Conditional Random Fields

+TGF-beta1
+Insulin-like growth factor-1
+CD86
+HS6ST2
+Snail1/2
+interferon-gamma
+Focal adhesion kinase
+protease-activated receptor-1
+mPAP
+nuclear factor erythroid 2-related factor 2
+NF-kB
+Fos
+HDAC6
+CD90
+interleukin-12p40
+Mitogen-activated protein kinase-activated protein kinase-2
+collagen-1, ET-1
+smooth muscle a-actin
+caspase-3
+Angiotensin II
+IL-23
+HDAC
+matriptase
+CD124
+Keap1
+transforming growth factor-beta-1
+TGF-a
+Cysteine-rich protein 1
+glycogen synthase kinase-3beta
+Cartilage oligomeric matrix protein
+TGFb2
+miR-338*
+C3aR
+E  -cadherin
+TGF beta 1
+miR-200b
+pVHL
+Activin
+BMP-8B
+Foxp-3
+HAI-1
+IL-1b
+WNT5A
+AQP5
+MT1
+stromal-cell-derived factor-1
+tgfb2
+monocyte chemotactic protein-1
+SpA
+IL-1 beta, -2, -4, -5, -6, -8, -10, -17
+insulin-like growth factor-I
+ECSOD
+SPARC
+E-CAD
+TGF-b(1)
+il17a
+COL1A2
+TGF-b-1
+Atg4b
+ET-B
+KGF
+NOX-4
+col1a2
+pten
+miR-26a
+S1PL
+alpha-smooth muscle actin
+Glut-1 and glucokinase
+TGFbeta1
+Transforming growth factor beta1
+CCl4
+transforming growth factor  -b1
+serum amyloid P
+miR-338
+Bone morphogenetic protein 3
+COL3A1
+ALK5
+PSPH
+HO-1
+histone deacetylase 4
+tsp1
+FGF-10
+interferon (IFN)-gamma
+E-Cad
+Protease nexin-1
+ILK
+TGF-b receptor II
+TGFB
+insulin promoting factor-1
+EGFR
+LXRa
+Interleukin 17A
+MiR-185
+Semaphorin-7A
+SPHK1
+transforming growth factor-b(1)
+K-ras
+p27
+pai1
+Mmp19
+Col1A1
+Follistatin-like 1
+Serine Protease
+Smad3 and 4
+Bone morphogenetic protein
+PDGF-B
+BMP-4
+min(-1
+ORP150
+bmp1
+RAGE
+SGPL1
+SOCS-1
+tagln2
+MMP-12
+DRB1
+MyD88
+STC1
+150-kDa oxygen-regulated protein
+MMP-9
+IP10
+terminal deoxynucleotidyl transferase
+TGF-beta 1
+NADPH oxidase-4
+transforming growth factor-beta
+Prostaglandin A(1)
+p70
+IgG1
+N-acetyl-l-cysteine
+Tgfbr1/2
+HGFA
+DNMT1
+nuclear factor kappa B
+plasminogen activator inhibitor 1
+S1P
+angiopoietin-2
+KCa3.1
+ENA-78
+WNT3a
+miR-134
+P53
+matrix metalloproteinase (MMP)  -2
+vimentin
+MMP-2
+endoglin
+tumor necrosis factor superfamily protein 14
+Transforming Growth Factor Beta 1
+Cebpb
+Mknk2
+SDF-1-TR1
+Endothelin-1
+HFL-1
+MIG
+TGF-beta receptors type I and II (T beta R-I and T beta R-II
+IL-8
+YY-1
+MMP1
+interferon gamma (IFN-y
+MIP-1 alpha
+IL-4RA
+HS6ST1
+BMPR2
+sL1
+transforming growth factor-alpha
+Transgelin
+TGF-beta 3
+lox
+CTGF
+MCP-1
+tumor necrosis factor
+MT3
+cytosolic phospholipase A(2)
+Thymic stromal lymphopoietin
+phosphoglycerate dehydrogenase
+Bax
+Caveolin-1 (cav-1
+UCHL5
+TIMP-1
+JunD
+Transforming growth factor (TGF)-b1
+MicroRNA  (miR)-221
+miR-424
+YAP
+Aortic carboxypeptidase-like protein
+Microsomal prostaglandin E synthase-1
+b2 -adrenoceptors
+YKL-40
+VE-cadherin
+transforming growth factor-beta(1)
+PML
+CXCL12
+VEGF-C
+LMP1
+miR-30a
+insulin-like growth factor)-1
+histone deacetylase
+b-catenin
+RANTES
+latent membrane protein (LMP) 1
+Itgb6
+CXCL1
+VEGFR-3
+glucokinase
+TNFSF14
+matrix metalloproteinase-3
+TNFa
+renin
+VCAM1
+GATA-6
+Transforming growth factor-b(1
+angiotensinogen
+Smad7
+cC1q-R
+IL-1R
+tgfbr1/2
+FoxP3
+a-SMA
+CCL12
+CCN2
+PDE1A
+PAR-2
+serum albumin (HSA)-thioredoxin 1
+tissue inhibitor of metalloproteinase (TIMP)-1
+HIF-1a
+FRNK
+TGF-alpha
+miR-200c
+poly-ADP ribose polymerase
+Spiruchostatin A
+Sgpl1
+FXa
+Extracellular superoxide dismutase
+Tgf-b
+Tb4
+CUX1
+gC1q-R
+FGF10
+Tpo
+AKT
+insulin-like growth factor-1
+IL-4R alpha
+IFN-gamma
+JAK2
+MMP-7
+smad3
+NOX4
+Bach1
+caspase-9
+transforming growth factor b1
+interleukin-6
+Serpin B3
+Pentraxin-2
+T-cell lymphoma invasion and metastasis 1
+GR
+prostaglandin F (PGF) receptor
+serine protease
+MMP-19
+SMAD 3
+MMP7
+p62
+connective tissue growth factor
+Renin
+discoidin domain receptor 2
+mothers against decapentaplegic homolog 3
+IL-1RA
+Trx
+HAI-2
+WNT1-inducible signaling pathway protein 1
+Ubiquitin carboxyl-terminal hydrolase-L5
+CC16
+interleukin-10
+LTBP-1
+EDA
+BMP-5
+miR-154
+CD80
+p110
+LTBP1 and 2
+periostin
+EP2
+TGF-beta
+C3a
+H2O2 and tumor necrosis factor alpha
+CD1
+Mir-154
+cyclooxygenase-2
+LTBP] 1, 2, and 4
+matrix metalloproteinase-14(+)/matrix metalloproteinase-2(+) myofibroblasts
+Chop
+TGF-beta(1)
+MK2
+SMO
+PPARy
+insulin-like growth factor binding protein-3
+TGF-beta(1), collagen type Ialpha1
+hyaluronan synthase 2
+endothelin type A receptors
+TNF-alpha
+TNC
+transforming growth factor (TGF)-beta 1
+Enhancer of zeste homolog 2
+Snail
+IL-1Ra
+MMP-1
+interleukin-8
+PGA(1)
+lymphotoxin beta receptor
+TGF-beta 2
+Lefty A
+Sulf1
+serine hydroxymethyltransferase 2
+IFN-y
+LOX
+Transforming growth factor (TGF)-b
+TGF- b
+NOS
+Smad 7
+hypoxia-inducible factor 1a
+Transglutaminase 2
+mTORC2
+C5a
+annexin V
+thyroid transcription factor (TTF)-1
+CXCL9
+transforming growth factor-beta 1
+Vascular endothelial growth factor
+beclin-1
+extracellular signal-regulated kinase (ERK)1/2
+TGF-{beta}1
+Caspase-3
+CCN5
+IL-17A
+ARPC2
+matrix metalloproteinase 9
+p16
+glucagon like peptide-1
+L1-CAM
+TGF  -b
+fibroblast growth factor-1
+TGFbeta
+IGFBP-1
+ubiquitin carboxyl-terminal hydrolase-L5
+SMAD3
+glucocorticoid receptor
+Transforming growth factor b1
+TNF)-alpha
+IL18
+TOB2
+TbRII
+WNT7B
+SMAD-3
+HLA-A, -B, -DRB1, tumor necrosis factor alpha
+TF
+miR-3107
+zonula occludens-1
+Nuclear factor-erythroid-related factor 2
+Sulf2
+ADAMTS9
+Surfactant Protein-C
+TNFalpha
+IL10
+actin related protein 2/3 complex, subunit 2
+secreted protein acidic and rich in cysteine
+Krebs Von Den Lungen-6
+Il-1b
+HNP-1
+Fstl1
+miR-382
+matrix metalloproteinase (MMP)-2 and -9
+SphK1/2
+IQGAP1
+SNAI2
+Rictor
+SHH
+ACTA2
+SIRT1
+Sema 7a-CD4
+WNT10A
+Insulin-like growth factor binding protein-3
+FSP-1
+poly(ADP-ribose) polymerase
+LRP5
+MMP-3
+Interleukin (IL) 8
+Wilms' tumor 1
+Fibrillin-2
+tnf-alpha
+aSMA
+IL-9
+HLA-A
+cartilage oligomeric matrix protein
+thrombin
+tumor necrosis factor alpha
+beta-catenin
+FAK
+Th1
+YY1
+NFkB
+Lox
+Caveolin-1
+Membrane-type (MT)-MMPs
+Galectin-3
+smoothened
+Smad3
+claudins-1 and -3
+ERK1/2
+Bone Morphogenic Protein Receptor 2
+acyl-CoA oxidase 1
+serpine1
+VASH-2
+miR-326
+TGFB1
+phosphoinositide 3-kinase
+bone morphogenetic protein
+interleukin (IL)-13
+c-Myc
+TGF-b3
+NFATc2
+TIMP-2
+SMAD2
+CD25
+Smad2/3
+V-ATPase
+LMP-1
+C1q receptor
+glutathione peroxidase 1
+C5a receptor
+IL-1 alpha, -1R, -1RA, -2, -4, -4R alpha, -6, -10
+platelet-derived growth factor isoforms (PDGF) A and B
+IL-1-beta
+Transforming growth factor-beta1
+galectin-3
+PAR1
+SIRT7
+p65
+Transforming growth factor beta
+cPLA(2)
+desmin
+Histone deacetylase 6
+EMT
+transforming growth factor (TGF)-beta1
+IGFBP-1 and -2
+TGFBR-2
+transforming growth factor beta
+HSP90
+miR-29b
+CD248
+PPARbeta
+follistatin
+TGF-beta(1
+Janus kinase type 2
+A-myb
+nuclear factor E2-related factor 2
+Heat shock protein (HSP) 47
+VCAM-1
+mmu-miR-326
+PARP
+LXA4 receptor
+G-CSF
+transforming-growth factor beta 1
+Matriptase
+MiR-5100
+IL-6
+VEGFR
+CXCL-9
+Rpn6
+IL-10
+alpha1 type I collagen
+Smad4
+matrix metalloproteinase-9
+PHLPP
+Tumor necrosis factor-alpha
+thyroid transcription factor-1
+insulin
+Ang-2
+basic FGF
+tagln
+TGFbeta(1)
+b-FGF
+miR-210
+Lrp5 and 6
+PDGF-b
+FN1
+HMGA2
+LYCAT
+Tumor necrosis factor a
+IL-2
+IL1-b
+PAI-1
+VEGFR-2
+igf1
+Ho-1
+aquaporin-5
+VEGF receptor-2
+COMP
+c-jun
+mir-155
+megakaryoblastic leukemia 1
+Kca3.1
+tissue inhibitors of metalloproteinases-1
+Secreted protein acidic and rich in cysteine
+CD-1
+Cyclin D1
+tenascin C
+phosphoserine aminotransferase 1
+Lin28B
+Gremlin
+tropomodulin 3
+PIAS4
+interleukin 10
+epidermal growth factor receptor
+c-IAP2
+fibroblast growth factor receptor 2
+CRP1
+Collagen Triple Helix Repeat-Containing-1
+transforming growth factor-b1
+PTX-2
+CD11b
+IL-4 R alpha
+TG2
+IGFBP-2
+cytochrome b
+BLTR
+lysyl oxidase
+alpha smooth muscle actin
+UCH37
+Receptor for advanced glycation end products
+IL-1 beta
+miR-376c
+miR-153
+Smad2/3/4
+LEF/TCF
+thymosin b4
+plasminogen activator inhibitor-1
+beta-galactosidase
+Stanniocalcin-1
+THP-1
+Egr-1
+beta-gal
+PDGFR
+Transforming growth factor b-1
+transforming growth factor beta 1
+miR-410
+TGF-b(1
+focal adhesion kinase
+STAT3
+Prostaglandin F(2alpha) receptor
+Nox-4
+Toll-like receptor 9
+CCL2
+GM-CSF
+folate receptor beta
+Elk1
+interleukin (IL)-1beta
+mTOR
+vascular cell adhesion molecule 1
+E-cadherin
+PPARgamma
+Serpine1
+PAI1
+TIMP
+SFTPC
+VEGF and IL-12
+LTBP 4
+Nuclear factor erythroid 2-related factor 2
+Jun NH2-terminal kinase
+FAK(Y397
+IL-18
+Transforming growth factor-b
+il-1b
+SphK
+DDR2
+FOXF1
+TIMP1
+SHMT2
+SOD3
+TGFb1
+FN
+TIMP2
+FRbeta
+Interleukin 4
+E-cad
+p38
+VEGF-D
+Periostin
+Sp1
+CC1q-R
+KL-6
+ADAM19
+miR-185
+USP11
+IL8
+Akt2
+BMPER
+IFN-gammaR
+Akt
+IL-1
+hepatocyte growth factor
+MAPKAPK2
+uncoupling protein 2
+thrombospondin-1
+serum response factor
+CD55
+Gpx1
+Id3
+PAR-1
+keratinocyte growth factor
+TIGAR
+NADPH oxidase 4
+integrin-linked kinase
+interleukin-1 receptor antagonist protein
+PHGDH
+mPGES-1
+matrix metalloproteinase 14
+STIP1
+CCN1
+angiopoietin-1
+CD44
+TGF-b1
+PN-1
+BMP endothelial cell precursor-derived regulator
+MFG-E8
+PPAR
+protein kinase B
+IGFBP-3
+EMMPRIN
+cyclosporine A
+semaphorin-7A
+SNAI1
+Pink1
+PINK1
+Bone morphogenetic protein-4
+CBP
+IL-17
+AT1
+TGFBR2
+N-acetyl-L-cysteine
+endothelin-1
+smad-2
+Interleukin (IL)-6
+ET-1
+AP-1
+HDAC4
+c-Fos
+HSP27
+WISP1
+Transforming growth factor beta 1
+jag1
+Nrf2
+cyclooxygenase 2
+smad6/7
+WNT5a
+mir-154
+SP-D
+Matrix metalloproteinase (MMP)-19
+Vasohibin-2
+caspase 3
+Smad1/5
+miR-200a
+TNF-a
+IGFBP-3 and -5
+p53
+Serpin B4
+Transcription factor GATA-6
+ACLP
+transgelin
+NADPH Oxidase 4
+ZO-1
+Cthrc1
+VEGF-A
+Plasminogen activator inhibitor 1
+p300
+extent, type B receptors
+il12p40
+miR-29c
+IL-1beta
+interleukin (IL)-17
+transforming growth factor b(1)
+LTB(4) receptor
+BMP
+extracellular signal--regulated kinase
+interleukin-1 beta
+TLR4
+AGT
+PP1
+IGF-1
+Thymosin b4
+SOCS1
+SMAD)2
+E prostanoid receptor 2
+b2 -AR
+microRNA (miR)-155
+peroxisome proliferator-activated receptor-y
+Discoidin Domain Receptor 2
+smad2/3
+gp130
+miR-31
+MKL1
+PPARalpha
+TTF-1
+Erk1/2
+ERK
+RXFP1
+interleukin-18
+protease nexin-1
+Syndecan-2
+RhoA
+CD34
+N  -cadherin
+Rta
+PI3K
+fibroblast specific protein-1
+IGFBP-5
+PDGB
+gremlin
+HMG-CoA) reductase
+Yin Yang 1
+interleukin-1
+p38 mitogen-activated protein kinase
+Vi
+CD11c
+IL-4
+NEU1
+VEGF
+CD46
+protease-activated receptor (PAR)-2
+C/EBP homologous protein
+ATG4B
+IKKa
+AKT2
+calnexin
+CXCR3
+peroxisome proliferator-activated receptor y
+fibroblast growth factor-2
+TGF-beta receptor II
+CsA
+miR  -221
+BAX inhibitor-1
+miR-5100
+Ang-1
+PEX13p
+SDC2
+PARK2
+5-HTR(1A/B) and 5-HTR(2B
+fibronectin
+interleukin (IL)-8
+BMP-7
+EP1
+CDCP1
+protease-activated receptor-2
+CD8
+CD206
+TGF-beta receptors (T beta R-I and T beta R-II
+HGF
+c-Jun NH-terminal kinase
+Col3a1
+IRAP
+Bcl-2
+GLP-1
+N-cadherin
+Sema 7a
+SDF-1
+Wnt
+GLP-1 receptor
+sphingosine kinase 1
+Smad2
+transforming growth factor b-1
+p63
+TLR9
+IL-13
+X-linked inhibitor of apoptosis
+CD19
+syndecan-2
+EGR1
+STUB1
+Lysocardiolipin acyltransferase
+IL8, -6, and -1B
+Wnt1-inducible signaling protein 1
+TGF-b
+tenascin
+hypoxia-inducible factor-1a
+IP-10
+XIAP
+transforming growth factor beta1
+caveolin-1
+endothelial nitric oxide synthase
+IGF-2
+CCR2
+inducible nitric oxide synthase
+bone morphogenetic protein 7
+platelet-derived growth factor, insulin-like growth factor type I, and transforming growth factor beta
+Itgb1/6
+HIF-1
+SRF
+miR-29a
+MPP-9
+miR-155
+PDGF-A and -B
+FoxO3a
+Cub domain containing protein 1
+Muc5ac
+Yin yang 1
+Transforming growth factor b
+Ltbp1
+NOX-2
+tissue inhibitor of metalloproteinase (TIMP)-1, -2, -3, and -4
+Nox1
+X-box-binding protein 1
+miR-21
+Wnt7B
+HSP90b
+PPAR-a
+leucine-rich alpha-2 glycoprotein
+TNF alpha
+estrogen receptor 1
+TSLP
+signal transducer and activator of transcription 3
+IL-8 and b-FGF
+matrix metalloproteinase-7
+mitogen-activated protein kinase-activated protein kinase-2
+Smad-3
+matrix metalloproteinase (MMP)-9
+beta 1 integrin
+interleukin (IL)-6
+basic-fibroblast growth factor
+gastrin
+Pdgfb
+Itga2/3
+HLF
+snail
+TGFb(1)
+Smurf2
+STAT1
+tissue factor
+Glucagon like peptide-1
+NAC
+Lrp5
+transforming growth factor b expression
+insulin-like growth factor (IGF)-I
+superoxide dismutase 3
+vascular endothelial growth factor receptor
+Wt1
+as c
+Transforming growth factor (TGF)-beta1
+IGF-I
+UCP2
+Protease activated receptor-1
+G1 and G2
+transforming growth factor beta-1
+FHIT
+Wnt5A
+TGF beta1
+MRTF-A
+platelet-derived growth factor receptor
+SphK1
+extracellular superoxide dismutase
+Acta2
+Toll-like receptor 4
+ICAT
+CXCL10
+alpha-SMA
+Bax inhibitor-1
+keratin 6 and 14
+AT2
+MT1- and MT2-MMPs
+NOX1
+beta 2
+PAI-1-siRNA
+fibrillin-2
+col3a1
+IPF-1, insulin, and glucokinase
+cyclin D1
+COX-2
+CD4
+MT2
+Transforming growth factor-beta
+matrix metalloprotease-1
+Thy-1
+ATG7
+neuraminidase 1
+Mkl1
+LPA1
+Ost-4
+MMP  -9
+HIF1a
+Semaphorin 7a
+EP3
+Transforming growth factor-b1
+PSAT1
+High mobility group AT-hook 2
+jagged 1
+n-cadherin
+Janus kinase 2
+let-7d
+Fas ligand
+integrin alpha v
+MK2(-/-) MEF
+interleukin-1beta
+p21
+Col1a2
+MT3-MMP
+PDGF-A
+JNK
+Transforming Growth Factor- b
+PP2A
+miR
+claudins-1, -3, and -5
+BARD1
+relaxin/insulin-like family peptide receptor 1
+MMP2
+ATG5
+MEK
+CAV1
+SIRT3
+ANGII
+activin
+p38 MAPK
+interleukin-1 (IL-1)Ra
+hsa-miR-326
+MAP3K19
+surfactant protein C
+Nox4
+collagen (Col)1a1
+SAP
+miR-9-5p
+interleukin (IL)-1b
+p21(waf1
+MicroRNA-29c
+H19
+Protease-activated receptor-1
+ALXR
+miR-487b
+TGF beta
+Connective tissue growth factor
+matrix metalloproteinase-14
+SERPINE1
+mir-21
+CC chemokine receptor 2
+PTEN
+IL-1 alpha
+IPF-1
+c-IAP)1
+Il-17a
+Pigment epithelium-derived factor
+fibroblast growth factor 10
+connective-tissue growth factor
+BMP3
+transforming growth factor-beta1
+Annexin V
+HS6ST1/2
+fibroblast growth factor-10
+BI-1
+lymphotactin
+tenascin-C
+miR-455
+MT1-MMP
+transforming growth factor-b
+3-hydroxy-3-methylglutaryl CoenzymeA (HMG CoA) reductase
+SMAD2/3
+MiR-338
+MMP-2 and -9
+LTBP)-1
+suppressor of cytokine signaling 1
+neutrophil peptide (HNP)-1
+SphK2
+S1P lyase
+ltbp1/2
+iNOS
+TGFb(1
+ACE
+BCL-2
+Oct-4
+SMA
+MMP-9 and tissue inhibitor of metalloproteinase-1
+Hepatocyte growth factor
+Ets1
+beta-actin
+VASH-1
+CD117
+THBS1
+HO1
+Hsp90
+Extracellular Matrix Metalloproteinase Inducer
+COL1A1
+AKT1
+FGF-1
+interleukin 6
+caspase-3/7
+IL6
+receptor for advanced glycation end products
+EP4
+TGFb
+HSP47
+miR-140
+heat shock protein (HSP)90
+insulin-like growth factor binding proteins (IGFBP)-3 and -5
+EZH2
+Toll-Like Receptor 9
+Col3A1
+Transforming Growth Factor- Beta1
+Osteopontin
+hFL1
+CXCR4
+MMP19
+IL-33
+miR-17   92
+fibrillin-1
+ET-A
+HDAC10
+ALK-5
+IL-31
+beclin 1
+c-Jun
+Sema7a
+MT5-MMP
+PI3
+ITGB6
+TIAM1
+angiotensin II
+LRG
+IL-1alpha
+TbetaRII
+transforming growth factor b
+FIEL1
+C5aR
+PEDF
+C1q
+IL-1ra
+tissue inhibitor of metalloproteinase
+ErbB2
+TGF  -b1
+PTEN-induced putative kinase 1
+AAG
+CD103
+a-smooth muscle actin
+cytokeratin 19
+CREB)-binding protein
+p110a
+Ets Domain-containing Protein Elk1
+insulin-like growth factor I
+Cytokeratin-8
+TIMP3
+BMP-15
+LC3
+Vimentin
+mTORC1
+SIRT6
+heme oxygenase-1
+Transforming growth factor-beta 1
+miR-127
+MIP-1 beta
+TRPV4
+Neutrophil elastase
+ANG converting enzyme
+ERK-1
+bFGF
+tumor necrosis factor-alpha
+Serpin B3/B4
+focal adhesion kinase-related nonkinase
+Stat3
+miR-1343
+SMAD7
+Endosialin
+FGF-2
+miR-101
+L1CAM
+thymic stromal lymphopoietin
+vascular endothelial growth factor
+PEX13
+heat shock protein (HSP) 47
+transient receptor potential vanilloid 4
+monocyte chemoattractant protein 1
+SPP1
+CD68
+TGF- b1
+T beta RII
+TGFb-1
+Forkhead Box F1

-# -*- coding: UTF-8 -*-
-
-import os
-from itertools import chain
-from optparse import OptionParser
-from time import time
-from collections import Counter
-
-import nltk
-import sklearn
-import scipy.stats
-import sys
-
-from sklearn.externals import joblib
-from sklearn.metrics import make_scorer
-from sklearn.cross_validation import cross_val_score
-from sklearn.grid_search import RandomizedSearchCV
-
-import sklearn_crfsuite
-from sklearn_crfsuite import scorers
-from sklearn_crfsuite import metrics
-
-from nltk.corpus import stopwords
-from trainingTesting_Sklearn_crfsuite import word2features
-from trainingTesting_Sklearn_crfsuite import sent2features
-# from trainingTesting_Sklearn_crfsuite import hasNonAlphaNum
-# from trainingTesting_Sklearn_crfsuite import hasDigit
-
-# Objective
-# Tagging transformed file with CRF model with sklearn-crfsuite.
-#
-# Input parameters
-# --inputPath=PATH    Path of transformed files x|y|z
-# --modelPath        Path to CRF model
-# --modelName    Model name
-# --outputPath=PATH    Output path to place output files
-# --filteringStopWords   Filtering stop words
-# --filterSymbols      Filtering punctuation marks
-
-# Output
-# 1) Tagged files in transformed format
-
-# Examples
-# Sentences
-# C:\Anaconda2\python tagging_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\classifying_TFSentences\corpus\ECK120011394_FhlA\transformed --modelName aspectsTraining.fStopWords_False.fSymbols_True --modelPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\classifying_TFSentences\corpus\ECK120011394_FhlA\transformed_CRFtagged --filterSymbols > output.taggingCRF.20161107.txt
-# C:\Anaconda2\python tagging_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\classifying_TFSentences\corpus\ECK120011394_FhlA\transformed --modelName sentencesTraining.fStopWords_False.fSymbols_False --modelPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\classifying_TFSentences\corpus\ECK120011394_FhlA\transformed_CRFtagged > output.taggingCRF.20161107.txt
-
-#################################
-#           FUNCTIONS           #
-#################################
-# def hasDigit(text):
-#     has = False
-#     if len(text) < 3:
-#         return False
-#     myRegex = nltk.re.compile('[0-9]')
-#     if myRegex.search(text) != None:
-#         has = True
-#     return has
-#
-#
-# def hasNonAlphaNum(text):
-#     has = False
-#     if len(text) < 3:
-#         return False
-#     myRegex = nltk.re.compile('\W')
-#     if myRegex.search(text) != None:
-#         has = True
-#     return has
-
-# IMPORTED FROM TRAINING SCRIPT
-# def word2features(sent, i):
-#     # print "i: " + str(i)
-#     # print "sent[i]" + sent[i]
-#     listElem = sent[i].split('|')
-#     word = listElem[0]
-#     lemma = listElem[1]
-#     postag = listElem[2]
-#
-#     features = {
-#         # Names of TF and genes change by lower and upper characters: 'word.lower()': word.lower(),
-#         # Suffixes
-#         'word[-3:]': word[-3:],
-#         'word[-2:]': word[-2:],
-#         'word[-1:]': word[-1:],
-#         'word.isupper()': word.isupper(),
-#         'word.istitle()': word.istitle(),
-#         'word.hasDigit()': hasDigit(word),
-#         'word.hasNonAlphaNum': hasNonAlphaNum(word),
-#         # 'word.isdigit()': word.isdigit(),
-#         'word': word,
-#         'lemma': lemma,
-#         'lemma[-3:]': lemma[-3:],
-#         'lemma[-2:]': lemma[-2:],
-#         'lemma[-1:]': lemma[-1:],
-#         'postag': postag,
-#         # Prefixes
-#         'postag[:2]': postag[:2],
-#         'postag[:1]': postag[:1],
-#     }
-#     if i > 0:
-#         listElem = sent[i - 1].split('|')
-#         word1 = listElem[0]
-#         lemma1 = listElem[1]
-#         postag1 = listElem[2]
-#         features.update({
-#             '-1:word.lower()': word1.lower(),
-#             '-1:word.istitle()': word1.istitle(),
-#             '-1:word.isupper()': word1.isupper(),
-#             '-1:word.hasDigit()': hasDigit(word1),
-#             '-1:word.hasNonAlphaNum': hasNonAlphaNum(word1),
-#             '-1:word': word1,
-#             '-1:lemma': lemma1,
-#             '-1:postag': postag1,
-#             '-1:postag[:2]': postag1[:2],
-#             '-1:postag[:1]': postag1[:1],
-#         })
-#     # else:
-#     #    features['BOS'] = True
-#
-#     if i < len(sent) - 1:
-#         listElem = sent[i + 1].split('|')
-#         word1 = listElem[0]
-#         lemma1 = listElem[1]
-#         postag1 = listElem[2]
-#         features.update({
-#             '+1:word.lower()': word1.lower(),
-#             '+1:word.istitle()': word1.istitle(),
-#             '+1:word.isupper()': word1.isupper(),
-#             '+1:word.hasDigit()': hasDigit(word1),
-#             '+1:word.hasNonAlphaNum': hasNonAlphaNum(word1),
-#             '+1:word': word1,
-#             '+1:lemma': lemma1,
-#             '+1:postag': postag1,
-#             '+1:postag[:2]': postag1[:2],
-#             '+1:postag[:1]': postag1[:1],
-#         })
-#     # else:
-#     #    features['EOS'] = True
-#     if i > 1:
-#         listElem = sent[i - 2].split('|')
-#         word2 = listElem[0]
-#         lemma2 = listElem[1]
-#         postag2 = listElem[2]
-#         features.update({
-#             '-2:word.lower()': word2.lower(),
-#             '-2:word.istitle()': word2.istitle(),
-#             '-2:word.isupper()': word2.isupper(),
-#             '-2:word.hasDigit()': hasDigit(word2),
-#             '-2:word.hasNonAlphaNum': hasNonAlphaNum(word2),
-#             '-2:word': word2,
-#             '-2:lemma': lemma2,
-#             '-2:postag': postag2,
-#             '-2:postag[:2]': postag2[:2],
-#             '-2:postag[:1]': postag2[:1],
-#         })
-#
-#     if i < len(sent) - 2:
-#         listElem = sent[i + 2].split('|')
-#         word2 = listElem[0]
-#         lemma2 = listElem[1]
-#         postag2 = listElem[2]
-#         features.update({
-#             '+2:word.lower()': word2.lower(),
-#             '+2:word.istitle()': word2.istitle(),
-#             '+2:word.isupper()': word2.isupper(),
-#             '+2:word.hasDigit()': hasDigit(word2),
-#             '+2:word.hasNonAlphaNum': hasNonAlphaNum(word2),
-#             '+2:word': word2,
-#             '+2:lemma': lemma2,
-#             '+2:postag': postag2,
-#             '+2:postag[:2]': postag2[:2],
-#             '+2:postag[:1]': postag2[:1],
-#         })
-#
-#     trigrams = False
-#     if trigrams:
-#         if i > 2:
-#             listElem = sent[i - 3].split('|')
-#             word3 = listElem[0]
-#             lemma3 = listElem[1]
-#             postag3 = listElem[2]
-#             features.update({
-#                 '-3:word.lower()': word3.lower(),
-#                 '-3:word.istitle()': word3.istitle(),
-#                 '-3:word.isupper()': word3.isupper(),
-#                 '-3:word.hasDigit()': hasDigit(word3),
-#                 '-3:word.hasNonAlphaNum': hasNonAlphaNum(word3),
-#                 '-3:word': word3,
-#                 '-3:lemma': lemma3,
-#                 '-3:postag': postag3,
-#                 '-3:postag[:2]': postag3[:2],
-#                 '-3:postag[:1]': postag3[:1],
-#             })
-#
-#         if i < len(sent) - 3:
-#             listElem = sent[i + 3].split('|')
-#             word3 = listElem[0]
-#             lemma3 = listElem[1]
-#             postag3 = listElem[2]
-#             features.update({
-#                 '+3:word.lower()': word3.lower(),
-#                 '+3:word.istitle()': word3.istitle(),
-#                 '+3:word.isupper()': word3.isupper(),
-#                 '+3:word.hasDigit()': hasDigit(word3),
-#                 '+3:word.hasNonAlphaNum': hasNonAlphaNum(word3),
-#                 '+3:word': word3,
-#                 '+3:lemma': lemma3,
-#                 '+3:postag': postag3,
-#                 '+3:postag[:2]': postag3[:2],
-#                 '+3:postag[:1]': postag3[:1],
-#             })
-#
-#     return features
-
-
-# def sent2features(sent):
-#     return [word2features(sent, i) for i in range(len(sent))]
-
-
-__author__ = 'CMendezC'
-
-##########################################
-#               MAIN PROGRAM             #
-##########################################
-
-if __name__ == "__main__":
-    # Defining parameters
-    parser = OptionParser()
-    parser.add_option("--inputPath", dest="inputPath",
-                      help="Path of training data set", metavar="PATH")
-    parser.add_option("--outputPath", dest="outputPath",
-                      help="Output path to place output files",
-                      metavar="PATH")
-    parser.add_option("--modelPath", dest="modelPath",
-                      help="Path to read CRF model",
-                      metavar="PATH")
-    parser.add_option("--modelName", dest="modelName",
-                      help="Model name", metavar="TEXT")
-    parser.add_option("--filterStopWords", default=False,
-                      action="store_true", dest="filterStopWords",
-                      help="Filtering stop words")
-    parser.add_option("--filterSymbols", default=False,
-                      action="store_true", dest="filterSymbols",
-                      help="Filtering punctuation marks")
-
-    (options, args) = parser.parse_args()
-    if len(args) > 0:
-        parser.error("Any parameter given.")
-        sys.exit(1)
-
-    print('-------------------------------- PARAMETERS --------------------------------')
-    print("Path to read input files: " + options.inputPath)
-    print("Mode name: " + str(options.modelName))
-    print("Model path: " + options.modelPath)
-    print("Path to place output files: " + options.outputPath)
-    print("Filtering stop words: " + str(options.filterStopWords))
-    symbols = ['.', ',', ':', ';', '?', '!', '\'', '"', '<', '>', '(', ')', '-', '_', '/', '\\', '¿', '¡', '+', '{',
-               '}', '[', ']', '*', '%', '$', '#', '&', '°', '`', '...']
-    # symbols = [sym.decode('utf-8') for sym in ['.', ',', ':', ';', '?', '!', '\'', '"', '<', '>', '(', ')', '-', '_', '/', '\\', '¿', '¡', '+', '{',
-    #            '}', '[', ']', '*', '%', '$', '#', '&', '°']]
-    # symbols = [u'.', u',', u':', u';', u'?', u'!', u'\'', u'"', u'<', u'>', u'(', u')', u'-', u'_', u'/', u'\\', u'¿', u'¡', u'+', u'{',
-    #             u'}', u'[', u']', u'*', u'%', u'$', u'#', u'&', u'°', u'`']
-    print("Filtering symbols " + str(symbols) + ': ' + str(options.filterSymbols))
-
-    print('-------------------------------- PROCESSING --------------------------------')
-
-    stopwords = [word.decode('utf-8') for word in stopwords.words('english')]
-
-    # Read CRF model
-    t0 = time()
-    print('Reading CRF model...')
-    crf = joblib.load(os.path.join(options.modelPath, 'models', options.modelName + '.mod'))
-    print("Reading CRF model done in: %fs" % (time() - t0))
-
-    print('Processing corpus...')
-    t0 = time()
-    labels = list(['MF', 'TF', 'DFAM', 'DMOT', 'DPOS', 'PRO'])
-    # Walk directory to read files
-    for path, dirs, files in os.walk(options.inputPath):
-        # For each file in dir
-        for file in files:
-            print("   Preprocessing file..." + str(file))
-            sentencesInputData = []
-            sentencesOutputData = []
-            with open(os.path.join(options.inputPath, file), "r") as iFile:
-                lines = iFile.readlines()
-                for line in lines:
-                    listLine = []
-                    # line = line.decode("utf-8")
-                    for token in line.strip('\n').split():
-                        if options.filterStopWords:
-                            listToken = token.split('|')
-                            lemma = listToken[1]
-                            # Original if lemma in stopwords.words('english'):
-                            if lemma in stopwords:
-                                continue
-                        if options.filterSymbols:
-                            listToken = token.split('|')
-                            lemma = listToken[1]
-                            if lemma in symbols:
-                                if lemma == ',':
-                                    print "Coma , identificada"
-                                continue
-                        listLine.append(token)
-                    sentencesInputData.append(listLine)
-                print "   Sentences input data: " + str(len(sentencesInputData))
-                # print sentencesInputData[0]
-                # print(sent2features(sentencesInputData[0])[0])
-                # print(sent2labels(sentencesInputData[0]))
-                X_input = [sent2features(s) for s in sentencesInputData]
-                print(sent2features(sentencesInputData[0])[0])
-                # y_test = [sent2labels(s) for s in sentencesInputData]
-                # Predicting tags
-                t1 = time()
-                print "   Predicting tags with model"
-                y_pred = crf.predict(X_input)
-                print y_pred[0]
-                print("      Prediction done in: %fs" % (time() - t1))
-                # Tagging with CRF model
-                print "   Tagging file"
-                for line, tagLine in zip(lines, y_pred):
-                    outputLine = ''
-                    idx_tagLine = 0
-                    line = line.strip('\n')
-                    print "\nLine: " + str(line)
-                    print "CRF tagged line: " + str(tagLine)
-                    for token in line.split():
-                        listToken = token.split('|')
-                        word = listToken[0]
-                        lemma = listToken[1]
-                        tag = listToken[2]
-                        if options.filterStopWords:
-                            if lemma in stopwords:
-                                outputLine += token + ' '
-                                continue
-                        if options.filterSymbols:
-                            if lemma in symbols:
-                                if lemma == ',':
-                                    print "Coma , identificada"
-                                outputLine += token + ' '
-                                continue
-                        CRFtag = tagLine[idx_tagLine]
-                        if (tag not in labels) and (CRFtag != 'O'):
-                            print "*** CRF change token {} to {}".format(token, CRFtag)
-                            outputLine += word + '|' + lemma + '|' + CRFtag + ' '
-                        else:
-                            outputLine += word + '|' + lemma + '|' + tag + ' '
-                        idx_tagLine += 1
-                    sentencesOutputData.append(outputLine.rstrip())
-            with open(os.path.join(options.outputPath, file), "w") as oFile:
-                for line in sentencesOutputData:
-                    oFile.write(line + '\n')
-
-    print("Processing corpus done in: %fs" % (time() - t0))

@@ -198,8 +198,8 @@ if __name__ == "__main__":
 
 
     print("Reading corpus done in: %fs" % (time() - t0))
     print("Reading corpus done in: %fs" % (time() - t0))
 
 
-    print(sent2features(sentencesTrainingData[0])[0])
-    print(sent2features(sentencesTestData[0])[0])
+    #print(sent2features(sentencesTrainingData[0])[0])
+    #print(sent2features(sentencesTestData[0])[0])
     t0 = time()
     t0 = time()
 
 
     X_train = [sent2features(s) for s in sentencesTrainingData]
     X_train = [sent2features(s) for s in sentencesTrainingData]