def monitor_variable(df, path, file, variable): run_ranges = pt.read_run_range(path=path,file=file) run_ranges[variable + '_mean'] = np.zeros(run_ranges.shape[0]) run_ranges[variable + '_std' ] = np.zeros(run_ranges.shape[0]) run_ranges[variable + '_peak'] = np.zeros(run_ranges.shape[0]) run_ranges[variable + '_nevt'] = np.zeros(run_ranges.shape[0]) for index, row in run_ranges.iterrows(): _data_ = df[np.logical_and(df['runNumber']>=row.run_min, df['runNumber']<=row.run_max)]['nPV'] run_ranges[variable + '_mean'][index] = _data_.mean() run_ranges[variable + '_std' ][index] = _data_.std() run_ranges[variable + '_nevt'][index] = _data_.size # find a maximum bins,hist = np.histogram(_data_,n) print run_ranges['run_number'][index], ' -- ', run_ranges['nPV_mean'][index] run_ranges[variable + '_sem' ] = run_ranges[variable + '_mean']/np.sqrt() run_ranges[variable + '_stde' ] = run_ranges[variable + '_std' ]/np.sqrt() run_ranges['bin'] = range(0,run_ranges.shape[0]) run_ranges['bin_error'] = 0.5 * np.ones(run_ranges.shape[0]) for k, spine in ax.spines.items(): spine.set_zorder(10) ax.grid(which='major', color='0.7' , linestyle='--',dashes=(5,1),zorder=0) ax.grid(which='minor', color='0.85', linestyle='--',dashes=(5,1),zorder=0) ax.errorbar(run_ranges['bin'],run_ranges['nPV_mean'], yerr=run_ranges['_sem' ], xerr=run_ranges['_error'], capthick=0,marker='o',ms=4,ls='None', zorder=10) plt.ylim([0,60]) plt.savefig('test.pdf')
def monitor_variable(df, path, file, variable): run_ranges = pt.read_run_range(path=path, file=file) run_ranges[variable + '_mean'] = np.zeros(run_ranges.shape[0]) run_ranges[variable + '_std'] = np.zeros(run_ranges.shape[0]) run_ranges[variable + '_peak'] = np.zeros(run_ranges.shape[0]) run_ranges[variable + '_nevt'] = np.zeros(run_ranges.shape[0]) for index, row in run_ranges.iterrows(): _data_ = df[np.logical_and(df['runNumber'] >= row.run_min, df['runNumber'] <= row.run_max)]['nPV'] run_ranges[variable + '_mean'][index] = _data_.mean() run_ranges[variable + '_std'][index] = _data_.std() run_ranges[variable + '_nevt'][index] = _data_.size # find a maximum bins, hist = np.histogram(_data_, n) print run_ranges['run_number'][index], ' -- ', run_ranges['nPV_mean'][ index] run_ranges[variable + '_sem'] = run_ranges[variable + '_mean'] / np.sqrt() run_ranges[variable + '_stde'] = run_ranges[variable + '_std'] / np.sqrt() run_ranges['bin'] = range(0, run_ranges.shape[0]) run_ranges['bin_error'] = 0.5 * np.ones(run_ranges.shape[0]) for k, spine in ax.spines.items(): spine.set_zorder(10) ax.grid(which='major', color='0.7', linestyle='--', dashes=(5, 1), zorder=0) ax.grid(which='minor', color='0.85', linestyle='--', dashes=(5, 1), zorder=0) ax.errorbar(run_ranges['bin'], run_ranges['nPV_mean'], yerr=run_ranges['_sem'], xerr=run_ranges['_error'], capthick=0, marker='o', ms=4, ls='None', zorder=10) plt.ylim([0, 60]) plt.savefig('test.pdf')
os.makedirs(plot_path) print "Starting plotmaking..." for category in pt.ecal_regions: print "Beginning category ", category, if "gold" in category: print " ...skipping: gold" continue if "bad" in category: print " ...skipping: bad" continue print #Get runrange and time info from the the runranges file d = pt.read_run_range(path=data_path, file=runRangeFile) #Get variables information from the stability monitoring .tex file d = pt.append_variables(path=data_path, file=stabilityFile, data=d, category=category) #Get variables to make plots of (data, not mc or err vars) variables = [] timeVars = [ 'Nevents', 'UnixTime', 'run_number', 'UnixTime_min', 'UnixTime_max', 'run_min', 'run_max', 'date_min', 'date_max', 'time' ] for label in d.columns.values.tolist(): if "MC" not in label and label not in timeVars and "_err" not in label: variables.append(label)
import IsolateClone import ParseTable import ClusterClone import translator import AnnotateProtein import WriteFast import ReadIgBlastn parser= argparse.ArgumentParser(prog='cat all.xls files',description="python PostAnalysis.py -d path -s species -c chain",epilog='') parser.add_argument ('-d','--directory',help='input file directory',default='/home/zhaiqi1/NGS/mycode/Ab_NGS_4/test/results',action='store') parser.add_argument('-s', '--species', help='mouse, rabbit or human', default="mouse") parser.add_argument('-c', '--chain', help="folder", default="H") args=parser.parse_args() ############### read the table from the Fastq2fastA################ raw_AbDict,count_seq=ParseTable.ParseTable(args.directory) print "There are total %s sequences in the table." % str(count_seq) print "Total number of sequences meets the keywords requirement\t:%s\n" % str(len(raw_AbDict)) Outfile_summary=open(os.path.join(args.directory,"Summary.txt"),'w') Outfile_summary.write("Total number of sequences meets the keywords requirement\t:%s\n" % str(len(raw_AbDict))) #print raw_AbDict ############################## cluster the clone based on the keywords_3, and then correct the pcr error ######## keywords_3=['CDR3-PRO','RID','DNAlen'] groupDict = IsolateClone.identifyClone(raw_AbDict,keywords_3) Outfile_keywords3=os.path.join(args.directory,"uniqueclone.txt") IsolateClone.writeCount(groupDict,Outfile_keywords3,keywords_3) #this output has not been corrected Outfile_summary.write("There are DNA sequences by same CDR3-DNA, GERMLINE-V, RID, DNAlen : %s \n " % str(len(groupDict))) print ("There are DNA sequences by same CDR3-DNA, GERMLINE-V, RID, DNAlen : %s \n" % str(len(groupDict)))
os.makedirs(plot_path) print "Starting plotmaking..." for category in pt.ecal_regions: print "Beginning category ", category, if "gold" in category: print " ...skipping: gold" continue if "bad" in category: print " ...skipping: bad" continue print #Get runrange and time info from the the runranges file d = pt.read_run_range(path=data_path,file=runRangeFile) #Get variables information from the stability monitoring .tex file d = pt.append_variables(path=data_path,file=stabilityFile,data=d,category=category) #Get variables to make plots of (data, not mc or err vars) variables = [] timeVars = ['Nevents', 'UnixTime', 'run_number', 'UnixTime_min', 'UnixTime_max', 'run_min', 'run_max', 'date_min', 'date_max', 'time'] for label in d.columns.values.tolist(): if "MC" not in label and label not in timeVars and "_err" not in label: variables.append(label) #Loop over the vars for var in variables: #Get associated monte carlo info, or a placeholder varmc = var.replace("data","MC")
formatter = ticker.FormatStrFormatter('%d') ax.xaxis.set_major_formatter(formatter) plot(warmpix['year'], np.array(warmpix[thresh]) / npix) xlim(2000, 2020) ylim(-0.005, 0.251) xlabel('Year') ylabel('Fraction') title('Warm pixel fraction (Nominal and Worst)') draw() # savefig(thresh + '_' + case + '.png') npix = 1024.0**2 secs2k = DateTime('2000:001:00:00:00').secs sec2year = 1 / (86400. * 365.25) yeardays = 365.25 alldarkcals = ParseTable.parse_table('darkcal_stats.dat') def make_darkmaps(case='nominal', initial='pristine'): """Make dark current maps by degrading the CCD using the best-fit model from fit_evol.py""" date0 = DateTime('1999-05-23T18:00:00') if initial == 'pristine': # Start from a synthetic pristine CCD. Probably no good reason to use this, # prefer starting from the pre-SSD-open dark cal on 1999223. dark = dark_models.pristine_ccd() darkcals = alldarkcals elif re.match('from|zero', initial):