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

best params:{'c1': 0.10224977118326696, 'c2': 0.08574073868552615}
best CV score:0.8625521557665096
model size: 0.15M

Flat F1: 0.7911337627473737
             precision    recall  f1-score   support

         OD      1.000     0.818     0.900        22
         pH      1.000     1.000     1.000         8
  Technique      0.955     0.913     0.933        23
        Med      1.000     0.962     0.981        53
       Temp      1.000     0.621     0.766        29
       Vess      1.000     1.000     1.000         1
       Agit      0.000     0.000     0.000         0
      Phase      0.875     0.933     0.903        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      0.880     0.776     0.825        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.820     0.784     0.802       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.847     0.749     0.791       451


Top likely transitions:
Supp   -> Supp    4.853883
Med    -> Med     4.656088
Temp   -> Temp    4.510100
Agit   -> Agit    4.465117
OD     -> OD      4.340142
Anti   -> Anti    4.196466
Air    -> Air     3.821484
Gtype  -> Gtype   3.782966
Gversion -> Gversion 3.606921
O      -> O       3.495921
Phase  -> Phase   3.323762
Technique -> Technique 2.563651
pH     -> pH      2.180795
O      -> Supp    0.898100
Substrain -> Gtype   0.754641
Air    -> O       0.647741
O      -> Technique 0.571928
O      -> Gtype   0.481770
Supp   -> O       0.402376
Gtype  -> Supp    0.324453
Med    -> O       0.307057
Technique -> Air     0.224294
Gtype  -> Air     0.168729
O      -> Anti    0.038118
O      -> Temp    0.032123
Gtype  -> pH      0.002908
Temp   -> O       0.000361
Strain -> O       0.000160
Technique -> Gversion -0.000416
Air    -> Agit    -0.005831
Supp   -> pH      -0.007270
OD     -> O       -0.014197
Gversion -> Supp    -0.015735
Gtype  -> OD      -0.028160
Supp   -> Phase   -0.029631
Anti   -> Temp    -0.035006
Phase  -> Gtype   -0.044350
OD     -> Supp    -0.044521
Gtype  -> Temp    -0.059821
Temp   -> Med     -0.060792
Gtype  -> Phase   -0.069441
OD     -> Technique -0.077261
Air    -> Technique -0.079069
O      -> Agit    -0.096763
Anti   -> Supp    -0.100222
Phase  -> OD      -0.103283
Supp   -> Gversion -0.124409
Anti   -> Air     -0.126752
O      -> OD      -0.131232
Supp   -> Anti    -0.144899


Top unlikely transitions:
OD     -> O       -0.014197
Gversion -> Supp    -0.015735
Gtype  -> OD      -0.028160
Supp   -> Phase   -0.029631
Anti   -> Temp    -0.035006
Phase  -> Gtype   -0.044350
OD     -> Supp    -0.044521
Gtype  -> Temp    -0.059821
Temp   -> Med     -0.060792
Gtype  -> Phase   -0.069441
OD     -> Technique -0.077261
Air    -> Technique -0.079069
O      -> Agit    -0.096763
Anti   -> Supp    -0.100222
Phase  -> OD      -0.103283
Supp   -> Gversion -0.124409
Anti   -> Air     -0.126752
O      -> OD      -0.131232
Supp   -> Anti    -0.144899
Agit   -> Air     -0.145881
Supp   -> Air     -0.148035
Anti   -> Gtype   -0.148967
Phase  -> O       -0.182539
Gtype  -> Gversion -0.218235
Phase  -> Supp    -0.220677
Agit   -> O       -0.221526
Supp   -> Technique -0.230155
Air    -> Med     -0.252173
Anti   -> O       -0.256819
Technique -> Supp    -0.258507
Phase  -> Technique -0.308300
O      -> Med     -0.322260
Air    -> Phase   -0.344611
OD     -> Air     -0.369099
Air    -> Supp    -0.381831
Technique -> OD      -0.386625
Supp   -> Gtype   -0.423661
Gversion -> O       -0.442929
Gtype  -> Med     -0.466529
Gtype  -> Technique -0.486041
Air    -> Temp    -0.495035
Technique -> Gtype   -0.512140
O      -> Air     -0.557928
Gtype  -> Anti    -0.639624
Supp   -> Med     -0.666805
Technique -> pH      -0.687130
Technique -> O       -0.804221
Gtype  -> O       -0.839737
Substrain -> O       -1.005940
Med    -> Supp    -1.140134


Top positive:
2.992522 O        b'postag:IN'
2.933510 Gtype    b'lemma[:1]:\xce\xb4'
2.698175 O        b'lemma:_'
2.698175 O        b'lemma[:1]:_'
2.698175 O        b'word:_'
2.580892 Technique b'lemma[:2]:Ch'
2.528828 Air      b'lemma[:2]:an'
2.520301 O        b'postag::'
2.475598 Air      b'word:Aerobic'
2.397019 O        b'lemma[:2]:re'
2.343308 O        b'lemma:2'
2.343308 O        b'word:2'
2.187375 OD       b'lemma[:1]:o'
2.132214 Air      b'lemma:anaerobic'
2.102690 O        b'lemma:1'
2.102690 O        b'word:1'
2.069208 Air      b'postag:RB'
2.011921 Supp     b'-1:word:Cra'
2.008921 O        b'postag:CC'
1.985815 O        b'word:Cra'
1.954962 O        b'word:A'
1.945886 O        b'-1:lemma:tag'
1.944651 Air      b'lemma[:1]:a'
1.942100 Gtype    b'lemma[:1]:w'
1.941658 O        b'isLower'
1.941416 O        b'lemma:3'
1.941416 O        b'word:3'
1.928794 Anti     b'lemma[:2]:an'
1.904875 O        b'lemma:-'
1.904875 O        b'word:-'
1.894461 Air      b'lemma[:2]:ae'
1.837551 Supp     b'+1:lemma:\xc2\xb5m'
1.837551 Supp     b'+1:word:\xc2\xb5M'
1.827021 O        b'lemma:with'
1.827021 O        b'word:with'
1.820722 O        b'lemma:.'
1.820722 O        b'postag:.'
1.820722 O        b'word:.'
1.782610 Phase    b'lemma:mid-log'
1.782610 Phase    b'word:mid-log'
1.757467 Technique b'lemma:chipseq'
1.743523 Technique b'lemma[:1]:C'
1.733249 Technique b'word:ChIPSeq'
1.723058 O        b'-1:word:tag'
1.679894 Gtype    b'lemma[:2]:pk'
1.670517 Technique b'lemma[:2]:rn'
1.646145 O        b'lemma[:2]:ge'
1.642888 Gtype    b'word:WT'
1.641812 Air      b'word:Anaerobic'
1.636107 Supp     b'lemma:pq'
1.636107 Supp     b'lemma[:2]:pq'
1.636107 Supp     b'word:PQ'
1.616520 Gtype    b'lemma:wt'
1.616520 Gtype    b'lemma[:2]:wt'
1.602692 Substrain b'lemma[:2]:mg'
1.595791 Gtype    b'symb'
1.591226 Gtype    b'hGreek'
1.580745 Gtype    b'lemma[:2]:ar'
1.553690 O        b'isNumber'
1.549681 Supp     b'-1:lemma:with'
1.549681 Supp     b'-1:word:with'
1.538810 Med      b'isUpper'
1.524255 Supp     b'lemma:Iron'
1.524255 Supp     b'lemma[:2]:Ir'
1.524255 Supp     b'word:Iron'
1.524255 Supp     b'+1:word:Deficient'
1.523875 Med      b'lemma[:1]:m'
1.507350 Supp     b'lemma:arginine'
1.506721 O        b'-1:word:Aerobic'
1.504743 O        b'lemma:b'
1.504743 O        b'word:B'
1.503810 O        b'+1:lemma:pq'
1.503810 O        b'+1:word:PQ'
1.485328 Gtype    b'lemma:arca8myc'
1.485328 Gtype    b'word:ArcA8myc'
1.478520 Phase    b'lemma[:2]:ex'
1.477705 Supp     b'-1:postag:CC'
1.473033 Strain   b'+1:lemma:substr'
1.473033 Strain   b'+1:word:substr'
1.471852 O        b'lemma[:1]:h'
1.470534 Gtype    b'lemma[:1]:f'
1.432902 Technique b'word:ChIP-Seq'
1.432272 Gtype    b'-1:lemma:\xe2\x88\x86'
1.432272 Gtype    b'-1:word:\xe2\x88\x86'
1.431861 Supp     b'lemma:acetate'
1.431861 Supp     b'word:acetate'
1.426205 pH       b'+1:postag:CD'
1.426130 O        b'lemma:a'
1.423474 Phase    b'lemma[:1]:e'
1.416394 Gtype    b'lemma[:2]:cr'
1.412091 O        b'-1:lemma:lb'
1.412091 O        b'-1:word:LB'
1.409559 O        b'+1:postag:NNP'
1.396235 Supp     b'-1:lemma:Cra'
1.391229 Technique b'lemma:ChIP-exo'
1.387275 Supp     b'lemma[:2]:gl'
1.381222 O        b'postag:VBN'
1.357861 Technique b'lemma[:2]:ch'
1.349464 O        b'-1:lemma:ChIP-exo'
1.337510 Supp     b'lemma:rifampicin'
1.337510 Supp     b'word:rifampicin'
1.333930 Supp     b'lemma[:2]:ri'
1.331717 Supp     b'lemma[:2]:ni'
1.308373 Air      b'+1:postag:IN'
1.302031 Gtype    b'lemma[:2]:de'
1.301579 Supp     b'lemma[:1]:I'
1.295057 Gtype    b'lemma:type'
1.295057 Gtype    b'lemma[:2]:ty'
1.295057 Gtype    b'word:type'
1.293141 Technique b'symb'
1.290443 Air      b'-1:lemma:ChIP-Seq'
1.290443 Air      b'-1:word:ChIP-Seq'
1.286791 Gversion b'lemma[:2]:00'
1.282084 pH       b'lemma[:2]:ph'
1.264843 Gversion b'word:ChIP-Seq'
1.249803 Supp     b'lemma[:2]:ac'
1.237133 O        b'postag:DT'
1.232242 Gversion b'lemma:chip-seq'
1.230130 Gversion b'-1:lemma:nc'
1.230130 Gversion b'-1:word:NC'
1.230000 O        b'lemma:rpob'
1.230000 O        b'word:RpoB'
1.206427 Air      b'lemma:Aerobic'
1.206427 Air      b'lemma[:2]:Ae'
1.198600 Technique b'-1:lemma:chip-exo'
1.196166 Phase    b'lemma:stationary'
1.196166 Phase    b'word:stationary'
1.186607 Supp     b'-1:lemma:vol'
1.186607 Supp     b'-1:word:vol'
1.185194 Gtype    b'-1:postag:VBG'
1.185039 Gversion b'lemma:nc'
1.185039 Gversion b'lemma[:2]:nc'
1.185039 Gversion b'word:NC'
1.183740 O        b'-1:lemma:0.3'
1.183740 O        b'-1:word:0.3'
1.183722 Substrain b'lemma[:1]:m'
1.178060 Med      b'lemma:MOPS'
1.178060 Med      b'lemma[:1]:M'
1.178060 Med      b'lemma[:2]:MO'
1.178060 Med      b'word:MOPS'
1.176455 Agit     b'+1:lemma:rpm'
1.176455 Agit     b'+1:word:rpm'
1.173660 Air      b'lemma[:1]:A'
1.171020 O        b'lemma[:1]:C'
1.169586 O        b'lemma:Custom'
1.169586 O        b'lemma[:2]:Cu'
1.169586 O        b'word:Custom'
1.169290 Supp     b'lemma[:1]:n'
1.164574 O        b'lemma[:1]:r'
1.163122 O        b'+1:word:were'
1.161543 O        b'+1:postag:RB'
1.160553 Med      b'+1:lemma:0.4'
1.160553 Med      b'+1:word:0.4'
1.157301 Gtype    b'lemma[:1]:t'
1.139447 O        b'-1:lemma:glucose'
1.139447 O        b'-1:word:glucose'
1.136363 Gtype    b'lemma[:1]:W'
1.123777 Gversion b'lemma:asm584v2'
1.123777 Gversion b'word:ASM584v2'
1.122043 Gversion b'lemma[:2]:as'
1.119834 Technique b'word:ChIP-exo'
1.116571 Supp     b'+1:lemma:1'
1.116571 Supp     b'+1:word:1'
1.109080 O        b'-1:lemma:anaerobic'
1.107414 O        b'lemma:ompr'
1.107414 O        b'word:OmpR'
1.104893 Gtype    b'+1:lemma:type'
1.104893 Gtype    b'+1:word:type'
1.101638 O        b'lemma:chip'
1.101186 Temp     b'isUpper'
1.098068 Gtype    b'lemma:nsrr'
1.098068 Gtype    b'lemma[:2]:ns'
1.098068 Gtype    b'word:NsrR'
1.097533 Strain   b'lemma:k-12'
1.097533 Strain   b'lemma[:2]:k-'
1.097533 Strain   b'word:K-12'
1.094717 Agit     b'lemma:rpm'
1.094717 Agit     b'word:rpm'
1.093697 Anti     b'+1:lemma:antibody'
1.093697 Anti     b'+1:word:antibody'
1.090349 Supp     b'-1:lemma:+'
1.090349 Supp     b'-1:word:+'
1.089812 Med      b'lemma:broth'
1.089812 Med      b'-1:lemma:L'
1.089812 Med      b'lemma[:2]:br'
1.089812 Med      b'word:broth'
1.089812 Med      b'-1:word:L'
1.089439 O        b'lemma[:1]:s'
1.089354 Supp     b'lemma:glucose'
1.089354 Supp     b'word:glucose'
1.075102 Gtype    b'-1:lemma:_'
1.075102 Gtype    b'-1:word:_'
1.074174 OD       b'-1:postag:IN'
1.069035 Air      b'-1:lemma:-'
1.069035 Air      b'-1:word:-'
1.064267 O        b'lemma[:2]:om'
1.059425 Med      b'-1:lemma:ml'
1.059425 Med      b'-1:word:ml'
1.055151 O        b'lemma[:2]:ga'
1.051054 Temp     b'isNumber'


Top negative:
-0.269566 Med      b'+1:postag:NN'
-0.271003 O        b'+1:word:C'
-0.272991 Gtype    b'lemma[:1]:g'
-0.281915 Substrain b'isLower'
-0.285097 Supp     b'+1:lemma:acetate'
-0.285097 Supp     b'+1:word:acetate'
-0.289196 O        b'-1:lemma:control'
-0.289196 O        b'-1:word:control'
-0.291783 O        b'lemma:30'
-0.291783 O        b'word:30'
-0.296669 Supp     b'+1:lemma:nacl'
-0.296669 Supp     b'+1:word:NaCl'
-0.299139 Gtype    b'lemma[:2]:rp'
-0.299802 Supp     b'lemma[:1]:a'
-0.300346 Supp     b'isNumber'
-0.302212 Anti     b'+1:lemma:anti-fur'
-0.302212 Anti     b'+1:word:anti-Fur'
-0.302389 O        b'+1:lemma:rep2'
-0.302389 O        b'+1:word:rep2'
-0.302698 O        b'lemma:methanol'
-0.302698 O        b'word:methanol'
-0.303420 Supp     b'+1:lemma:fructose'
-0.303420 Supp     b'+1:word:fructose'
-0.305531 O        b'lemma:aerobically'
-0.305531 O        b'word:aerobically'
-0.306175 pH       b'isNumber'
-0.306838 O        b'lemma[:1]:d'
-0.308262 Gtype    b'+1:lemma:-rrb-'
-0.308262 Gtype    b'+1:word:-RRB-'
-0.312558 O        b'-1:lemma:mm'
-0.312558 O        b'-1:word:mM'
-0.313202 O        b'-1:postag:-LRB-'
-0.317810 O        b'lemma:of'
-0.317810 O        b'lemma[:2]:of'
-0.317810 O        b'word:of'
-0.319439 O        b'-1:lemma:final'
-0.319439 O        b'-1:word:final'
-0.321317 O        b'lemma:anaerobically'
-0.321317 O        b'word:anaerobically'
-0.325460 O        b'lemma[:1]:L'
-0.330481 O        b'lemma[:1]:A'
-0.332032 O        b'+1:lemma:at'
-0.332032 O        b'+1:word:at'
-0.333829 OD       b'hUpper'
-0.333829 OD       b'hLower'
-0.334342 O        b'lemma[:1]:\xce\xb4'
-0.338105 O        b'-1:lemma:37'
-0.338105 O        b'-1:word:37'
-0.345520 O        b'lemma[:1]:4'
-0.346277 Vess     b'hUpper'
-0.346277 Vess     b'hLower'
-0.351779 O        b'-1:lemma:cra'
-0.354108 Supp     b'-1:lemma:-lrb-'
-0.354108 Supp     b'-1:word:-LRB-'
-0.354176 O        b'lemma:0.3'
-0.354176 O        b'word:0.3'
-0.357826 O        b'+1:lemma:1m'
-0.357826 O        b'+1:word:1M'
-0.365975 O        b'-1:lemma:rpob'
-0.365975 O        b'-1:word:RpoB'
-0.369791 Supp     b'lemma[:2]:an'
-0.382535 Technique b'-1:postag::'
-0.385806 O        b'-1:lemma:ph'
-0.385806 O        b'-1:word:pH'
-0.390600 Strain   b'isLower'
-0.390996 Med      b'+1:postag:IN'
-0.397681 Technique b'isUpper'
-0.402341 O        b'lemma[:2]:ph'
-0.407916 O        b'-1:lemma:nsrr'
-0.407916 O        b'-1:word:NsrR'
-0.408181 pH       b'isUpper'
-0.408383 O        b'lemma[:1]:p'
-0.410419 O        b'-1:lemma:dissolve'
-0.410419 O        b'+1:lemma:methanol'
-0.410419 O        b'-1:word:dissolved'
-0.410419 O        b'+1:word:methanol'
-0.411632 O        b'+1:lemma:until'
-0.411632 O        b'+1:word:until'
-0.422310 O        b'+1:postag:IN'
-0.422805 O        b'lemma:wt'
-0.422805 O        b'lemma[:2]:wt'
-0.429703 Air      b'-1:lemma:or'
-0.429703 Air      b'-1:word:or'
-0.430609 O        b'lemma:soxs-8myc'
-0.430609 O        b'word:soxS-8myc'
-0.437708 O        b'word:cells'
-0.439438 Supp     b'-1:postag:-LRB-'
-0.443616 O        b'lemma[:2]:mg'
-0.447807 O        b'-1:postag:IN'
-0.454881 Technique b'postag:NN'
-0.455283 O        b'-1:lemma:30'
-0.455283 O        b'-1:word:30'
-0.455942 Med      b'-1:postag:CD'
-0.456974 O        b'-1:lemma:chip-exo'
-0.463642 O        b'lemma:2h'
-0.463642 O        b'-1:lemma:additional'
-0.463642 O        b'lemma[:2]:2h'
-0.463642 O        b'word:2h'
-0.463642 O        b'-1:word:additional'
-0.463824 O        b'lemma[:2]:ni'
-0.473738 O        b'-1:lemma:\xe2\x88\x86'
-0.473738 O        b'-1:word:\xe2\x88\x86'
-0.483472 Air      b'-1:postag:JJ'
-0.485640 O        b'lemma[:1]:k'
-0.489700 Agit     b'symb'
-0.491876 O        b'lemma[:2]:gl'
-0.493145 O        b'-1:lemma:1'
-0.493145 O        b'-1:word:1'
-0.493324 Supp     b'lemma[:1]:s'
-0.495721 O        b'-1:lemma:until'
-0.495721 O        b'-1:word:until'
-0.510059 O        b'+1:word:ChIP-exo'
-0.532260 Supp     b'-1:postag:NNP'
-0.532617 O        b'lemma:mid-log'
-0.532617 O        b'word:mid-log'
-0.538747 O        b'lemma[:2]:ar'
-0.539864 Temp     b'postag:NN'
-0.544326 Gtype    b'postag::'
-0.550034 O        b'lemma[:1]:n'
-0.552433 Technique b'isNumber'
-0.552875 O        b'-1:lemma:co2'
-0.552875 O        b'-1:word:CO2'
-0.553836 O        b'+1:lemma:mm'
-0.553836 O        b'+1:word:mM'
-0.575360 Agit     b'hUpper'
-0.575360 Agit     b'hLower'
-0.587589 O        b'+1:lemma:2.0'
-0.587589 O        b'+1:word:2.0'
-0.589156 Air      b'symb'
-0.593266 O        b'-1:lemma:IP'
-0.593266 O        b'-1:word:IP'
-0.606709 O        b'+1:lemma:+'
-0.606709 O        b'+1:word:+'
-0.623013 O        b'word:ChIP-exo'
-0.624809 Med      b'-1:postag:IN'
-0.644672 Med      b'symb'
-0.652610 O        b'lemma[:2]:an'
-0.663037 O        b'+1:postag:VBG'
-0.669924 Air      b'isLower'
-0.670219 O        b'+1:lemma:g/l'
-0.670219 O        b'+1:word:g/L'
-0.695683 pH       b'isLower'
-0.700730 O        b'-1:lemma:ml'
-0.700730 O        b'-1:word:ml'
-0.708528 Technique b'isLower'
-0.713532 Gtype    b'lemma[:1]:c'
-0.723267 O        b'postag:VBP'
-0.726763 Med      b'-1:postag:NN'
-0.730007 O        b'-1:lemma:fresh'
-0.730007 O        b'-1:word:fresh'
-0.732472 Gtype    b'isNumber'
-0.754791 Anti     b'postag:NNP'
-0.763751 O        b'lemma[:1]:I'
-0.765472 Phase    b'hUpper'
-0.765472 Phase    b'hLower'
-0.777034 O        b'postag:RB'
-0.783888 O        b'+1:lemma:1'
-0.783888 O        b'+1:word:1'
-0.819356 Supp     b'+1:postag:VBN'
-0.832076 Supp     b'+1:postag:-LRB-'
-0.834887 Supp     b'+1:lemma:-lrb-'
-0.834887 Supp     b'+1:word:-LRB-'
-0.845588 O        b'lemma[:2]:ri'
-0.859382 O        b'+1:lemma:in'
-0.859382 O        b'+1:word:in'
-0.863969 O        b'-1:lemma:2'
-0.863969 O        b'-1:word:2'
-0.863985 Supp     b'postag:JJ'
-0.879910 O        b'lemma:rifampicin'
-0.879910 O        b'word:rifampicin'
-0.890013 O        b'-1:lemma:sample'
-0.908122 O        b'lemma[:2]:me'
-0.918685 O        b'lemma[:2]:30'
-0.977725 Supp     b'symb'
-0.998621 Gtype    b'lemma[:1]:a'
-1.009514 O        b'lemma[:2]:ae'
-1.010867 Supp     b'lemma[:1]:c'
-1.019909 Supp     b'hGreek'
-1.025689 Gversion b'isLower'
-1.028787 O        b'-1:postag::'
-1.033347 Gtype    b'lemma[:1]:r'
-1.058669 Phase    b'postag:JJ'
-1.063118 OD       b'+1:postag:NN'
-1.085470 O        b'+1:lemma:2'
-1.085470 O        b'+1:word:2'
-1.097595 Temp     b'+1:postag:IN'
-1.104571 O        b'-1:lemma:vol'
-1.104571 O        b'-1:word:vol'
-1.105747 Phase    b'-1:postag:JJ'
-1.193803 Supp     b'+1:lemma:,'
-1.193803 Supp     b'+1:postag:,'
-1.193803 Supp     b'+1:word:,'
-1.225152 Gtype    b'isUpper'
-1.342867 Air      b'postag:NN'
-1.648816 O        b'-1:postag:VBG'
-1.734459 O        b'-1:lemma:_'
-1.734459 O        b'-1:word:_'
-1.809222 O        b'lemma[:2]:fl'
-2.034354 O        b'-1:lemma::'
-2.034354 O        b'-1:word::'