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

best params:{'c1': 0.08021472274752509, 'c2': 0.027005041681951836}
best CV score:0.8779980427772918
model size: 0.14M

Flat F1: 0.7956040707847014
             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      0.556     0.362     0.439        69
       Anti      1.000     1.000     1.000        11
     Strain      0.000     0.000     0.000         1
      Gtype      0.882     0.882     0.882        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.713     0.799     0.754       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.814     0.787     0.796       451


Top likely transitions:
Temp   -> Temp    5.388784
OD     -> OD      5.140817
Agit   -> Agit    5.132255
Med    -> Med     4.721438
Supp   -> Supp    4.664079
Anti   -> Anti    4.454963
Phase  -> Phase   4.208793
Gtype  -> Gtype   4.106042
Gversion -> Gversion 3.988002
O      -> O       3.877714
Air    -> Air     3.520636
Technique -> Technique 3.339322
pH     -> pH      2.756365
Substrain -> Gtype   1.679774
O      -> Technique 0.976956
Gtype  -> Supp    0.888340
O      -> Gtype   0.667038
Gtype  -> Air     0.494333
O      -> Supp    0.432374
Gtype  -> pH      0.400152
Air    -> O       0.329339
Technique -> Air     0.314540
Temp   -> O       0.185583
Med    -> O       0.110105
Supp   -> O       0.051605
O      -> Temp    0.006740
O      -> Phase   -0.001639
pH     -> Supp    -0.012353
Med    -> Air     -0.021759
Air    -> Agit    -0.033843
Phase  -> Air     -0.037477
Anti   -> Supp    -0.046737
O      -> Agit    -0.058265
Vess   -> O       -0.085300
Gversion -> O       -0.093271
Supp   -> Gtype   -0.153393
Supp   -> Air     -0.154232
Gversion -> Supp    -0.158359
OD     -> Supp    -0.173307
Agit   -> Air     -0.179206
Phase  -> O       -0.181634
Anti   -> O       -0.199623
Phase  -> OD      -0.205312
O      -> OD      -0.243252
Gtype  -> Anti    -0.275895
Agit   -> O       -0.297460
OD     -> Air     -0.307988
Technique -> pH      -0.314407
OD     -> O       -0.327494
Technique -> O       -0.386077


Top unlikely transitions:
pH     -> pH      2.756365
Substrain -> Gtype   1.679774
O      -> Technique 0.976956
Gtype  -> Supp    0.888340
O      -> Gtype   0.667038
Gtype  -> Air     0.494333
O      -> Supp    0.432374
Gtype  -> pH      0.400152
Air    -> O       0.329339
Technique -> Air     0.314540
Temp   -> O       0.185583
Med    -> O       0.110105
Supp   -> O       0.051605
O      -> Temp    0.006740
O      -> Phase   -0.001639
pH     -> Supp    -0.012353
Med    -> Air     -0.021759
Air    -> Agit    -0.033843
Phase  -> Air     -0.037477
Anti   -> Supp    -0.046737
O      -> Agit    -0.058265
Vess   -> O       -0.085300
Gversion -> O       -0.093271
Supp   -> Gtype   -0.153393
Supp   -> Air     -0.154232
Gversion -> Supp    -0.158359
OD     -> Supp    -0.173307
Agit   -> Air     -0.179206
Phase  -> O       -0.181634
Anti   -> O       -0.199623
Phase  -> OD      -0.205312
O      -> OD      -0.243252
Gtype  -> Anti    -0.275895
Agit   -> O       -0.297460
OD     -> Air     -0.307988
Technique -> pH      -0.314407
OD     -> O       -0.327494
Technique -> O       -0.386077
O      -> Med     -0.415206
Phase  -> Supp    -0.417896
Gtype  -> Technique -0.431421
Air    -> Supp    -0.649044
Supp   -> Med     -0.707950
Gtype  -> Med     -0.744940
Air    -> Med     -0.785274
Gtype  -> O       -0.922070
O      -> Air     -0.953447
Technique -> Gtype   -1.117886
Substrain -> O       -1.261444
Med    -> Supp    -1.996253


Top positive:
5.209266 Anti     b'-2:lemma:antibody'
4.636548 Air      b'word:Aerobic'
4.563533 O        b'-2:lemma:_'
3.873699 Air      b'lemma:anaerobic'
3.819274 Technique b'word:ChIP-Seq'
3.473174 Air      b'postag:RB'
3.322114 Gtype    b'-2:lemma:genotype/variation'
3.225119 O        b'lemma:_'
3.225119 O        b'word:_'
3.207626 O        b'word:Cra'
3.196439 O        b'lemma:2'
3.196439 O        b'word:2'
3.188154 O        b'postag:IN'
3.118289 Phase    b'-2:lemma:phase'
3.010588 O        b'lemma:1'
3.010588 O        b'word:1'
2.977143 O        b'-1:lemma:ChIP-exo'
2.908964 Technique b'word:ChIP-exo'
2.879517 Technique b'lemma:rna-seq'
2.849540 Supp     b'lemma:pq'
2.849540 Supp     b'word:PQ'
2.843713 Gtype    b'lemma:wild-type'
2.797382 O        b'-2:lemma:flagtag'
2.727206 Gtype    b'-2:lemma:genotype'
2.725314 Supp     b'lemma:nh4cl'
2.719430 Technique b'word:ChIPSeq'
2.689034 O        b'postag::'
2.685688 Supp     b'-1:word:Cra'
2.678793 Air      b'word:Anaerobic'
2.665007 Gtype    b'word:WT'
2.645459 Gtype    b'lemma:wt'
2.625521 Technique b'lemma:ChIP-exo'
2.608931 O        b'lemma:.'
2.608931 O        b'postag:.'
2.608931 O        b'word:.'
2.573935 Gtype    b'lemma:type'
2.573935 Gtype    b'word:type'
2.549931 O        b'-2:lemma:medium'
2.537319 O        b'lemma:3'
2.537319 O        b'word:3'
2.427062 O        b'+1:postag:RB'
2.424260 O        b'lemma:-'
2.424260 O        b'word:-'
2.419048 Gtype    b'-2:lemma:affyexp'
2.394367 Phase    b'lemma:mid-log'
2.394367 Phase    b'word:mid-log'
2.378379 O        b'lemma:rpob'
2.378379 O        b'word:RpoB'
2.361578 Supp     b'+2:lemma:iptg'
2.347760 Gtype    b'lemma:\xce\xb4cra'
2.343560 Gtype    b'word:\xce\x94cra'
2.293225 Gtype    b'-2:postag:DT'
2.263496 O        b'postag:VBN'
2.203079 Supp     b'lemma:Iron'
2.203079 Supp     b'word:Iron'
2.203079 Supp     b'+1:word:Deficient'
2.203079 Supp     b'-2:lemma:Anaerobic'
2.187753 O        b'+2:lemma:\xc2\xb0c'
2.174225 Technique b'lemma:chipseq'
2.117805 Med      b'lemma:MOPS'
2.117805 Med      b'word:MOPS'
2.105813 O        b'lemma:b'
2.105813 O        b'word:B'
2.071927 Supp     b'lemma:acetate'
2.071927 Supp     b'word:acetate'
2.071919 Supp     b'lemma:no3'
2.071919 Supp     b'word:NO3'
2.055002 Supp     b'lemma:arginine'
2.035285 O        b'word:A'
2.016143 Gtype    b'+1:lemma:type'
2.016143 Gtype    b'+1:word:type'
2.009171 O        b'+2:postag:JJ'
1.999599 Supp     b'lemma:nacl'
1.999599 Supp     b'word:NaCl'
1.999489 Anti     b'+2:lemma:antibody'
1.985618 Gtype    b'lemma:\xe2\x88\x86'
1.985618 Gtype    b'word:\xe2\x88\x86'
1.978131 Technique b'+2:lemma:ph5'
1.976542 O        b'-1:word:Aerobic'
1.941068 pH       b'+1:postag:CD'
1.938974 O        b'lemma:a'
1.902900 Supp     b'-1:lemma:with'
1.902900 Supp     b'-1:word:with'
1.901213 Gtype    b'-1:lemma:\xe2\x88\x86'
1.901213 Gtype    b'-1:word:\xe2\x88\x86'
1.887695 Med      b'+2:postag:CC'
1.876457 O        b'-1:lemma:tag'
1.873546 Gtype    b'-2:lemma:delta'
1.857185 Gtype    b'lemma:flag-tag'
1.857185 Gtype    b'-1:lemma:c-terminal'
1.857185 Gtype    b'word:Flag-tag'
1.857185 Gtype    b'-1:word:C-terminal'
1.856146 Air      b'lemma:Aerobic'
1.838321 Substrain b'lemma:mg1655'
1.838321 Substrain b'word:MG1655'
1.823456 Technique b'lemma:rnaseq'
1.823456 Technique b'word:RNASeq'
1.808424 O        b'postag:CC'
1.786772 Supp     b'lemma:glucose'
1.786772 Supp     b'word:glucose'
1.780540 O        b'-2:lemma:myc'
1.770799 Gversion b'lemma:chip-seq'
1.753973 O        b'lemma:ompr'
1.753973 O        b'word:OmpR'
1.753471 Supp     b'+1:lemma:\xc2\xb5m'
1.753471 Supp     b'+1:word:\xc2\xb5M'
1.740692 Air      b'word:anaerobic'
1.736806 Gtype    b'+2:lemma:glucose'
1.735768 Gversion b'-2:lemma:nc'
1.720567 Substrain b'-2:lemma:substr'
1.719577 Supp     b'-1:postag:CC'
1.715683 Gtype    b'lemma:\xce\xb4soxr'
1.715683 Gtype    b'word:\xce\x94soxR'
1.704129 Technique b'word:RNA-Seq'
1.703347 Gversion b'word:ChIP-Seq'
1.700970 Phase    b'lemma:exponential'
1.700970 Phase    b'word:exponential'
1.700970 Phase    b'lemma:stationary'
1.700970 Phase    b'word:stationary'
1.697610 Supp     b'lemma:nitrate'
1.697610 Supp     b'word:nitrate'
1.694771 Gtype    b'lemma:\xce\xb4fur'
1.694771 Gtype    b'word:\xce\x94fur'
1.679649 Supp     b'-2:lemma:media'
1.678872 O        b'postag:VBG'
1.675866 O        b'lemma:chip'
1.670928 O        b'+1:postag:NNP'
1.665585 O        b'lemma:with'
1.665585 O        b'word:with'
1.664286 Technique b'-1:lemma:chip-exo'
1.660487 O        b'-1:lemma:0.3'
1.660487 O        b'-1:word:0.3'
1.652275 Supp     b'-1:lemma:Cra'
1.650781 Supp     b'lemma:rifampicin'
1.650781 Supp     b'word:rifampicin'
1.616567 O        b'isLower'
1.615630 O        b'-1:lemma:lb'
1.615630 O        b'-1:word:LB'
1.611807 Med      b'isUpper'
1.602289 O        b'lemma:harbor'
1.602289 O        b'word:harboring'
1.600482 O        b'+1:word:ChIP-Seq'
1.598776 Strain   b'+1:lemma:substr'
1.598776 Strain   b'+1:word:substr'
1.598776 Strain   b'-2:lemma:str'
1.595708 O        b'+2:lemma:polyclonal'
1.581382 O        b'+2:lemma:70'
1.571652 O        b'-1:lemma:anaerobic'
1.571048 O        b'+2:lemma:cra'
1.564139 O        b'+2:lemma:_'
1.554416 Med      b'+2:lemma:b2'
1.552289 O        b'-1:word:tag'
1.551146 Gtype    b'+1:lemma:with'
1.551146 Gtype    b'+1:word:with'
1.544208 O        b'+2:lemma:fructose'
1.537359 O        b'+1:lemma:arca-8myc'
1.537359 O        b'+1:word:ArcA-8myc'
1.532438 Supp     b'-2:lemma:agent'
1.511808 O        b'lemma:culture'
1.508582 Supp     b'lemma:Leu'
1.508582 Supp     b'word:Leu'
1.508582 Supp     b'-2:lemma:Lrp'
1.507149 O        b'-1:lemma:glucose'
1.507149 O        b'-1:word:glucose'
1.489396 O        b'-1:lemma:media'
1.489396 O        b'-1:word:media'
1.479777 Air      b'+1:postag:IN'
1.474767 Supp     b'-2:lemma:induce'
1.473528 Strain   b'lemma:k-12'
1.473528 Strain   b'word:K-12'
1.443528 O        b'lemma:Cra'
1.442381 Gtype    b'-1:postag:VBG'
1.440793 O        b'-2:lemma:~'
1.438342 Agit     b'lemma:rpm'
1.438342 Agit     b'word:rpm'
1.431163 Temp     b'isNumber'
1.427166 Temp     b'+2:postag:DT'
1.399898 OD       b'-1:postag:IN'
1.387409 Gversion b'+2:lemma:000913'
1.386073 Med      b'lemma:lb'
1.386073 Med      b'word:LB'
1.384321 Gversion b'lemma:nc'
1.384321 Gversion b'word:NC'
1.373722 Air      b'lemma:aerobic'
1.373289 O        b'+1:lemma:pq'
1.373289 O        b'+1:word:PQ'
1.366737 O        b'lemma:Custom'
1.366737 O        b'word:Custom'
1.358073 Supp     b'-2:lemma:for'
1.355336 Supp     b'-1:lemma:+'
1.355336 Supp     b'-1:word:+'
1.342861 Gtype    b'postag:JJ'
1.340505 Temp     b'-2:lemma:\xcf\x8332'
1.336886 Phase    b'+2:lemma:o.d.'
1.334497 Med      b'lemma:media'
1.334497 Med      b'word:media'
1.330110 Gtype    b'lemma:dfnr'
1.330110 Gtype    b'word:dFNR'
1.327344 Gtype    b'lemma:pk4854'
1.327344 Gtype    b'word:PK4854'


Top negative:
-0.287905 O        b'-1:lemma:37'
-0.287905 O        b'-1:word:37'
-0.288095 O        b'+1:lemma:supplement'
-0.288095 O        b'+1:word:supplemented'
-0.289812 Strain   b'isLower'
-0.289812 O        b'-2:lemma:supplement'
-0.290075 O        b'+2:lemma:fnr'
-0.290683 Supp     b'-1:postag:-LRB-'
-0.294223 Phase    b'+2:postag:NN'
-0.297159 O        b'+2:lemma:.'
-0.297159 O        b'+2:postag:.'
-0.303489 O        b'-2:lemma:nh4cl'
-0.305843 O        b'-2:lemma:genome'
-0.308014 O        b'-1:lemma:dissolve'
-0.308014 O        b'+1:lemma:methanol'
-0.308014 O        b'-1:word:dissolved'
-0.308014 O        b'+1:word:methanol'
-0.308864 O        b'-1:lemma:co2'
-0.308864 O        b'-1:word:CO2'
-0.310620 O        b'+2:lemma:reference'
-0.315887 Supp     b'+2:postag::'
-0.317964 O        b'lemma:aerobic'
-0.318575 Gtype    b'-1:postag:CD'
-0.321321 O        b'lemma:fructose'
-0.321321 O        b'word:fructose'
-0.334085 O        b'+2:lemma:10'
-0.336754 Phase    b'-1:postag:NN'
-0.337443 O        b'-2:lemma:rpob'
-0.337566 O        b'word:ChIP-exo'
-0.344905 O        b'-2:postag:SYM'
-0.349662 O        b'lemma:minimal'
-0.349662 O        b'word:minimal'
-0.351886 O        b'-1:lemma:fresh'
-0.351886 O        b'-1:word:fresh'
-0.355535 O        b'+2:lemma:-rrb-'
-0.355990 O        b'lemma:methanol'
-0.355990 O        b'word:methanol'
-0.355990 O        b'-2:lemma:dissolve'
-0.358472 Air      b'+1:postag:JJ'
-0.363373 O        b'+2:lemma:add'
-0.364945 O        b'-1:lemma:chip-exo'
-0.366081 O        b'-2:lemma:glucose'
-0.368793 O        b'lemma:37'
-0.368793 O        b'word:37'
-0.373039 O        b'-1:lemma:2'
-0.373039 O        b'-1:word:2'
-0.381340 O        b'+1:lemma:1m'
-0.381340 O        b'+1:word:1M'
-0.381340 O        b'-2:lemma:vol'
-0.382066 OD       b'+2:postag:NN'
-0.389528 O        b'+2:lemma:mid-log'
-0.392861 O        b'+2:lemma:at'
-0.394964 O        b'-1:lemma:ml'
-0.394964 O        b'-1:word:ml'
-0.396605 Phase    b'-2:postag:NN'
-0.399009 O        b'-2:lemma:minimal'
-0.399247 O        b'-1:lemma:rpob'
-0.399247 O        b'-1:word:RpoB'
-0.401395 O        b'lemma:aerobically'
-0.401395 O        b'word:aerobically'
-0.404932 Temp     b'-2:postag:NN'
-0.407934 Anti     b'+1:lemma:anti-fur'
-0.407934 Anti     b'+1:word:anti-Fur'
-0.411618 O        b'-1:lemma:\xe2\x88\x86'
-0.411618 O        b'-1:word:\xe2\x88\x86'
-0.411709 Med      b'-1:postag:NN'
-0.413181 O        b'-2:lemma:dpd'
-0.420107 O        b'-1:postag::'
-0.421275 O        b'-2:lemma:pahse'
-0.421606 Phase    b'isUpper'
-0.422247 O        b'lemma:anaerobic'
-0.423121 O        b'-1:lemma:mm'
-0.423121 O        b'-1:word:mM'
-0.431573 O        b'+1:word:ChIP-exo'
-0.437729 O        b'+1:lemma:+'
-0.437729 O        b'+1:word:+'
-0.441474 O        b'+2:postag:-RRB-'
-0.447120 Supp     b'+1:lemma:,'
-0.447120 Supp     b'+1:postag:,'
-0.447120 Supp     b'+1:word:,'
-0.450941 O        b'lemma:nitrogen'
-0.450941 O        b'word:nitrogen'
-0.457611 Supp     b'+1:lemma:-lrb-'
-0.457611 Supp     b'+1:word:-LRB-'
-0.461438 pH       b'isUpper'
-0.465061 O        b'lemma:anaerobically'
-0.465061 O        b'word:anaerobically'
-0.469056 Supp     b'postag:CC'
-0.476893 O        b'-2:lemma:anaerobically'
-0.484124 Supp     b'+1:postag:-LRB-'
-0.488236 O        b'lemma:glucose'
-0.488236 O        b'word:glucose'
-0.489327 O        b'-2:lemma:at'
-0.491584 O        b'lemma:2h'
-0.491584 O        b'-1:lemma:additional'
-0.491584 O        b'word:2h'
-0.491584 O        b'-1:word:additional'
-0.506103 O        b'lemma:\xce\xb4fur'
-0.506103 O        b'word:\xce\x94fur'
-0.506640 O        b'-2:lemma:IP'
-0.514942 O        b'-1:lemma:grow'
-0.520575 O        b'-1:lemma:30'
-0.520575 O        b'-1:word:30'
-0.523583 O        b'-2:postag:DT'
-0.523650 O        b'lemma:of'
-0.523650 O        b'word:of'
-0.531778 Phase    b'+1:postag:NN'
-0.532589 O        b'-2:lemma:media'
-0.563587 Gtype    b'postag:VBG'
-0.564326 Supp     b'-2:lemma:treat'
-0.565411 Supp     b'-1:postag:NNP'
-0.584731 O        b'-1:lemma:IP'
-0.584731 O        b'-1:word:IP'
-0.587211 Supp     b'-2:postag:JJ'
-0.593339 Med      b'+2:postag:VBN'
-0.596474 O        b'-2:lemma:fresh'
-0.602774 O        b'+1:lemma:in'
-0.602774 O        b'+1:word:in'
-0.611915 O        b'+1:lemma:until'
-0.611915 O        b'+1:word:until'
-0.628338 O        b'-2:postag:RB'
-0.630514 O        b'lemma:media'
-0.630514 O        b'word:media'
-0.631529 O        b'-1:lemma:nsrr'
-0.631529 O        b'-1:word:NsrR'
-0.639248 O        b'+1:lemma:at'
-0.639248 O        b'+1:word:at'
-0.642022 O        b'+1:lemma:2.0'
-0.642022 O        b'+1:word:2.0'
-0.642115 Supp     b'+2:lemma:glucose'
-0.647250 O        b'+2:lemma:b'
-0.667222 Supp     b'-2:lemma:grow'
-0.673515 O        b'lemma:0.3'
-0.673515 O        b'word:0.3'
-0.676110 O        b'lemma:wt'
-0.680222 O        b'-2:lemma:aerobically'
-0.681123 O        b'-1:lemma:vol'
-0.681123 O        b'-1:word:vol'
-0.681123 O        b'-2:lemma:1/100'
-0.681123 O        b'+2:lemma:1m'
-0.682710 O        b'+2:lemma:250'
-0.694576 Med      b'-2:postag:VBN'
-0.697856 O        b'-2:lemma:phase'
-0.699444 pH       b'isLower'
-0.700808 O        b'+1:lemma:g/l'
-0.700808 O        b'+1:word:g/L'
-0.717388 Agit     b'isUpper'
-0.722541 O        b'lemma:mid-log'
-0.722541 O        b'word:mid-log'
-0.737608 O        b'-1:lemma:1'
-0.737608 O        b'-1:word:1'
-0.740499 O        b'lemma:nitrate'
-0.740499 O        b'word:nitrate'
-0.752485 O        b'lemma:30'
-0.752485 O        b'word:30'
-0.755988 O        b'+1:postag:IN'
-0.779938 O        b'lemma:rifampicin'
-0.779938 O        b'word:rifampicin'
-0.783115 Anti     b'isUpper'
-0.806261 O        b'-2:lemma::'
-0.824477 Technique b'isNumber'
-0.832052 Gtype    b'-2:lemma:\xe2\x88\x86'
-0.863480 O        b'+2:lemma:then'
-0.879672 Gversion b'isLower'
-0.884306 O        b'+2:lemma:rifampicin'
-0.892663 Air      b'postag:NN'
-0.922574 Gtype    b'isLower'
-0.971352 Temp     b'postag:NN'
-0.971492 Supp     b'+2:postag:CD'
-0.981487 O        b'postag:RB'
-0.986273 Gtype    b'isNumber'
-0.986626 Gtype    b'+2:lemma:cra'
-0.999664 O        b'-2:lemma:rifampicin'
-1.005327 O        b'+2:lemma:+'
-1.017639 O        b'-1:lemma:sample'
-1.052917 O        b'+1:postag:VBG'
-1.113487 O        b'postag:VBP'
-1.137187 Technique b'isLower'
-1.137961 Anti     b'+2:lemma:polyclonal'
-1.218218 OD       b'+1:postag:NN'
-1.218506 O        b'+1:lemma:1'
-1.218506 O        b'+1:word:1'
-1.244460 O        b'-2:lemma:until'
-1.246287 O        b'-2:lemma:0.3'
-1.318837 Med      b'-2:lemma:grow'
-1.418176 O        b'+1:lemma:2'
-1.418176 O        b'+1:word:2'
-1.420021 Supp     b'+2:lemma:1'
-1.433666 Supp     b'+2:lemma:fructose'
-1.518266 Supp     b'+2:lemma:2'
-1.707448 OD       b'+2:lemma:aerobically'
-1.740887 Supp     b'postag:JJ'
-1.755089 Anti     b'postag:NNP'
-2.017589 O        b'-1:postag:VBG'
-2.050337 O        b'-1:lemma::'
-2.050337 O        b'-1:word::'
-2.210536 Phase    b'-1:postag:JJ'
-2.269742 O        b'-1:lemma:_'
-2.269742 O        b'-1:word:_'
-2.429764 Phase    b'postag:JJ'