How to use ambiguity method in avocado

Best Python code snippet using avocado_python

scoring_loader.py

Source:scoring_loader.py

1"""2* Software Name : DAGOBAH Radar Station3* Version: <1.0.0>4* SPDX-FileCopyrightText: Copyright (c) 2022 Orange5* SPDX-License-Identifier: BSD-3-Clause6* This software is confidential and proprietary information of Orange.7* You shall not disclose such Confidential Information and shall not copy, use or distribute it8* in whole or in part without the prior written consent of Orange9* Author: Jixiong Liu, Viet-Phi Huynh, Yoan Chabot, and Raphael Troncy10* Software description: DAGOBAH Radar Station is a hybrid system that aims to add a semantic disambiguation step after a previously11identified cell-entity annotation. Radar Station takes into account the entire column as context and uses graph embeddings to capture12latent relationships between entities to improve their disambiguation.13"""14import json15import os16import csv17import ast18import copy19class Data_loader():20    def __init__(self, scoringSystem, annotationSe, goldStandard, tableFolder):21        self.scoringSystem = scoringSystem22        self.annotationSe = annotationSe23        self.goldStandard = goldStandard24        self.tableFolder = tableFolder25    def loader_manager(self, fileName):26        if self.scoringSystem == 'MTab':27            tableRepresentation = self.Mtab_scoring_loader(fileName)28            return tableRepresentation29        if self.scoringSystem == 'DAGOBAHSL':30            tableRepresentation = self.dagobah_scoring_loader(fileName)31            return tableRepresentation32        if self.scoringSystem == 'bbw':33            tableRepresentation = self.bbw_scoring_loader(fileName)34            return tableRepresentation35        if self.scoringSystem == 'semtab2022':36            tableRepresentation = self.semtab2022_scoring_loader(fileName)37            return tableRepresentation38    def semtab2022_scoring_loader(self, tableName):39        fileName =  self.tableFolder + "/BaselineScoring/Semtab2022/Valid/" + tableName + ".json"40        with open(fileName, 'r', encoding='latin1') as load_f:41            annotations = json.load(load_f)42        load_f.close()43        TableRepresentation = {}44        for aCell in annotations["CEA"]:45            ambiguityCandidate = []46            row = aCell["row"]47            column = aCell["column"]48            presenceOfAmbiguity = False49            highestScoring = aCell["annotation"][0]['score']50            for one_candidate in aCell["annotation"]:51                if one_candidate['score'] < (self.annotationSe * highestScoring):52                    break53                id = copy.deepcopy(one_candidate['uri'].replace("http://www.wikidata.org/entity/",""))54                acandidate = {}55                acandidate["id"] = id56                acandidate["score"] = copy.deepcopy(one_candidate['score'])57                ambiguityCandidate.append(acandidate)58            if len(ambiguityCandidate) > 1:59                presenceOfAmbiguity = True60            if aCell['column'] in TableRepresentation:61                TableRepresentation[aCell['column']].append(62                    {"row": row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,63                     "TopCandidatesNumbers": len(ambiguityCandidate),64                     "TopCandidates": ambiguityCandidate})65            else:66                TableRepresentation[aCell['column']] = [67                    {"row": row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,68                     "TopCandidatesNumbers": len(ambiguityCandidate),69                     "TopCandidates": ambiguityCandidate}]70        return TableRepresentation71    def dagobah_scoring_loader(self, tableName):72        '''73        Loading the table and scoring74        Detection of ambiguities75        '''76        if self.goldStandard in ['2T', 'ShortTable', 'Limaye']:77            fileName = self.tableFolder + "/BaselineScoring/DAGOBAHSL_Scoring/" + self.goldStandard + "_Result" + "/" + tableName + '/scores.json'78            if self.goldStandard in ['T2D']:79                fileName = self.tableFolder + "/BaselineScoring/DAGOBAHSL_Scoring/" + self.goldStandard + "_Result" + "/" + tableName + '/score.json'80            if os.path.exists(fileName) is False:81                return None82            with open(fileName, 'r', encoding='latin1') as load_f:83                annotations = json.load(load_f)84            load_f.close()85            TableRepresentation = {}86            for aCell in annotations:87                ambiguityCandidate = []88                row = aCell["row"]89                column = aCell["column"]90                presenceOfAmbiguity = False91                sorted_candidate = sorted(aCell['scores'], key=lambda i: i['score'], reverse=True)92                highestScoring = sorted_candidate[0]['score']93                for one_candidate in sorted_candidate:94                    if one_candidate['score'] < (self.annotationSe * highestScoring):95                        break96                    ambiguityCandidate.append(one_candidate)97                if len(ambiguityCandidate) > 1:98                    presenceOfAmbiguity = True99                if aCell['column'] in TableRepresentation:100                    TableRepresentation[aCell['column']].append(101                        {"row": row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,102                         "TopCandidatesNumbers": len(ambiguityCandidate),103                         "TopCandidates": ambiguityCandidate})104                else:105                    TableRepresentation[aCell['column']] = [106                        {"row": row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,107                         "TopCandidatesNumbers": len(ambiguityCandidate),108                         "TopCandidates": ambiguityCandidate}]109            return TableRepresentation110        else:111            tablePath = self.tableFolder + "/BaselineScoring/DAGOBAHSL_Scoring/" + self.goldStandard + "_Result" + "/" + tableName + '.json'112            with open(tablePath, 'r', encoding='latin1') as load_f:113                jsonFile = json.load(load_f)114            TableRepresentation = {}115            candidateList = jsonFile['annotated']['CEA']116            # ambiguities detection from Dagobah-SL117            for aCell in candidateList:118                ambiguityCandidate = []119                highestScoring = 0120                row = aCell["row"]121                column = aCell["column"]122                presenceOfAmbiguity = False123                sorted_candidate = sorted(aCell['annotation'], key=lambda i: i['score'], reverse=True)124                highestScoring = sorted_candidate[0]['score']125                for one_candidate in sorted_candidate:126                    if one_candidate['score'] < self.annotationSe * highestScoring:127                        break128                    ambiguityCandidate.append(one_candidate)129                if len(ambiguityCandidate) > 1:130                    presenceOfAmbiguity = True131                if aCell['column'] in TableRepresentation:132                    TableRepresentation[aCell['column']].append(133                        {"row": row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,134                         "TopCandidatesNumbers": len(ambiguityCandidate),135                         "TopCandidates": ambiguityCandidate})136                else:137                    TableRepresentation[aCell['column']] = [138                        {"row": row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,139                         "TopCandidatesNumbers": len(ambiguityCandidate),140                         "TopCandidates": ambiguityCandidate}]141            return TableRepresentation142    def bbw_scoring_loader(self, fileName):143        fileName = fileName.replace(".json","").replace(".csv","")144        tablePath = self.tableFolder + "/BaselineScoring/BBW_Scoring/" + self.goldStandard + '/' + fileName + ".csv"145        if self.goldStandard == "T2D":146            tablePath = tablePath.replace(".csv",".json")147        TableRepresentation = {}148        csv_reader = csv.reader(open(tablePath))149        for line in csv_reader:150            if len(line) == 0:151                continue152            row = int(line[0])153            column = int(line[1])154            presenceOfAmbiguity = False155            line[2] = ast.literal_eval(line[2])156            if len(line[2]) == 0:157                continue158            highestScoring = line[2][0][1]159            ambiguityCandidate = []160            for one_candidate in line[2]:161                if one_candidate[1] < (self.annotationSe * highestScoring):162                    break163                formedcandidate = {}164                formedcandidate['id'] = one_candidate[0]165                formedcandidate['score'] = one_candidate[1] / highestScoring166                ambiguityCandidate.append(formedcandidate)167            if len(ambiguityCandidate) > 1:168                presenceOfAmbiguity = True169            if column in TableRepresentation:170                TableRepresentation[column].append(171                    {"row": row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,172                     "TopCandidatesNumbers": len(ambiguityCandidate),173                     "TopCandidates": ambiguityCandidate})174            else:175                TableRepresentation[column] = [176                    {"row": row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,177                     "TopCandidatesNumbers": len(ambiguityCandidate),178                     "TopCandidates": ambiguityCandidate}]179        return TableRepresentation180    def Mtab_scoring_loader(self, fileName):181        fileName = fileName.replace(".json","")182        tablePath = self.tableFolder + "/BaselineScoring/MTab_Scoring/" + self.goldStandard + '/' + fileName + '.json'183        with open(tablePath, 'r', encoding='latin1') as load_f:184            load_dict = json.load(load_f)185            load_dict = load_dict.replace('\n','').replace('\t','')186            MtabScores = json.loads(load_dict)187            TableRepresentation = {}188            for aCell in MtabScores['semantic']['cea']:189                ambiguityCandidate = []190                row = aCell[0]191                column = aCell[1]192                presenceOfAmbiguity = False193                highestScoring = aCell[2][0][1]194                for one_candidate in aCell[2]:195                    if one_candidate[1] < (self.annotationSe * highestScoring):196                        break197                    formedcandidate = {}198                    formedcandidate['id'] = one_candidate[0]199                    formedcandidate['score'] = one_candidate[1]200                    ambiguityCandidate.append(formedcandidate)201                if len(ambiguityCandidate) > 1:202                    presenceOfAmbiguity = True203                if column in TableRepresentation:204                    TableRepresentation[column].append({"row":row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,205                                            "TopCandidatesNumbers": len(ambiguityCandidate),206                                            "TopCandidates" : ambiguityCandidate})207                else:208                    TableRepresentation[column] = [{"row":row, "column": column, "presenceOfAmbiguity": presenceOfAmbiguity,209                                            "TopCandidatesNumbers": len(ambiguityCandidate),210                                            "TopCandidates" : ambiguityCandidate}]211            return TableRepresentation212if __name__ == '__main__':...

Ambiguity.py

Source:Ambiguity.py

1import HelperFunctions as hf2import random3import numpy as np4import math5from copy import deepcopy6from ROOT import gROOT, TCanvas, TF1, TFile, gStyle,TH2F, TH1F, TGraph, TGraphErrors7import time8from array import array910hf.SetSeed(2022)11np.random.seed(53234)12saveStripMaps=False13useHalfStrips=False1415NLoops=100016size=20 #cm1718#beam properties19width=25 #mm20posX=0.0 #cm21posY=0.0 #cm2223#X-Y24tolerance=math.sqrt(2.0)/2.0 #no need for tolerance as X-Y guaranteed to overlap25angles=[0,90]2627#X-U-V28#tolerance=0.67 #~pitch*2/3 (triangle innit), area=5774.0 for 100um29#angles=[0,60,120]3031#X-U-V-Y32#tolerance=1.5 #needed for 4 planes, why?33#angles=[0,45,90,135]3435effTolerance=1.0363738xmax=size*50003940#gStyle.SetOptStat(0000)41gROOT.SetBatch(True)4243_aMeanProton,_aAmbiguity=array('d'),array('d')44_aMeanProtonError,_aAmbiguityError=array('d'),array('d')4546#setup histograms47ambiguityRate=TH2F("ambiguityRate","Ambiguitie Rate (%) for uniform beam of width "+(str)(width)+"cm", 5,10.0,110, 13,0.5,13.5)48ambiguityRate.GetXaxis().SetTitle("Strip Pitch (#mum)")49ambiguityRate.GetYaxis().SetTitle("nProtons")50ambiguityRateRefined=TH2F("ambiguityRateRefined","Ambiguitie Rate (%) for uniform beam of width "+(str)(width)+"cm", 5,10.0,110, 13,0.5,13.5)51ambiguityRateRefined.GetXaxis().SetTitle("Strip Pitch (#mum)")52ambiguityRateRefined.GetYaxis().SetTitle("nProtons")53hNProtons=TH1F("hNProtons","",30,-0.5,29.5)5455for nMeanProton in range(10,11):56        for pitch in range (100,101,20):5758                nRawHits=0.059                nRefinedHits=0.060                totalProtons=0.06162                nProton_RawEffCorrected=0.063                nProton_RefinedEffCorrected=0.06465                #reset output file and setup histograms for loop66                #MyFile =TFile("/disk/moose/bilpa/Optima/aw/Ambiguities/nP"+(str)(nProton)+"_pitch"+(str)(pitch)+"um_Array"+(str)(size)+"cm.root","RECREATE");67                MyFile =TFile("test.root","RECREATE");68                hRawHits=TH1F("hRawHits","n Reconstructed Hits (Raw)",100,-0.5,100.5)69                hRawEfficiency=TH1F("hRawEfficiency","Raw Efficiency",20,-2.5,102.5)7071                hRefinedHits=TH1F("hRefinedHits","n Reconstructed Hits (Refined)",100,-0.5,100.5)72                hRefinedEfficiency=TH1F("hRefinedEfficiency","Refined Efficiency",20,-2.5,102.5)7374                myHitMap=TH2F("myHitMap","Hit Locations",(int)(2*xmax/pitch),-xmax,xmax,(int)(2*xmax/pitch),-xmax,xmax)7576                for i in range(NLoops):77                        if i%1 == 0:78                                print("Processing loop "+(str)(i))7980                        #nProton=nMeanProton81                        nProton=np.random.poisson(nMeanProton)82                        hNProtons.Fill(nProton)83                        totalProtons+=nProton84                        if nProton==0:85                                continue86                                87                        #generate N=10 random points for x-y 88                        XY=hf.GetRandomXY(nProton,size,width,posX,posY)89                        #print XY9091                        #convert points into a strip number for each layer 92                        Strips=hf.GetStripCoOrds(XY,pitch,angles)93                        #print Strips9495                        #cycle through all strip combinations, find intersections of pairs of planes, see if they are within tolerance of each other96                        #returns hit objects of form (XCoord,YCoord,[stripX,stripU,stripV],[radial distance to intersections])97                        allHits=hf.FindOverlaps(Strips,pitch,angles,tolerance,useHalfStrips)98                        nRawHits+=len(allHits)99                        hRawHits.Fill(len(allHits))100                        for hit in allHits:101                                myHitMap.Fill(hit[0],hit[1])102                                103                        rawEff=hf.GetEfficiency(allHits,XY,pitch,tolerance)104                        hRawEfficiency.Fill(100.0*rawEff)105                        nProton_RawEffCorrected+=nProton*rawEff106107                        if saveStripMaps:108                                hf.PlotHitMap("RawHits",allHits,XY,Strips,pitch,size,i,angles)109110111                        #for hit in allHits:112                        #        area=hf.GetPixelArea(hit,angles,pitch)113                        #        if area>1.0:114                        #                print "Area=",area,hit115                                116117                        #remove duplicate hits (separated by < tolerance) 118                        #refinedHits=hf.RemoveAdjacentHits(allHits,tolerance,pitch)119                        refinedHits=hf.MergeAdjacentHits(allHits,effTolerance,pitch)120121122                        nRefinedHits+=len(refinedHits)123                        hRefinedHits.Fill(len(refinedHits))124                        refinedEff=hf.GetEfficiency(refinedHits,XY,pitch,effTolerance)125                        hRefinedEfficiency.Fill(100*refinedEff)126                        nProton_RefinedEffCorrected+=nProton*refinedEff127128                        if saveStripMaps:129                                hf.PlotHitMap("RefinedHits",refinedHits,XY,Strips,pitch,size,i,angles)130                        #if len(refinedHits)<len(allHits):131                        #        print("Found a duplicate")132                        #        print allHits133134                rawAmbiguity=100*(nRawHits-totalProtons)/totalProtons135                refinedAmbiguity=100*(nRefinedHits-totalProtons)/totalProtons136137                refinedAmbiguityAlt=100.0*((hRefinedHits.GetMean())-nMeanProton)/nMeanProton138                fractionalUncertaintyAlt=hRefinedHits.GetMeanError()/hRefinedHits.GetMean()139140                print "nMeanProton="+(str)(totalProtons)+",nReco= "+(str)(nRawHits)+",nReco2= "+(str)(nRefinedHits)+", pitch="+(str)(pitch)+", rawAmbiguity="+(str)(rawAmbiguity)+"%"+", refinedAmbiguity="+(str)(refinedAmbiguity)141                print "Efficiency: raw="+(str)(hRawEfficiency.GetMean())+", refined="+(str)(hRefinedEfficiency.GetMean())142                print "alt ambiguity=",refinedAmbiguityAlt,"+/-",fractionalUncertaintyAlt*refinedAmbiguityAlt143                hRawHits.Write()144                hRawEfficiency.Write()145                hRefinedHits.Write()146                hRefinedEfficiency.Write()147                myHitMap.Write()148                hNProtons.Write()149                MyFile.Close()150                ambiguityRate.Fill(pitch,nMeanProton,rawAmbiguity)151                ambiguityRateRefined.Fill(pitch,nMeanProton,refinedAmbiguity)152                _aMeanProton.append(nMeanProton)153                _aMeanProtonError.append(0)154                _aAmbiguity.append(refinedAmbiguity)155                _aAmbiguityError.append(refinedAmbiguity*fractionalUncertaintyAlt)156                157mycanvas = TCanvas( "c1", "Ambiguities", 550,195,800,700 )158ambiguityRate.Draw("COLZText")159mycanvas.SaveAs("OutputData/outputAmbiguities_"+(str)(width)+"cm.C")160mycanvas.SaveAs("OutputData/outputAmbiguities_"+(str)(width)+"cm.png")161ambiguityRateRefined.Draw("COLZTEXT")162mycanvas.SaveAs("OutputData/outputAmbiguitiesRefined_"+(str)(width)+"cm.C")163mycanvas.SaveAs("OutputData/outputAmbiguitiesRefined_"+(str)(width)+"cm.png")164165if len(_aAmbiguity) >1:166        graph=TGraphErrors(len(_aAmbiguity),_aMeanProton,_aAmbiguity,_aMeanProtonError,_aAmbiguityError)167        graph.SetMarkerStyle(5)168        graph.GetXaxis().SetTitle("Mean N Proton")169        graph.GetYaxis().SetTitle("Ambiguity (%)")170        graph.SetTitle("")171        graph.Draw("AP")172        graph.Fit("pol2")173        mycanvas.SaveAs("OutputData/AmbiguitiesGraph.C")
...

removing_ambiguity.py

Source:removing_ambiguity.py

...9import math10#Loading data 11data = list(SeqIO.parse("derep_DNA_whole_16S_strep.fasta", "fasta"))12#Counting ambiguity13def ambiguity(data, file_name):14    """Counts number of ambiguous nucleotides15    in sequences in FASAT format and returns16    count number in a list (excludes sequences17    with 0 ambiguity count). 18    Sequences with at least 1 ambiguity residue19    are saved to a separate FASTA file. 20    21    :param data: FASTA file 22    :file_name: file name to which sequences23    with at least 1 ambiguity residue will be save to. 24    """25    data = list(SeqIO.parse(data, "fasta"))26    amgu_count = []27    seq = []28    for record in data:29        ambiguity = len(record.seq) - record.seq.count('A') - record.seq.count('C') - record.seq.count('G') - record.seq.count('T')30        if ambiguity > 0:31            amgu_count.append(ambiguity)32            seq.append(record)33            SeqIO.write(seq, file_name , "fasta")34    return amgu_count35ambiguity_count = ambiguity("derep_DNA_whole_16S_strep.fasta", "all_ambiguity_seq.fasta")36print(f'Average count of ambiguity per sequence {np.mean(ambiguity_count)}')37print(f'Variance {np.var(ambiguity_count)}')38def total_bases_count(data):39    """Counts total number of bases40    in a given FASTA file41    """42    sequence_length = []43    data = list(SeqIO.parse(data, "fasta"))44    for record in data:45        seq_len = len(record.seq)46        sequence_length.append(seq_len)47    return sum(sequence_length)48total_bases = total_bases_count("all_ambiguity_seq.fasta")49#Visualisation50def ambiguity_distplot(data, s_bin, save_as):51    """Density plot. 52    :param data: list of integres53    :param s_bin: bin size 54    :param save_as: string of file name which55    the figure will be save as56    """57    sns.displot(data, binwidth=s_bin, log=True)58    plt.tight_layout()59    plt.xlabel("Ambiguity Count Per Sequence")60    plt.ylabel("log10(count)")61    plt.xlim((min(data)-1), (max(data)+1))62    plt.savefig(save_as)63    return plt.show()64ambiguity_distplot(ambiguity_count, 5, "ambiguity_dist.pdf")65#Finding parameters for statistical model66#mean count of ambiguity symbols per sequence67mean_ambiguity = np.mean(ambiguity_count)68#probablity69probablity = sum(ambiguity_count)/total_bases70print(f'Probablity (total count of ambiguity/total count of all bases) {probablity}')71#run of positive outcomes (size)72size = (mean_ambiguity*probablity)/(1-probablity)73print(f'Size {size}')74def discard_ambiguity(data, num, file_name):75    """ Discards sequences with 76    <= num of ambiguity count. 77    :param data: FASTA file78    :param num: number of maximum ambiguity79    count allowed80    :param file_name: file name to which81    seq will be save to82    """83    data = list(SeqIO.parse(data, "fasta"))84    seq = []85    for record in data:86        ambiguity = len(record.seq) - record.seq.count('A') - record.seq.count('C') - record.seq.count('G') - record.seq.count('T')87        if ambiguity <= num:88            seq.append(record)89    90    return SeqIO.write(seq, file_name, "fasta")...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.