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

best params:{'c1': 0.15406215902868822, 'c2': 0.04226744278958694}
best CV score:0.8596370019235678
model size: 0.12M

Flat F1: 0.7628595463981331
             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     0.925     0.961        53
       Temp      1.000     0.690     0.816        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      0.579     1.000     0.733        11
     Strain      0.000     0.000     0.000         1
      Gtype      0.877     0.753     0.810        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.675     0.806     0.735       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.793     0.752     0.763       451


Top likely transitions:
Temp   -> Temp    5.110459
Agit   -> Agit    5.017935
Anti   -> Anti    4.938650
OD     -> OD      4.825556
Supp   -> Supp    4.712858
Gtype  -> Gtype   4.678424
Med    -> Med     4.638385
Gversion -> Gversion 4.224640
Air    -> Air     4.223412
O      -> O       3.873161
Phase  -> Phase   3.806018
Technique -> Technique 3.527725
pH     -> pH      2.599944
Gtype  -> Supp    1.497521
Substrain -> Gtype   1.352716
O      -> Gtype   1.238587
O      -> Supp    1.162728
Air    -> O       1.113709
O      -> Technique 1.086494
Gtype  -> Air     0.890610
Technique -> Air     0.790851
Gtype  -> pH      0.476347
Supp   -> O       0.342000
O      -> Temp    0.264657
Med    -> O       0.256803
Temp   -> O       0.225939
O      -> Anti    0.129094
O      -> OD      0.005737
O      -> Phase   0.003554
Supp   -> Air     -0.000004
Anti   -> O       -0.000506
O      -> Agit    -0.012375
Technique -> OD      -0.029963
Phase  -> O       -0.035227
Air    -> Temp    -0.053461
Supp   -> Gtype   -0.074666
O      -> Med     -0.080001
Air    -> Phase   -0.085473
Phase  -> Supp    -0.126042
Agit   -> O       -0.135568
Technique -> O       -0.155818
Gtype  -> Med     -0.295463
Phase  -> OD      -0.308398
Gtype  -> Anti    -0.318100
Technique -> pH      -0.318842
OD     -> Air     -0.391856
Gtype  -> O       -0.411784
O      -> Air     -0.438824
Supp   -> Med     -0.713976
Technique -> Gtype   -0.921584


Top unlikely transitions:
Anti   -> Anti    4.938650
OD     -> OD      4.825556
Supp   -> Supp    4.712858
Gtype  -> Gtype   4.678424
Med    -> Med     4.638385
Gversion -> Gversion 4.224640
Air    -> Air     4.223412
O      -> O       3.873161
Phase  -> Phase   3.806018
Technique -> Technique 3.527725
pH     -> pH      2.599944
Gtype  -> Supp    1.497521
Substrain -> Gtype   1.352716
O      -> Gtype   1.238587
O      -> Supp    1.162728
Air    -> O       1.113709
O      -> Technique 1.086494
Gtype  -> Air     0.890610
Technique -> Air     0.790851
Gtype  -> pH      0.476347
Supp   -> O       0.342000
O      -> Temp    0.264657
Med    -> O       0.256803
Temp   -> O       0.225939
O      -> Anti    0.129094
O      -> OD      0.005737
O      -> Phase   0.003554
Supp   -> Air     -0.000004
Anti   -> O       -0.000506
O      -> Agit    -0.012375
Technique -> OD      -0.029963
Phase  -> O       -0.035227
Air    -> Temp    -0.053461
Supp   -> Gtype   -0.074666
O      -> Med     -0.080001
Air    -> Phase   -0.085473
Phase  -> Supp    -0.126042
Agit   -> O       -0.135568
Technique -> O       -0.155818
Gtype  -> Med     -0.295463
Phase  -> OD      -0.308398
Gtype  -> Anti    -0.318100
Technique -> pH      -0.318842
OD     -> Air     -0.391856
Gtype  -> O       -0.411784
O      -> Air     -0.438824
Supp   -> Med     -0.713976
Technique -> Gtype   -0.921584
Substrain -> O       -1.113692
Med    -> Supp    -1.471991


Top positive:
4.749372 Air      b'word:Aerobic'
4.524583 O        b'lemma:_'
4.524583 O        b'word:_'
4.098279 Air      b'lemma:anaerobic'
3.877804 O        b'postag:IN'
3.595104 O        b'word:Cra'
3.530479 O        b'postag::'
3.410481 Technique b'word:ChIP-Seq'
3.231475 Air      b'postag:RB'
3.216656 Gtype    b'lemma:wt'
3.136173 Gtype    b'lemma:wild-type'
3.108997 Technique b'word:ChIP-exo'
3.044194 O        b'-1:lemma:ChIP-exo'
2.991141 Air      b'word:Anaerobic'
2.905621 Supp     b'lemma:nh4cl'
2.900437 Technique b'word:ChIPSeq'
2.896382 Technique b'lemma:ChIP-exo'
2.892866 Gtype    b'word:WT'
2.840495 Supp     b'lemma:Iron'
2.840495 Supp     b'word:Iron'
2.840495 Supp     b'+1:word:Deficient'
2.808087 O        b'lemma:2'
2.808087 O        b'word:2'
2.787965 Phase    b'lemma:mid-log'
2.787965 Phase    b'word:mid-log'
2.749236 Supp     b'lemma:pq'
2.749236 Supp     b'word:PQ'
2.657709 Technique b'lemma:rna-seq'
2.573610 O        b'lemma:rpob'
2.573610 O        b'word:RpoB'
2.535672 Supp     b'-1:word:Cra'
2.480323 O        b'postag:CC'
2.478905 O        b'lemma:1'
2.478905 O        b'word:1'
2.437366 Gversion b'lemma:asm584v2'
2.437366 Gversion b'word:ASM584v2'
2.416156 Strain   b'+1:lemma:substr'
2.416156 Strain   b'+1:word:substr'
2.414892 O        b'lemma:-'
2.414892 O        b'word:-'
2.342731 O        b'lemma:3'
2.342731 O        b'word:3'
2.332854 O        b'lemma:.'
2.332854 O        b'postag:.'
2.332854 O        b'word:.'
2.332241 Gtype    b'lemma:type'
2.332241 Gtype    b'word:type'
2.300103 Gtype    b'lemma:\xce\xb4cra'
2.297195 Gtype    b'word:\xce\x94cra'
2.292746 Med      b'lemma:MOPS'
2.292746 Med      b'word:MOPS'
2.285733 Technique b'lemma:chipseq'
2.278904 Supp     b'+1:lemma:\xc2\xb5m'
2.278904 Supp     b'+1:word:\xc2\xb5M'
2.247697 O        b'lemma:a'
2.221104 O        b'lemma:chip'
2.208674 O        b'-1:lemma:tag'
2.169172 Gtype    b'+1:lemma:type'
2.169172 Gtype    b'+1:word:type'
2.090683 O        b'lemma:Custom'
2.090683 O        b'word:Custom'
2.057527 Phase    b'lemma:exponential'
2.057527 Phase    b'word:exponential'
2.057527 Phase    b'lemma:stationary'
2.057527 Phase    b'word:stationary'
2.052897 Supp     b'lemma:glucose'
2.052897 Supp     b'word:glucose'
2.046732 O        b'lemma:b'
2.046732 O        b'word:B'
2.046220 pH       b'+1:postag:CD'
2.039388 Air      b'word:anaerobic'
2.024557 O        b'postag:VBN'
1.999765 O        b'-1:word:tag'
1.998647 Gtype    b'-1:postag:VBG'
1.985487 Supp     b'lemma:nacl'
1.985487 Supp     b'word:NaCl'
1.972682 Substrain b'lemma:mg1655'
1.972682 Substrain b'word:MG1655'
1.936337 Supp     b'lemma:arginine'
1.923159 Gtype    b'lemma:flag-tag'
1.923159 Gtype    b'-1:lemma:c-terminal'
1.923159 Gtype    b'word:Flag-tag'
1.923159 Gtype    b'-1:word:C-terminal'
1.916724 Gversion b'lemma:nc'
1.916724 Gversion b'word:NC'
1.913111 O        b'+1:word:were'
1.902708 Agit     b'+1:lemma:rpm'
1.902708 Agit     b'+1:word:rpm'
1.898835 Strain   b'lemma:k-12'
1.898835 Strain   b'word:K-12'
1.890731 Technique b'lemma:rnaseq'
1.890731 Technique b'word:RNASeq'
1.878930 Supp     b'lemma:nitrate'
1.878930 Supp     b'word:nitrate'
1.876600 Gtype    b'lemma:delta-fnr'
1.876600 Gtype    b'word:delta-fnr'
1.871969 O        b'+1:lemma:pq'
1.871969 O        b'+1:word:PQ'
1.852036 O        b'+1:postag:RB'
1.844216 Supp     b'lemma:acetate'
1.844216 Supp     b'word:acetate'
1.808898 O        b'-1:word:Aerobic'
1.797382 Technique b'-1:lemma:chip-exo'
1.794780 O        b'word:A'
1.780521 Supp     b'lemma:rifampicin'
1.780521 Supp     b'word:rifampicin'
1.778273 Gtype    b'-1:lemma:\xe2\x88\x86'
1.778273 Gtype    b'-1:word:\xe2\x88\x86'
1.771797 Supp     b'-1:lemma:with'
1.771797 Supp     b'-1:word:with'
1.768638 O        b'lemma:ompr'
1.768638 O        b'word:OmpR'
1.733628 O        b'+1:postag:NNP'
1.710033 Gtype    b'lemma:\xe2\x88\x86'
1.710033 Gtype    b'word:\xe2\x88\x86'
1.709664 Gtype    b'lemma:arca8myc'
1.709664 Gtype    b'word:ArcA8myc'
1.705119 Supp     b'-1:lemma:Cra'
1.699139 O        b'+1:word:ChIP-Seq'
1.687699 O        b'lemma:rep1'
1.687699 O        b'word:rep1'
1.687382 Gtype    b'postag:-LRB-'
1.664564 O        b'isLower'
1.628461 Vess     b'lemma:flask'
1.628461 Vess     b'-1:lemma:warm'
1.628461 Vess     b'word:flask'
1.628461 Vess     b'-1:word:warmed'
1.625452 Gtype    b'+1:lemma:ph5'
1.625452 Gtype    b'+1:word:pH5'
1.614155 O        b'lemma:rep3'
1.614155 O        b'word:rep3'
1.604080 Agit     b'lemma:rpm'
1.604080 Agit     b'word:rpm'
1.598554 Gversion b'-1:lemma:nc'
1.598554 Gversion b'-1:word:NC'
1.595352 Gtype    b'lemma:pk4854'
1.595352 Gtype    b'word:PK4854'
1.594618 O        b'-1:lemma:lb'
1.594618 O        b'-1:word:LB'
1.573032 Anti     b'lemma:seqa'
1.573032 Anti     b'word:SeqA'
1.572524 Med      b'+1:lemma:0.4'
1.572524 Med      b'+1:word:0.4'
1.562391 Gtype    b'postag:NN'
1.542677 Gtype    b'word:cra'
1.526806 O        b'lemma:culture'
1.526423 Air      b'lemma:aerobic'
1.513795 Med      b'-1:lemma:ml'
1.513795 Med      b'-1:word:ml'
1.512620 Gtype    b'lemma:\xce\xb4soxr'
1.512620 Gtype    b'word:\xce\x94soxR'
1.507915 O        b'lemma:Cra'
1.506239 Med      b'isUpper'
1.484419 Air      b'-1:postag::'
1.474572 Phase    b'isLower'
1.473040 Gversion b'lemma:chip-seq'
1.473008 Gtype    b'+1:lemma:with'
1.473008 Gtype    b'+1:word:with'
1.471321 Air      b'lemma:anaeroibc'
1.471321 Air      b'word:Anaeroibc'
1.469722 Supp     b'lemma:no3'
1.469722 Supp     b'word:NO3'
1.461978 Supp     b'-1:lemma:+'
1.461978 Supp     b'-1:word:+'
1.456064 O        b'-1:lemma:glucose'
1.456064 O        b'-1:word:glucose'
1.455233 Air      b'-1:lemma:ChIP-Seq'
1.455233 Air      b'-1:word:ChIP-Seq'
1.454619 Anti     b'lemma:none'
1.454619 Anti     b'word:none'
1.448341 Technique b'word:RNA-Seq'
1.445166 O        b'lemma:with'
1.445166 O        b'word:with'
1.437837 Air      b'lemma:Aerobic'
1.425780 Gversion b'word:ChIP-Seq'
1.420913 Supp     b'lemma:Fe'
1.420913 Supp     b'word:Fe'
1.415834 Gtype    b'+1:postag::'
1.413544 Supp     b'-1:lemma:vol'
1.413544 Supp     b'-1:word:vol'
1.412341 Anti     b'lemma:\xcf\x8332'
1.412341 Anti     b'word:\xcf\x8332'
1.411854 Supp     b'-1:lemma:sodium'
1.411854 Supp     b'-1:word:Sodium'
1.405489 O        b'-1:lemma:0.3'
1.405489 O        b'-1:word:0.3'
1.396245 O        b'lemma:at'
1.392279 Air      b'lemma:aerobically'
1.392279 Air      b'word:aerobically'
1.381644 Temp     b'isNumber'
1.375696 Supp     b'lemma:Leu'
1.375696 Supp     b'word:Leu'
1.370498 Gtype    b'postag:-RRB-'
1.368435 OD       b'-1:postag:IN'
1.368324 Air      b'lemma:anaerobically'
1.368324 Air      b'word:anaerobically'
1.362352 Anti     b'+1:lemma:antibody'
1.362352 Anti     b'+1:word:antibody'
1.351031 Gtype    b'lemma:\xce\xb4fur'
1.351031 Gtype    b'word:\xce\x94fur'


Top negative:
-0.161425 O        b'+1:lemma:for'
-0.161435 O        b'-1:word:from'
-0.163031 O        b'-1:postag:JJ'
-0.170208 pH       b'isNumber'
-0.175388 Phase    b'-1:word:at'
-0.176185 O        b'-1:lemma:final'
-0.176185 O        b'-1:word:final'
-0.179051 Temp     b'isLower'
-0.182276 O        b'-1:lemma:1m'
-0.182276 O        b'-1:word:1M'
-0.182335 O        b'lemma:nitrate'
-0.182335 O        b'word:nitrate'
-0.186837 O        b'-1:lemma:of'
-0.186837 O        b'-1:word:of'
-0.187743 O        b'lemma:20'
-0.187743 O        b'word:20'
-0.191386 Gtype    b'-1:lemma:mg1655'
-0.191386 Gtype    b'-1:word:MG1655'
-0.196154 Phase    b'+1:postag:NN'
-0.202412 O        b'-1:lemma:delta'
-0.202412 O        b'-1:word:delta'
-0.212437 O        b'-1:lemma:the'
-0.212759 O        b'-1:lemma:-lrb-'
-0.212759 O        b'-1:word:-LRB-'
-0.213350 O        b'word:cells'
-0.216427 O        b'-1:word:the'
-0.240040 O        b'+1:lemma:.'
-0.240040 O        b'+1:postag:.'
-0.240040 O        b'+1:word:.'
-0.243920 O        b'-1:lemma:37'
-0.243920 O        b'-1:word:37'
-0.251381 O        b'lemma:fructose'
-0.251381 O        b'word:fructose'
-0.258298 Gtype    b'+1:postag:CD'
-0.264062 O        b'lemma:glucose'
-0.264062 O        b'word:glucose'
-0.265863 O        b'-1:lemma:n2'
-0.265863 O        b'-1:word:N2'
-0.266546 Med      b'+1:postag:IN'
-0.269386 Technique b'-1:postag::'
-0.281436 Gtype    b'-1:postag:CD'
-0.293367 OD       b'isNumber'
-0.297545 Med      b'-1:postag:CD'
-0.298264 Med      b'+1:postag:NN'
-0.299287 O        b'+1:postag:-LRB-'
-0.310462 O        b'+1:word:C'
-0.312013 O        b'+1:lemma:supplement'
-0.312013 O        b'+1:word:supplemented'
-0.315139 Air      b'isUpper'
-0.323254 O        b'lemma:minimal'
-0.323254 O        b'word:minimal'
-0.325354 Air      b'isLower'
-0.330197 O        b'lemma:medium'
-0.330197 O        b'word:medium'
-0.334804 O        b'+1:word:was'
-0.338934 O        b'lemma:mid-log'
-0.338934 O        b'word:mid-log'
-0.339837 O        b'-1:lemma:ph'
-0.339837 O        b'-1:word:pH'
-0.343351 O        b'+1:postag:IN'
-0.352158 O        b'lemma:aerobically'
-0.352158 O        b'word:aerobically'
-0.353505 Supp     b'+1:lemma:acetate'
-0.353505 Supp     b'+1:word:acetate'
-0.354637 O        b'-1:lemma:until'
-0.354637 O        b'-1:word:until'
-0.366063 Gtype    b'+1:lemma:-lrb-'
-0.366063 Gtype    b'+1:word:-LRB-'
-0.366626 O        b'+1:lemma:1m'
-0.366626 O        b'+1:word:1M'
-0.367334 O        b'lemma:\xce\xb4fur'
-0.367334 O        b'word:\xce\x94fur'
-0.367534 Supp     b'+1:lemma:rifampicin'
-0.367534 Supp     b'+1:word:rifampicin'
-0.376560 Air      b'postag:CD'
-0.381184 O        b'word:ChIP-exo'
-0.381356 O        b'-1:postag:-LRB-'
-0.384332 Supp     b'+1:lemma:nacl'
-0.384332 Supp     b'+1:word:NaCl'
-0.386705 Supp     b'+1:postag:VBN'
-0.388164 O        b'-1:lemma:mm'
-0.388164 O        b'-1:word:mM'
-0.390523 O        b'+1:postag:-RRB-'
-0.398465 Supp     b'+1:lemma:fructose'
-0.398465 Supp     b'+1:word:fructose'
-0.401244 Supp     b'-1:lemma:-lrb-'
-0.401244 Supp     b'-1:word:-LRB-'
-0.402437 O        b'lemma:methanol'
-0.402437 O        b'word:methanol'
-0.409150 O        b'+1:lemma:2.0'
-0.409150 O        b'+1:word:2.0'
-0.411366 Anti     b'isUpper'
-0.423965 pH       b'isUpper'
-0.430054 O        b'-1:lemma:co2'
-0.430054 O        b'-1:word:CO2'
-0.440932 Supp     b'-1:postag:-LRB-'
-0.442403 O        b'+1:lemma:until'
-0.442403 O        b'+1:word:until'
-0.446535 O        b'lemma:37'
-0.446535 O        b'word:37'
-0.457767 O        b'-1:lemma:rpob'
-0.457767 O        b'-1:word:RpoB'
-0.477776 O        b'-1:lemma:dissolve'
-0.477776 O        b'+1:lemma:methanol'
-0.477776 O        b'-1:word:dissolved'
-0.477776 O        b'+1:word:methanol'
-0.477792 O        b'+1:lemma:at'
-0.477792 O        b'+1:word:at'
-0.483118 Supp     b'postag:CC'
-0.489848 Phase    b'isUpper'
-0.495038 O        b'-1:lemma:chip-exo'
-0.497308 Air      b'-1:lemma:or'
-0.497308 Air      b'-1:word:or'
-0.506461 O        b'postag:RB'
-0.529298 O        b'+1:lemma:+'
-0.529298 O        b'+1:word:+'
-0.531127 O        b'-1:lemma:\xe2\x88\x86'
-0.531127 O        b'-1:word:\xe2\x88\x86'
-0.538507 O        b'+1:lemma:mm'
-0.538507 O        b'+1:word:mM'
-0.548092 O        b'lemma:0.3'
-0.548092 O        b'word:0.3'
-0.563525 O        b'+1:lemma:g/l'
-0.563525 O        b'+1:word:g/L'
-0.570744 O        b'-1:lemma:ml'
-0.570744 O        b'-1:word:ml'
-0.591829 O        b'lemma:anaerobically'
-0.591829 O        b'word:anaerobically'
-0.598110 O        b'lemma:2h'
-0.598110 O        b'-1:lemma:additional'
-0.598110 O        b'word:2h'
-0.598110 O        b'-1:word:additional'
-0.600779 O        b'-1:postag:IN'
-0.607624 Med      b'-1:postag:IN'
-0.609092 pH       b'isLower'
-0.613065 O        b'+1:word:ChIP-exo'
-0.626312 O        b'-1:lemma:30'
-0.626312 O        b'-1:word:30'
-0.630541 O        b'-1:lemma:2'
-0.630541 O        b'-1:word:2'
-0.638505 Med      b'-1:postag:NN'
-0.651973 O        b'lemma:30'
-0.651973 O        b'word:30'
-0.665379 Supp     b'-1:postag:NNP'
-0.670601 O        b'-1:lemma:nsrr'
-0.670601 O        b'-1:word:NsrR'
-0.680571 Temp     b'postag:NN'
-0.684733 O        b'-1:lemma:1'
-0.684733 O        b'-1:word:1'
-0.687802 O        b'lemma:media'
-0.687802 O        b'word:media'
-0.721685 O        b'lemma:nitrogen'
-0.721685 O        b'word:nitrogen'
-0.722056 O        b'lemma:wt'
-0.741258 O        b'-1:lemma:fresh'
-0.741258 O        b'-1:word:fresh'
-0.753223 O        b'-1:lemma:IP'
-0.753223 O        b'-1:word:IP'
-0.763524 O        b'-1:postag::'
-0.789743 O        b'+1:lemma:1'
-0.789743 O        b'+1:word:1'
-0.826009 Agit     b'isUpper'
-0.838640 O        b'lemma:of'
-0.838640 O        b'word:of'
-0.900576 Technique b'isNumber'
-0.929708 Air      b'+1:postag:JJ'
-0.932673 Air      b'postag:NN'
-0.941122 O        b'-1:lemma:sample'
-0.941205 Supp     b'+1:lemma:-lrb-'
-0.941205 Supp     b'+1:word:-LRB-'
-0.985729 O        b'+1:postag:VBG'
-0.986793 O        b'+1:lemma:in'
-0.986793 O        b'+1:word:in'
-1.003856 Supp     b'+1:postag:-LRB-'
-1.027764 Gtype    b'isLower'
-1.044653 Supp     b'+1:lemma:,'
-1.044653 Supp     b'+1:postag:,'
-1.044653 Supp     b'+1:word:,'
-1.056696 O        b'postag:VBP'
-1.079385 O        b'+1:lemma:2'
-1.079385 O        b'+1:word:2'
-1.104140 Phase    b'postag:JJ'
-1.176289 O        b'lemma:rifampicin'
-1.176289 O        b'word:rifampicin'
-1.182781 Gtype    b'isUpper'
-1.265677 Gversion b'isLower'
-1.274432 O        b'-1:lemma:vol'
-1.274432 O        b'-1:word:vol'
-1.294047 Technique b'isLower'
-1.345193 Gtype    b'isNumber'
-1.368743 OD       b'+1:postag:NN'
-1.433260 Anti     b'postag:NNP'
-1.439292 Temp     b'+1:postag:IN'
-1.581204 Supp     b'postag:JJ'
-1.682734 Phase    b'-1:postag:JJ'
-1.916711 O        b'-1:postag:VBG'
-1.991385 O        b'-1:lemma:_'
-1.991385 O        b'-1:word:_'
-2.027885 O        b'-1:lemma::'
-2.027885 O        b'-1:word::'