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

best params:{'c1': 0.03780171336875179, 'c2': 0.012718090480016972}
best CV score:0.8741870589668248
model size: 0.16M

Flat F1: 0.764435455440298
             precision    recall  f1-score   support

         OD      0.818     0.818     0.818        22
         pH      1.000     1.000     1.000         8
  Technique      0.955     0.913     0.933        23
        Med      1.000     0.925     0.961        53
       Temp      1.000     0.759     0.863        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      0.556     0.362     0.439        69
       Anti      1.000     1.000     1.000        11
     Strain      0.000     0.000     0.000         1
      Gtype      0.869     0.859     0.864        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.593     0.806     0.684       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.769     0.778     0.764       451


Top likely transitions:
Temp   -> Temp    5.633437
Agit   -> Agit    5.242920
Med    -> Med     5.205888
OD     -> OD      4.820634
Supp   -> Supp    4.795672
Anti   -> Anti    4.563286
Gversion -> Gversion 4.480777
Gtype  -> Gtype   4.410238
O      -> O       4.309533
Phase  -> Phase   4.099270
Air    -> Air     3.591014
Technique -> Technique 3.585887
pH     -> pH      2.997587
Substrain -> Gtype   1.829751
O      -> Technique 0.949969
Gtype  -> Supp    0.738864
O      -> Gtype   0.585802
Gtype  -> Air     0.391269
Gtype  -> pH      0.344184
Technique -> Air     0.264778
O      -> Supp    0.191022
Air    -> O       0.116016
Temp   -> O       0.097547
Med    -> O       0.057304
O      -> Anti    0.017577
pH     -> Supp    -0.028693
O      -> Phase   -0.048549
Technique -> OD      -0.055283
Anti   -> Med     -0.056104
Supp   -> O       -0.109106
Air    -> Temp    -0.113829
OD     -> Supp    -0.116904
Gversion -> Supp    -0.118460
Technique -> Supp    -0.137571
Air    -> OD      -0.151166
Agit   -> O       -0.182410
Air    -> Gtype   -0.230985
Supp   -> Gtype   -0.235813
Med    -> Air     -0.245332
Phase  -> O       -0.254973
Supp   -> Phase   -0.254988
Phase  -> Air     -0.262541
OD     -> O       -0.278938
Anti   -> O       -0.285405
Air    -> Phase   -0.291613
Gtype  -> Technique -0.321912
Anti   -> Supp    -0.329510
O      -> OD      -0.360061
Gtype  -> Anti    -0.380808
Gtype  -> Med     -0.399195


Top unlikely transitions:
Gtype  -> pH      0.344184
Technique -> Air     0.264778
O      -> Supp    0.191022
Air    -> O       0.116016
Temp   -> O       0.097547
Med    -> O       0.057304
O      -> Anti    0.017577
pH     -> Supp    -0.028693
O      -> Phase   -0.048549
Technique -> OD      -0.055283
Anti   -> Med     -0.056104
Supp   -> O       -0.109106
Air    -> Temp    -0.113829
OD     -> Supp    -0.116904
Gversion -> Supp    -0.118460
Technique -> Supp    -0.137571
Air    -> OD      -0.151166
Agit   -> O       -0.182410
Air    -> Gtype   -0.230985
Supp   -> Gtype   -0.235813
Med    -> Air     -0.245332
Phase  -> O       -0.254973
Supp   -> Phase   -0.254988
Phase  -> Air     -0.262541
OD     -> O       -0.278938
Anti   -> O       -0.285405
Air    -> Phase   -0.291613
Gtype  -> Technique -0.321912
Anti   -> Supp    -0.329510
O      -> OD      -0.360061
Gtype  -> Anti    -0.380808
Gtype  -> Med     -0.399195
Supp   -> Air     -0.399750
O      -> Med     -0.419285
Phase  -> OD      -0.436501
Air    -> Agit    -0.455472
Technique -> O       -0.530788
Temp   -> Med     -0.544192
Technique -> pH      -0.577493
Supp   -> Med     -0.646950
OD     -> Air     -0.730559
Phase  -> Supp    -0.748627
Air    -> Med     -0.810512
Gtype  -> O       -0.913442
Air    -> Supp    -0.986614
Agit   -> Air     -1.033744
O      -> Air     -1.071275
Substrain -> O       -1.325541
Technique -> Gtype   -1.554985
Med    -> Supp    -2.340793


Top positive:
5.181623 Air      b'word:Aerobic'
5.069692 O        b'-2:lemma:_'
4.702830 Anti     b'-2:lemma:antibody'
4.290692 Air      b'lemma:anaerobic'
4.139968 Gtype    b'-2:lemma:genotype/variation'
4.052057 O        b'word:Cra'
3.610352 Technique b'word:ChIP-Seq'
3.589676 O        b'lemma:_'
3.589676 O        b'word:_'
3.543264 O        b'lemma:1'
3.543264 O        b'word:1'
3.538307 O        b'lemma:2'
3.538307 O        b'word:2'
3.447474 Gtype    b'-2:lemma:genotype'
3.421203 Air      b'postag:RB'
3.390076 Phase    b'-2:lemma:phase'
3.349265 Supp     b'lemma:pq'
3.349265 Supp     b'word:PQ'
3.332208 O        b'-2:lemma:medium'
3.230628 O        b'-1:lemma:ChIP-exo'
3.167256 Technique b'lemma:rna-seq'
3.159409 O        b'-2:lemma:flagtag'
3.114586 Technique b'word:ChIP-exo'
3.101194 Technique b'lemma:ChIP-exo'
2.986312 Supp     b'lemma:nh4cl'
2.980962 Technique b'word:ChIPSeq'
2.961365 Gtype    b'lemma:type'
2.961365 Gtype    b'word:type'
2.960004 Air      b'word:Anaerobic'
2.947966 Gtype    b'word:WT'
2.932783 O        b'+2:lemma:\xc2\xb0c'
2.920653 Supp     b'+2:lemma:iptg'
2.872474 O        b'lemma:.'
2.872474 O        b'postag:.'
2.872474 O        b'word:.'
2.867743 Gtype    b'lemma:wild-type'
2.834804 Supp     b'-1:word:Cra'
2.831538 O        b'lemma:-'
2.831538 O        b'word:-'
2.798161 O        b'lemma:3'
2.798161 O        b'word:3'
2.798112 Gtype    b'-2:lemma:affyexp'
2.692314 O        b'lemma:rpob'
2.692314 O        b'word:RpoB'
2.675098 O        b'postag::'
2.664980 Gtype    b'lemma:wt'
2.604579 Gtype    b'lemma:\xce\xb4cra'
2.592394 O        b'postag:VBN'
2.550258 Supp     b'lemma:no3'
2.550258 Supp     b'word:NO3'
2.533320 Gtype    b'word:\xce\x94cra'
2.500008 Technique b'lemma:chipseq'
2.463493 Med      b'lemma:MOPS'
2.463493 Med      b'word:MOPS'
2.459381 O        b'+2:lemma:70'
2.452341 Supp     b'lemma:Iron'
2.452341 Supp     b'word:Iron'
2.452341 Supp     b'+1:word:Deficient'
2.452341 Supp     b'-2:lemma:Anaerobic'
2.449771 Med      b'+2:postag:CC'
2.435165 Phase    b'+2:lemma:o.d.'
2.430391 O        b'-1:lemma:tag'
2.425850 Phase    b'lemma:mid-log'
2.425850 Phase    b'word:mid-log'
2.407993 O        b'postag:IN'
2.398217 Phase    b'lemma:exponential'
2.398217 Phase    b'word:exponential'
2.398217 Phase    b'lemma:stationary'
2.398217 Phase    b'word:stationary'
2.392837 Supp     b'lemma:acetate'
2.392837 Supp     b'word:acetate'
2.385444 Gtype    b'+1:lemma:type'
2.385444 Gtype    b'+1:word:type'
2.380980 Anti     b'+2:lemma:antibody'
2.369810 Supp     b'-2:lemma:agent'
2.356829 O        b'word:A'
2.351468 Med      b'+2:lemma:b2'
2.300790 Supp     b'lemma:arginine'
2.298306 Supp     b'lemma:nacl'
2.298306 Supp     b'word:NaCl'
2.295477 O        b'+1:postag:NNP'
2.243176 O        b'-1:word:Aerobic'
2.239344 Air      b'lemma:Aerobic'
2.178927 O        b'lemma:b'
2.178927 O        b'word:B'
2.167680 Gtype    b'lemma:\xe2\x88\x86'
2.167680 Gtype    b'word:\xe2\x88\x86'
2.163673 Supp     b'lemma:glucose'
2.163673 Supp     b'word:glucose'
2.149402 Technique b'+2:lemma:ph5'
2.131320 O        b'lemma:with'
2.131320 O        b'word:with'
2.107004 Substrain b'lemma:mg1655'
2.107004 Substrain b'word:MG1655'
2.093423 O        b'+2:lemma:fructose'
2.092930 Supp     b'-1:lemma:with'
2.092930 Supp     b'-1:word:with'
2.072607 Supp     b'-1:lemma:Cra'
2.061502 O        b'+1:word:ChIP-Seq'
2.048739 O        b'lemma:ompr'
2.048739 O        b'word:OmpR'
2.041804 O        b'lemma:culture'
2.035926 Gtype    b'-2:postag:DT'
2.033981 Substrain b'-2:lemma:substr'
2.015820 Gtype    b'lemma:\xce\xb4soxr'
2.015820 Gtype    b'word:\xce\x94soxR'
2.002657 Gtype    b'lemma:flag-tag'
2.002657 Gtype    b'-1:lemma:c-terminal'
2.002657 Gtype    b'word:Flag-tag'
2.002657 Gtype    b'-1:word:C-terminal'
1.981109 Supp     b'+1:lemma:\xc2\xb5m'
1.981109 Supp     b'+1:word:\xc2\xb5M'
1.977275 O        b'+2:lemma:cra'
1.976163 Strain   b'+1:lemma:substr'
1.976163 Strain   b'+1:word:substr'
1.976163 Strain   b'-2:lemma:str'
1.966819 Technique b'lemma:rnaseq'
1.966819 Technique b'word:RNASeq'
1.966131 O        b'-2:lemma:myc'
1.956221 O        b'lemma:harbor'
1.956221 O        b'word:harboring'
1.947790 Gtype    b'-1:lemma:\xe2\x88\x86'
1.947790 Gtype    b'-1:word:\xe2\x88\x86'
1.943715 O        b'-1:lemma:lb'
1.943715 O        b'-1:word:LB'
1.942277 O        b'lemma:a'
1.929064 Gversion b'lemma:chip-seq'
1.918408 Technique b'word:RNA-Seq'
1.915726 pH       b'+1:postag:CD'
1.882795 O        b'+1:lemma:arca-8myc'
1.882795 O        b'+1:word:ArcA-8myc'
1.881377 O        b'-2:lemma:fructose'
1.853522 O        b'+1:postag:RB'
1.851023 Supp     b'postag:VBP'
1.845767 Supp     b'-2:lemma:induce'
1.833461 Gtype    b'lemma:\xce\xb4fur'
1.833461 Gtype    b'word:\xce\x94fur'
1.825330 Gversion b'word:ChIP-Seq'
1.815756 O        b'-1:lemma:glucose'
1.815756 O        b'-1:word:glucose'
1.815639 Gtype    b'+1:lemma:with'
1.815639 Gtype    b'+1:word:with'
1.809036 Gtype    b'-2:lemma:delta'
1.806217 Technique b'-1:lemma:chip-exo'
1.804393 Temp     b'isNumber'
1.797896 O        b'-1:word:tag'
1.786674 Supp     b'-2:lemma:purr'
1.783032 Supp     b'-2:lemma:argr'
1.765681 O        b'+2:postag:JJ'
1.765181 Supp     b'-1:postag:CC'
1.753024 Air      b'word:anaerobic'
1.751122 Gtype    b'-1:postag:VBG'
1.742490 Supp     b'-2:lemma:media'
1.737277 Med      b'+2:lemma:b1'
1.734728 O        b'+2:lemma:_'
1.710506 Gtype    b'+2:lemma:glucose'
1.709022 Supp     b'lemma:Leu'
1.709022 Supp     b'word:Leu'
1.709022 Supp     b'-2:lemma:Lrp'
1.707829 Supp     b'-2:lemma:condition'
1.695253 Gtype    b'lemma:\xce\xb4ompr'
1.695253 Gtype    b'word:\xce\x94ompR'
1.687283 Med      b'+1:lemma:0.4'
1.687283 Med      b'+1:word:0.4'
1.680612 Air      b'+1:postag:IN'
1.676466 O        b'lemma:soxs'
1.676466 O        b'word:SoxS'
1.676466 O        b'lemma:soxr'
1.676466 O        b'word:SoxR'
1.666118 O        b'lemma:Cra'
1.639338 O        b'-1:lemma:anaerobic'
1.636477 O        b'isLower'
1.632852 Med      b'lemma:media'
1.632852 Med      b'word:media'
1.629462 O        b'-2:lemma:treat'
1.626732 Gtype    b'lemma:dfnr'
1.626732 Gtype    b'word:dFNR'
1.623468 O        b'lemma:Custom'
1.623468 O        b'word:Custom'
1.621644 O        b'postag:CC'
1.618806 Gtype    b'lemma:\xce\xb4oxyr'
1.618806 Gtype    b'word:\xce\x94oxyR'
1.618168 Med      b'lemma:lb'
1.618168 Med      b'word:LB'
1.618066 O        b'-1:lemma:media'
1.618066 O        b'-1:word:media'
1.611062 Gtype    b'postag:JJ'
1.608968 O        b'lemma:argr'
1.608968 O        b'word:ArgR'
1.603897 Gversion b'-2:lemma:nc'
1.594090 O        b'lemma:trpr'
1.594090 O        b'word:TrpR'
1.583791 Air      b'lemma:aerobic'
1.567884 O        b'+1:postag:VBP'
1.567340 O        b'-1:lemma:0.3'
1.567340 O        b'-1:word:0.3'
1.561344 O        b'lemma::'
1.561344 O        b'word::'
1.560411 O        b'lemma:rep2'
1.560411 O        b'word:rep2'


Top negative:
-0.317190 OD       b'+2:postag:NN'
-0.317236 O        b'-2:postag::'
-0.319090 O        b'+1:lemma:2.0'
-0.319090 O        b'+1:word:2.0'
-0.319182 O        b'+2:lemma:30'
-0.325633 O        b'lemma:nh4cl'
-0.326977 Temp     b'+1:postag:IN'
-0.328963 O        b'lemma:methanol'
-0.328963 O        b'word:methanol'
-0.328963 O        b'-2:lemma:dissolve'
-0.330771 O        b'-1:lemma:rpob'
-0.330771 O        b'-1:word:RpoB'
-0.332385 Supp     b'+2:lemma:acetate'
-0.336346 O        b'+2:lemma:reference'
-0.340150 Strain   b'isLower'
-0.351888 Phase    b'+2:postag:NN'
-0.354760 O        b'-1:lemma:ph'
-0.354760 O        b'-1:word:pH'
-0.356359 O        b'word:tag'
-0.356948 O        b'-1:lemma:dissolve'
-0.356948 O        b'+1:lemma:methanol'
-0.356948 O        b'-1:word:dissolved'
-0.356948 O        b'+1:word:methanol'
-0.360165 O        b'lemma:aerobic'
-0.361875 O        b'-1:lemma:2'
-0.361875 O        b'-1:word:2'
-0.364393 O        b'lemma:medium'
-0.364393 O        b'word:medium'
-0.364434 O        b'lemma:anaerobic'
-0.365818 O        b'-1:lemma:co2'
-0.365818 O        b'-1:word:CO2'
-0.372268 O        b'-1:lemma:\xe2\x88\x86'
-0.372268 O        b'-1:word:\xe2\x88\x86'
-0.380490 Temp     b'isLower'
-0.386775 O        b'+1:lemma:1m'
-0.386775 O        b'+1:word:1M'
-0.386775 O        b'-2:lemma:vol'
-0.390297 Supp     b'-2:lemma:.'
-0.390297 Supp     b'-2:postag:.'
-0.405236 O        b'+2:lemma:fnr'
-0.408221 O        b'+2:lemma:mid-log'
-0.413792 O        b'lemma:fructose'
-0.413792 O        b'word:fructose'
-0.413863 Temp     b'-2:postag:NN'
-0.414885 O        b'-1:postag::'
-0.422156 O        b'+1:lemma:+'
-0.422156 O        b'+1:word:+'
-0.427210 O        b'-1:lemma:37'
-0.427210 O        b'-1:word:37'
-0.429642 Supp     b'+1:lemma:,'
-0.429642 Supp     b'+1:postag:,'
-0.429642 Supp     b'+1:word:,'
-0.434934 O        b'lemma:37'
-0.434934 O        b'word:37'
-0.449375 O        b'word:ChIP-exo'
-0.453085 pH       b'isUpper'
-0.454154 O        b'-2:lemma:IP'
-0.455382 Temp     b'+2:postag:IN'
-0.460059 Air      b'+1:postag:JJ'
-0.464417 O        b'-1:lemma:mm'
-0.464417 O        b'-1:word:mM'
-0.467555 O        b'+2:lemma:at'
-0.467980 O        b'lemma:anaerobically'
-0.467980 O        b'word:anaerobically'
-0.470071 O        b'-2:lemma:control'
-0.471057 O        b'+2:lemma:add'
-0.480066 O        b'+1:postag:IN'
-0.484390 O        b'lemma:of'
-0.484390 O        b'word:of'
-0.485748 O        b'lemma:aerobically'
-0.485748 O        b'word:aerobically'
-0.496119 O        b'-2:lemma:pahse'
-0.501405 O        b'-2:lemma:genome'
-0.513871 O        b'-2:postag:RB'
-0.528240 O        b'-2:postag:DT'
-0.554221 O        b'-1:lemma:ml'
-0.554221 O        b'-1:word:ml'
-0.555233 O        b'lemma:nitrogen'
-0.555233 O        b'word:nitrogen'
-0.557362 O        b'lemma:2h'
-0.557362 O        b'-1:lemma:additional'
-0.557362 O        b'word:2h'
-0.557362 O        b'-1:word:additional'
-0.574744 O        b'+1:postag:VBG'
-0.577749 Supp     b'+1:lemma:-lrb-'
-0.577749 Supp     b'+1:word:-LRB-'
-0.584147 O        b'-2:lemma:glucose'
-0.589012 O        b'+1:lemma:g/l'
-0.589012 O        b'+1:word:g/L'
-0.592857 O        b'lemma:glucose'
-0.592857 O        b'word:glucose'
-0.601655 O        b'-1:lemma:fresh'
-0.601655 O        b'-1:word:fresh'
-0.603478 Supp     b'+1:postag:-LRB-'
-0.621366 O        b'+1:lemma:in'
-0.621366 O        b'+1:word:in'
-0.622465 O        b'-1:lemma:30'
-0.622465 O        b'-1:word:30'
-0.622636 Supp     b'-1:postag:NNP'
-0.623045 Temp     b'postag:NN'
-0.628719 O        b'-2:lemma:minimal'
-0.629272 O        b'+2:lemma:250'
-0.632193 Supp     b'+1:postag:NNS'
-0.632244 O        b'-2:lemma:nh4cl'
-0.639178 O        b'+1:word:ChIP-exo'
-0.641094 Anti     b'+1:lemma:anti-fur'
-0.641094 Anti     b'+1:word:anti-Fur'
-0.652774 Supp     b'postag:CC'
-0.659478 Agit     b'isUpper'
-0.660753 O        b'-2:lemma:rpob'
-0.662803 O        b'+1:lemma:until'
-0.662803 O        b'+1:word:until'
-0.684151 O        b'-2:postag:SYM'
-0.701908 O        b'lemma:0.3'
-0.701908 O        b'word:0.3'
-0.708244 O        b'-2:lemma:aerobically'
-0.717945 pH       b'isLower'
-0.724124 O        b'-1:lemma:1'
-0.724124 O        b'-1:word:1'
-0.748149 O        b'lemma:media'
-0.748149 O        b'word:media'
-0.748561 O        b'-2:lemma:fresh'
-0.766386 O        b'-2:lemma:anaerobically'
-0.773055 O        b'-1:lemma:nsrr'
-0.773055 O        b'-1:word:NsrR'
-0.780146 O        b'lemma:\xce\xb4fur'
-0.780146 O        b'word:\xce\x94fur'
-0.780683 O        b'-1:lemma:grow'
-0.793481 Supp     b'+2:postag:CD'
-0.793996 Supp     b'+2:lemma:glucose'
-0.802497 Phase    b'isUpper'
-0.818377 O        b'+2:lemma:b'
-0.827115 O        b'lemma:nitrate'
-0.827115 O        b'word:nitrate'
-0.842837 O        b'-2:lemma:dpd'
-0.844530 Anti     b'isUpper'
-0.848235 O        b'lemma:wt'
-0.848520 Supp     b'-2:lemma:treat'
-0.856415 O        b'-1:lemma:chip-exo'
-0.857668 O        b'-2:lemma:rifampicin'
-0.870943 Med      b'-2:postag:VBN'
-0.880457 Med      b'-1:postag:NN'
-0.892873 Supp     b'-2:postag:JJ'
-0.904754 O        b'+1:lemma:at'
-0.904754 O        b'+1:word:at'
-0.911903 Med      b'+2:postag:VBN'
-0.952984 Air      b'postag:NN'
-0.961352 Technique b'isNumber'
-0.969534 O        b'lemma:rifampicin'
-0.969534 O        b'word:rifampicin'
-0.972230 Gtype    b'isNumber'
-0.979689 O        b'-1:lemma:vol'
-0.979689 O        b'-1:word:vol'
-0.979689 O        b'-2:lemma:1/100'
-0.979689 O        b'+2:lemma:1m'
-0.994381 O        b'lemma:mid-log'
-0.994381 O        b'word:mid-log'
-0.998905 O        b'-1:lemma:IP'
-0.998905 O        b'-1:word:IP'
-1.010402 O        b'-1:lemma:sample'
-1.039200 O        b'+2:lemma:then'
-1.063285 Supp     b'-2:lemma:grow'
-1.070057 Gversion b'isLower'
-1.088636 O        b'-2:lemma::'
-1.111068 O        b'+2:lemma:rifampicin'
-1.141806 O        b'lemma:30'
-1.141806 O        b'word:30'
-1.155863 Gtype    b'isLower'
-1.158383 O        b'-2:lemma:media'
-1.163155 Gtype    b'-2:lemma:\xe2\x88\x86'
-1.183034 O        b'-2:lemma:phase'
-1.187663 O        b'-2:lemma:until'
-1.205548 O        b'+2:lemma:+'
-1.219191 Technique b'isLower'
-1.223177 O        b'postag:RB'
-1.253855 OD       b'+1:postag:NN'
-1.256714 O        b'+1:lemma:1'
-1.256714 O        b'+1:word:1'
-1.263687 Anti     b'+2:lemma:polyclonal'
-1.291590 O        b'+2:lemma:for'
-1.317736 Gtype    b'+2:lemma:cra'
-1.346822 Supp     b'postag:JJ'
-1.369654 Gtype    b'postag:VBG'
-1.433422 O        b'postag:VBP'
-1.476722 O        b'+1:lemma:2'
-1.476722 O        b'+1:word:2'
-1.525519 O        b'-2:lemma:0.3'
-1.666455 Supp     b'+2:lemma:1'
-1.826364 Med      b'-2:lemma:grow'
-1.900619 Phase    b'-1:postag:JJ'
-1.925903 Supp     b'+2:lemma:2'
-2.114791 O        b'-1:postag:VBG'
-2.153462 Supp     b'+2:lemma:fructose'
-2.237029 Anti     b'postag:NNP'
-2.314282 O        b'-1:lemma::'
-2.314282 O        b'-1:word::'
-2.363285 O        b'-1:lemma:_'
-2.363285 O        b'-1:word:_'
-2.770952 OD       b'+2:lemma:aerobically'
-3.794024 Phase    b'postag:JJ'