word embeddings

+# missing word embeddings:
+29c
+14
+31
+26a
+beta1
+486
+profibrotic
+92a
+29a
+matricellular
+155
+13
+b1
+etiopathology
+nexin
+avb6
+21
+19
+acetylglucosaminidase
+326
+dermatan
+1b
+p38
+47
+68
+3p
+dedifferentiating
+alpha3beta1
+chymase
+2alpha
+90
+7d
+5100
+18a
+1a
+alpha3
+150
+1343
+140
+541
+fibrogenesis
+221
+mitophagy
+b4
+p63
+10
+5p
+haptotactic
+nonkinase
+farnesoid
+lymphopoietin
+7a
+18
+338
+1beta
+424
+199a
+154
+smad2
+17
+185
+bronchoalveolar
+101
+profibrogenic
+153
+gambogic
+ubiquitinating
+p110y
+200
+323a
+196a
+dysregulates
+fibrogenic
+salvianolic
+# missing MI weights:
+Tumor
+sTNFR
+Compromised
+Modulating
+Renin
+Invasive
+Cytokine
+D1
+C3aR
+Prostaglandin
+Diagnostic
+HLA
+Interstitial
+Transforming
+Phenotypes
+Up
+Clinical
+TGFb
+Interplay
+Animal
+Decoction
+Foxp3high
+Leucine
+CCL2
+SDKP
+IL
+Correct
+Elk1
+Participation
+Azithromycin
+Amplification
+1A
+Endothelin
+Kinase
+Possible
+Associated
+MicroRNA
+sL1
+Action
+For
+Development
+Establishment
+Extracellular
+Epstein
+MUM
+Serine
+Interactions
+Macrophage
+Pseudomonas
+Cytokines
+IGFBP
+Calu
+PI3K
+B4
+Chinese
+Cigarette
+BALF
+NK
+alphaEbeta7
+microRNAs
+Gene
+True
+Pneumonia
+CUX1
+miRNA
+Ubiquitin
+Wnt
+CDCP1
+Barr
+ORP150
+Curcumin
+aB
+Myofibroblast
+JNK
+Aortic
+L5
+Hsp90
+Smoke
+IFN
+Reactive
+Significance
+aVb6
+Th2
+Constitutive
+Melatonin
+Mediates
+AP
+Lindau
+ALK5
+AKT2
+EMT
+Reversion
+Patients
+Solution
+Focal
+Immunoglobulin
+RhoA
+Neutrophil
+BMPR2
+CXCL9
+Lower
+Olodaterol
+Lavage
+Induces
+Induced
+Beyond
+MMP
+Fstl1
+cAMP
+Aging
+SPARC
+Activity
+ECM
+Human
+Fibrotic
+Repression
+Prostatic
+NOX4
+Against
+Discovery
+Resveratrol
+Interleukin
+Deleted
+Differentiation
+Spiruchostatin
+Insulin
+PXS64
+MCTC
+HP
+Triptolide
+Values
+Differential
+Lysyl
+FGF
+Promote
+Yin
+Tissue
+BMP
+CAM
+Discoidin
+Overproduction
+Wilms
+Regulates
+Reduced
+Mesenchymal
+Inflammation
+PINK1
+Release
+E2
+CD44V6
+TGFbeta1
+Rg1
+H441
+kDa
+M2
+Expression
+Data
+Contribution
+Negative
+Nintedanib
+Pulmonary
+Emphysema
+Intrinsic
+17A
+Marks
+26S
+RXFP1
+Neovessel
+Genetic
+Protective
+Tensin
+Inducer
+Like
+Determining
+Increased
+Microsatellite
+Sphingosine
+TRPV4
+Club
+Methylation
+Phenoconversion
+Serpin
+Activated
+Muc5ac
+MyD88
+Glucagon
+IPF
+SIRT6
+Rapamycin
+Essential
+TNFalpha
+Corilagin
+Sorafenib
+Epithelial
+T869C
+Induction
+Long
+Wt1
+Molecules
+TGFBR2
+P110
+Nuclear
+Old
+Targeting
+WNT7B
+Thy
+Potential
+TGF
+Tubastatin
+Semaphorin
+Attenuating
+Smad
+Pigment
+Homolog
+Binding
+microRNA
+C57BL
+Regulating
+Implications
+Hydrogen
+BARD1
+A549
+Homeostasis
+Selectivity
+Medical
+Model
+Cytoskeletal
+Differing
+BMP3
+Enhances
+NADPH
+Fibrogenesis
+Defect
+Two
+FAK
+RNA
+Quantifying
+Epigenetic
+Profibrotic
+Ambroxol
+Trigger
+Titration
+Transcription
+Regulation
+Mitochondrial
+H1N1
+Recent
+BMPER
+PPARs
+VCAM
+Microsomal
+Hippel
+Renshen
+Absence
+Anchorage
+Applying
+Free
+OSF
+PGE
+Tannic
+Plasminogen
+TGFBR
+Channel
+Age
+Cell
+Connective
+Proteasomal
+RAGE
+Bach1
+Pirfenidone
+Outcomes
+GATA
+Small
+Autoimmunity
+III
+VEGF
+Control
+HSP27
+Cartilage
+Periostin
+Idiopathic
+COL1A1
+CBP
+Bronchoalveolar
+Crosstalk
+Amplified
+Evidence
+Simvastatin
+Sphingolipids
+Mechanisms
+JAK2
+Rats
+Mice
+Protease
+From
+LPA1
+Collagen
+Carbon
+Molecular
+Stat3
+Genomewide
+Stem
+S1P
+Novel
+EBV
+Serum
+Abrogation
+That
+Pingfei
+Stromal
+Current
+Molecule
+MAP3K19
+Decisive
+Protein
+Fluid
+HDAC4
+Angiotensin
+SOCS1
+Different
+Membrane
+Domain
+Secretory
+Signalling
+NCI
+Bax
+ADAM
+Are
+Beta1
+Activation
+Problem
+Prognostic
+II
+Sputum
+Phosphatase
+Inhibition
+Profile
+Dogs
+HRCT
+lncRNA
+Storage
+Nitrated
+Box
+Forkhead
+CREB
+Sirtuin
+Cryptogenic
+Decreased
+Inhibits
+Formation
+MK2
+Comparison
+Mediated
+Latent
+Recombinant
+Microencapsulation
+PHGDH
+Organizing
+Dysfunction
+Way
+Using
+Peripheral
+Markers
+MiR
+Anti
+Studies
+May
+Significant
+Morphogenic
+Low
+Lactic
+Overexpression
+Protects
+Arsenic
+Caveolin
+pH
+Inhibit
+Proteasome
+MicroRNAs
+Toll
+Herpes
+CTGF
+Normal
+Defective
+CD44
+Large
+Ligands
+Axis
+NH2
+Progression
+Smad3
+Phenotype
+Ets
+Identification
+kB
+Role
+Relation
+Mode
+Developmental
+Fibrosis
+Stanniocalcin
+WNT10A
+Integrated
+Syndecan
+Metalloproteinase
+TOB2
+USP11
+WISP1
+Dysregulated
+Th17
+Progressive
+Key
+Subpleural
+Mast
+Rho
+Growth
+Upregulation
+Alleviates
+Re
+Preventive
+ITGB6
+Fibroblasts
+ATG4B
+Comparative
+Cthrc1
+mRNA
+Peptide
+SNAI
+BM
+ATPase
+AKT
+Fibroblastic
+Matriptase
+Sub
+Sustained
+Pleiotropic
+New
+Regulator
+Receptor
+Therapeutic
+Vimentin
+IGF
+Cells
+LIGHT
+Production
+D2
+Dehydroepiandrosterone
+Lin28B
+Antifibrotic
+Raised
+Proliferation
+Dependent
+COL1
+Lysocardiolipin
+Epithelium
+STAT3
+Prevents
+Th1
+NF
+CCN5
+Snail
+Myogenic
+CD4
+Akt
+TGFb1
+Accelerated
+PDGF
+Intratracheal
+TGFB1
+Cysteine
+Oxidant
+Effect
+Reprogramming
+IIP
+MS80
+FOXF1
+Promotes
+Assessment
+BLM
+CC16
+BAL
+CD248
+Ginsenoside
+Secreted
+Association
+IQ
+mTORC2
+Established
+The
+Combined
+Jun
+UIP
+Sulf2
+Thalidomide
+Bioenergetics
+TNF
+CCN2
+NEU1
+Attenuates
+HMGA2
+Group
+Conversion
+Predisposition
+Transglutaminase
+Pathway
+Reviews
+Treg
+DDR2
+Autophagy
+Hyper
+Bile
+Sunitinib
+Stiffening
+Signal
+Resolution
+De
+Type
+Factor
+Smad2
+Single
+PPAR
+WNT5A
+Novo
+An
+EGFR
+Cub
+GLI
+HSP47
+Early
+ERK1
+TGFbeta
+Deficiency
+hydroxytryptamine2A
+BAX
+Inhibitory
+Integrin
+Suppression
+Shikonin
+SMAD3
+Effects
+Metformin
+F1
+MAPK
+Modulation
+Bleomycin
+Injury
+Elevated
+Cellular
+Radioligand
+Citrus
+TIAM1
+Subjects
+Lung
+ARPC2
+H19
+EZH2
+Pathways
+Is
+Microarray
+Fas
+CCN1
+Ac
+miRNAs
+Myofibroblasts
+FFPE
+Inhibitor
+During
+Matrix
+Nrf2
+Immunomodulation
+C5aR
+Gremlin
+High
+Concentration
+Evaluation
+Roles
+Number
+Bone
+ACLP
+Hypertension
+Lipogenic
+Uncoupling
+Signaling
+Lrp5
+Berberine
+A4
+CD11c
+miR
+Chop
+Galectin
+Alveolar
+Transition
+Plasma
+Impacts
+Smad4
+Its
+Pathogenesis
+Inappropriate
+Investigation
+Beta
+Ca
+ERK
+Deregulation
+MSCs
+PTEN
+Lipoxin
+Nitric
+C1q
+KCa3
+kappaB
+Involvement
+MCP
+Pleural
+EMMPRIN
+Smooth
+Synthesis
+Blockade
+Compared
+Transgelin

+# missing word embeddings:
+profibrogenic
+199a
+p38
+beta1
+68
+etiopathology
+1343
+lymphopoietin
+29c
+185
+5p
+17
+dermatan
+1a
+13
+424
+101
+p63
+140
+b1
+fibrogenic
+gambogic
+nonkinase
+21
+alpha3
+154
+2alpha
+chymase
+18a
+196a
+5100
+smad2
+7d
+541
+1b
+acetylglucosaminidase
+326
+47
+dysregulates
+92a
+200
+29a
+90
+31
+mitophagy
+b4
+3p
+nexin
+dedifferentiating
+155
+150
+ubiquitinating
+10
+486
+19
+avb6
+fibrogenesis
+farnesoid
+haptotactic
+alpha3beta1
+14
+323a
+matricellular
+7a
+profibrotic
+bronchoalveolar
+26a
+18
+salvianolic
+338
+1beta
+p110y
+221
+153
+# missing MI weights:
+Compared
+Are
+True
+Ambroxol
+Diagnostic
+Alveolar
+Smad2
+Neovessel
+RXFP1
+Normal
+Shikonin
+Spiruchostatin
+ORP150
+Tubastatin
+That
+Bone
+WISP1
+Wt1
+Smad4
+ECM
+Syndecan
+Radioligand
+BAX
+De
+FAK
+Prevents
+Endothelin
+kB
+Promote
+Reversion
+Determining
+Cytokines
+Glucagon
+Pathways
+Myogenic
+SOCS1
+Investigation
+Regulating
+Targeting
+Decoction
+Stromal
+PPARs
+HP
+Focal
+Transgelin
+Association
+Effects
+EGFR
+Gene
+Human
+Metalloproteinase
+Lower
+Rg1
+Binding
+Therapeutic
+Mesenchymal
+CD248
+Formation
+Cysteine
+Caveolin
+Type
+Signaling
+Molecular
+Alleviates
+Early
+Transforming
+Potential
+COL1A1
+Plasminogen
+Factor
+Semaphorin
+CC16
+Integrated
+Like
+Stat3
+Tissue
+Signalling
+Phenotype
+TGFBR2
+Homolog
+III
+MiR
+Lactic
+Pulmonary
+Fibroblastic
+Defect
+Molecules
+Yin
+MCP
+MicroRNA
+LIGHT
+Beyond
+Recombinant
+Compromised
+Ginsenoside
+P110
+Production
+Lipogenic
+HRCT
+Its
+Implications
+Problem
+NH2
+Fibrogenesis
+TOB2
+SMAD3
+Lin28B
+Significance
+Differential
+Cytokine
+Progressive
+Solution
+Identification
+Peptide
+Synthesis
+Protein
+Macrophage
+PDGF
+Repression
+CREB
+Cellular
+Plasma
+A4
+Latent
+Wnt
+Proteasome
+Kinase
+Proteasomal
+Pathway
+Sirtuin
+MSCs
+D2
+Absence
+Cells
+Thalidomide
+Regulation
+Hippel
+pH
+Chinese
+Th17
+Uncoupling
+Periostin
+Promotes
+Amplification
+Smad
+Profibrotic
+Patients
+Subpleural
+Cytoskeletal
+Progression
+Lavage
+Angiotensin
+Domain
+Peripheral
+Inhibitor
+Associated
+Involvement
+Serum
+Toll
+Activation
+SPARC
+Attenuating
+Resveratrol
+PI3K
+Induced
+Matrix
+Leucine
+BALF
+Defective
+Negative
+JNK
+Receptor
+Reprogramming
+CD11c
+Nuclear
+hydroxytryptamine2A
+Is
+Sustained
+Essential
+Beta
+CBP
+miRNA
+Pathogenesis
+Aging
+Neutrophil
+Nitrated
+Resolution
+Signal
+Low
+New
+Contribution
+Homeostasis
+HLA
+Sub
+26S
+HMGA2
+Treg
+Significant
+Blockade
+HSP27
+Clinical
+Th1
+Triptolide
+Dependent
+Inflammation
+VEGF
+PINK1
+H1N1
+E2
+Discovery
+Interplay
+Secretory
+CCL2
+Dehydroepiandrosterone
+Modulation
+Mechanisms
+MMP
+Mediated
+H19
+Morphogenic
+Ac
+Corilagin
+Tannic
+Hypertension
+WNT10A
+MCTC
+Possible
+Studies
+Pigment
+Wilms
+Hydrogen
+Azithromycin
+Number
+Transglutaminase
+Outcomes
+NCI
+RNA
+WNT5A
+Mice
+Methylation
+Novel
+Nitric
+Cell
+HSP47
+TRPV4
+Protease
+Release
+For
+Ligands
+TGF
+Epithelium
+Aortic
+NADPH
+Herpes
+Bach1
+Ca
+Dysregulated
+Membrane
+TGFBR
+Connective
+Decreased
+TIAM1
+Serpin
+Fstl1
+CCN1
+BLM
+Sphingosine
+C57BL
+Data
+Dogs
+Organizing
+IGF
+COL1
+CD44V6
+BMPER
+ARPC2
+Galectin
+Lindau
+Inappropriate
+Microencapsulation
+Oxidant
+M2
+Renshen
+Sputum
+Snail
+Inducer
+Prognostic
+Storage
+MAPK
+Citrus
+PPAR
+Collagen
+Matriptase
+Arsenic
+Long
+F1
+Deleted
+Genomewide
+PXS64
+Lysyl
+ERK
+Calu
+MyD88
+aB
+Activity
+Applying
+Secreted
+Control
+BM
+Mitochondrial
+Age
+EZH2
+Overproduction
+Way
+The
+DDR2
+1A
+Rho
+Bronchoalveolar
+TGFbeta1
+Akt
+ERK1
+Novo
+Curcumin
+FGF
+C5aR
+17A
+Lysocardiolipin
+Protects
+Predisposition
+Thy
+C1q
+Nintedanib
+High
+KCa3
+Olodaterol
+Reviews
+Proliferation
+Immunomodulation
+Attenuates
+Gremlin
+Cthrc1
+Vimentin
+Elk1
+Lipoxin
+IQ
+Roles
+BAL
+Relation
+Autophagy
+IGFBP
+Inhibition
+BMP
+Anchorage
+ITGB6
+Mode
+Modulating
+miRNAs
+Inhibit
+PHGDH
+Up
+Phosphatase
+TGFbeta
+C3aR
+Pseudomonas
+Comparative
+Reduced
+Crosstalk
+Conversion
+Injury
+Phenotypes
+CD4
+MicroRNAs
+Regulates
+TNFalpha
+Pirfenidone
+Raised
+Old
+Cartilage
+Prostaglandin
+BMP3
+BARD1
+Deficiency
+RhoA
+AKT2
+NF
+Cigarette
+GATA
+MAP3K19
+sTNFR
+NK
+Different
+Subjects
+Autoimmunity
+Mast
+Single
+Microsomal
+WNT7B
+MK2
+TGFb1
+CCN2
+Growth
+Prostatic
+PGE
+Abrogation
+Stem
+EBV
+Microsatellite
+Nrf2
+Epstein
+Club
+TGFB1
+ATG4B
+Differentiation
+EMMPRIN
+Smad3
+Genetic
+Sorafenib
+IFN
+Impacts
+Key
+Activated
+AKT
+Th2
+PTEN
+USP11
+IL
+Effect
+HDAC4
+Free
+Sunitinib
+Established
+Fluid
+Decisive
+Inhibits
+Marks
+mTORC2
+Trigger
+Concentration
+Intratracheal
+Participation
+Against
+Expression
+kappaB
+Role
+Rats
+Intrinsic
+Epigenetic
+Smooth
+NOX4
+Tumor
+Rapamycin
+microRNA
+Overexpression
+Current
+Muc5ac
+Combined
+II
+D1
+Accelerated
+Regulator
+Pleural
+Invasive
+alphaEbeta7
+From
+MUM
+Immunoglobulin
+Beta1
+Small
+Sphingolipids
+Stiffening
+FFPE
+miR
+LPA1
+B4
+Two
+Extracellular
+Enhances
+Evaluation
+Recent
+Elevated
+Re
+IIP
+CD44
+Interactions
+CXCL9
+Protective
+Ets
+Preventive
+Establishment
+ALK5
+Increased
+Values
+kDa
+Large
+May
+Transcription
+ACLP
+Cryptogenic
+Ubiquitin
+GLI
+L5
+Discoidin
+Bleomycin
+Carbon
+Renin
+CUX1
+Correct
+Constitutive
+SNAI
+Bile
+Assessment
+Fibrotic
+Differing
+Development
+Channel
+Simvastatin
+CAM
+Fibroblasts
+Melatonin
+SIRT6
+STAT3
+Tensin
+Pingfei
+Stanniocalcin
+Bax
+Group
+mRNA
+Selectivity
+Emphysema
+Barr
+Berberine
+Metformin
+Hsp90
+CDCP1
+T869C
+EMT
+ADAM
+Cub
+Pneumonia
+Induces
+FOXF1
+Upregulation
+H441
+RAGE
+Myofibroblasts
+JAK2
+Interstitial
+Amplified
+Fibrosis
+Microarray
+Developmental
+CTGF
+Serine
+Integrin
+AP
+Fas
+During
+CCN5
+Insulin
+Pleiotropic
+TGFb
+Evidence
+Phenoconversion
+Comparison
+Smoke
+Box
+microRNAs
+Anti
+Suppression
+A549
+Chop
+Jun
+Myofibroblast
+Dysfunction
+Axis
+IPF
+MS80
+S1P
+Inhibitory
+Interleukin
+Action
+Bioenergetics
+Transition
+Hyper
+Lrp5
+Model
+cAMP
+Medical
+SDKP
+UIP
+Animal
+Forkhead
+lncRNA
+Lung
+Antifibrotic
+Induction
+Titration
+Epithelial
+OSF
+ATPase
+Reactive
+TNF
+aVb6
+Molecule
+NEU1
+Deregulation
+Idiopathic
+An
+Using
+Quantifying
+BMPR2
+Foxp3high
+sL1
+Profile
+Sulf2
+Mediates
+Markers
+VCAM

+#!/usr/bin/python
+# -*- coding: latin-1 -*-
+# Python2.7
+
+import numpy as np
+import logging
+import os
+from functools import partial
+from pdb import set_trace as st
+logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
+                    level=logging.INFO)
+
+
+class wisse(object):
+    """ Both the TFIDFVectorizer and the word embedding model must be pretrained, either from the local 
+        sentence corpus or from model persintence.
+    """
+    def __init__(self, embeddings, vectorizer, tf_tfidf, combiner = "sum"):
+        self.tokenize = vectorizer.build_tokenizer()
+        self.tfidf = vectorizer
+        self.embedding = embeddings
+        self.pred_tfidf = tf_tfidf
+        if combiner.startswith("avg"):
+            self.comb = partial(np.mean, axis = 0)
+        else:
+            self.comb = partial(np.sum, axis = 0)
+
+
+    def fit(self, X, y = None): # Scikit-learn template
+        if isinstance(X, list):
+            self.sentences = X
+
+        return self
+
+
+    def transform(self, X):
+        if isinstance(X, list):
+            return self.fit(X)
+
+        elif isinstance(X, str):
+            return self.infer_sentence(X)
+
+    
+    def fit_transform(self, X, y=None):
+        return self.transform(X)
+
+
+    def infer_sentence(self, sent):
+        ss = self.tokenize(sent)
+        missing_bow = []
+        missing_cbow = []
+        series = {}
+
+        if not ss == []:
+            self.weights, m = self.infer_tfidf_weights(ss)
+        else:
+            return None
+
+        missing_bow += m
+
+        for w in self.weights:
+            try:
+                series[w] = (self.weights[w], self.embedding[w])
+            except KeyError:
+                series[w] = None
+                missing_cbow.append(w)
+                continue
+            except IndexError:
+                continue
+
+        if self.weights == {}: return None
+        # Embedding the sentence... :
+        sentence = np.array([series[w][1] for w in series if not series[w] is None])
+        series = {}
+
+        return missing_cbow, missing_bow, self.comb(sentence)
+
+
+    def infer_tfidf_weights(self, sentence):
+        existent = {}
+        missing = []
+
+        if not self.tfidf:
+            for word in sentence:
+                existent[word] = 1.0
+
+            return existent, missing
+
+        if self.pred_tfidf:
+            unseen = self.tfidf.transform([" ".join(sentence)]).toarray()
+            for word in sentence:
+                try:
+                    existent[word] = unseen[0][self.tfidf.vocabulary_[word]]
+                except KeyError:
+                    missing.append(word)
+                    continue
+        else:
+            for word in sentence:
+                try:
+                    weight = vectorizer.idf_[vectorizer.vocabulary_[word]]
+                    existent[word] = weight if weight > 2 else 0.01
+                except KeyError:
+                    missing.append(word)
+                    continue
+
+        return existent, missing
+
+
+    def __iter__(self):
+        for s in self.sentences:
+            yield self.transform(s)
+
+
+def save_dense(directory, filename, array):
+    directory=os.path.normpath(directory) + '/'
+#    try:
+    if filename.isalpha():
+            np.save(directory + filename, array)
+    else:
+            return None
+#    except UnicodeEncodeError:
+#        return None    
+
+def load_dense(filename):
+    return np.load(filename)
+
+
+def load_sparse_bsr(filename):
+    loader = np.load(filename) 
+    return bsr_matrix((loader['data'], loader['indices'], loader['indptr']),                       
+        shape=loader['shape']) 
+
+
+def save_sparse_bsr(directory, filename, array):     
+# note that .npz extension is added automatically     
+    directory=os.path.normpath(directory) + '/'
+    if word.isalpha():
+        array=array.tobsr()
+        np.savez(directory + filename, data=array.data, indices=array.indices,              
+            indptr=array.indptr, shape=array.shape) 
+    else:
+        return None
+
+
+class vector_space(object):
+    def __init__(self, directory, sparse = False):
+        self.sparse = sparse 
+        ext = ".npz" if sparse else ".npy"
+        if directory.endswith(".tar.gz"):
+            self._tar = True
+            import tarfile
+            self.tar = tarfile.open(directory)
+            file_list = self.tar.getnames() #[os.path.basename(n) for n in self.tar.getnames()]
+            self.words = {os.path.basename(word).replace(ext, ''): word 
+                                                    for word in file_list}
+        else:
+            self._tar = False
+            directory = os.path.normpath(directory) + '/' 
+            file_list = os.listdir(directory)
+            self.words = {word.replace(ext, ''): directory + word 
+                                                for word in file_list}
+
+
+    def __getitem__(self, item):
+        if self.sparse:
+            if self._tar:
+                member = self.tar.getmember(self.words[item])
+                word = self.tar.extractfile(member)
+            else:
+                word = self.words[item]
+            #return load_sparse_bsr(self.words[item])
+            return load_sparse_bsr(word) 
+
+        else:
+            if self._tar:
+                member = self.tar.getmember(self.words[item])
+                word = self.tar.extractfile(member)
+            else:
+                word = self.words[item]
+            #return load_sparse_bsr(self.words[item])
+            return load_dense(word)
+
+
+def keyed2indexed(keyed_model, output_dir = "word_embeddings/", parallel = True, n_jobs = -1):
+    output_dir = os.path.normpath(output_dir) + '/'
+    if not os.path.exists(output_dir):
+        os.makedirs(output_dir)
+
+    if parallel:
+        from joblib import Parallel, delayed
+
+        Parallel(n_jobs = n_jobs, verbose = 10)(delayed(save_dense)(output_dir, word, keyed_model[word]) 
+                                                        for word, _ in keyed_model.vocab.items())
+    else:
+        for word, _ in keyed_model.vocab.items():
+            save_dense(output_dir, word, keyed_model[word])
+    
+
+class streamer(object):
+    def __init__(self, file_name):
+        self.file_name = file_name
+
+    def __iter__(self):
+        for s in open(self.file_name):
+            yield s.strip()

+#!/usr/bin/python
+# -*- coding: latin-1 -*-
+# Python2.7
+from gensim.models.keyedvectors import KeyedVectors as vDB
+from sklearn.feature_extraction.text import TfidfVectorizer
+import numpy as np
+#import numexpr as ne
+import argparse
+#import _pickle as pickle
+#import cPickle as pickle
+import logging
+import os
+from functools import partial
+import wisse
+
+
+load_vectors = vDB.load_word2vec_format
+
+logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
+                    level=logging.INFO)
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser(description="""This use example shows sentence 
+        embedding by using WISSE. The input is a text file which has a sentece in 
+        each of its rows. The output file has two tab-separated columns: the index
+        line of the sentece in the input file and the sentence vector representation
+        .""")
+    parser.add_argument("--idfmodel", help = """Input file containing IDF
+                                        pre-trained weights. If not provided,
+                                        all word vector weights will be set to
+                                        1.0. If 'local' tf-idf weights will be
+                                        computed locally from the input file
+                                        (pickled sklearn object).""",
+                                        default = None)
+    parser.add_argument("--embedmodel", help = """Input file containing word
+                                            embeddings model (binary and text
+                                            are allowed).""", required = True)
+    parser.add_argument("--output", help = """Output file containing the sentence
+                                            embeddings.""", default = "")
+    parser.add_argument("--input", help = """Input file containing a sentence
+                                            by row.""", required = True)
+    parser.add_argument("--comb", help = """Desired word vector combination for
+                                        sentence representation {sum, avg}.
+                                        (default = 'sum')""", default = "sum")
+    parser.add_argument("--suffix", nargs = '?', help = """A suffix to be added
+                                        to the output file (default = '')""",
+                                            default = "", required = False)
+    parser.add_argument("--tfidf", help="""To predict TFIDF complete weights
+                                        ('tfidf') or use only partial IDFs
+                                        ('idf'). (default = 'tfidf')""",
+                                        default = "tfidf")
+    parser.add_argument("--localw", help = """TFIDF word vector weights
+                                    computed locally from the input file of
+                                    sentences {freq, binary, sublinear}
+                                    (default='none').""", default = "none")
+    parser.add_argument("--stop", help = """Toggles stripping stop words in
+                                    locally computed word vector weights.""",
+                                                        action = "store_true")
+    parser.add_argument("--format", help = """The format of the embedding model
+                                     file: {binary, text, wisse}. 
+                                    default = 'binary'""", default = "binary")
+    args = parser.parse_args()
+
+
+    if not args.format.startswith("wisse"):
+        if not os.path.isfile(args.embedmodel):
+            logging.info("""Embedding model file does not exist (EXIT):
+                \n%s\n ...""" % args.embedmodel)
+            exit()
+    elif not os.path.exists(args.embedmodel):
+        logging.info("""Embedding model directory does not exist (EXIT):
+                \n%s\n ...""" % args.embedmodel)
+        exit()
+
+    if not os.path.isfile(args.idfmodel) and not args.idfmodel.startswith("local"):
+        logging.info("""IDF model file does not exist (EXIT):
+                \n%s\n ...""" % args.idfmodel)
+        exit()
+    if not os.path.isfile(args.input):
+        logging.info("""Input file does not exist (EXIT):
+                \n%s\n ...""" % args.input)
+        exit()
+    if args.output != "":
+        if os.path.dirname(args.output) != "":
+            if not os.path.exists(os.path.dirname(args.output)):
+                logging.info("""Output directory does not exist (EXIT):
+                    \n%s\n ...""" % args.output)
+                exit()
+            else:
+                output_name = args.output
+        else:
+            output_name = args.output
+    else:
+        suffix = "_".join([embedding_name,
+            args.comb,
+            args.tfidf,
+            "local" if args.idfmodel.startswith("local") else tfidf_name,
+            args.suffix]).strip("_")
+        output_name = args.input + ".output_" + suffix
+
+
+    if args.tfidf.startswith("tfidf"):
+        pred_tfidf = True
+    elif args.tfidf.startswith("idf"):
+        pred_tfidf = False
+    else:
+        pred_tfidf = False
+        tfidf = False
+
+    vectorizer = TfidfVectorizer(min_df = 1,
+                encoding = "latin-1",
+                decode_error = "replace",
+                lowercase = True,
+                binary = True if args.localw.startswith("bin") else False,
+                sublinear_tf = True if args.localw.startswith("subl") else False,
+                stop_words = "english" if args.stop else None)
+
+    sentences = wisse.streamer(args.input)
+
+    if args.idfmodel.startswith("local"):
+        logging.info("Fitting local TFIDF weights from: %s ..." % args.input)
+        tfidf = vectorizer.fit(sentences)
+
+    elif os.path.isfile(args.idfmodel):
+        logging.info("Loading global TFIDF weights from: %s ..." % args.idfmodel)
+        with open(args.idfmodel, 'rb') as f:
+            tfidf = pickle.load(f)#, encoding = 'latin-1')
+
+    else:
+        tfidf = False
+
+    try:
+        if args.format.startswith("bin"):
+            embedding = load_vectors(args.embedmodel, binary = True,
+                                                        encoding = "latin-1")
+        elif args.format.startswith("tex"):
+            embedding = load_vectors(args.embedmodel, binary = False,
+                                                        encoding = "latin-1")
+        else:
+            embedding = wisse.vector_space(args.embedmodel, sparse = False)
+
+    except:
+        logging.info(
+            """Error while loading word embedding model. Verify if the file
+            is broken (EXIT)...\n%s\n""" % args.embedmodel)
+        exit()
+
+    embedding_name = os.path.basename(args.embedmodel).split(".")[0]
+    tfidf_name = os.path.basename(args.idfmodel).split(".")[0]
+
+    missing_bow = []    # Stores missing words in the TFIDF model
+    missing_cbow = []   # Stores missing words in the W2V model
+    sidx = 0 # The index of the sentence according to the input file
+    logging.info("\n\nEmbedding sentences and saving then to a the output file..\n%s\n" % output_name)
+
+    with open(output_name, "w") as fo:
+        for sent in sentences:
+            sidx += 1
+            series = wisse.wisse(embeddings = embedding, vectorizer = tfidf, 
+                                                tf_tfidf = True, combiner='sum')
+            try:
+                mc, mb, vector = series.transform(sent)
+            except TypeError:
+                continue
+
+            # At this point you can use the embedding 'vector' for any application as it
+            # is a numpy array. Also you can simply save the vectors in text format as
+            # follows:
+            missing_cbow += mc
+            missing_bow += mb
+            fo.write("%d\t%s\n" % (sidx, np.array2string(vector,
+                                formatter = {'float_kind':lambda x: "%.6f" % x},
+                                max_line_width = 20000).strip(']').strip('[') ))
+
+    missing_name = (os.path.basename(args.input).split(".")[0] + "_" +
+                                                        embedding_name + "_" +
+                                                        tfidf_name + ".missing")
+    logging.info("\n\nSaving missing vocabulary to %s ..\n\n" % missing_name)
+
+    with open(missing_name, "w") as f:
+        f.write("# missing word embeddings:\n")
+        for w in set(missing_cbow):
+            f.write("%s\n" % w)
+
+        f.write("# missing MI weights:\n")
+        for w in set(missing_bow):
+            f.write("%s\n" % w)
+
+    logging.info("FINISHED! \n")