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

best params:{'c1': 0.04937325798482469, 'c2': 0.021347060592283952}
best CV score:0.8727912197138052
model size: 0.16M

Flat F1: 0.7834470810208732
             precision    recall  f1-score   support

         OD      0.857     0.818     0.837        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      1.000     0.621     0.766        29
       Vess      1.000     1.000     1.000         1
       Agit      0.000     0.000     0.000         0
      Phase      0.882     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      0.885     0.812     0.847        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.735     0.806     0.769       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.818     0.763     0.783       451


Top likely transitions:
Temp   -> Temp    5.697885
Med    -> Med     5.203676
Supp   -> Supp    5.023623
Anti   -> Anti    4.919423
Agit   -> Agit    4.878209
OD     -> OD      4.490452
Gtype  -> Gtype   4.342655
Phase  -> Phase   4.265502
Gversion -> Gversion 4.228866
O      -> O       3.927755
Air    -> Air     3.904248
Technique -> Technique 3.337823
pH     -> pH      3.047130
Substrain -> Gtype   0.928380
O      -> Technique 0.767492
O      -> Supp    0.345238
O      -> Gtype   0.335711
Technique -> Air     0.302367
Air    -> O       0.238748
Gtype  -> Supp    0.106918
Temp   -> O       0.099174
O      -> Anti    0.028918
O      -> Temp    0.024359
Gtype  -> Air     0.000872
O      -> Strain  -0.006968
OD     -> Med     -0.016869
Vess   -> O       -0.025460
Air    -> Agit    -0.030216
Technique -> Supp    -0.054732
Gtype  -> Temp    -0.066953
Air    -> Technique -0.074730
Phase  -> Gtype   -0.080334
O      -> Phase   -0.082037
Anti   -> Supp    -0.094817
O      -> Agit    -0.122548
Anti   -> Gtype   -0.136175
Agit   -> Air     -0.139559
Phase  -> Technique -0.151160
Gtype  -> Gversion -0.170913
Supp   -> Phase   -0.196758
Supp   -> O       -0.208933
Agit   -> O       -0.223185
Supp   -> Technique -0.223482
Phase  -> OD      -0.285779
Supp   -> Gversion -0.304736
Technique -> OD      -0.319741
Supp   -> Anti    -0.336780
Med    -> O       -0.359992
Temp   -> Med     -0.365995
Supp   -> Air     -0.395049


Top unlikely transitions:
Vess   -> O       -0.025460
Air    -> Agit    -0.030216
Technique -> Supp    -0.054732
Gtype  -> Temp    -0.066953
Air    -> Technique -0.074730
Phase  -> Gtype   -0.080334
O      -> Phase   -0.082037
Anti   -> Supp    -0.094817
O      -> Agit    -0.122548
Anti   -> Gtype   -0.136175
Agit   -> Air     -0.139559
Phase  -> Technique -0.151160
Gtype  -> Gversion -0.170913
Supp   -> Phase   -0.196758
Supp   -> O       -0.208933
Agit   -> O       -0.223185
Supp   -> Technique -0.223482
Phase  -> OD      -0.285779
Supp   -> Gversion -0.304736
Technique -> OD      -0.319741
Supp   -> Anti    -0.336780
Med    -> O       -0.359992
Temp   -> Med     -0.365995
Supp   -> Air     -0.395049
Anti   -> Temp    -0.433807
Air    -> Med     -0.443745
Technique -> Gtype   -0.461980
Anti   -> O       -0.477920
Phase  -> Med     -0.496773
Phase  -> Supp    -0.504111
Supp   -> Gtype   -0.542703
Air    -> Supp    -0.549017
OD     -> Air     -0.590463
Gtype  -> Technique -0.617626
OD     -> O       -0.633869
Gversion -> O       -0.665626
Technique -> pH      -0.667545
Phase  -> O       -0.674680
Air    -> Phase   -0.701860
Air    -> Temp    -0.825208
Gtype  -> Anti    -0.861670
O      -> Med     -0.887587
O      -> OD      -1.001120
Technique -> O       -1.008992
Gtype  -> Med     -1.115268
Supp   -> Med     -1.155087
Gtype  -> O       -1.446717
O      -> Air     -1.553604
Substrain -> O       -1.560176
Med    -> Supp    -1.895924


Top positive:
4.079246 Gtype    b'lemma[:1]:\xce\xb4'
3.875929 Technique b'lemma[:2]:Ch'
3.769086 O        b'lemma[:2]:re'
3.421852 Air      b'word:Aerobic'
3.297057 O        b'word:Cra'
3.280691 Air      b'lemma:anaerobic'
3.279696 O        b'lemma:_'
3.279696 O        b'lemma[:1]:_'
3.279696 O        b'word:_'
3.054016 O        b'-1:word:tag'
2.950170 O        b'-1:lemma:tag'
2.923311 Supp     b'-1:word:Cra'
2.917103 O        b'lemma:-'
2.917103 O        b'word:-'
2.673438 O        b'lemma:2'
2.673438 O        b'word:2'
2.601916 Anti     b'lemma[:2]:an'
2.548804 Air      b'word:Anaerobic'
2.540901 O        b'lemma:with'
2.540901 O        b'word:with'
2.527977 Supp     b'+1:lemma:\xc2\xb5m'
2.527977 Supp     b'+1:word:\xc2\xb5M'
2.513465 Gtype    b'lemma[:2]:pk'
2.467865 Air      b'lemma[:2]:ae'
2.465142 Supp     b'-1:lemma:vol'
2.465142 Supp     b'-1:word:vol'
2.430821 O        b'word:A'
2.414676 O        b'+1:lemma:pq'
2.414676 O        b'+1:word:PQ'
2.381594 Supp     b'lemma:arginine'
2.365113 Strain   b'+1:lemma:substr'
2.365113 Strain   b'+1:word:substr'
2.358430 O        b'lemma:3'
2.358430 O        b'word:3'
2.281060 O        b'+1:postag:RB'
2.274077 Gtype    b'lemma:wt'
2.274077 Gtype    b'lemma[:2]:wt'
2.271330 Gtype    b'lemma[:1]:w'
2.262507 Gtype    b'lemma[:2]:de'
2.230752 O        b'-1:word:Aerobic'
2.223212 Gtype    b'lemma[:2]:ar'
2.204027 Gtype    b'word:WT'
2.203708 Supp     b'lemma:pq'
2.203708 Supp     b'lemma[:2]:pq'
2.203708 Supp     b'word:PQ'
2.195032 Technique b'lemma[:2]:rn'
2.177901 Air      b'lemma[:2]:an'
2.152688 O        b'lemma[:2]:ge'
2.152187 O        b'lemma:1'
2.152187 O        b'word:1'
2.147937 Phase    b'lemma:stationary'
2.147937 Phase    b'word:stationary'
2.139876 Phase    b'lemma:mid-log'
2.139876 Phase    b'word:mid-log'
2.082317 O        b'lemma:Custom'
2.082317 O        b'lemma[:2]:Cu'
2.082317 O        b'word:Custom'
2.081417 Technique b'lemma[:1]:C'
2.059825 O        b'lemma:b'
2.059825 O        b'word:B'
2.051640 Technique b'word:ChIPSeq'
2.044050 Supp     b'lemma:Iron'
2.044050 Supp     b'lemma[:2]:Ir'
2.044050 Supp     b'word:Iron'
2.044050 Supp     b'+1:word:Deficient'
2.034480 O        b'-1:lemma:ChIP-exo'
2.021616 Technique b'lemma[:2]:ch'
2.004928 Substrain b'lemma[:2]:mg'
1.992585 Gtype    b'lemma[:1]:f'
1.988583 Gtype    b'lemma[:2]:cr'
1.983400 O        b'+1:postag:NNP'
1.976657 O        b'lemma[:1]:h'
1.975191 O        b'-1:lemma:lb'
1.975191 O        b'-1:word:LB'
1.973175 Supp     b'lemma[:1]:I'
1.969412 O        b'lemma:.'
1.969412 O        b'postag:.'
1.969412 O        b'postag[:1]:.'
1.969412 O        b'word:.'
1.954569 Phase    b'lemma[:2]:ex'
1.946311 O        b'lemma:delta'
1.946311 O        b'word:delta'
1.942336 Supp     b'postag:VBP'
1.917047 Technique b'word:ChIP-Seq'
1.916217 Supp     b'-1:lemma:Cra'
1.899702 Supp     b'lemma:rifampicin'
1.899702 Supp     b'word:rifampicin'
1.898554 Supp     b'-1:lemma:with'
1.898554 Supp     b'-1:word:with'
1.892222 Air      b'lemma[:1]:a'
1.892185 Supp     b'lemma[:2]:ri'
1.887353 Technique b'lemma:chipseq'
1.852638 O        b'-1:lemma:0.3'
1.852638 O        b'-1:word:0.3'
1.839355 pH       b'lemma[:2]:ph'
1.838181 Gtype    b'hGreek'
1.837034 O        b'-1:lemma:glucose'
1.837034 O        b'-1:word:glucose'
1.821428 Gtype    b'lemma:arca8myc'
1.821428 Gtype    b'word:ArcA8myc'
1.821045 Med      b'lemma:MOPS'
1.821045 Med      b'lemma[:1]:M'
1.821045 Med      b'lemma[:2]:MO'
1.821045 Med      b'word:MOPS'
1.813601 Technique b'-1:lemma:chip-exo'
1.811851 Gversion b'word:ChIP-Seq'
1.810109 O        b'lemma:ompr'
1.810109 O        b'word:OmpR'
1.807989 Supp     b'-1:lemma:+'
1.807989 Supp     b'-1:word:+'
1.805457 OD       b'lemma[:1]:o'
1.789186 Gtype    b'lemma[:1]:t'
1.787157 Supp     b'lemma[:2]:gl'
1.784556 Gtype    b'symb'
1.769736 Gversion b'lemma:chip-seq'
1.769144 O        b'lemma[:2]:om'
1.756478 Temp     b'+1:lemma:in'
1.756478 Temp     b'+1:word:in'
1.750825 O        b'lemma:rpob'
1.750825 O        b'word:RpoB'
1.744454 Gversion b'-1:lemma:nc'
1.744454 Gversion b'-1:word:NC'
1.743983 Technique b'lemma:ChIP-exo'
1.738988 Gtype    b'-1:lemma:\xe2\x88\x86'
1.738988 Gtype    b'-1:word:\xe2\x88\x86'
1.737321 Supp     b'lemma[:2]:30'
1.719994 Gversion b'lemma[:2]:00'
1.691622 Med      b'+1:lemma:0.4'
1.691622 Med      b'+1:word:0.4'
1.690183 Supp     b'lemma:acetate'
1.690183 Supp     b'word:acetate'
1.680098 Gtype    b'lemma[:1]:W'
1.669697 Phase    b'lemma[:1]:e'
1.654569 O        b'-1:lemma:into'
1.654569 O        b'-1:word:into'
1.646155 Agit     b'+1:lemma:rpm'
1.646155 Agit     b'+1:word:rpm'
1.639372 Supp     b'lemma[:2]:ni'
1.637838 Supp     b'-1:postag:CC'
1.633069 Med      b'-1:lemma:ml'
1.633069 Med      b'-1:word:ml'
1.626970 Gtype    b'-1:postag:VBG'
1.625020 O        b'+1:word:ChIP-Seq'
1.592935 Air      b'lemma[:1]:A'
1.581837 Supp     b'lemma[:2]:ac'
1.581166 Gversion b'lemma:asm584v2'
1.581166 Gversion b'word:ASM584v2'
1.576758 Gversion b'lemma[:2]:as'
1.566133 Air      b'lemma:Aerobic'
1.566133 Air      b'lemma[:2]:Ae'
1.556942 Air      b'+1:postag:IN'
1.540738 Air      b'postag:RB'
1.540738 Air      b'postag[:1]:R'
1.540738 Air      b'postag[:2]:RB'
1.537191 O        b'-1:lemma:phase'
1.537191 O        b'-1:word:phase'
1.528090 Air      b'-1:lemma:-'
1.528090 Air      b'-1:word:-'
1.527198 Gtype    b'lemma:type'
1.527198 Gtype    b'lemma[:2]:ty'
1.527198 Gtype    b'word:type'
1.520984 O        b'lemma[:1]:C'
1.511967 Air      b'-1:postag::'
1.501971 O        b'postag::'
1.501971 O        b'postag[:1]::'
1.500818 Gtype    b'lemma[:2]:wi'
1.494237 O        b'+1:word:were'
1.488912 O        b'postag:CC'
1.488912 O        b'postag[:2]:CC'
1.488215 Agit     b'lemma:rpm'
1.488215 Agit     b'word:rpm'
1.486647 Supp     b'+1:lemma:1'
1.486647 Supp     b'+1:word:1'
1.483688 Temp     b'-1:lemma:\xcf\x8332'
1.483688 Temp     b'-1:word:\xcf\x8332'
1.483025 Air      b'word:anaerobic'
1.481168 O        b'lemma:a'
1.480233 Gversion b'lemma:nc'
1.480233 Gversion b'lemma[:2]:nc'
1.480233 Gversion b'word:NC'
1.465788 O        b'-1:lemma:anaerobic'
1.464120 O        b'+1:lemma:od600'
1.464120 O        b'+1:word:OD600'
1.459126 O        b'+1:postag:VBN'
1.449825 Phase    b'lemma:exponential'
1.449825 Phase    b'word:exponential'
1.443892 O        b'-1:lemma:0.3-0.35'
1.443892 O        b'-1:word:0.3-0.35'
1.429105 Technique b'symb'
1.428375 O        b'lemma[:2]:ga'
1.423820 Technique b'word:ChIP-exo'
1.422037 O        b'lemma:chip'
1.420614 O        b'isNumber'
1.417035 pH       b'+1:postag:CD'
1.414508 Phase    b'lemma[:2]:st'
1.410028 O        b'isLower'
1.399604 Med      b'+1:postag:CD'
1.398736 Med      b'+1:lemma:2.0'
1.398736 Med      b'+1:word:2.0'
1.374106 O        b'-1:lemma:wt'


Top negative:
-0.314411 Supp     b'postag[:1]:N'
-0.314411 Supp     b'postag[:2]:NN'
-0.316666 OD       b'+1:lemma:0.4'
-0.316666 OD       b'+1:word:0.4'
-0.319400 O        b'+1:word:for'
-0.319616 Substrain b'isLower'
-0.329221 O        b'+1:lemma:supplement'
-0.329221 O        b'+1:word:supplemented'
-0.334710 Gtype    b'+1:lemma:-rrb-'
-0.334710 Gtype    b'+1:word:-RRB-'
-0.335324 Supp     b'+1:lemma:nacl'
-0.335324 Supp     b'+1:word:NaCl'
-0.338195 Phase    b'lemma[:2]:pa'
-0.343360 Med      b'+1:postag:NNS'
-0.343534 O        b'+1:postag:IN'
-0.344316 Temp     b'postag:NN'
-0.345297 O        b'lemma:wt'
-0.345297 O        b'lemma[:2]:wt'
-0.355887 Air      b'isLower'
-0.356867 O        b'-1:lemma:from'
-0.358831 O        b'lemma:c'
-0.359856 O        b'lemma:37'
-0.359856 O        b'lemma[:2]:37'
-0.359856 O        b'word:37'
-0.360624 O        b'-1:lemma:final'
-0.360624 O        b'-1:word:final'
-0.361530 Med      b'-1:postag:NN'
-0.362367 Technique b'-1:postag::'
-0.362612 O        b'lemma:of'
-0.362612 O        b'lemma[:2]:of'
-0.362612 O        b'word:of'
-0.368278 O        b'-1:word:from'
-0.374267 O        b'-1:lemma:30'
-0.374267 O        b'-1:word:30'
-0.376045 O        b'lemma:glucose'
-0.376045 O        b'word:glucose'
-0.379443 Gtype    b'lemma[:2]:rp'
-0.382310 Gtype    b'lemma[:1]:s'
-0.383855 Supp     b'-1:lemma:-lrb-'
-0.383855 Supp     b'-1:word:-LRB-'
-0.385029 O        b'-1:lemma:delta'
-0.385029 O        b'-1:word:delta'
-0.390702 O        b'-1:lemma:dissolve'
-0.390702 O        b'+1:lemma:methanol'
-0.390702 O        b'-1:word:dissolved'
-0.390702 O        b'+1:word:methanol'
-0.395103 O        b'-1:lemma:nsrr'
-0.395103 O        b'-1:word:NsrR'
-0.399202 Supp     b'lemma[:1]:a'
-0.403898 O        b'-1:lemma:1'
-0.403898 O        b'-1:word:1'
-0.404014 Temp     b'hGreek'
-0.406161 O        b'-1:lemma:\xe2\x88\x86'
-0.406161 O        b'-1:word:\xe2\x88\x86'
-0.417535 O        b'-1:postag:IN'
-0.418404 Supp     b'-1:postag:-LRB-'
-0.428053 O        b'-1:lemma:ph'
-0.428053 O        b'-1:word:pH'
-0.432185 Supp     b'postag:JJ'
-0.432252 O        b'lemma[:1]:L'
-0.435862 Air      b'-1:lemma:or'
-0.435862 Air      b'-1:word:or'
-0.437167 Supp     b'postag[:1]:J'
-0.437167 Supp     b'postag[:2]:JJ'
-0.439673 Vess     b'hUpper'
-0.439673 Vess     b'hLower'
-0.443285 O        b'lemma[:2]:gl'
-0.444141 Temp     b'isLower'
-0.449813 Supp     b'lemma[:2]:an'
-0.455745 O        b'-1:lemma:37'
-0.455745 O        b'-1:word:37'
-0.465238 O        b'lemma[:2]:ni'
-0.469627 Supp     b'lemma[:1]:s'
-0.472157 Air      b'+1:postag:JJ'
-0.477980 O        b'lemma:2h'
-0.477980 O        b'-1:lemma:additional'
-0.477980 O        b'lemma[:2]:2h'
-0.477980 O        b'word:2h'
-0.477980 O        b'-1:word:additional'
-0.493105 Agit     b'symb'
-0.493489 O        b'lemma:methanol'
-0.493489 O        b'word:methanol'
-0.495166 O        b'lemma:mid-log'
-0.495166 O        b'word:mid-log'
-0.497445 Air      b'-1:postag:JJ'
-0.499724 O        b'+1:lemma:g/l'
-0.499724 O        b'+1:word:g/L'
-0.501348 O        b'+1:lemma:mm'
-0.501348 O        b'+1:word:mM'
-0.507557 O        b'lemma[:2]:me'
-0.508454 Gtype    b'postag[:1]:V'
-0.508454 Gtype    b'postag[:2]:VB'
-0.508460 Gtype    b'postag::'
-0.508460 Gtype    b'postag[:1]::'
-0.529784 O        b'+1:lemma:at'
-0.529784 O        b'+1:word:at'
-0.537465 O        b'lemma[:1]:0'
-0.542594 Supp     b'-1:lemma:.'
-0.542594 Supp     b'-1:postag:.'
-0.542594 Supp     b'-1:word:.'
-0.546062 O        b'lemma[:1]:4'
-0.548259 O        b'-1:lemma:rpob'
-0.548259 O        b'-1:word:RpoB'
-0.552281 O        b'-1:lemma:IP'
-0.552281 O        b'-1:word:IP'
-0.553960 Phase    b'postag:JJ'
-0.562367 O        b'lemma:0.3'
-0.562367 O        b'word:0.3'
-0.573524 Med      b'-1:postag:CD'
-0.574613 Technique b'postag:NN'
-0.578197 O        b'-1:lemma:chip-exo'
-0.579399 O        b'+1:lemma:1m'
-0.579399 O        b'+1:word:1M'
-0.584655 O        b'word:ChIP-exo'
-0.585801 O        b'lemma:soxs-8myc'
-0.585801 O        b'word:soxS-8myc'
-0.599558 O        b'lemma[:2]:ar'
-0.600604 O        b'word:cells'
-0.606899 O        b'+1:lemma:until'
-0.606899 O        b'+1:word:until'
-0.607019 Air      b'symb'
-0.640639 pH       b'isNumber'
-0.656724 O        b'+1:word:ChIP-exo'
-0.664247 O        b'+1:lemma:2.0'
-0.664247 O        b'+1:word:2.0'
-0.664520 Med      b'+1:postag:IN'
-0.664576 O        b'-1:lemma:co2'
-0.664576 O        b'-1:word:CO2'
-0.665370 O        b'+1:lemma:rep2'
-0.665370 O        b'+1:word:rep2'
-0.671212 O        b'lemma[:2]:mg'
-0.724471 Agit     b'hUpper'
-0.724471 Agit     b'hLower'
-0.739501 O        b'lemma[:1]:I'
-0.755281 O        b'lemma[:2]:30'
-0.762653 pH       b'isLower'
-0.780673 Air      b'postag:NN'
-0.793295 Supp     b'symb'
-0.826875 O        b'-1:postag::'
-0.853583 O        b'lemma[:2]:ri'
-0.880894 O        b'-1:lemma:until'
-0.880894 O        b'-1:word:until'
-0.884934 Supp     b'+1:postag:VBN'
-0.893108 O        b'lemma[:1]:k'
-0.902922 O        b'lemma[:2]:ae'
-0.926126 O        b'lemma:rifampicin'
-0.926126 O        b'word:rifampicin'
-0.929148 Med      b'-1:postag:IN'
-0.936796 Anti     b'postag:NNP'
-0.952559 Supp     b'-1:postag:NNP'
-0.962974 Med      b'symb'
-0.981592 Technique b'isNumber'
-1.019994 O        b'-1:lemma:2'
-1.019994 O        b'-1:word:2'
-1.023240 O        b'+1:lemma:1'
-1.023240 O        b'+1:word:1'
-1.023642 O        b'-1:lemma:ml'
-1.023642 O        b'-1:word:ml'
-1.035572 Phase    b'hUpper'
-1.035572 Phase    b'hLower'
-1.036376 O        b'lemma[:1]:n'
-1.044060 Gtype    b'lemma[:1]:c'
-1.051632 Phase    b'postag[:1]:J'
-1.051632 Phase    b'postag[:2]:JJ'
-1.074102 Gtype    b'lemma[:1]:a'
-1.077239 O        b'+1:lemma:+'
-1.077239 O        b'+1:word:+'
-1.084820 O        b'+1:lemma:in'
-1.084820 O        b'+1:word:in'
-1.107631 Gtype    b'isNumber'
-1.117617 Supp     b'+1:postag:-LRB-'
-1.129026 Technique b'isLower'
-1.149735 Supp     b'hGreek'
-1.156144 Supp     b'+1:lemma:-lrb-'
-1.156144 Supp     b'+1:word:-LRB-'
-1.229045 Gtype    b'lemma[:1]:r'
-1.231933 O        b'+1:postag:VBG'
-1.262559 Gversion b'isLower'
-1.277633 O        b'-1:lemma:fresh'
-1.277633 O        b'-1:word:fresh'
-1.381763 OD       b'+1:postag:NN'
-1.472372 O        b'+1:lemma:2'
-1.472372 O        b'+1:word:2'
-1.571807 Gtype    b'isUpper'
-1.677845 Supp     b'lemma[:1]:c'
-1.687951 O        b'-1:lemma:vol'
-1.687951 O        b'-1:word:vol'
-1.695736 Supp     b'+1:lemma:,'
-1.695736 Supp     b'+1:postag:,'
-1.695736 Supp     b'+1:word:,'
-1.723752 O        b'-1:lemma:sample'
-1.785262 Phase    b'-1:postag:JJ'
-1.895238 O        b'postag:VBP'
-1.908071 O        b'-1:postag:VBG'
-2.171310 O        b'-1:lemma:_'
-2.171310 O        b'-1:word:_'
-2.491839 O        b'lemma[:2]:fl'
-2.929187 O        b'-1:lemma::'
-2.929187 O        b'-1:word::'
-2.957042 Temp     b'+1:postag:IN'