Skip to content

Instantly share code, notes, and snippets.

View gmlee7's full-sized avatar

Gene Moo Lee gmlee7

18 followers · 8 following
View GitHub Profile
@gmlee7
gmlee7 / gist:f64d01af7564ea0d6ecedac3dc92fe39
Created October 22, 2017 07:28
{
"embeddings": [
{
"tensorName": "1995-2016 SIC7",
"tensorShape": [
15164,
50
],
"tensorPath": "https://gist.githubusercontent.com/gmlee7/b1bf53e0e5dd873454fd8a1a14bb26d4/raw/b4a95932877adf42ea38da95a4734713ec457b48/corpus.raw.txt.1995-2016-7-partI.doc2vec.dim50_tensor.tsv",
"metadataPath": "https://gist.githubusercontent.com/gmlee7/f52e8f05f99d3acba689cc38c52b1290/raw/506f2524feb82c2ea78f5b2365db775942302c87/corpus.raw.txt.1995-2016-7-partI.doc2vec.dim50_metadata.tsv"
@gmlee7
gmlee7 / corpus.raw.txt.1995-2016-7-partI.doc2vec.dim50_metadata.tsv
Created October 22, 2017 07:25
We can't make this file beautiful and searchable because it's too large.
CONFORMED-NAME TICKER SIC CIK YEAR
AUTOMATIC DATA PROCESSING INC-95 ADP 7374 8670 1995
BI INC-95 Unknown 7380 716629 1995
SANDS REGENT-95 SNDS 7990 753899 1995
INTERNATIONAL THOROUGHBRED BREEDERS INC-95 ITGB 7948 320573 1995
G&K SERVICES INC-95 GK 7200 39648 1995
AMPLICON INC-95 CFNB 7377 803016 1995
HENRY JACK & ASSOCIATES INC-95 JKHY 7373 779152 1995
ALLIANCE GAMING CORP-95 BYI 7990 2491 1995
AMSERV HEALTHCARE INC-95 Unknown 7363 78302 1995
@gmlee7
gmlee7 / corpus.raw.txt.1995-2016-7-partI.doc2vec.dim50_tensor.tsv
Created October 22, 2017 07:25
We can't make this file beautiful and searchable because it's too large.
-1.29622 -2.5758 1.57536 0.304169 -2.8914 0.956299 -5.01183 -0.128681 -1.7079 -1.28633 4.45663 -0.123759 1.33454 -2.11928 3.29124 -1.16728 -0.968831 -1.72555 1.81108 -0.133416 -0.353848 0.62766 2.60836 0.012916 3.00945 0.001172 -0.963998 0.563607 1.46406 2.83302 3.1693 2.81951 2.36704 -0.217462 0.595511 2.07829 3.01764 0.128381 4.94812 -2.0086 1.20421 -1.28868 0.767241 4.02909 5.15392 0.270517 3.26827 1.86359 -1.18469 0.435385
0.42774 -3.09271 0.886854 -1.11256 0.290253 -0.200272 -1.79465 -1.02552 -1.45545 0.453915 0.306131 -3.35527 0.288395 -0.590091 0.244442 -3.61336 -2.17616 -0.206573 1.88767 -0.872388 -2.21841 0.37271 0.749281 -0.369485 1.4829 0.650744 -1.15339 0.481757 4.02024 1.13126 0.349212 1.49292 1.42025 3.78393 -0.292947 0.701802 -1.05004 3.67362 7.13439 0.303521 -0.79184 -5.44381 -1.35389 0.651742 1.84338 3.76345 3.3148 -0.536374 -1.42891 1.09313
5.16972 -3.02284 2.69015 2.7626 1.36239 1.71538 2.85325 -4.70855 2.85379 2.17872 2.72414 0.47376 -0.737917 4.50664 -0.959017 -2.65131 0.05297 -5.30614 -0
@gmlee7
gmlee7 / corpus.raw.txt.1995-2015-partI.doc2vec.dim100_metadata.tsv
Created October 22, 2017 05:14
CONFORMED-NAME TICKER SIC CIK YEAR
REPUBLIC GYPSUM CO-95 Unknown 2631.0 83226 1995
MOYCO INDUSTRIES INC-95 Unknown 3843.0 200533 1995
NOVACARE INC-95 Unknown 8090.0 802843 1995
MEREDITH CORP-95 MDP 2721.0 65011 1995
STARRETT L S CO-95 SCX 3420.0 93676 1995
II-VI INC-95 IIVI 3827.0 820318 1995
HARMAN INTERNATIONAL INDUSTRIES INC /DE/-95 HAR 3651.0 800459 1995
RAYCHEM CORP-95 Unknown 3640.0 82206 1995
CARDINAL HEALTH INC-95 CAH 5122.0 721371 1995
@gmlee7
gmlee7 / corpus.raw.txt.1995-2015-partI.doc2vec.dim100_tensor.tsv
Created October 22, 2017 05:13
We can't make this file beautiful and searchable because it's too large.
2.22909 -1.05757 -0.992291 1.16085 -0.520851 -0.194228 0.318973 -4.56769 0.05816 -1.19087 1.84401 -2.27414 2.58934 2.19464 -1.20885 0.898445 -4.84643 -5.00306 1.23319 1.75867 -1.06353 1.39266 0.430433 -0.205404 1.93358 1.25452 -1.04266 -1.19911 5.16662 1.11048 -1.46935 -0.578948 -1.15931 -0.665537 0.410324 -0.052529 -1.54438 -3.16617 0.126807 -2.36665 -0.529469 -0.133105 -1.59741 0.973976 -1.96969 -1.26542 -2.63717 -1.90495 0.435309 0.597144 -0.128881 1.64771 0.881843 1.8464 1.21126 2.20286 0.358316 1.83856 6.08856 -2.56991 -1.17329 -1.74324 0.958311 0.005677 2.15536 -2.14403 -2.95947 -0.73896 3.65231 2.04575 2.96774 1.32528 1.08722 -2.06717 0.600734 -0.511471 0.199232 3.24694 -1.04071 0.941403 4.28093 -0.081506 1.3559 0.090353 0.834822 -0.013726 -0.620089 1.65916 0.654821 1.75521 0.056686 0.845232 -0.353251 1.19653 1.32571 0.121657 -0.029998 0.844698 -0.873836 -1.80739
0.455128 -3.9968 0.467253 3.33139 -0.909395 1.81923 -2.81525 -2.84832 -1.30712 1.90306 -1.8906 2.28385 0.230977 -2.66844 -0.872105 -3.28361 -
@gmlee7
gmlee7 / gist:a4c99c3df34a88b9fb2ea7cb67ea126a
Created October 20, 2017 20:46
{
"embeddings": [
{
"tensorPath": "https://gist.githubusercontent.com/gmlee7/97bbf07d3f2880d227baf8f3c69f744e/raw/13e38c1baa919ab8640c9dd6bf849e34d685fc6d/corpus.raw.txt.2016-2016-partI.doc2vec.dim50_tensor.tsv",
"tensorName": "2016-2016-partI",
"tensorShape": [
5797,
50
],
"metadataPath": "https://gist.githubusercontent.com/gmlee7/72cb9983a650f1e09292bc4bd19280f6/raw/29305ceae403068bc7fbf697eda8c02ba49b6822/corpus.raw.txt.2016-2016-partI.doc2vec.dim50_metadata.tsv"
@gmlee7
gmlee7 / corpus.raw.txt.2016-2016-partI.doc2vec.dim50_metadata.tsv
Created October 20, 2017 20:45
CONFORMED-NAME TICKER SIC CIK YEAR
SPAN AMERICA MEDICAL SYSTEMS INC-16 SPAN 3842 718924 2016
UNIVERSAL DETECTION TECHNOLOGY-16 UNDT 3823 763950 2016
MYnd Analytics, Inc.-16 CNSO 8090 822370 2016
4NET SOFTWARE INC-16 FNSI 7370 812149 2016
Cannabics Pharmaceuticals Inc.-16 AMCM 1000 1343009 2016
PHOTRONICS INC-16 PLAB 3674 810136 2016
LUMIOX, INC.-16 Unknown 3640 1631001 2016
CAN CAL RESOURCES LTD-16 CCRE 1000 1083848 2016
TRANSATLANTIC CAPITAL INC.-16 ACRI 8742 1228386 2016
@gmlee7
gmlee7 / corpus.raw.txt.2016-2016-partI.doc2vec.dim50_tensor.tsv
Created October 20, 2017 20:44
We can't make this file beautiful and searchable because it's too large.
-5.64484 -2.3455 2.33225 -0.340933 2.97321 -2.52982 2.04795 -0.587872 0.894495 2.1158 4.6887 -5.27207 3.99876 1.68786 0.916962 -2.8928 -1.30793 3.46356 0.178436 0.30817 0.895194 -0.138478 1.44461 -2.19956 -0.287432 -2.73281 0.073892 0.268029 -0.556107 1.26284 1.05286 2.55217 2.4471 2.34245 -3.04382 -1.05614 -0.455674 0.845222 -0.45407 -2.46946 -1.44319 -0.355273 -0.933428 2.08383 -1.72863 2.26093 -0.624831 -2.83096 -0.705852 -1.63445
-2.88709 -0.578997 0.190661 -0.892476 1.32937 -1.69474 0.34574 0.038717 0.496774 0.536797 3.50776 -0.619793 1.5936 2.23343 -0.339012 -2.40026 -2.05661 0.504965 -2.68601 2.6067 -0.347801 -0.977304 3.74428 -2.61294 0.896223 1.14253 0.160125 -0.616808 -1.89597 -1.48558 -1.28658 -0.154389 0.447036 1.44332 -0.070457 -2.61385 -0.250294 1.30272 0.799536 -1.18469 -0.673465 -1.37813 -0.713246 0.520242 1.32518 0.813632 -0.772252 3.97018 -0.466071 -3.46903
-0.53719 -3.70528 3.5365 1.76065 1.46077 -1.24937 -0.355787 -1.07356 -1.82262 -3.12973 3.4235 -3.57048 1.30068 1.17129 0.072179 -0.46747
@gmlee7
gmlee7 / gist:0c0cf95802539ffa862c4e703fd01674
Created October 10, 2017 20:38
{
"embeddings": [
{
"tensorName": "CBL to Breach test",
"tensorShape": [
5000,
366
],
"tensorPath": "https://gist.githubusercontent.com/gmlee7/50812235c4025387b3be14f80d594e59/raw/809beebfe2e2af4d2cbac2edc65bc6d8a7ae7e5b/ddid_cbl_updated.tsv",
"metadataPath": "https://gist.githubusercontent.com/gmlee7/576d743835e97b4bd8a9bb5f14d7ce8d/raw/62a54e3f80bc0d1515d3f936bb9a901ae0cd18a5/ddid_cbl_y.tsv"
@gmlee7
gmlee7 / ddid_cbl_y.tsv
Created October 10, 2017 20:37
DDID results
201363373916 True
201312281313 True
20161030083 True
20131036889 True
20151007951 True
20131009503 True
20151031628 True
20131631103 True
20141437922 True