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

best params:{'c1': 0.16617627893415826, 'c2': 0.016246283722594547}
best CV score:0.8677299702871124
model size: 0.09M

Flat F1: 0.8100263815531699
             precision    recall  f1-score   support

         OD      1.000     0.818     0.900        22
         pH      1.000     1.000     1.000         8
  Technique      1.000     0.913     0.955        23
        Med      1.000     0.943     0.971        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      0.565     0.377     0.452        69
       Anti      1.000     1.000     1.000        11
     Strain      0.000     0.000     0.000         1
      Gtype      0.889     0.847     0.867        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.811     0.799     0.805       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.845     0.783     0.810       451


Top likely transitions:
Agit   -> Agit    6.716949
Temp   -> Temp    6.219197
OD     -> OD      5.656758
Med    -> Med     5.510885
Supp   -> Supp    5.091598
Anti   -> Anti    4.770668
Gversion -> Gversion 4.530576
Phase  -> Phase   4.343162
Air    -> Air     4.176421
Gtype  -> Gtype   3.872949
O      -> O       3.576273
Technique -> Technique 3.464421
pH     -> pH      3.115258
O      -> Technique 0.821082
Substrain -> Gtype   0.704368
O      -> Supp    0.589038
Air    -> O       0.511427
Gtype  -> Supp    0.510592
Gtype  -> Air     0.474170
Temp   -> O       0.189513
O      -> Gtype   0.176860
Supp   -> O       0.145242
Technique -> Air     0.118103
Med    -> O       0.093609
O      -> Anti    0.090099
Phase  -> O       0.002296
O      -> Temp    0.002073
O      -> Phase   0.000043
O      -> Med     -0.015745
Gtype  -> Med     -0.042610
Supp   -> Med     -0.045443
O      -> OD      -0.113818
Air    -> Supp    -0.115743
Technique -> pH      -0.124518
OD     -> Air     -0.194892
Gversion -> O       -0.196158
Gtype  -> Technique -0.579025
Technique -> O       -0.829124
O      -> Air     -0.902346
Gtype  -> O       -0.925779
Med    -> Supp    -1.463243
Substrain -> O       -1.475265


Top unlikely transitions:
Agit   -> Agit    6.716949
Temp   -> Temp    6.219197
OD     -> OD      5.656758
Med    -> Med     5.510885
Supp   -> Supp    5.091598
Anti   -> Anti    4.770668
Gversion -> Gversion 4.530576
Phase  -> Phase   4.343162
Air    -> Air     4.176421
Gtype  -> Gtype   3.872949
O      -> O       3.576273
Technique -> Technique 3.464421
pH     -> pH      3.115258
O      -> Technique 0.821082
Substrain -> Gtype   0.704368
O      -> Supp    0.589038
Air    -> O       0.511427
Gtype  -> Supp    0.510592
Gtype  -> Air     0.474170
Temp   -> O       0.189513
O      -> Gtype   0.176860
Supp   -> O       0.145242
Technique -> Air     0.118103
Med    -> O       0.093609
O      -> Anti    0.090099
Phase  -> O       0.002296
O      -> Temp    0.002073
O      -> Phase   0.000043
O      -> Med     -0.015745
Gtype  -> Med     -0.042610
Supp   -> Med     -0.045443
O      -> OD      -0.113818
Air    -> Supp    -0.115743
Technique -> pH      -0.124518
OD     -> Air     -0.194892
Gversion -> O       -0.196158
Gtype  -> Technique -0.579025
Technique -> O       -0.829124
O      -> Air     -0.902346
Gtype  -> O       -0.925779
Med    -> Supp    -1.463243
Substrain -> O       -1.475265


Top positive:
6.433973 Technique b'lemma[:2]:Ch'
6.360815 O        b'lemma:2'
5.662452 Anti     b'-2:lemma:antibody'
5.635583 O        b'lemma:1'
5.375548 O        b'-2:lemma:_'
5.334062 O        b'lemma:3'
4.328011 Gtype    b'lemma[:1]:\xce\xb4'
4.274267 O        b'lemma[:2]:re'
4.227305 Phase    b'lemma:mid-log'
4.196090 Air      b'lemma[:2]:ae'
3.698810 Gtype    b'-1:lemma:\xe2\x88\x86'
3.689545 Substrain b'lemma[:2]:mg'
3.405547 Air      b'lemma:anaerobic'
3.375450 Technique b'lemma:chipseq'
3.355381 O        b'-2:lemma:medium'
3.263554 O        b'lemma:with'
3.228684 O        b'lemma:b'
3.212301 Technique b'lemma[:2]:rn'
3.141015 Supp     b'lemma:acetate'
3.091356 Phase    b'-2:lemma:phase'
3.034572 Gtype    b'lemma:type'
3.034572 Gtype    b'lemma[:2]:ty'
3.019205 O        b'-1:lemma:tag'
2.976419 Air      b'lemma[:2]:an'
2.958977 O        b'+2:lemma:\xc2\xb0c'
2.937672 O        b'lemma[:2]:ge'
2.921253 O        b'lemma[:1]:h'
2.903272 Gtype    b'-2:lemma:genotype/variation'
2.893999 Supp     b'lemma:arginine'
2.891850 O        b'lemma:-'
2.870735 Supp     b'-1:lemma:with'
2.863673 Gtype    b'+1:lemma:type'
2.803093 Supp     b'lemma:pq'
2.803093 Supp     b'lemma[:2]:pq'
2.800209 O        b'lemma:a'
2.752078 Med      b'+2:postag:CC'
2.708393 Gtype    b'lemma[:2]:pk'
2.703014 Supp     b'-1:lemma:Cra'
2.629891 O        b'lemma:_'
2.629891 O        b'lemma[:1]:_'
2.596183 Supp     b'lemma:Iron'
2.596183 Supp     b'lemma[:2]:Ir'
2.596183 Supp     b'-2:lemma:Anaerobic'
2.569027 O        b'+2:lemma:70'
2.544018 Supp     b'+2:lemma:iptg'
2.496912 OD       b'lemma[:1]:o'
2.467329 Supp     b'+1:lemma:\xc2\xb5m'
2.456900 O        b'lemma:.'
2.456900 O        b'postag:.'
2.456900 O        b'postag[:1]:.'
2.453094 O        b'+1:lemma:pq'
2.442390 O        b'-1:lemma:ChIP-exo'
2.433484 Technique b'lemma[:2]:ch'
2.399879 Anti     b'+2:lemma:antibody'
2.363621 Air      b'lemma:Aerobic'
2.363621 Air      b'lemma[:2]:Ae'
2.358981 Gtype    b'-2:lemma:delta'
2.342573 O        b'-2:lemma:myc'
2.331321 Supp     b'lemma:no3'
2.313202 Supp     b'lemma:rifampicin'
2.312753 Anti     b'+1:lemma:antibody'
2.297741 Supp     b'lemma[:2]:ri'
2.281621 Air      b'-2:lemma:IP'
2.278366 Med      b'lemma:MOPS'
2.278366 Med      b'lemma[:1]:M'
2.278366 Med      b'lemma[:2]:MO'
2.270655 OD       b'lemma[:2]:od'
2.263438 Gversion b'lemma:chip-seq'
2.231180 O        b'-1:lemma:glucose'
2.206950 Gtype    b'lemma:wt'
2.206950 Gtype    b'lemma[:2]:wt'
2.187730 Supp     b'lemma[:2]:gl'
2.186178 pH       b'+1:postag:CD'
2.183027 Technique b'-1:lemma:input'
2.179683 O        b'lemma[:1]:-'
2.172484 Air      b'-1:lemma:ChIP-Seq'
2.160518 Phase    b'lemma:stationary'
2.150044 Phase    b'lemma[:2]:ex'
2.145423 O        b'postag:IN'
2.145423 O        b'postag[:1]:I'
2.145423 O        b'postag[:2]:IN'
2.135783 O        b'-1:lemma:lb'
2.115167 O        b'-1:lemma:anaerobic'
2.106797 O        b'lemma:rpob'
2.094643 O        b'+2:lemma:cra'
2.046836 Gtype    b'-2:postag:DT'
2.035645 Gtype    b'lemma:nsrr'
2.035645 Gtype    b'lemma[:2]:ns'
2.034890 Technique b'lemma[:1]:C'
2.033641 O        b'+1:postag:RB'
2.013660 Supp     b'+1:lemma:1'
2.011345 Supp     b'lemma:fructose'
2.002182 Supp     b'-2:lemma:media'
1.998148 Gtype    b'hGreek'
1.992371 Temp     b'-1:lemma:\xcf\x8332'
1.980657 O        b'postag::'
1.980657 O        b'postag[:1]::'
1.979866 Supp     b'-1:lemma:final'
1.974647 Med      b'+2:lemma:b2'
1.964961 Temp     b'-1:lemma:sample'
1.959365 Strain   b'+1:lemma:substr'
1.959365 Strain   b'-2:lemma:str'
1.931532 Temp     b'-2:lemma:\xcf\x8332'
1.926204 pH       b'lemma[:2]:ph'
1.924918 Supp     b'-2:lemma:agent'
1.911949 Supp     b'lemma[:1]:n'
1.895649 Supp     b'+2:lemma:rifampicin'
1.895108 Temp     b'+2:postag:DT'
1.894074 Air      b'-1:lemma:-'
1.892359 Gtype    b'lemma:\xe2\x88\x86'
1.892359 Gtype    b'lemma[:1]:\xe2\x88\x86'
1.886561 O        b'-1:lemma:media'
1.878120 Gtype    b'lemma[:1]:w'
1.849654 Air      b'-1:lemma:co2'
1.819415 Supp     b'-1:lemma:+'
1.819234 Med      b'lemma:L'
1.819234 Med      b'+1:lemma:broth'
1.811008 Anti     b'lemma[:2]:an'
1.807476 O        b'-1:lemma:0.3'
1.795731 O        b'-1:postag:NNS'
1.794762 O        b'postag:CC'
1.794762 O        b'postag[:2]:CC'
1.793009 Gtype    b'-1:postag:VBG'
1.774172 O        b'lemma[:1]:C'
1.769427 Temp     b'lemma[:1]:3'
1.750065 Med      b'lemma:broth'
1.750065 Med      b'-1:lemma:L'
1.750065 Med      b'lemma[:2]:br'
1.731860 Air      b'lemma[:1]:A'
1.729863 Supp     b'-1:postag:CC'
1.711219 Gtype    b'+1:lemma:with'
1.710940 O        b'+1:postag:NNP'
1.706914 O        b'+1:lemma:coli'
1.705143 Phase    b'lemma[:1]:e'
1.701557 O        b'lemma:chip'
1.688302 Gtype    b'lemma[:2]:ar'
1.687398 Gtype    b'-1:lemma:_'
1.679707 Supp     b'-2:lemma:induce'
1.674594 O        b'+1:lemma:250'
1.667872 O        b'-2:lemma:ChIP-Seq'
1.653279 Gtype    b'+1:lemma::'
1.627724 O        b'lemma:A'
1.622722 Supp     b'lemma[:2]:ac'
1.617166 O        b'postag:VBN'
1.614130 Substrain b'lemma[:1]:m'
1.610355 Gtype    b'-2:lemma:genotype'
1.606189 O        b'+2:postag:JJ'
1.605995 O        b'lemma:0.4'
1.600992 Substrain b'+1:lemma:phtpg'
1.591094 O        b'-1:lemma:Aerobic'
1.589843 Supp     b'-1:lemma:_'
1.579672 Air      b'+1:postag:IN'
1.566124 Temp     b'lemma:43'
1.566124 Temp     b'lemma[:2]:43'
1.563526 O        b'-1:lemma:type'
1.558846 Supp     b'lemma[:2]:30'
1.552158 O        b'-1:lemma:aerobically'
1.551882 Gversion b'lemma:nc'
1.551882 Gversion b'lemma[:2]:nc'
1.536623 Supp     b'+1:lemma:_'
1.536256 O        b'-1:lemma:\xc2\xb0c'
1.524621 Air      b'lemma[:1]:a'
1.511586 Temp     b'-1:lemma:43'
1.506306 O        b'lemma[:1]:b'
1.506103 Gtype    b'lemma[:2]:wi'
1.498210 Supp     b'+1:lemma:2'
1.491309 Gtype    b'+1:lemma:flagtag'
1.490390 Med      b'+1:lemma:0.4'
1.485550 O        b'+2:lemma:fructose'
1.479904 Supp     b'lemma:Leu'
1.479904 Supp     b'lemma[:2]:Le'
1.479904 Supp     b'-2:lemma:Lrp'
1.475818 Supp     b'lemma:glucose'
1.472393 Gtype    b'lemma[:2]:fl'
1.471237 Gtype    b'-1:lemma:rpob'
1.464668 Med      b'lemma:lb'
1.464668 Med      b'lemma[:2]:lb'
1.462458 O        b'+1:lemma:mid-log'
1.460719 Med      b'+2:lemma:b1'
1.459376 O        b'lemma[:2]:ha'
1.450388 Supp     b'lemma[:1]:I'
1.442333 Gtype    b'-1:lemma:vector'
1.442007 Med      b'+1:lemma:g/l'
1.435558 Supp     b'lemma[:2]:ni'
1.434864 O        b'lemma:ml'
1.434864 O        b'lemma[:2]:ml'
1.431207 Technique b'symb'
1.424801 O        b'lemma[:1]:r'
1.421918 Supp     b'+2:lemma:mid-log'
1.413708 O        b'lemma[:1]:s'
1.383477 O        b'-2:postag:FW'
1.383257 O        b'-1:lemma:into'
1.382919 O        b'lemma[:2]:ga'
1.354991 O        b'lemma[:1]:c'
1.346926 Med      b'+1:lemma:minimal'
1.336028 Gtype    b'lemma[:1]:f'
1.335008 O        b'+1:postag:VBN'
1.329569 pH       b'lemma:ph5'
1.329569 pH       b'+1:lemma:.5'
1.326705 Gtype    b'-2:lemma:affyexp'


Top negative:
-0.155596 Supp     b'-1:lemma:10'
-0.157470 O        b'+2:lemma:ph'
-0.158631 Supp     b'lemma[:1]:s'
-0.159053 O        b'-1:lemma:from'
-0.160270 Supp     b'-1:lemma:-lrb-'
-0.160524 Gtype    b'+2:postag:CD'
-0.161112 Air      b'postag[:1]:N'
-0.161112 Air      b'postag[:2]:NN'
-0.161768 pH       b'postag:NN'
-0.161818 OD       b'symb'
-0.167771 Supp     b'-2:lemma:treat'
-0.176292 O        b'lemma:co2'
-0.177197 O        b'-1:lemma:g/l'
-0.181198 O        b'-1:lemma:1m'
-0.181198 O        b'+2:lemma:7.6'
-0.186508 O        b'-2:lemma:genome'
-0.193058 Supp     b'+2:lemma:-rrb-'
-0.194306 Gtype    b'lemma[:1]:h'
-0.194450 Supp     b'-1:postag:-LRB-'
-0.195692 Anti     b'symb'
-0.197135 O        b'-2:lemma:of'
-0.201423 O        b'-2:lemma:-lrb-'
-0.201718 O        b'-1:lemma:0.2'
-0.207096 Temp     b'postag[:1]:N'
-0.207096 Temp     b'postag[:2]:NN'
-0.208637 Temp     b'-2:postag:NN'
-0.210816 Technique b'-2:postag:NN'
-0.212139 O        b'lemma:in'
-0.215720 Supp     b'+2:postag:-RRB-'
-0.227268 O        b'+2:lemma:-rrb-'
-0.229192 O        b'lemma:anaerobic'
-0.229556 O        b'+1:lemma:.'
-0.229556 O        b'+1:postag:.'
-0.229949 Vess     b'hUpper'
-0.229949 Vess     b'hLower'
-0.232026 O        b'lemma[:1]:n'
-0.239837 O        b'lemma:30'
-0.244559 O        b'lemma:anaerobically'
-0.245601 Phase    b'+1:postag:NN'
-0.249673 O        b'-2:lemma:aerobically'
-0.251037 O        b'-2:lemma:a'
-0.251989 O        b'lemma[:1]:d'
-0.252202 Supp     b'lemma[:1]:a'
-0.253068 O        b'-2:postag:-LRB-'
-0.258564 O        b'+1:lemma:mm'
-0.260363 O        b'-1:lemma:fresh'
-0.261060 O        b'-2:lemma:anaerobically'
-0.262340 Air      b'-1:lemma:or'
-0.263528 pH       b'postag[:1]:N'
-0.263528 pH       b'postag[:2]:NN'
-0.265074 O        b'-2:postag::'
-0.265217 O        b'-2:lemma:IP'
-0.269304 Med      b'+1:postag:NN'
-0.285401 O        b'-2:lemma:rpob'
-0.295781 Supp     b'lemma[:2]:an'
-0.296045 O        b'lemma[:2]:ar'
-0.296575 O        b'-2:lemma:fresh'
-0.301913 O        b'lemma:media'
-0.307515 O        b'lemma[:2]:gl'
-0.308163 O        b'-1:postag:IN'
-0.311903 O        b'-1:lemma:mm'
-0.312159 O        b'-2:lemma:nh4cl'
-0.322974 Anti     b'+2:postag:JJ'
-0.325164 Supp     b'-2:postag:JJ'
-0.328654 Supp     b'-1:postag:NNP'
-0.332535 O        b'-1:lemma:of'
-0.341258 O        b'lemma:methanol'
-0.341258 O        b'-2:lemma:dissolve'
-0.346421 Supp     b'+2:lemma:glucose'
-0.353210 Technique b'-1:postag::'
-0.357081 O        b'+1:lemma:supplement'
-0.362827 O        b'lemma:2h'
-0.362827 O        b'-1:lemma:additional'
-0.362827 O        b'lemma[:2]:2h'
-0.373258 O        b'-1:lemma:final'
-0.373355 O        b'+2:lemma:at'
-0.376466 Supp     b'+1:postag:NNS'
-0.379434 O        b'-1:lemma:IP'
-0.379949 O        b'lemma[:1]:0'
-0.380927 O        b'-2:lemma:phase'
-0.384075 O        b'lemma:glucose'
-0.384929 Med      b'-1:postag:NN'
-0.387171 O        b'lemma[:1]:k'
-0.388425 O        b'lemma:\xe2\x88\x86'
-0.388425 O        b'lemma[:1]:\xe2\x88\x86'
-0.390156 Temp     b'postag:NN'
-0.390965 O        b'+1:lemma:g/l'
-0.410576 Med      b'-1:postag:CD'
-0.411791 O        b'+1:lemma:1m'
-0.411791 O        b'-2:lemma:vol'
-0.418447 Gtype    b'+1:lemma:-rrb-'
-0.418498 O        b'-1:lemma:rpob'
-0.422355 O        b'-2:lemma:until'
-0.434852 Technique b'postag:NN'
-0.435566 Supp     b'postag:JJ'
-0.439076 Supp     b'postag[:1]:J'
-0.439076 Supp     b'postag[:2]:JJ'
-0.442452 O        b'-1:lemma:30'
-0.455337 Med      b'+2:postag:VBN'
-0.455366 Air      b'postag:NN'
-0.461874 O        b'+2:lemma:fnr'
-0.467110 O        b'-2:lemma:supplement'
-0.468087 O        b'-1:lemma:dissolve'
-0.468087 O        b'+1:lemma:methanol'
-0.486893 Gtype    b'-2:lemma:\xe2\x88\x86'
-0.493653 O        b'lemma[:1]:L'
-0.497715 O        b'+2:lemma:10'
-0.498822 O        b'lemma:of'
-0.498822 O        b'lemma[:2]:of'
-0.507436 O        b'lemma[:2]:0.'
-0.510139 Med      b'+1:postag:IN'
-0.513295 O        b'+2:lemma:tag'
-0.514818 O        b'+1:lemma:+'
-0.532828 O        b'-1:lemma:\xe2\x88\x86'
-0.536622 O        b'+2:lemma:mid-log'
-0.538561 Supp     b'+1:lemma:-lrb-'
-0.543996 O        b'+2:lemma:.'
-0.543996 O        b'+2:postag:.'
-0.557797 Supp     b'+1:postag:-LRB-'
-0.568152 O        b'+2:lemma:a'
-0.585265 O        b'-2:lemma:pahse'
-0.590510 O        b'-2:lemma:glucose'
-0.590875 O        b'+1:lemma:until'
-0.605869 O        b'-1:lemma:nsrr'
-0.609882 O        b'-2:lemma:dpd'
-0.616188 Phase    b'-1:postag:JJ'
-0.618132 Air      b'-1:postag:JJ'
-0.624517 O        b'-2:postag:SYM'
-0.626955 Gtype    b'lemma[:1]:c'
-0.627961 Anti     b'+2:lemma:polyclonal'
-0.635434 Med      b'symb'
-0.635949 Phase    b'postag[:1]:J'
-0.635949 Phase    b'postag[:2]:JJ'
-0.636258 OD       b'hUpper'
-0.636258 OD       b'hLower'
-0.636750 O        b'lemma[:2]:ri'
-0.647062 O        b'+1:postag:IN'
-0.654730 O        b'-2:lemma:2'
-0.655657 Phase    b'postag:JJ'
-0.655964 Supp     b'symb'
-0.660356 O        b'+2:lemma:+'
-0.661231 O        b'+1:lemma:2.0'
-0.662145 O        b'-2:lemma:media'
-0.666872 O        b'+2:lemma:b'
-0.675694 Anti     b'+1:lemma:anti-fur'
-0.688911 O        b'-1:lemma:co2'
-0.690102 Gtype    b'postag[:1]:V'
-0.690102 Gtype    b'postag[:2]:VB'
-0.694375 Gtype    b'lemma[:1]:r'
-0.706144 O        b'lemma[:2]:me'
-0.718038 O        b'lemma:mid-log'
-0.724228 O        b'lemma:rifampicin'
-0.735529 O        b'-2:lemma::'
-0.743194 Med      b'-2:postag:VBN'
-0.786989 Supp     b'+1:lemma:,'
-0.786989 Supp     b'+1:postag:,'
-0.789461 O        b'-2:postag:RB'
-0.815790 Agit     b'hUpper'
-0.815790 Agit     b'hLower'
-0.824637 O        b'+2:postag:-RRB-'
-0.828411 O        b'-1:lemma:cra'
-0.834312 O        b'+1:lemma:at'
-0.864833 O        b'-1:lemma:vol'
-0.864833 O        b'-2:lemma:1/100'
-0.864833 O        b'+2:lemma:1m'
-0.896137 O        b'-2:postag:DT'
-0.903408 Phase    b'hUpper'
-0.903408 Phase    b'hLower'
-0.954592 Gtype    b'lemma[:1]:a'
-0.958219 Gtype    b'+2:lemma:cra'
-0.959188 O        b'-1:lemma:ph'
-1.006021 O        b'-2:lemma:0.3'
-1.010964 O        b'lemma[:2]:ae'
-1.026041 Med      b'-2:lemma:grow'
-1.037767 O        b'-1:postag::'
-1.062839 O        b'-1:lemma:sample'
-1.105188 Supp     b'lemma[:1]:c'
-1.107601 OD       b'+1:postag:NN'
-1.109127 Agit     b'symb'
-1.130040 Supp     b'+2:postag:CD'
-1.149221 O        b'lemma:0.3'
-1.151210 O        b'-1:lemma:1'
-1.172944 O        b'lemma[:2]:30'
-1.211332 O        b'+2:lemma:then'
-1.263528 Supp     b'+2:lemma:fructose'
-1.346921 O        b'+2:lemma:rifampicin'
-1.394447 O        b'postag:VBP'
-1.459260 Supp     b'+2:lemma:1'
-1.504864 Anti     b'postag:NNP'
-1.616873 O        b'-1:lemma:2'
-1.627873 Supp     b'+2:lemma:2'
-1.790611 O        b'-1:postag:VBG'
-1.925758 O        b'-2:lemma:rifampicin'
-2.014829 O        b'+1:lemma:in'
-2.028945 OD       b'+2:lemma:aerobically'
-2.287808 O        b'+1:lemma:1'
-2.798978 O        b'+1:lemma:2'
-2.902688 O        b'lemma[:2]:fl'
-3.487913 O        b'-1:lemma::'
-4.880856 O        b'-1:lemma:_'