Python PassingData.target_id_set方法代码示例

# 需要导入模块: from pymodule import PassingData [as 别名]
# 或者: from pymodule.PassingData import target_id_set [as 别名]
	def getStrainidTargetidFromFile(self, db, QC_method_id, input_fname, max_mismatch_rate, min_no_of_non_NAs=20):
		"""
		2008-09-10
			column in input_fname is determined on the fly
		2008-08-29
			to get strain id and target id set from the qc_cross_match result file.
		"""
		sys.stderr.write("Getting set of strain_id & target_id ... \n")
		reader = csv.reader(open(input_fname), delimiter='\t')
		#figure out which variable is in which column
		header = reader.next()
		col_name2index = {}
		for i in range(len(header)):
			column_name = header[i]
			col_name2index[column_name] = i
		
		strain_id_set = Set()
		target_id_set = Set()
		i = 0
		for row in reader:
			#id, strainid, target_id, qc_method_id, mismatch_rate, no_of_mismatches, no_of_non_NA_pairs, readme_id =row
			strainid = int(row[col_name2index['strainid']])	#2008-09-10
			target_id = int(row[col_name2index['target_id']])
			qc_method_id = int(row[col_name2index['qc_method_id']])
			mismatch_rate = float(row[col_name2index['mismatch_rate']])
			no_of_mismatches = int(row[col_name2index['no_of_mismatches']])
			no_of_non_NA_pairs = int(row[col_name2index['no_of_non_NA_pairs']])
			if qc_method_id == QC_method_id and no_of_non_NA_pairs>=min_no_of_non_NAs and mismatch_rate<=max_mismatch_rate:
				if QC_method_id==4:	#strain_id_set = target_id_set
					strain_id_set.add(strainid)
					strain_id_set.add(target_id)
				else:
					strain_id_set.add(strainid)
					target_id_set.add(target_id)
			i +=1
			if self.report and i%100000==0:
				sys.stderr.write("%s\t%s"%('\x08'*40, i))
			if self.debug and i>1000000:
				break
		if self.report:
			sys.stderr.write("%s\t%s\n"%('\x08'*40, i))
		return_data = PassingData()
		return_data.strain_id_set = strain_id_set
		return_data.target_id_set = target_id_set
		del reader
		sys.stderr.write("%s strainids and %s target_ids. Done.\n"%(len(strain_id_set), len(target_id_set)))
		return return_data

# 需要导入模块: from pymodule import PassingData [as 别名]
# 或者: from pymodule.PassingData import target_id_set [as 别名]
	def run(self):	
		if self.debug:
			import pdb
			pdb.set_trace()
		db = StockDB.StockDB(drivername=self.drivername, username=self.db_user,
						password=self.db_passwd, hostname=self.hostname, database=self.dbname, schema=self.schema)
		db.setup(create_tables=False)
		session = db.session
		order_by_sentence = " order by c.longitude, c.latitude, e.longitude, e.latitude, e.nativename "	#how to order strains.
		if self.QC_method_id ==4:
			sql_table_str = "from %s e, %s s, %s a, %s c"%(StockDB.Ecotype.table.name, StockDB.Site.table.name, StockDB.Address.table.name,\
								StockDB.Country.table.name)
			common_where_condition = "where e.siteid=s.id and s.addressid=a.id and a.countryid=c.id %s " + order_by_sentence
			
			strain_where_condition = common_where_condition%(" and e.id=st.ecotypeid")
			strain_id_info_query = "select distinct st.id as strainid, e.id as ecotypeid, e.nativename, s.name as sitename, c.abbr %s, %s st %s"%(sql_table_str, StockDB.Strain.table.name, strain_where_condition)
		else:
			sql_table_str = "from %s q, %s e, %s s, %s a, %s c"%(StockDB.QCCrossMatch.table.name, StockDB.Ecotype.table.name, StockDB.Site.table.name, StockDB.Address.table.name,\
									StockDB.Country.table.name)
			common_where_condition = "where e.siteid=s.id and s.addressid=a.id and a.countryid=c.id %s"+ " and q.qc_method_id=%s and q.no_of_non_NA_pairs>=%s and q.mismatch_rate<=%s "%\
				(self.QC_method_id, self.min_no_of_non_NAs, self.max_mismatch_rate) + order_by_sentence
			
			strain_where_condition = common_where_condition%(" and e.id=st.ecotypeid and st.id=q.strainid")
			strain_id_info_query = "select distinct q.strainid, e.id as ecotypeid, e.nativename, s.name as sitename, c.abbr %s, %s st %s"%(sql_table_str, StockDB.Strain.table.name, strain_where_condition)
		
		if self.how_to_group_strains==2 or self.how_to_group_strains==3:
			plate_info = self.alignStrainsAccordingToSeqPlate(db)
			id_set_data = PassingData()
			id_set_data.strain_id_set = None
			id_set_data.target_id_set = None
		elif self.input_fname:
			id_set_data = self.getStrainidTargetidFromFile(db, self.QC_method_id, self.input_fname, self.max_mismatch_rate, self.min_no_of_non_NAs)
		else:
			id_set_data = PassingData()
			id_set_data.strain_id_set = None
			id_set_data.target_id_set = None
		
		if self.how_to_group_strains==2 or self.how_to_group_strains==3:
			strain_id_info = self.getStrainInfoGivenPlateInfo(db, plate_info, strain_id_info_query, strain_id_set=None)
		else:
			strain_id_info = self.getStrainIDInfo(db, strain_id_info_query, id_set_data.strain_id_set)
		
		if self.QC_method_id==4:
			if self.how_to_group_strains==3:
				#2008-09-15 column strain id is in country, strain-longitude order
				target_id_info = self.getStrainIDInfo(db, strain_id_info_query, id_set_data.strain_id_set)
			else:
				target_id_info = strain_id_info
		else:
			target_where_condition = common_where_condition%(" and e.id=q.target_id")
			target_id_info_query = "select distinct e.id as strainid, e.id as ecotypeid, e.nativename, s.name as sitename, c.abbr %s %s"%(sql_table_str, target_where_condition)
			target_id_info = self.getStrainIDInfo(db, target_id_info_query)
		
		if self.input_fname:
			rdata = self.get_data_matrixFromFile(db, strain_id_info, target_id_info,  self.QC_method_id, self.input_fname, self.max_mismatch_rate, self.min_no_of_non_NAs)
		else:
			rdata = self.get_data_matrix(db, strain_id_info, target_id_info, self.QC_method_id, self.max_mismatch_rate, self.min_no_of_non_NAs)
		
		rdata.data_matrix = self.markDataMatrixBoundary(rdata.data_matrix, strain_id_info, target_id_info)
		
		header = ['strain info', ''] + target_id_info.strain_label_ls
		strain_acc_list = strain_id_info.strain_label_ls
		category_list = [1]*len(strain_acc_list)
		if SNPData.isDataMatrixEmpty(rdata.data_matrix):
			sys.stderr.write("Nothing fetched from database.\n")
			sys.exit(3)
		if self.output_fname:
			write_data_matrix(rdata.data_matrix, self.output_fname, header, strain_acc_list, category_list)
		
		if self.fig_fname:
			font = get_font(self.font_path, font_size=self.font_size)	#2008-08-01
			value2color_func = lambda x: Value2Color.value2HSLcolor(x, rdata.min_value, rdata.max_value)
			im_legend = drawContinousLegend(rdata.min_value, rdata.max_value, self.no_of_ticks, value2color_func, font)
			#im.save('%s_legend.png'%self.fig_fname_prefix)
			im = drawMatrix(rdata.data_matrix, value2color_func, strain_id_info.strain_label_ls,\
						target_id_info.strain_label_ls, with_grid=1, font=font)
			im = combineTwoImages(im, im_legend, font=font)
			im.save(self.fig_fname)