import dataParser as parser import helperFiles.buildPlot as plotBuilder df = pd.read_csv('../merged_1.6.1.csv') # data = [] # labels = set # # inputs = ['RAD51B'] # inputs = set() # samples = parser.samples # for category in samples: # for gene in samples[category]: # labels.add(gene) # print(inputs) pValues = parser.load_obj('pvalues') data = parser.load_obj('data') for i in data: print(len(i) == 0) quit() fig, ax1 = plt.subplots(figsize=(15, 5)) fig.canvas.set_window_title('A Boxplot Example') fig.subplots_adjust(left=0.075, right=0.95, top=0.9, bottom=0.25) bp = ax1.boxplot(data, notch=0, sym='+', vert=1, whis=1.5, showmeans=True) plt.setp(bp['boxes'], color='black') plt.setp(bp['whiskers'], color='black') plt.setp(bp['fliers'], color='red', marker='+') # Add a horizontal grid to the plot, but make it very light in color
import json import os import re import urllib import pandas as pd import dataParser df = pd.read_csv('../merged_1.6.1.csv') patients = df['donor_unique_id'].unique() rangeDict = dataParser.buildRangeDict() if (os.path.isfile("obj/completedDonors3.pkl")): completed = dataParser.load_obj("completedDonors3") else: completed = set() size = int(len(patients) / 4) for patient in patients[size + size + size + 1:int(len(patients))]: if (os.path.isfile("obj/GenewithDonorsWithSVsInGene3.pkl")): results = dataParser.load_obj("GenewithDonorsWithSVsInGene3") else: results = {} match = re.match('.*::(.+)', patient) donorid = dataParser.getKeyword(match[1]) if donorid in completed: continue print(donorid) mutsinDonor = dataParser.mutationsInDonorCount(donorid) to_nearest_hunderd = 101 - (mutsinDonor % 100)
# donorDF = df[(df['donor_unique_id'] == donor)] # notaffected.append(len(donorDF.index)) # if(len(affected) == 0): # affected.append(0) # if(len(notaffected) == 0): # notaffected.append(0) # data.append(notaffected) # data.append(affected) # value = stats.ttest_ind(affected, notaffected)[1] # pValues.append(value) # print(value) # parser.save_obj(pValues, 'WTvsmUTsubsetpValues') # parser.save_obj(data, 'WTvsMUTsubsetData') # parser.save_obj(labels, 'WTvsMUTsubsetLabels') pValues = parser.load_obj('WTvsmUTsubsetpValues') data = parser.load_obj('WTvsMUTsubsetData') labels = parser.load_obj('WTvsMUTsubsetLabels') # the x locations for the groups ind = np.arange(start=0, stop=len(data) * 1.5, step=3) width = 1.25 # the width of the bars fig2, ax2 = plt.subplots(figsize=(20, 15)) means = [] stdevs = [] print(ind) for dataset in data: means.append(mean(dataset)) for dataset in data: try: stdevs.append(stdev(dataset)) except:
import json import os import re import urllib import pandas as pd import dataParser rangeDict = dataParser.buildRangeDict() if(os.path.isfile("obj/completedDonors0.pkl")): completed = dataParser.load_obj("completedDonors0") else: completed = set() patients = dataParser.load_obj("patients") size = int(len(patients)/4) for patient in patients[0:size+1]: if(os.path.isfile("obj/GenewithDonorsWithSVsInGene0.pkl")): results = dataParser.load_obj("GenewithDonorsWithSVsInGene0") else: results = {} match = re.match('.*::(.+)', patient) donorid = dataParser.getKeyword(match[1]) if donorid in completed: continue print(donorid) mutsinDonor = dataParser.mutationsInDonorCount(donorid) to_nearest_hunderd = 101 - (mutsinDonor % 100) try: for i in range(0, mutsinDonor+to_nearest_hunderd, 100):
intrachromosomal = [] samples = parser.samples labels = [] s = set() counter = 0 # for category in samples: # for gene in samples[category]: # if(gene in s): # continue # print(gene) # if(not parser.checkValid(gene)): # continue # else: # s.add(gene) # labels.append(gene) labels = parser.load_obj('WTvsMUTsubsetLabels') for gene in labels: print(gene) try: geneDF, chromsome = parser.getGeneDF(gene) geneDataIntra = 0 geneDataInter = 0 for index, row in geneDF.iterrows(): if (int(row['seqnames']) == chromsome) and (int(row['altchr']) == chromsome): geneDataIntra += 1 if (int(row['seqnames'])) != (int(row['altchr'])): geneDataInter += 1 intrachromosomal.append(geneDataIntra) interchromosomal.append(geneDataInter) except: intrachromosomal.append(0)