Annot = Annotation.Annotation()
Annot.annotationID = ann[0]
Annot.Content = ann[1]
Annot.Start = ann[2]
Annot.End = ann[3]
Annot.AnnotationCID = ann[4]
Annot.AnnotationDesc =ann[5]
Annot.AgentName = ann[6]
Annot.AgentType = ann[7]
Annot.AnnotationURL = ann[8]
cell_annotations.append(Annot)
cell.Annotations = cell_annotations
cells.append(cell)
return cells
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","ddi_data", )
queryclass.CreateAdditionalDDITables()
cursor = queryclass.db.cursor()
#Get tables
sql = """SELECT idArticle,Title,SpecId,idTable,TableOrder,TableCaption,Section FROM ddi_data.article inner join
arttable on idArticle=Article_idArticle where Section='34073-7'"""
#Get cells and annotations that contain potential DDIs
#sql = """select annotation.Content,AnnotationDescription,Table_idTable,RowN,ColumnN,TableOrder,idArticle,Title,SpecId,
#AnnotationID from annotation inner join cell on cell.idCell=annotation.Cell_idCell inner join arttable on
#arttable.idTable=cell.Table_idTable inner join article on article.idArticle = arttable.Article_idArticle
#where Section='34073-7' and AnnotationDescription IN ('Pharmacologic Substance (phsu)','Biologically Active Substance (bacs)',
#'Organic Chemical (orch)','Hazardous or Poisonous Substance (hops)','Carbohydrate (carb)','Element, Ion, or Isotope (elii)',
#'Nucleic Acid, Nucleoside, or Nucleotide (nnon)','Indicator, Reagent, or Diagnostic Aid (irda)',
#'Biomedical or Dental Material (bodm)', 'Inorganic Chemical (inch)','Hormone (horm)')
#"""
cursor.execute(sql)
Annot.End = ann[3]
Annot.AnnotationCID = ann[4]
Annot.AnnotationDesc = ann[5]
Annot.AgentName = ann[6]
Annot.AgentType = ann[7]
Annot.AnnotationURL = ann[8]
cell_annotations.append(Annot)
cell.Annotations = cell_annotations
cells.append(cell)
return cells
if __name__ == "__main__":
queryclass = QueryDBCalss(
"localhost",
"root",
"",
"table_db_amia",
)
queryclass.CreateAdditionalDDITables()
cursor = queryclass.db.cursor()
#Get tables
sql = """SELECT idArticle,Title,SpecId,idTable,TableOrder,TableCaption,Section FROM table_db_amia.article inner join
arttable on idArticle=Article_idArticle where Section='34073-7'"""
#Get cells and annotations that contain potential DDIs
#sql = """select annotation.Content,AnnotationDescription,Table_idTable,RowN,ColumnN,TableOrder,idArticle,Title,SpecId,
#AnnotationID from annotation inner join cell on cell.idCell=annotation.Cell_idCell inner join arttable on
#arttable.idTable=cell.Table_idTable inner join article on article.idArticle = arttable.Article_idArticle
#where Section='34073-7' and AnnotationDescription IN ('Pharmacologic Substance (phsu)','Biologically Active Substance (bacs)',
#'Organic Chemical (orch)','Hazardous or Poisonous Substance (hops)','Carbohydrate (carb)','Element, Ion, or Isotope (elii)',
#'Nucleic Acid, Nucleoside, or Nucleotide (nnon)','Indicator, Reagent, or Diagnostic Aid (irda)',
#'Biomedical or Dental Material (bodm)', 'Inorganic Chemical (inch)','Hormone (horm)')
'''
Created on 2 Mar 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db" )
queryclass.DeleteAttribute("BMI")
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
for row in results:
articleIds.append(row[0])
del results
#articleIds = [1501]
for id in articleIds:
results = queryclass.getArticleTables(id)
tables = []
for t in results:
table = Table()
table.tableId = t[0]
table.tableOrder = t[1]
table.tableCaption = t[2]
table.tableFooter = t[3]
table.StructureType = t[4]
'''
Created on 18 Oct 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db_amia", )
queryclass.CreateAdditionalDDITables()
cursor = queryclass.db.cursor()
d = {}
with open("Categories.txt") as f:
for line in f:
spl = line.split('\t')
print spl[0]
d[spl[0].lower()] = spl[1].replace('\n','').lower()
print d
sql = """select Content,Table_idTable,RowN,ColumnN,TableOrder,idArticle,Title,SpecId,CellRole_idCellRole from cell inner join arttable on arttable.idTable=cell.Table_idTable inner join article on
article.idArticle = arttable.Article_idArticle inner join cellroles on cellroles.Cell_idCell=cell.idCell where Section='34073-7'"""
cursor.execute(sql)
results = cursor.fetchall()
columnOfDrugs = -1
isfirst = False
for res in results:
# -*- coding: utf-8 -*-
'''
Created on 26 Feb 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__ == "__main__":
queryclass = QueryDBCalss("localhost", "root", "", "table_db")
queryclass.ClearCreatedTables()
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
PMCs = []
for row in results:
articleIds.append(row[0])
PMCs.append(row[1])
del results
l = 0
#articleIds = [5531]
for id in articleIds:
results = queryclass.getArticleTablesWithPragmatic(
id, "BaselineCharacteristic")
tables = []
for t in results:
table = Table()
#!/usr/bin/env python
# -*- coding: utf-8 -*-
'''
Created on Apr 14, 2016
@author: Nikola
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db" )
results = queryclass.getDataForDevDataset()
target = open("developmentCellDataset.csv", 'w')
target.write("ArticleId,PMCid,TableName,SpecPragmatics,CellContent,Header,Stub,SuperRow,rowN,columnN,function,class\n")
for res in results:
idArticle = res[0]
PMCid = res[1]
idTable = res[2]
TableOrder = res[3]
SpecPragmatic = res[4]
idCell = res[5]
CellType = res[6]
RowN = res[7]
ColumnN =res[8]
Content = res[9]
Header = res[10]
Stub = res[11]
#!/usr/bin/env python
# -*- coding: utf-8 -*-
'''
Created on 7 Apr 2016
@author: mbaxknm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
from collections import Counter
import re
if __name__ == "__main__":
queryclass = QueryDBCalss("localhost", "root", "", "table_db")
queryclass.ClearCreatedTables()
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
for row in results:
articleIds.append(row[0])
del results
#articleIds = [2418]
for id in articleIds:
results = queryclass.getArticleTablesWithPragmatic(id, "AdverseEvent")
tables = []
for t in results:
table = Table()
table.tableId = t[0]
table.tableOrder = t[1]
'''
Created on 22 Aug 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
from AnalyzePattern import GetMean,GetRange
import re
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db", )
queryclass.DeleteAttribute("Age")
queryclass.CreateAdditionalTables()
results = queryclass.getCellsWithMetaMapAnnotation("BaselineCharacteristic","orga")
lastCellID = -1
for res in results:
CellID = res[0]
if(CellID==lastCellID):
continue
TableID = res[3]
RowN = res[4]
ColumtnN = res[5]
Content = res[9]
Header = res [10]
Stub = res[11]
SuperRow = res[12]
AnnotationContent = res[14]
AnnotationDesc = res[19]
'''
Created on 11 Apr 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db" )
queryclass.DeleteAttribute("BMI")
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
for row in results:
articleIds.append(row[0])
del results
for id in articleIds:
results = queryclass.getArticleTables(id)
tables = []
for t in results:
table = Table()
table.tableId = t[0]
table.tableOrder = t[1]
table.tableCaption = t[2]
table.tableFooter = t[3]
table.StructureType = t[4]
table.PrgamaticType = t[5]
from QueryDBClass import QueryDBCalss
queryclass = QueryDBCalss(
"localhost",
"root",
"",
"table_db",
)
cursor = queryclass.db.cursor()
#Get tables
sql = """SELECT Content FROM table_db.article inner join arttable on arttable.Article_idArticle=article.idArticle inner
join cell on arttable.idTable=cell.Table_idTable where Title like '%asthma%' or Title like '%Asthma%' or Abstract like
'%asthma%' or Abstract like '%Asthma%';"""
cursor.execute(sql)
results = cursor.fetchall()
file = open("content_asthma.txt", "w")
for res in results:
file.write(res[0].encode('utf-8') + '\n')
file.close()
print "Done Asthma"
sql = """SELECT Content FROM table_db.article inner join arttable on arttable.Article_idArticle=article.idArticle inner
join cell on arttable.idTable=cell.Table_idTable where Title like '%COPD%' or Title like '%copd%' or Abstract like
'%COPD%' or Abstract like '%copd%' or Title like '%chronic obstructive pulmonary disease%' or Title like '%Chronic obstructive pulmonary disease%' or
Abstract like '%Chronic obstructive pulmonary disease%' or Abstract like "%chronic obstructive pulmonary disease%";"""
cursor.execute(sql)
results = cursor.fetchall()
file = open("content_copd.txt", "w")
for res in results:
file.write(res[0].encode('utf-8') + '\n')
#!/usr/bin/env python
# -*- coding: utf-8 -*-
'''
Created on 2 Mar 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
from AnalyzePattern import GetMean,GetRange
import re
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db", )
queryclass.DeleteAttribute("Age")
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
PMCs = []
for row in results:
articleIds.append(row[0])
PMCs.append(row[1])
del results
#articleIds = [1252]
l = 0
for id in articleIds:
results = queryclass.getArticleTablesWithPragmatic(id,"BaselineCharacteristic")
tables = []
for t in results:
'''
Created on 2 Mar 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db" )
queryclass.DeleteAttribute("Age")
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
for row in results:
articleIds.append(row[0])
del results
for id in articleIds:
results = queryclass.getArticleTables(id)
tables = []
for t in results:
table = Table()
table.tableId = t[0]
table.tableOrder = t[1]
table.tableCaption = t[2]
table.tableFooter = t[3]
table.StructureType = t[4]
table.PrgamaticType = t[5]
#!/usr/bin/env python
# -*- coding: utf-8 -*-
'''
Created on Apr 14, 2016
@author: Nikola
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__ == "__main__":
queryclass = QueryDBCalss("localhost", "root", "", "table_db")
results = queryclass.getDataForDevDataset()
target = open("developmentCellDataset.csv", 'w')
target.write(
"ArticleId,PMCid,TableName,SpecPragmatics,CellContent,Header,Stub,SuperRow,rowN,columnN,function,class\n"
)
for res in results:
idArticle = res[0]
PMCid = res[1]
idTable = res[2]
TableOrder = res[3]
SpecPragmatic = res[4]
idCell = res[5]
CellType = res[6]
RowN = res[7]
ColumnN = res[8]
Content = res[9]
#!/usr/bin/env python
# -*- coding: utf-8 -*-
'''
Created on 7 Apr 2016
@author: mbaxknm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
from collections import Counter
import re
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db" )
queryclass.ClearCreatedTables()
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
for row in results:
articleIds.append(row[0])
del results
articleIds = [1334]
for id in articleIds:
results = queryclass.getArticleTablesWithPragmatic(id,"AdverseEvent")
tables = []
for t in results:
table = Table()
table.tableId = t[0]
table.tableOrder = t[1]
'''
Created on 11 Apr 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__ == "__main__":
queryclass = QueryDBCalss("localhost", "root", "", "table_db")
queryclass.DeleteAttribute("BMI")
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
for row in results:
articleIds.append(row[0])
del results
for id in articleIds:
results = queryclass.getArticleTables(id)
tables = []
for t in results:
table = Table()
table.tableId = t[0]
table.tableOrder = t[1]
table.tableCaption = t[2]
table.tableFooter = t[3]
table.StructureType = t[4]
table.PrgamaticType = t[5]
'''
Created on 2 Mar 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__ == "__main__":
queryclass = QueryDBCalss("localhost", "root", "", "table_db")
queryclass.DeleteAttribute("BMI")
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
for row in results:
articleIds.append(row[0])
del results
#articleIds = [1501]
for id in articleIds:
results = queryclass.getArticleTables(id)
tables = []
for t in results:
table = Table()
table.tableId = t[0]
table.tableOrder = t[1]
table.tableCaption = t[2]
table.tableFooter = t[3]
table.StructureType = t[4]
'''
Created on 2 Mar 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
from AnalyzePattern import GetMean, GetRange
import re
if __name__ == "__main__":
queryclass = QueryDBCalss(
"localhost",
"root",
"",
"table_db",
)
queryclass.DeleteAttribute("Age")
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
PMCs = []
for row in results:
articleIds.append(row[0])
PMCs.append(row[1])
del results
#articleIds = [1252]
l = 0
for id in articleIds:
results = queryclass.getArticleTablesWithPragmatic(
# -*- coding: utf-8 -*-
'''
Created on 26 Feb 2016
@author: mbaxkhm4
Created at the University of Manchester, School of Computer Science
Licence GNU/GPL 3.0
'''
from QueryDBClass import QueryDBCalss
from Data.Table import Table
import re
if __name__=="__main__":
queryclass = QueryDBCalss("localhost","root","","table_db" )
queryclass.ClearCreatedTables()
queryclass.CreateAdditionalTables()
results = queryclass.getArticles()
articleIds = []
PMCs = []
for row in results:
articleIds.append(row[0])
PMCs.append(row[1])
del results
l=0
#articleIds = [5531]
for id in articleIds:
results = queryclass.getArticleTablesWithPragmatic(id,"BaselineCharacteristic")
tables = []
for t in results:
table = Table()
table.tableId = t[0]