|
+
<option name="localTasksCounter" value="9" />
|
|
673
676
|
<servers />
|
|
674
677
|
</component>
|
|
675
678
|
<component name="TestHistory">
|
|
@@ -705,10 +708,10 @@
|
|
|
705
708
|
</history-entry>
|
|
706
709
|
</component>
|
|
707
710
|
<component name="TimeTrackingManager">
|
|
708
|
-
<option name="totallyTimeSpent" value="
|
|
711
|
+
<option name="totallyTimeSpent" value="12005000" />
|
|
709
712
|
</component>
|
|
710
713
|
<component name="ToolWindowManager">
|
|
711
|
-
<frame x="54" y="-8" width="1874" height="1096" extended-state="
|
|
714
|
+
<frame x="54" y="-8" width="1874" height="1096" extended-state="6" />
|
|
712
715
|
<editor active="true" />
|
|
713
716
|
<layout>
|
|
714
717
|
<window_info id="Project" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="true" show_stripe_button="true" weight="0.238699" sideWeight="0.5" order="0" side_tool="false" content_ui="combo" />
|
|
@@ -742,7 +745,8 @@
|
|
|
742
745
|
<MESSAGE value="minor updates" />
|
|
743
746
|
<MESSAGE value="Major Code Refactoring" />
|
|
744
747
|
<MESSAGE value="code refactoring" />
|
|
745
|
-
<
|
|
748
|
+
<MESSAGE value="check company type" />
|
|
749
|
+
<option name="LAST_COMMIT_MESSAGE" value="check company type" />
|
|
746
750
|
</component>
|
|
747
751
|
<component name="XDebuggerManager">
|
|
748
752
|
<breakpoint-manager />
|
|
@@ -785,11 +789,7 @@
|
|
|
785
789
|
<provider selected="true" editor-type-id="text-editor">
|
|
786
790
|
<state relative-caret-position="697">
|
|
787
791
|
<caret line="41" column="3" lean-forward="false" selection-start-line="41" selection-start-column="3" selection-end-line="41" selection-end-column="3" />
|
|
788
|
-
<folding
|
|
789
|
-
<marker date="1490107467162" expanded="true" signature="188:993" ph=" ... end" />
|
|
790
|
-
<marker date="1490107467162" expanded="true" signature="322:502" ph="##..." />
|
|
791
|
-
<marker date="1490107467162" expanded="true" signature="536:985" ph=" ... end" />
|
|
792
|
-
</folding>
|
|
792
|
+
<folding />
|
|
793
793
|
</state>
|
|
794
794
|
</provider>
|
|
795
795
|
</entry>
|
|
@@ -869,11 +869,7 @@
|
|
|
869
869
|
<provider selected="true" editor-type-id="text-editor">
|
|
870
870
|
<state relative-caret-position="697">
|
|
871
871
|
<caret line="41" column="3" lean-forward="false" selection-start-line="41" selection-start-column="3" selection-end-line="41" selection-end-column="3" />
|
|
872
|
-
<folding
|
|
873
|
-
<marker date="1490107467162" expanded="true" signature="188:993" ph=" ... end" />
|
|
874
|
-
<marker date="1490107467162" expanded="true" signature="322:502" ph="##..." />
|
|
875
|
-
<marker date="1490107467162" expanded="true" signature="536:985" ph=" ... end" />
|
|
876
|
-
</folding>
|
|
872
|
+
<folding />
|
|
877
873
|
</state>
|
|
878
874
|
</provider>
|
|
879
875
|
</entry>
|
|
@@ -944,14 +940,6 @@
|
|
|
944
940
|
</state>
|
|
945
941
|
</provider>
|
|
946
942
|
</entry>
|
|
947
|
-
<entry file="file://$PROJECT_DIR$/lib/company/mapping/document_utils/text_document.rb">
|
|
948
|
-
<provider selected="true" editor-type-id="text-editor">
|
|
949
|
-
<state relative-caret-position="544">
|
|
950
|
-
<caret line="32" column="7" lean-forward="false" selection-start-line="32" selection-start-column="7" selection-end-line="32" selection-end-column="7" />
|
|
951
|
-
<folding />
|
|
952
|
-
</state>
|
|
953
|
-
</provider>
|
|
954
|
-
</entry>
|
|
955
943
|
<entry file="file://$PROJECT_DIR$/lib/company/mapping/tfidf/tf/normalized_term_frequency.rb">
|
|
956
944
|
<provider selected="true" editor-type-id="text-editor">
|
|
957
945
|
<state relative-caret-position="204">
|
|
@@ -992,38 +980,34 @@
|
|
|
992
980
|
</state>
|
|
993
981
|
</provider>
|
|
994
982
|
</entry>
|
|
995
|
-
<entry file="file://$PROJECT_DIR$/lib/company/mapping/
|
|
983
|
+
<entry file="file://$PROJECT_DIR$/lib/company/mapping/document_utils/corpus.rb">
|
|
996
984
|
<provider selected="true" editor-type-id="text-editor">
|
|
997
|
-
<state relative-caret-position="
|
|
998
|
-
<caret line="
|
|
999
|
-
<folding
|
|
1000
|
-
<marker date="1490107467162" expanded="true" signature="188:993" ph=" ... end" />
|
|
1001
|
-
<marker date="1490107467162" expanded="true" signature="322:502" ph="##..." />
|
|
1002
|
-
<marker date="1490107467162" expanded="true" signature="536:985" ph=" ... end" />
|
|
1003
|
-
</folding>
|
|
985
|
+
<state relative-caret-position="119">
|
|
986
|
+
<caret line="7" column="0" lean-forward="true" selection-start-line="7" selection-start-column="0" selection-end-line="7" selection-end-column="0" />
|
|
987
|
+
<folding />
|
|
1004
988
|
</state>
|
|
1005
989
|
</provider>
|
|
1006
990
|
</entry>
|
|
1007
|
-
<entry file="file://$PROJECT_DIR$/lib/company/mapping/document_utils/
|
|
991
|
+
<entry file="file://$PROJECT_DIR$/lib/company/mapping/document_utils/company_corpus.rb">
|
|
1008
992
|
<provider selected="true" editor-type-id="text-editor">
|
|
1009
|
-
<state relative-caret-position="
|
|
1010
|
-
<caret line="
|
|
993
|
+
<state relative-caret-position="260">
|
|
994
|
+
<caret line="20" column="11" lean-forward="true" selection-start-line="20" selection-start-column="11" selection-end-line="20" selection-end-column="11" />
|
|
1011
995
|
<folding />
|
|
1012
996
|
</state>
|
|
1013
997
|
</provider>
|
|
1014
998
|
</entry>
|
|
1015
|
-
<entry file="file://$PROJECT_DIR$/lib/company/mapping.rb">
|
|
999
|
+
<entry file="file://$PROJECT_DIR$/lib/company/mapping/document_utils/text_document.rb">
|
|
1016
1000
|
<provider selected="true" editor-type-id="text-editor">
|
|
1017
|
-
<state relative-caret-position="
|
|
1018
|
-
<caret line="
|
|
1001
|
+
<state relative-caret-position="544">
|
|
1002
|
+
<caret line="32" column="7" lean-forward="false" selection-start-line="32" selection-start-column="7" selection-end-line="32" selection-end-column="7" />
|
|
1019
1003
|
<folding />
|
|
1020
1004
|
</state>
|
|
1021
1005
|
</provider>
|
|
1022
1006
|
</entry>
|
|
1023
|
-
<entry file="file://$PROJECT_DIR$/lib/company/mapping/
|
|
1007
|
+
<entry file="file://$PROJECT_DIR$/lib/company/mapping/company_mapper.rb">
|
|
1024
1008
|
<provider selected="true" editor-type-id="text-editor">
|
|
1025
|
-
<state relative-caret-position="
|
|
1026
|
-
<caret line="
|
|
1009
|
+
<state relative-caret-position="226">
|
|
1010
|
+
<caret line="19" column="32" lean-forward="false" selection-start-line="19" selection-start-column="32" selection-end-line="19" selection-end-column="32" />
|
|
1027
1011
|
<folding />
|
|
1028
1012
|
</state>
|
|
1029
1013
|
</provider>
|
|
@@ -1036,6 +1020,14 @@
|
|
|
1036
1020
|
</state>
|
|
1037
1021
|
</provider>
|
|
1038
1022
|
</entry>
|
|
1023
|
+
<entry file="file://$PROJECT_DIR$/lib/company/mapping.rb">
|
|
1024
|
+
<provider selected="true" editor-type-id="text-editor">
|
|
1025
|
+
<state relative-caret-position="102">
|
|
1026
|
+
<caret line="6" column="0" lean-forward="true" selection-start-line="6" selection-start-column="0" selection-end-line="6" selection-end-column="0" />
|
|
1027
|
+
<folding />
|
|
1028
|
+
</state>
|
|
1029
|
+
</provider>
|
|
1030
|
+
</entry>
|
|
1039
1031
|
<entry file="file://$PROJECT_DIR$/lib/company/mapping/version.rb">
|
|
1040
1032
|
<provider selected="true" editor-type-id="text-editor">
|
|
1041
1033
|
<state relative-caret-position="34">
|
|
@@ -13,7 +13,13 @@ module Company
|
|
|
13
13
|
|
|
14
14
|
#maps a given company to a company exists to the given corpus. If the maximum name similarity found exceeds the given
|
|
15
15
|
# threshold then the company's id is returned as a match
|
|
16
|
-
def map(
|
|
16
|
+
def map(company_doc, threshold)
|
|
17
|
+
if (company_doc.is_a? String)
|
|
18
|
+
company = new TextDocument.new
|
|
19
|
+
company.contents = company_doc
|
|
20
|
+
company.id = "new_comp"
|
|
21
|
+
end
|
|
22
|
+
|
|
17
23
|
@tfidf.calculate_tfidf_weights_of_new_document(company)
|
|
18
24
|
|
|
19
25
|
maxSim = 0.0
|