Python pylab.pie() Examples

def show_pie(self):
        """a simple example to demonstrate how to visualise number of
        interactions found in various databases

        """
        try:
            from pylab import pie, clf, title, show, legend
        except ImportError:
            from bioservices import BioServicesError
            raise BioServicesError("You must install pylab/matplotlib to use this functionality")
        labels = range(1, self.N + 1)
        print(labels)
        counting = [len(self.relevant_interactions[i]) for i in labels]

        clf()
        #pie(counting, labels=[str(int(x)) for x in labels], shadow=True)
        pie(counting, labels=[str(x) for x in counting], shadow=True)
        title("Number of interactions found in N databases")
        legend([str(x) + " database(s)" for x in labels])
        show() 

def generateImages(picklefile, pickledir, filehash, imagedir, pietype):

	leaf_file = open(os.path.join(pickledir, picklefile), 'rb')
	(piedata, pielabels) = cPickle.load(leaf_file)
	leaf_file.close()

	pylab.figure(1, figsize=(6.5,6.5))
	ax = pylab.axes([0.2, 0.15, 0.6, 0.6])

	pylab.pie(piedata, labels=pielabels)

	pylab.savefig(os.path.join(imagedir, '%s-%s.png' % (filehash, pietype)))
	pylab.gcf().clear()
	os.unlink(os.path.join(pickledir, picklefile)) 

def create_pie_chart(self, snapshot, filename=''):
        """
        Create a pie chart that depicts the distribution of the allocated memory
        for a given `snapshot`. The chart is saved to `filename`.
        """
        try:
            from pylab import figure, title, pie, axes, savefig
            from pylab import sum as pylab_sum
        except ImportError:
            return self.nopylab_msg % ("pie_chart")

        # Don't bother illustrating a pie without pieces.
        if not snapshot.tracked_total:
            return ''

        classlist = []
        sizelist = []
        for k, v in list(snapshot.classes.items()):
            if v['pct'] > 3.0:
                classlist.append(k)
                sizelist.append(v['sum'])
        sizelist.insert(0, snapshot.asizeof_total - pylab_sum(sizelist))
        classlist.insert(0, 'Other')
        #sizelist = [x*0.01 for x in sizelist]

        title("Snapshot (%s) Memory Distribution" % (snapshot.desc))
        figure(figsize=(8,8))
        axes([0.1, 0.1, 0.8, 0.8])
        pie(sizelist, labels=classlist)
        savefig(filename, dpi=50)

        return self.chart_tag % (self.relative_path(filename)) 

def plotSumPie(all_result_outputs, label=''):
    merged_data =  mergeSamples(all_result_outputs, ['Total reads'] + ALL_LABELS, data_label='perOligoCounts')
    for col in ALL_LABELS:
        merged_data[col + ' Perc'] = merged_data[col + ' Sum']*100.0/merged_data['Total reads Sum']
    merged_data.to_csv('data_dump_indel_pie.txt',sep='\t',columns=['Oligo Id'] + [col + ' Perc' for col in ALL_LABELS])
    pie_vals = [merged_data[col + ' Perc'].mean() for col in ALL_LABELS]
    PL.figure(figsize=(4,4))
    PL.pie(pie_vals, labels=ALL_LABELS, autopct='%.1f', labeldistance=1.05, startangle=90.0, counterclock=False, colors=COLORS)
    PL.title('Average distribution\n of mutations\n per gRNA')
    PL.show(block=False)
    saveFig('pie_chart_cats') 

def plotMCIPie(all_result_outputs, label=''):
    mci_merged_data = mergeSamples(all_result_outputs, ['MCI Type','Most Common Indel'], data_label='perOligoMCI')
    mci_common = mci_merged_data.loc[(mci_merged_data['Most Common Indel']==mci_merged_data['Most Common Indel 2']) & (mci_merged_data['Most Common Indel']==mci_merged_data['Most Common Indel 3'])]
    pie_vals, pie_labels = [], []
    for mci_type in ALL_LABELS:
        pie_vals.append(len(mci_common.loc[mci_common['MCI Type'] == mci_type]))
        pie_labels.append(mci_type)
    pie_vals.append(len(mci_merged_data)-len(mci_common))
    pie_labels.append('Inconsistent\nbetween\nreplicates')

    PL.figure(figsize=(4,4))
    PL.pie(pie_vals, labels=pie_labels, autopct='%.1f', labeldistance=1.05, startangle=90.0, counterclock=False, colors=COLORS)
    PL.title('Most frequent\nmutation per gRNA')
    PL.show(block=False)
    saveFig('pie_chart_cats_dominant') 

def computePieDataWithAmbig(data,label='', norm='I1 Total'):
    merged_data = mergeWithIndelData(data)
    pie_labels = ['I1_Rpt Left Reads - NonAmb','Ambiguous Rpt Reads','I1_Rpt Right Reads - NonAmb','I1_NonRpt Reads']
    labels = ['Repeated\nleft nucleotide', 'Ambiguous\n(Left = Right)', 'Repeated\nright nucleotide', 'Non-repeated\nnucleotide']
    pie_data = {x: (merged_data[x]*100.0/merged_data[norm]).mean(axis=0) for x in pie_labels}
    PL.figure(figsize=(3,3))
    PL.pie([pie_data[x] for x in pie_labels], labels=labels, autopct='%.1f', labeldistance=1.05, startangle=120.0, counterclock=False)
    PL.title('Single nucleotide insertions (I1)')
    PL.show(block=False)
    saveFig('ambig_pie_%s' % label)
    return pie_data, pie_labels, data['Total reads'].median() 

def computeFractionWithI1Repeats(data, label=''):
    merged_data = mergeWithIndelData(data)
    pie_label = 'Oligos with I1 Repeats'
    perc_with_11Rpt = len(merged_data.loc[(merged_data['I1_Rpt Left Reads - NonAmb'] + merged_data['Ambiguous Rpt Reads'])> 0.0])*100.0/len(merged_data)
    pie_data = {pie_label:perc_with_11Rpt}
    PL.figure()
    PL.pie([perc_with_11Rpt, 1-perc_with_11Rpt], labels=[pie_label,'Oligos without I1 Repeats'], autopct='%.1f', labeldistance=1.05, startangle=90.0, counterclock=False)
    PL.title(label)
    PL.show(block=False)
    return pie_data, [pie_label], merged_data['Total reads'].median() 

def plotDominantPieDataWithAmbig(all_result_outputs, label=''):
    pie_labels = ['I1_Rpt Left Reads - NonAmb','Ambiguous Rpt Reads','I1_Rpt Right Reads - NonAmb','I1_NonRpt Reads']
    mci_merged_data = mergeSamples(all_result_outputs, [], data_label='i1IndelData')
    mci_merged_data['Equal MCI'] = (mci_merged_data['Most Common Indel']==mci_merged_data['Most Common Indel 2']) & (mci_merged_data['Most Common Indel']==mci_merged_data['Most Common Indel 3'])
    mci_common_i1 = mci_merged_data.loc[mci_merged_data['Equal MCI'] & (mci_merged_data['MCI Type'] == 'I1')]
    labels = ['Repeated\nleft nucleotide', 'Ambiguous\n(Left = Right)', 'Repeated\nright nucleotide', 'Non-repeated\nnucleotide']
    pie_data = []
    for label in pie_labels:
        is_rpt = lambda row: row['MCI Reads'] == row[label]
        pie_data.append(sum(mci_common_i1.apply(is_rpt,axis=1))*100.0/len(mci_common_i1))
    PL.figure(figsize=(3,3))
    PL.pie(pie_data, labels=labels, autopct='%.1f', labeldistance=1.05, startangle=180.0, counterclock=False)
    PL.title('Dominant single nucleotide insertions (I1)\n%d from %d gRNAs' % (len(mci_common_i1), len(mci_merged_data)))
    PL.show(block=False)
    saveFig('I1_dom_pie_3_rep') 

def plotD1(all_result_outputs, label=''):
    mci_merged_data = mergeSamples(all_result_outputs, [], data_label='perOligoMCI')
    mci_merged_data['Equal MCI'] = (mci_merged_data['Most Common Indel']==mci_merged_data['Most Common Indel 2']) & (mci_merged_data['Most Common Indel']==mci_merged_data['Most Common Indel 3'])
    mci_common = mci_merged_data.loc[mci_merged_data['Equal MCI']]
    pie_vals, pie_labels = [], []
    dmci_data = mci_common.loc[(mci_common['MCI Type'] == 'D1')] #Note: type check discards equally most common indels

    spans_cutsite = lambda indel: tokFullIndel(indel)[2]['L'] < -1 and tokFullIndel(indel)[2]['R'] > 0
    for nt in 'ATGC':
        is_mh = lambda alt_seq: len(alt_seq) >= 2 and alt_seq == (len(alt_seq)*nt)
        num_repeat_nt = len(dmci_data.loc[dmci_data['Altered Sequence'].apply(is_mh) & dmci_data['Most Common Indel'].apply(spans_cutsite)])
        pie_vals.append(num_repeat_nt*100.0/len(dmci_data))
        print(num_repeat_nt)
        pie_labels.append('Removal of %s\nfrom %s|%s' % (nt,nt,nt))
    is_non_repeat = lambda seq: len(seq) < 2 or seq != (seq[0]*len(seq))
    num_non_repeat  = len(dmci_data.loc[dmci_data['Altered Sequence'].apply(is_non_repeat) | ~dmci_data['Most Common Indel'].apply(spans_cutsite)])
    pie_vals.append(num_non_repeat*100.0/len(dmci_data))
    print(num_non_repeat)
    pie_labels.append('Removal from non-repeat')
    PL.figure(figsize=(4,4))
    PL.pie(pie_vals, labels=pie_labels, autopct='%.1f', labeldistance=1.1, counterclock=False, colors=OLD_COLORS)
    PL.title('Size 1 deletions that are\n"most common" for their gRNA in all 3 replicates\n(%d gRNAs from %d total)' % (len(dmci_data), len(mci_merged_data)))
    PL.show(block=False)
    saveFig('pie_chart_D1')
    

    oligo_data =  pd.read_csv(getHighDataDir() + '/ST_June_2017/data/self_target_oligos_details_with_pam_details.csv',sep='\t')
    remove_under = lambda x: x.replace('_','')
    oligo_data['Oligo Id'] = oligo_data['ID'].apply(remove_under)
    merged_mci_data = pd.merge(mci_merged_data, oligo_data[['Oligo Id','Guide']], how='inner',on='Oligo Id')
    print(len(merged_mci_data))

    nt_dbl_perc_d1, cnt_labels = [], []
    is_d1 = lambda indel: (indel.split('_')[0] == 'D1')
    non_dbl_nt = lambda row: row['Guide'][-4] != row['Guide'][-3]    
    nts = 'ATGC'
    for nt in nts:
        double_nt = lambda row: row['Guide'][-4:-2] == (nt+nt)
        dbl_data = merged_mci_data.loc[merged_mci_data.apply(double_nt,axis=1)]
        num_dbl_d1 = sum(dbl_data['Most Common Indel'].apply(is_d1) & dbl_data['Equal MCI'] & (dbl_data['Oligo Id']!='Oligo28137')) #Oligo28137: Corner case where a guide has CT|T and loses the C
        nt_dbl_perc_d1.append(num_dbl_d1*100.0/len(dbl_data))
        cnt_labels.append('%d/%d' % (num_dbl_d1,len(dbl_data)))
        print(len(dbl_data))
    non_dbl_data = merged_mci_data.loc[merged_mci_data.apply(non_dbl_nt,axis=1)]
    print(len(non_dbl_data))
    num_non_dbl_d1 = sum(non_dbl_data['Most Common Indel'].apply(is_d1) & non_dbl_data['Equal MCI'])
    nt_dbl_perc_d1.append(num_non_dbl_d1*100.0/len(non_dbl_data))
    cnt_labels.append('%d/%d' % (num_non_dbl_d1,len(non_dbl_data)))
    
    PL.figure()
    PL.bar(range(5), nt_dbl_perc_d1, width=0.8)
    for i, cnt in enumerate(cnt_labels):
        PL.text(i-0.3,nt_dbl_perc_d1[i]+5.0,cnt)
    PL.xticks(range(5), ['%s' % x*2 for x in nts] + ['Other'])
    PL.ylim((0,40))
    PL.xlabel('Nucleotides on either side of cut site')
    PL.ylabel('Percent gRNAs with single nucleotide deletion\nas most common indel in all 3 replicates')
    PL.show(block=False)
    saveFig('D1_bar_3_rep')