********** TRAINING AND TESTING REPORT **********
Training file: training-data-set-70.txt

best params:{'c1': 0.14456252410554848, 'c2': 0.011570925278244349}
best CV score:0.8716328545433987
model size: 0.08M

Flat F1: 0.7636412886634287
             precision    recall  f1-score   support

         OD      1.000     0.818     0.900        22
         pH      1.000     1.000     1.000         8
  Technique      1.000     0.870     0.930        23
        Med      1.000     0.925     0.961        53
       Temp      0.923     0.828     0.873        29
       Vess      1.000     1.000     1.000         1
       Agit      0.000     0.000     0.000         0
      Phase      0.882     1.000     0.938        15
        Air      0.545     0.348     0.425        69
       Anti      1.000     1.000     1.000        11
     Strain      0.000     0.000     0.000         1
      Gtype      0.867     0.847     0.857        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.588     0.799     0.677       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.772     0.774     0.764       451


Top likely transitions:
Temp   -> Temp    6.024803
Agit   -> Agit    5.753028
Supp   -> Supp    5.295546
Med    -> Med     5.289039
OD     -> OD      5.264385
Anti   -> Anti    4.686479
Phase  -> Phase   4.417910
Gversion -> Gversion 4.395019
Gtype  -> Gtype   4.186766
Air    -> Air     4.136213
O      -> O       3.983716
Technique -> Technique 3.660895
pH     -> pH      2.993749
Substrain -> Gtype   1.904754
Gtype  -> Supp    1.311934
O      -> Supp    1.064130
Air    -> O       1.010529
O      -> Technique 0.929538
O      -> Gtype   0.674914
Gtype  -> Air     0.657462
Technique -> Air     0.573565
Supp   -> O       0.528829
Temp   -> O       0.495755
Med    -> O       0.454783
O      -> Temp    0.096626
Phase  -> O       0.074667
O      -> Phase   0.052955
O      -> Med     0.050244
Gtype  -> pH      0.043509
O      -> Anti    0.028320
Gtype  -> Technique -0.027765
Agit   -> O       -0.075594
Technique -> O       -0.250844
Gtype  -> Med     -0.292682
Supp   -> Med     -0.310233
OD     -> Air     -0.365882
O      -> Air     -0.729567
Phase  -> OD      -0.765060
Gtype  -> O       -0.784406
Technique -> Gtype   -1.361493
Substrain -> O       -1.377371
Med    -> Supp    -1.830126


Top unlikely transitions:
Temp   -> Temp    6.024803
Agit   -> Agit    5.753028
Supp   -> Supp    5.295546
Med    -> Med     5.289039
OD     -> OD      5.264385
Anti   -> Anti    4.686479
Phase  -> Phase   4.417910
Gversion -> Gversion 4.395019
Gtype  -> Gtype   4.186766
Air    -> Air     4.136213
O      -> O       3.983716
Technique -> Technique 3.660895
pH     -> pH      2.993749
Substrain -> Gtype   1.904754
Gtype  -> Supp    1.311934
O      -> Supp    1.064130
Air    -> O       1.010529
O      -> Technique 0.929538
O      -> Gtype   0.674914
Gtype  -> Air     0.657462
Technique -> Air     0.573565
Supp   -> O       0.528829
Temp   -> O       0.495755
Med    -> O       0.454783
O      -> Temp    0.096626
Phase  -> O       0.074667
O      -> Phase   0.052955
O      -> Med     0.050244
Gtype  -> pH      0.043509
O      -> Anti    0.028320
Gtype  -> Technique -0.027765
Agit   -> O       -0.075594
Technique -> O       -0.250844
Gtype  -> Med     -0.292682
Supp   -> Med     -0.310233
OD     -> Air     -0.365882
O      -> Air     -0.729567
Phase  -> OD      -0.765060
Gtype  -> O       -0.784406
Technique -> Gtype   -1.361493
Substrain -> O       -1.377371
Med    -> Supp    -1.830126


Top positive:
6.812438 O        b'lemma:2'
6.703250 Phase    b'lemma:mid-log'
6.559342 O        b'lemma:1'
6.133494 Anti     b'-2:lemma:antibody'
5.903347 Air      b'lemma:anaerobic'
5.834979 O        b'-2:lemma:_'
5.776253 Air      b'lemma:Aerobic'
5.551637 Gtype    b'lemma:wt'
5.548591 Gtype    b'lemma:type'
5.516753 O        b'lemma:3'
5.468775 O        b'-2:lemma:flagtag'
5.270765 Supp     b'lemma:pq'
5.224920 Technique b'lemma:chipseq'
5.217760 O        b'lemma:_'
5.150603 Technique b'lemma:ChIP-exo'
4.842010 O        b'-1:lemma:ChIP-exo'
4.788720 Air      b'lemma:aerobic'
4.755345 Gtype    b'lemma:\xce\xb4cra'
4.651993 Med      b'lemma:MOPS'
4.537114 Gtype    b'lemma:\xe2\x88\x86'
4.464327 Gtype    b'lemma:wild-type'
4.427065 O        b'postag:IN'
4.254029 Supp     b'lemma:no3'
4.245214 Gtype    b'lemma:flag-tag'
4.245214 Gtype    b'-1:lemma:c-terminal'
4.223016 O        b'lemma:b'
4.196865 Technique b'lemma:rna-seq'
4.184006 Gtype    b'+1:lemma:type'
4.176776 O        b'lemma:-'
4.152973 Phase    b'-2:lemma:phase'
4.056463 Gtype    b'-2:lemma:genotype/variation'
3.986855 Supp     b'lemma:Iron'
3.986855 Supp     b'-2:lemma:Anaerobic'
3.973602 O        b'lemma:rpob'
3.966116 Supp     b'lemma:acetate'
3.938991 O        b'lemma:.'
3.938991 O        b'postag:.'
3.894365 Supp     b'lemma:nacl'
3.881738 Gtype    b'lemma:\xce\xb4fur'
3.877245 Gtype    b'-1:lemma:\xe2\x88\x86'
3.815337 Technique b'lemma:chip-seq'
3.743495 O        b'lemma:with'
3.732573 Supp     b'lemma:nh4cl'
3.716505 Air      b'postag:RB'
3.640623 O        b'+2:lemma:\xc2\xb0c'
3.608559 Med      b'lemma:lb'
3.571656 O        b'postag:VBN'
3.549390 O        b'postag:CC'
3.503089 O        b'-2:lemma:medium'
3.502227 Gtype    b'lemma:dfnr'
3.494672 O        b'lemma:a'
3.490805 Supp     b'-1:lemma:Cra'
3.447774 Supp     b'lemma:nitrate'
3.423108 O        b'lemma:Cra'
3.418016 Gtype    b'lemma:\xce\xb4soxr'
3.395324 Gtype    b'-2:lemma:genotype'
3.386697 Supp     b'lemma:glucose'
3.344372 Technique b'+2:lemma:ph5'
3.251866 Supp     b'-1:lemma:with'
3.249713 O        b'postag::'
3.200140 Gtype    b'-2:lemma:affyexp'
3.182935 Supp     b'lemma:arginine'
3.180726 Gversion b'lemma:chip-seq'
3.161435 Technique b'lemma:rnaseq'
3.148795 Supp     b'+2:lemma:iptg'
3.067497 Substrain b'lemma:mg1655'
3.056568 O        b'lemma:CEL'
3.013304 Med      b'lemma:m63'
3.005306 Gtype    b'-2:lemma:delta'
3.005008 O        b'lemma:harbor'
3.001202 Air      b'-1:lemma:ChIP-Seq'
2.966077 O        b'-1:lemma:\xc2\xb0c'
2.927961 Gtype    b'lemma:nsrr'
2.909022 Gtype    b'lemma:pk4854'
2.878177 Air      b'-2:lemma:IP'
2.876549 Technique b'lemma:ChIP-Seq'
2.870544 O        b'+1:lemma:arca-8myc'
2.865302 O        b'-2:lemma:myc'
2.847767 Technique b'-2:lemma:Fur'
2.847429 Gtype    b'+1:lemma:with'
2.829243 O        b'-1:lemma:0.3'
2.778649 O        b'lemma:rep2'
2.776931 Technique b'-1:lemma:IP'
2.773491 Supp     b'+1:lemma:\xc2\xb5m'
2.763337 O        b'postag:DT'
2.746233 Supp     b'+1:lemma:1'
2.744343 Anti     b'+2:lemma:antibody'
2.730395 O        b'lemma:chip'
2.728846 O        b'-1:lemma:tag'
2.664541 O        b'-1:lemma:media'
2.622991 Supp     b'lemma:rifampicin'
2.586777 Temp     b'-1:lemma:\xcf\x8332'
2.573215 Gtype    b'+1:lemma:ph5'
2.573215 Gtype    b'+2:lemma:.5'
2.566604 O        b'-1:lemma:lb'
2.552670 Temp     b'-2:lemma:\xcf\x8332'
2.541452 O        b'-1:lemma:type'
2.526524 pH       b'+1:postag:CD'
2.516979 O        b'-1:lemma:glucose'
2.501080 Technique b'-1:lemma:chip-exo'
2.497698 Gtype    b'lemma:\xce\xb4ompr'
2.495468 Substrain b'-2:lemma:substr'
2.481730 O        b'postag:VBG'
2.475769 Med      b'+2:lemma:b2'
2.463569 Gtype    b'lemma:\xce\xb4oxyr'
2.457060 O        b'+1:postag:RB'
2.438239 Temp     b'lemma:43'
2.435108 Supp     b'lemma:Leu'
2.435108 Supp     b'-2:lemma:Lrp'
2.434323 O        b'-2:lemma:min'
2.423093 Supp     b'-2:lemma:agent'
2.399905 O        b'+1:postag:NNP'
2.392843 Anti     b'+1:lemma:antibody'
2.387723 Supp     b'-1:lemma:+'
2.375278 O        b'lemma:ompr'
2.375177 O        b'lemma:ml'
2.351025 O        b'+2:lemma:cra'
2.328145 Supp     b'-2:lemma:media'
2.315613 pH       b'lemma:ph5'
2.315613 pH       b'+1:lemma:.5'
2.295509 Phase    b'lemma:exponential'
2.295509 Phase    b'lemma:stationary'
2.282923 Strain   b'+1:lemma:substr'
2.282923 Strain   b'-2:lemma:str'
2.282875 Gversion b'lemma:.2'
2.282875 Gversion b'-1:lemma:u00096'
2.271205 Supp     b'+1:lemma:2'
2.268299 Air      b'lemma:anaeroibc'
2.262222 Air      b'-1:lemma:-'
2.253598 O        b'lemma:s'
2.235400 Temp     b'-1:lemma:43'
2.227662 Phase    b'lemma:phase'
2.215669 Phase    b'-1:lemma:mid-log'
2.203744 Med      b'+2:postag:CC'
2.189036 Substrain b'+1:lemma:phtpg'
2.178331 Gtype    b'-1:lemma:rpob'
2.173660 Strain   b'lemma:k-12'
2.160417 Gtype    b'-1:postag:VBG'
2.141054 Agit     b'+2:lemma:at'
2.140046 Med      b'lemma:broth'
2.140046 Med      b'-1:lemma:L'
2.132754 Temp     b'+1:lemma:\xc2\xb0c'
2.122883 O        b'lemma:soxs'
2.122883 O        b'lemma:soxr'
2.115213 O        b'postag:VBD'
2.111512 O        b'lemma:\xcf\x8332'
2.083781 Agit     b'lemma:rpm'
2.051564 O        b'lemma:culture'
2.049120 O        b'+1:lemma:condition'
2.041245 Gversion b'lemma:nc'
2.038470 O        b'+1:lemma:250'
2.033120 O        b'lemma:Custom'
2.025823 O        b'postag:NNS'
2.016924 O        b'+2:lemma:70'
2.010539 O        b'+2:postag:JJ'
2.006555 O        b'-1:lemma:aerobically'
1.996814 O        b'-2:lemma:~'
1.984709 O        b'+2:lemma:polyclonal'
1.976905 Supp     b'lemma:Adenine'
1.976120 Technique b'-1:lemma:input'
1.964721 Air      b'lemma:aerobically'
1.957500 Gversion b'lemma:u00096'
1.957500 Gversion b'+1:lemma:.2'
1.944301 O        b'+1:lemma:chip-seq'
1.944163 Temp     b'-1:lemma:sample'
1.935179 O        b'lemma:trpr'
1.934476 O        b'+1:lemma:coli'
1.932800 Supp     b'lemma:fructose'
1.929974 Med      b'lemma:media'
1.923950 O        b'-1:lemma:anaerobic'
1.922151 Gversion b'+2:lemma:000913'
1.917131 Temp     b'lemma:\xc2\xb0c'
1.887292 OD       b'lemma:od450'
1.883152 Agit     b'+1:lemma:rpm'
1.879063 Gtype    b'lemma:ptac'
1.875710 O        b'+1:lemma:pq'
1.873042 O        b'+2:lemma:fructose'
1.856178 Supp     b'+1:lemma:_'
1.855822 Gtype    b'-1:lemma:ptac'
1.853574 Supp     b'+2:lemma:rifampicin'
1.850128 Med      b'+2:lemma:b1'
1.848750 O        b'-1:lemma:into'
1.826684 Gversion b'-2:lemma:nc'
1.820054 Supp     b'+2:lemma:feso4'
1.808700 Supp     b'-2:lemma:condition'
1.799712 O        b'-1:lemma:Aerobic'
1.787048 Med      b'+1:lemma:0.4'
1.768038 O        b'lemma:argr'
1.752493 Supp     b'-2:lemma:induce'
1.749745 O        b'+1:lemma:acetate'
1.744647 O        b'+1:lemma:od600'
1.730393 O        b'lemma:genotype/variation'
1.700932 Gtype    b'-2:postag:DT'
1.688694 Gtype    b'+1:lemma:flagtag'
1.685861 Gversion b'-2:lemma:build'
1.683071 Supp     b'-2:lemma:purr'
1.676299 Gversion b'lemma:asm584v2'
1.648539 Technique b'-1:lemma:rna-seq'
1.647830 Air      b'+2:lemma:L'
1.643928 Med      b'-1:lemma:in'


Top negative:
-0.078150 O        b'-2:lemma:0.1'
-0.081643 O        b'lemma:methanol'
-0.081643 O        b'-2:lemma:dissolve'
-0.082341 Supp     b'-2:postag:-LRB-'
-0.086140 Supp     b'-1:lemma:dpd'
-0.088476 Air      b'-1:lemma:or'
-0.088979 Supp     b'+2:postag:NN'
-0.089036 Supp     b'+2:postag:NNP'
-0.089839 O        b'+1:lemma:ph'
-0.091080 O        b'-1:lemma:0.2'
-0.092461 Technique b'-1:postag::'
-0.092726 Agit     b'postag:NN'
-0.097852 Med      b'-1:postag:IN'
-0.100389 Supp     b'+2:lemma:.'
-0.100389 Supp     b'+2:postag:.'
-0.100772 Strain   b'postag:NN'
-0.101155 O        b'lemma:\xe2\x88\x86'
-0.101175 O        b'+2:lemma:supplement'
-0.103582 O        b'+1:lemma:of'
-0.104478 O        b'-1:lemma:37'
-0.104623 Technique b'-2:postag:NN'
-0.106509 O        b'-1:lemma:iptg'
-0.106780 O        b'+2:lemma:ph'
-0.107862 Air      b'-2:postag:CC'
-0.109728 O        b'+1:lemma:.'
-0.109728 O        b'+1:postag:.'
-0.113993 Supp     b'-1:lemma:10'
-0.114214 O        b'lemma:7.6'
-0.114214 O        b'+1:lemma:;'
-0.115982 Agit     b'-1:postag:NN'
-0.119361 O        b'-1:lemma:until'
-0.124272 Gtype    b'-2:postag:CD'
-0.129779 O        b'lemma:;'
-0.129779 O        b'-1:lemma:7.6'
-0.136518 O        b'+1:postag:-LRB-'
-0.139593 O        b'-1:lemma:of'
-0.140386 O        b'+1:lemma:a'
-0.142883 O        b'+1:lemma:95'
-0.143055 O        b'-2:lemma:pahse'
-0.149480 O        b'-2:lemma:the'
-0.150711 O        b'-1:lemma:contain'
-0.151497 Temp     b'-2:postag:NN'
-0.151937 O        b'-2:postag::'
-0.153171 O        b'+2:lemma:-rrb-'
-0.153549 Supp     b'postag:CC'
-0.158194 O        b'+1:lemma:fecl2'
-0.160887 Supp     b'+1:lemma:-rrb-'
-0.161707 Supp     b'+2:lemma:dpd'
-0.166764 O        b'-2:lemma:phase'
-0.171348 Supp     b'+1:lemma:acetate'
-0.171861 O        b'-1:lemma:sodium'
-0.171861 O        b'+2:lemma:1/100'
-0.178092 Supp     b'-1:lemma:-lrb-'
-0.181338 O        b'lemma:dissolve'
-0.181338 O        b'+2:lemma:methanol'
-0.187811 Supp     b'+2:lemma:glucose'
-0.194739 O        b'-1:lemma:1m'
-0.194739 O        b'+2:lemma:7.6'
-0.197753 Supp     b'-1:postag:-LRB-'
-0.199612 Med      b'-1:postag:NN'
-0.202024 O        b'-1:lemma:n2'
-0.203121 Med      b'+1:postag:IN'
-0.207404 O        b'lemma:ph'
-0.210173 O        b'-2:lemma:aerobically'
-0.225375 O        b'-1:lemma:cra'
-0.226782 O        b'+2:lemma:reference'
-0.229562 O        b'-2:lemma:genome'
-0.233367 O        b'-2:lemma:dpd'
-0.239153 Supp     b'+1:postag:VBN'
-0.249635 O        b'-1:postag:IN'
-0.252658 Med      b'postag:CD'
-0.254030 Med      b'+1:postag:NN'
-0.256499 O        b'lemma:fecl2'
-0.259528 Supp     b'-2:postag:NNS'
-0.262022 O        b'-1:lemma:ml'
-0.263583 Air      b'+2:postag:IN'
-0.268766 O        b'-2:lemma:mm'
-0.270868 O        b'+1:postag:IN'
-0.271998 O        b'+2:lemma:250'
-0.273382 O        b'+1:lemma:%'
-0.280464 Supp     b'+1:postag:-RRB-'
-0.288772 O        b'+2:lemma:.'
-0.288772 O        b'+2:postag:.'
-0.293729 Gtype    b'-1:postag:NN'
-0.294905 Med      b'-1:postag:CD'
-0.308324 Phase    b'-2:postag:NN'
-0.328837 O        b'-2:lemma:anaerobically'
-0.334523 O        b'lemma:37'
-0.338413 O        b'-1:lemma:fresh'
-0.346729 O        b'-2:lemma:rpob'
-0.351198 Gtype    b'-2:lemma:\xe2\x88\x86'
-0.355232 Supp     b'+2:lemma:-rrb-'
-0.356631 O        b'lemma:mid-log'
-0.357653 O        b'-1:lemma:minimal'
-0.359546 O        b'+1:lemma:+'
-0.363243 O        b'+1:lemma:minimal'
-0.365382 O        b'-2:lemma:until'
-0.385235 O        b'+2:lemma:at'
-0.389156 Anti     b'+2:postag:JJ'
-0.391480 O        b'+1:lemma:g/l'
-0.399222 Supp     b'+2:postag:-RRB-'
-0.412306 O        b'lemma:minimal'
-0.429953 O        b'+1:lemma:1m'
-0.429953 O        b'-2:lemma:vol'
-0.431351 O        b'lemma:nitrate'
-0.432398 O        b'-2:lemma:media'
-0.449447 Supp     b'+1:lemma:rifampicin'
-0.451303 O        b'-2:lemma:fresh'
-0.457431 O        b'+1:lemma:supplement'
-0.461836 Supp     b'-1:postag:NNP'
-0.463561 O        b'+1:postag:VBG'
-0.472320 Anti     b'+1:lemma:anti-fur'
-0.484075 O        b'lemma:aerobically'
-0.484194 O        b'-1:postag::'
-0.498931 Supp     b'+1:postag:NNS'
-0.503746 Supp     b'+1:lemma:,'
-0.503746 Supp     b'+1:postag:,'
-0.516754 Supp     b'-2:lemma:treat'
-0.528514 O        b'+2:lemma:add'
-0.529405 O        b'-2:lemma:glucose'
-0.533457 O        b'+1:lemma:mm'
-0.546157 Supp     b'lemma:10'
-0.565127 Supp     b'+1:lemma:-lrb-'
-0.566088 Med      b'-2:postag:VBN'
-0.566661 O        b'-1:lemma:dissolve'
-0.566661 O        b'+1:lemma:methanol'
-0.570423 O        b'lemma:wt'
-0.580351 O        b'-2:lemma:supplement'
-0.586279 Phase    b'+1:postag:NN'
-0.593248 Supp     b'+1:postag:-LRB-'
-0.597210 O        b'-1:lemma:grow'
-0.598482 O        b'-1:lemma:co2'
-0.601257 O        b'lemma:anaerobically'
-0.603375 O        b'-2:lemma::'
-0.604605 O        b'+2:lemma:10'
-0.608424 Med      b'+2:postag:VBN'
-0.640686 O        b'-1:lemma:rpob'
-0.648211 O        b'-1:lemma:mm'
-0.677339 O        b'+2:lemma:a'
-0.691258 pH       b'postag:NN'
-0.714470 O        b'-2:postag:SYM'
-0.753388 O        b'-2:postag:RB'
-0.759391 O        b'-1:lemma:vol'
-0.759391 O        b'-2:lemma:1/100'
-0.759391 O        b'+2:lemma:1m'
-0.777706 O        b'+2:lemma:fnr'
-0.785687 O        b'lemma:aerobic'
-0.789592 Air      b'+1:postag:JJ'
-0.815302 O        b'postag:VBP'
-0.841098 O        b'lemma:2h'
-0.841098 O        b'-1:lemma:additional'
-0.842931 O        b'+2:lemma:mid-log'
-0.851282 O        b'+2:lemma:then'
-0.861129 O        b'+1:lemma:until'
-0.862940 Supp     b'-2:postag:JJ'
-0.870874 O        b'+2:postag:-RRB-'
-0.875415 O        b'-2:lemma:2'
-0.885220 O        b'lemma:of'
-0.896666 O        b'-1:lemma:30'
-0.902553 Air      b'postag:NN'
-0.931783 O        b'+2:lemma:+'
-0.932080 O        b'-2:postag:DT'
-1.044263 O        b'+2:lemma:b'
-1.102463 O        b'lemma:rifampicin'
-1.119605 O        b'lemma:\xce\xb4fur'
-1.163234 O        b'lemma:media'
-1.202846 O        b'-1:lemma:ph'
-1.209159 O        b'-1:lemma:nsrr'
-1.238185 O        b'-1:lemma:2'
-1.242160 O        b'+1:lemma:at'
-1.252527 Temp     b'postag:NN'
-1.263981 Med      b'-2:lemma:grow'
-1.295021 O        b'-2:lemma:0.3'
-1.322790 Phase    b'-1:postag:JJ'
-1.350768 O        b'-1:lemma:IP'
-1.357106 Gtype    b'+2:lemma:cra'
-1.384802 O        b'+1:lemma:in'
-1.421905 O        b'+1:lemma:2.0'
-1.436909 OD       b'+1:postag:NN'
-1.437140 Anti     b'+2:lemma:polyclonal'
-1.442674 Supp     b'+2:lemma:2'
-1.474029 O        b'-1:postag:VBG'
-1.510725 O        b'-1:lemma:1'
-1.511208 O        b'+2:lemma:rifampicin'
-1.539773 Supp     b'+2:lemma:1'
-1.576652 O        b'-1:lemma:sample'
-1.596285 Supp     b'+2:postag:CD'
-1.602706 Supp     b'+2:lemma:fructose'
-1.609888 OD       b'+2:lemma:aerobically'
-1.653266 O        b'-2:lemma:rifampicin'
-1.693828 O        b'lemma:30'
-1.745628 Supp     b'postag:JJ'
-1.754845 Phase    b'postag:JJ'
-2.081244 Gtype    b'postag:VBG'
-2.085569 O        b'lemma:0.3'
-2.233412 O        b'+1:lemma:1'
-2.309269 Anti     b'postag:NNP'
-2.656990 O        b'+1:lemma:2'
-3.924521 O        b'-1:lemma::'
-4.650524 O        b'-1:lemma:_'