Python pylab.xticks() Examples

def plot_confusion_matrix(self, matrix, labels):
        if not self.to_save and not self.to_show:
            return

        pylab.figure()
        pylab.imshow(matrix, interpolation='nearest', cmap=pylab.cm.jet)
        pylab.title("Confusion Matrix")

        for i, vi in enumerate(matrix):
            for j, vj in enumerate(vi):
                pylab.annotate("%.1f" % vj, xy=(j, i), horizontalalignment='center', verticalalignment='center', fontsize=9)

        pylab.colorbar()

        classes = np.arange(len(labels))
        pylab.xticks(classes, labels)
        pylab.yticks(classes, labels)

        pylab.ylabel('Expected label')
        pylab.xlabel('Predicted label') 

def plot_barchart(self, data, labels, colors, xlabel, ylabel, xticks, legendloc=1):
        self.big_figure()

        index = np.arange(len(data[0][0]))
        bar_width = 0.25

        pylab.grid("on", axis='y')
        pylab.ylim([0.5, 1.0])

        for i in range(0, len(data)):
            rects = pylab.bar(bar_width / 2 + index + (i * bar_width), data[i][0], bar_width,
                              alpha=0.5, color=colors[i],
                              yerr=data[i][1],
                              error_kw={'ecolor': '0.3'},
                              label=labels[i])

        pylab.legend(loc=legendloc, prop={'size': 12})

        pylab.xlabel(xlabel)
        pylab.ylabel(ylabel)
        pylab.xticks(bar_width / 2 + index + ((bar_width * (len(data[0]) + 1)) / len(data[0])), xticks) 

def plotVerticalHistSummary(all_result_outputs, label='', data_label='', y_label='', plot_label='', hist_width=1000, hist_bins=100, oligo_id_str='Oligo ID', val_str = 'Cut Rate', total_reads_str= 'Total Reads'):
   
    datas = [x[0][data_label][0] for x in all_result_outputs]
    sample_names = [shortDirLabel(x[1]) for x in all_result_outputs]
    
    merged_data = pd.merge(datas[0],datas[1],how='inner',on=oligo_id_str, suffixes=['', ' 2'])
    for i, data in enumerate(datas[2:]):
        merged_data = pd.merge(merged_data, data,how='inner',on=oligo_id_str, suffixes=['', ' %d' % (i+3)])
    suffix = lambda i: ' %d' % (i+1) if i > 0 else ''

    xpos = [x*hist_width for x in range(len(sample_names))]

    PL.figure(figsize=(12,8))
    for i,label1 in enumerate(sample_names):
        dvs = merged_data[val_str + suffix(i)]
        PL.hist(dvs, bins=hist_bins, bottom=i*hist_width, orientation='horizontal')
    PL.xticks(xpos, sample_names, rotation='vertical')
    PL.ylabel(y_label)   
    PL.title(label)
    PL.show(block=False)
    PL.savefig(getPlotDir() + '/%s_%s.png' % (plot_label, label.replace(' ','_')), bbox_inches='tight') 

def plotKLBoxes(data):
    cols = [x for x in data.columns if 'KL' in x and 'Class KL' not in x and 'Old' not in x and 'Conventional' not in x and 'Combined' not in x]
    cols.reverse()
    cols_label, max_kl = 'KL', 9
    PL.figure(figsize=(4,5))

    pt = data.loc[(data['Combined v Predicted KL'] > 0.75) & (data['Combined v Predicted KL'] < 0.8) & (data['Old v New KL'] > 0.75) & (data['Old v New KL'] < 0.8)]
    print(pt['Old Oligo Id'])

    PL.boxplot([data[col] for col in cols], positions=range(len(cols)),patch_artist=True,boxprops=dict(facecolor='C2'),medianprops=dict(linewidth=2.5, color='C1'),showfliers=False)
    PL.xticks(range(len(cols)),[renameCol(x) for x in cols], rotation='vertical')
    for i,col in enumerate(cols):
        PL.text(i-0.15, np.median(data[col])+0.02, '%.2f' % np.median(data[col]))
    PL.ylabel(cols_label)
    PL.subplots_adjust(left=0.1,right=0.95,top=0.95, bottom=0.5)
    PL.show(block=False)
    saveFig('kl_compare_old_new_predicted_%s' % cols_label.replace(' ','')) 

def plotInFrame(overbeek_inframes, ours_inframes, oof_sel_overbeek_ids, pred_results_dir):

    PL.figure(figsize=(4.2,4.2))
    data = pd.read_csv(pred_results_dir + '/old_new_kl_predicted_summaries.txt', sep='\t').fillna(-1.0)
    label1, label2 = 'New 2x800x In Frame Perc', 'New 1600x In Frame Perc'
    xdata, ydata = data[label1], data[label2]
    PL.plot(xdata,ydata, '.', label='Synthetic between library (R=%.2f)' %  pearsonr(xdata,ydata)[0], color='C0',alpha=0.15)
    PL.plot(overbeek_inframes, ours_inframes, '^', label='Synthetic vs Endogenous (R=%.2f)' % pearsonr(overbeek_inframes, ours_inframes)[0], color='C1')
    for (x,y,id) in zip(overbeek_inframes, ours_inframes, oof_sel_overbeek_ids):
        if abs(x-y) > 25.0: PL.text(x,y,id)
    PL.plot([0,100],[0,100],'k--')
    PL.ylabel('Percent In-Frame Mutations')
    PL.xlabel('Percent In-Frame Mutations')
    PL.legend()
    PL.xticks([],[])
    PL.yticks([],[])
    PL.show(block=False)
    saveFig('in_frame_full_scatter') 

def heatmap(df,fname=None,cmap='seismic',log=False):
    """Plot a heat map"""

    from matplotlib.colors import LogNorm
    f=plt.figure(figsize=(8,8))
    ax=f.add_subplot(111)
    norm=None
    df=df.replace(0,.1)
    if log==True:
        norm=LogNorm(vmin=df.min().min(), vmax=df.max().max())
    hm = ax.pcolor(df,cmap=cmap,norm=norm)
    plt.colorbar(hm,ax=ax,shrink=0.6,norm=norm)
    plt.yticks(np.arange(0.5, len(df.index), 1), df.index)
    plt.xticks(np.arange(0.5, len(df.columns), 1), df.columns, rotation=90)
    #ax.axvline(4, color='gray'); ax.axvline(8, color='gray')
    plt.tight_layout()
    if fname != None:
        f.savefig(fname+'.png')
    return ax 

def plot_functional_map(C, newfig=True):
    vmax = max(np.abs(C.max()), np.abs(C.min()))
    vmin = -vmax
    C = ((C - vmin) / (vmax - vmin)) * 2 - 1
    if newfig:
        pl.figure(figsize=(5,5))
    else:
        pl.clf()
    ax = pl.gca()
    pl.pcolor(C[::-1], edgecolor=(0.9, 0.9, 0.9, 1), lw=0.5,
              vmin=-1, vmax=1, cmap=nice_mpl_color_map())
    # colorbar
    tick_locs   = [-1., 0.0, 1.0]
    tick_labels = ['min', 0, 'max']
    bar = pl.colorbar()
    bar.locator = matplotlib.ticker.FixedLocator(tick_locs)
    bar.formatter = matplotlib.ticker.FixedFormatter(tick_labels)
    bar.update_ticks()
    ax.set_aspect(1)
    pl.xticks([])
    pl.yticks([])
    if newfig:
        pl.show() 

def plot_confusion_matrix(test_label, pred):

    mapping = {1:'co2',2:'humidity',3:'pressure',4:'rmt',5:'status',6:'stpt',7:'flow',8:'HW sup',9:'HW ret',10:'CW sup',11:'CW ret',12:'SAT',13:'RAT',17:'MAT',18:'C enter',19:'C leave',21:'occu',30:'pos',31:'power',32:'ctrl',33:'fan spd',34:'timer'}
    cm_ = CM(test_label, pred)
    cm = normalize(cm_.astype(np.float), axis=1, norm='l1')
    fig = pl.figure()
    ax = fig.add_subplot(111)
    cax = ax.matshow(cm, cmap=Color.YlOrBr)
    fig.colorbar(cax)
    for x in range(len(cm)):
        for y in range(len(cm)):
            ax.annotate(str("%.3f(%d)"%(cm[x][y], cm_[x][y])), xy=(y,x),
                        horizontalalignment='center',
                        verticalalignment='center',
                        fontsize=9)
    cm_cls =np.unique(np.hstack((test_label, pred)))
    cls = []
    for c in cm_cls:
        cls.append(mapping[c])
    pl.yticks(range(len(cls)), cls)
    pl.ylabel('True label')
    pl.xticks(range(len(cls)), cls)
    pl.xlabel('Predicted label')
    pl.title('Confusion Matrix (%.3f)'%(ACC(pred, test_label)))
    pl.show() 

def compareMHK562lines(all_result_outputs, label='', y_axis = 'Percent Non-Null Reads', data_label='RegrLines'):

    dirnames = [x[1] for x in all_result_outputs]
    clrs = ['silver','grey','darkgreen','green','lightgreen','royalblue','dodgerblue','skyblue','mediumpurple','orchid','red','orange','salmon']

    fig = PL.figure(figsize=(6,6))
    leg_handles = []
    mh_lens = [3,4,5,6,7,8,9,10,11,12,13,14,15]
    for mh_len, clr in zip(mh_lens,clrs):
        regr_lines = [x[0][data_label][mh_len] for x in all_result_outputs]
        mean_line = np.mean([x[:2] for x in regr_lines], axis=0)
        leg_handles.append(PL.plot(mean_line[0], mean_line[1], label='MH Len=%d  (R=%.1f)' % (mh_len,np.mean([x[2] for x in regr_lines])) , linewidth=2, color=clr )[0])
    PL.xlabel('Distance between nearest ends of\nmicrohomologous sequences',fontsize=16)
    PL.ylabel('Correspondng microhomology-mediated deletion\n as percent of total mutated reads',fontsize=16)
    PL.tick_params(labelsize=16)
    PL.legend(handles=[x for x in reversed(leg_handles)], loc='upper right')
    PL.ylim((0,80))
    PL.xlim((0,20))
    PL.xticks(range(0,21,5))
    PL.show(block=False)  
    saveFig('mh_regr_lines_K562') 

def i1RepeatNucleotides(data, label=''):
    merged_data = mergeWithIndelData(data)
    nt_mean_percs, nts = [], ['A','T','G','C']
    for nt in nts:
        nt_data  = merged_data.loc[merged_data['Repeat Nucleotide Left'] == nt]  
        nt_mean_percs.append((nt_data['I1_Rpt Left Reads - NonAmb']*100.0/nt_data['Total reads']).mean())
    PL.figure(figsize=(3,3))
    PL.bar(range(4),nt_mean_percs)
    for i in range(4):
        PL.text(i-0.25,nt_mean_percs[i]+0.8,'%.1f' % nt_mean_percs[i])
    PL.xticks(range(4),nts)
    PL.ylim((0,26))
    PL.xlabel('PAM distal nucleotide\nadjacent to the cut site')
    PL.ylabel('I1 repeated left nucleotide\nas percent of total mutated reads')
    PL.show(block=False)
    saveFig('i1_rtp_nt_%s' % label) 

def plotMergedI1Repeats(all_result_outputs, label=''):
    merged_data = mergeSamples(all_result_outputs, ['I1_Rpt Left Reads - NonAmb','Total reads'], data_label='i1IndelData', merge_on=['Oligo Id','Repeat Nucleotide Left'])
    nt_mean_percs, nts = [], ['A','T','G','C']
    for nt in nts:
        nt_data  = merged_data.loc[merged_data['Repeat Nucleotide Left'] == nt]  
        nt_mean_percs.append((nt_data['I1_Rpt Left Reads - NonAmb Sum']*100.0/nt_data['Total reads Sum']).mean())
    PL.figure(figsize=(3,3))
    PL.bar(range(4),nt_mean_percs)
    for i in range(4):
        PL.text(i-0.25,nt_mean_percs[i]+0.8,'%.1f' % nt_mean_percs[i])
    PL.xticks(range(4),nts)
    PL.ylim((0,26))
    PL.xlabel('PAM distal nucleotide\nadjacent to the cut site')
    PL.ylabel('I1 repeated left nucleotide\nas percent of total mutated reads')
    PL.show(block=False)
    saveFig('i1_rtp_nt') 

def simple_lineal_regression(file_path):
        records = ReviewETL.load_file(file_path)
        data = [[record['review_count']] for record in records]
        ratings = [record['stars'] for record in records]

        num_testing_records = int(len(ratings) * 0.8)
        training_data = data[:num_testing_records]
        testing_data = data[num_testing_records:]
        training_ratings = ratings[:num_testing_records]
        testing_ratings = ratings[num_testing_records:]

        # Create linear regression object
        regr = linear_model.LinearRegression()

        # Train the model using the training sets
        regr.fit(training_data, training_ratings)

        # The coefficients
        print('Coefficients: \n', regr.coef_)
        print('Intercept: \n', regr.intercept_)
        # The root mean square error
        print("RMSE: %.2f"
              % (np.mean(
            (regr.predict(testing_data) - testing_ratings) ** 2)) ** 0.5)

        print(
            'Variance score: %.2f' % regr.score(testing_data, testing_ratings))

        # Plot outputs
        import pylab as pl

        pl.scatter(testing_data, testing_ratings, color='black')
        pl.plot(testing_data, regr.predict(testing_data), color='blue',
                linewidth=3)

        pl.xticks(())
        pl.yticks(())

        pl.show() 

def spikes_diagram(ts, gids, name, path):
    """
    Function for making spike diagrams
    :param ts:   (list) times
    :param gids: (list) global IDs of neurons
    :param name: (str) name of brain part
    :param path: (str) path to save results
    :return: None
    """
    pylab.figure()
    color_marker = "."
    color_bar = "blue"
    color_edge = "black"
    ylabel = "Neuron ID"
    hist_binwidth = 5.0
    location = pylab.axes([0.1, 0.3, 0.85, 0.6])
    pylab.plot(ts, gids, color_marker)
    pylab.ylabel(ylabel)
    xlim = pylab.xlim()
    pylab.xticks([])
    pylab.axes([0.1, 0.1, 0.85, 0.17])
    t_bins = numpy.arange(numpy.amin(ts), numpy.amax(ts), hist_binwidth)
    n, bins = pylab.histogram(ts, bins=t_bins)
    num_neurons = len(numpy.unique(gids))
    heights = (1000 * n / (hist_binwidth * num_neurons))
    # FixMe t_bins[:-1] should work without cutting the end value
    pylab.bar(t_bins[:-1], heights, width=hist_binwidth, color=color_bar, edgecolor=color_edge)
    pylab.yticks([int(a) for a in numpy.linspace(0.0, int(max(heights) * 1.1) + 5, 4)])
    pylab.ylabel("Rate (Hz)")
    pylab.xlabel("Time (ms)")
    pylab.grid(True)
    pylab.axes(location)
    pylab.title(name)
    pylab.xlim(xlim)
    pylab.draw()
    pylab.savefig("{0}{1}.png".format(path, name), dpi=dpi_n, format='png')
    pylab.close() 

def runAnalysis():
	
    data = pd.read_csv(getHighDataDir() + '/old_new_kl_summaries.txt', sep='\t').fillna(-1.0)
    kl_cols = [x for x in data.columns if 'KL' in x and 'Class KL' not in x and 'Old v Old' not in x]
    max_kl = 9
    PL.figure(figsize=(2.5,4))
    bps= []
    box_types = [('C2','Within Library'),('C0','Between Library')]
    for i,(clr,box_type) in enumerate(box_types):
        col_box_data = [data[col] for col in kl_cols if renameCol(col) == box_type]
        pos = [2*x + i + 1 for x in range(len(col_box_data))]
        print('KL', box_type, np.median(col_box_data, axis=1))
        bps.append(PL.boxplot(col_box_data, positions=pos,patch_artist=True,boxprops=dict(facecolor=clr),showfliers=False))
    PL.xticks([1.5,3.5,5.5],['Same\ngRNA','Other\ngRNA','Other\ngRNA\n(Rpt)'])
    PL.plot([2.5, 2.5],[0, max_kl],'-', color='silver')
    PL.plot([4.5, 4.5],[0, max_kl],'-', color='silver')
    PL.xlim((0.5,6.5))
    PL.ylim((0,max_kl))
    PL.ylabel('KL')
    PL.subplots_adjust(left=0.1,right=0.95,top=0.95, bottom=0.25)
    PL.legend([bp["boxes"][0] for bp in bps],[x[1] for x in box_types], loc='upper left')
    PL.show(block=False)
    saveFig('kl_compare_old_new_KL') 

def plotDominantBars(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_merged_data['Is Dominant I1'] = (mci_merged_data['Equal MCI'] & (mci_merged_data['MCI Type'] == 'I1'))
    
    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')

    nt_perc_i1, cnt_labels = [], []
    nts = 'ATGC'
    for nt in nts:
        is_nt = lambda guide: (guide[-4] == nt)
        nt_data = merged_mci_data.loc[merged_mci_data['Guide'].apply(is_nt)]
        nt_perc_i1.append(sum(nt_data['Is Dominant I1'])*100.0/len(nt_data))
        cnt_labels.append('%d/%d' % (sum(nt_data['Is Dominant I1']),  len(nt_data)))
    
    PL.figure()
    PL.bar(range(4), nt_perc_i1, width=0.8)
    for i, cnt in enumerate(cnt_labels):
        PL.text(i-0.3,nt_perc_i1[i]+5.0,cnt)
    PL.xticks(range(4), [x for x in nts])
    PL.xlabel('Nucleotide on Left of cut-site')
    PL.ylabel('Percent gRNAs with single nucleotide insertion\nas most common indel in all 3 replicates')
    PL.show(block=False)
    saveFig('I1_bar_3_rep') 

def plotGCContent(all_result_outputs, label=''):
    
    #Merge data across samples
    unique_cols = ['Oligo ID','Indel', 'GC Content', 'MH Len', 'MH Dist'] 
    datas = [x[0]['Data'][unique_cols + ['Indel Reads', 'Non-Null Reads']] for x in all_result_outputs]
    merged_data = datas[0]
    for i, data in enumerate(datas[1:]):
        merged_data = pd.merge(merged_data, data, on=unique_cols, suffixes=('','%d' % (i+2)), how='outer')
    suffix = lambda i: '%d' % (i+1) if i > 0 else ''
    merged_data['Indel Reads Sum'] = merged_data[['Indel Reads' + suffix(i) for i in range(len(datas))]].sum(axis=1)
    merged_data['Non-Null Reads Sum'] = merged_data[['Non-Null Reads' + suffix(i) for i in range(len(datas))]].sum(axis=1)

    #Compute mean regression lines across samples for each MH length
    mean_lines = {}
    for mh_len in range(2,16):
        if mh_len not in all_result_outputs[0][0]['RegrLines']: continue
        regr_lines = [x[0]['RegrLines'][mh_len][:2] for x in all_result_outputs]
        mean_lines[mh_len] = np.mean(regr_lines, axis=0)

    #Restrict to only MH dist in (0,10) and adjust for mh len-dist relationship
    for mh_len in [9]:
        compute_resid = lambda row: row['Perc Reads']# - getRegrValue(row['MH Len'],row['MH Dist'],mean_lines)
        sel_data = merged_data.loc[(merged_data['MH Len'] == mh_len) & (merged_data['MH Dist'] >= 0) & (merged_data['MH Dist'] <= 10)]
        sel_data['Perc Reads'] = sel_data['Indel Reads Sum']*100.0/sel_data['Non-Null Reads Sum']
        sel_data['Perc Reads Residual'] = sel_data.apply(compute_resid, axis=1)
        PL.figure(figsize=(4,4))
        gcs = sel_data['GC Content'].unique(); gcs.sort()
        boxdata_lk = {gc: sel_data.loc[sel_data['GC Content'] == gc]['Perc Reads Residual'] for gc in gcs}
        gcs = [gc for gc in gcs if len(boxdata_lk[gc])>20]  #Limit to GC with at least 20 data points
        boxdata = [boxdata_lk[gc] for gc in gcs]
        print([len(x) for x in boxdata])
        PL.boxplot(boxdata)
        PL.ylabel('Percent total mutated reads of MH-mediated deletion')
        PL.xlabel('GC content of microhomologous sequence')
        PL.title('Microhomology of length %d\n(at max 10 distance)' % mh_len)
        PL.xticks(range(1,len(gcs)+1),gcs)
        PL.show(block=False)
        saveFig('gc_content_mh%d' % mh_len) 

def plotHeatMap(data, col='KL without null', label=''):

    #Compute and collate medians
    sel_cols = [x for x in data.columns if col in x]
    cmp_meds = data[sel_cols].median(axis=0)
    samples = sortSampleNames(getUniqueSamples(sel_cols))
    cell_lines = ['CHO', 'E14TG2A', 'BOB','RPE1', 'HAP1','K562','eCAS9','TREX2']
    sample_idxs = [(cell_lines.index(parseSampleName(x)[0]),x) for x in getUniqueSamples(sel_cols)]
    sample_idxs.sort()
    samples = [x[1] for x in sample_idxs]

    N = len(samples)
    meds = np.zeros((N,N))
    for colname in sel_cols:
        dir1, dir2 = getDirsFromFilename(colname.split('$')[-1])
        idx1, idx2 = samples.index(dir1), samples.index(dir2)
        meds[idx1,idx2] = cmp_meds[colname]
        meds[idx2,idx1] = cmp_meds[colname]

    for i in range(N):
        print(' '.join(['%.2f' % x for x in meds[i,:]]))
    print( np.median(meds[:,:-4],axis=0))

	#Display in Heatmap
    PL.figure(figsize=(5,5))
    PL.imshow(meds, cmap='hot_r', vmin = 0.0, vmax = 3.0, interpolation='nearest')
    PL.colorbar()
    PL.xticks(range(N))
    PL.yticks(range(N))
    PL.title("Median KL") # between %d mutational profiles (for %s with >%d mutated reads)" % (col, len(data), label, MIN_READS))
    ax1 = PL.gca()
    ax1.set_yticklabels([getSimpleName(x) for x in samples], rotation='horizontal')
    ax1.set_xticklabels([getSimpleName(x) for x in samples], rotation='vertical')
    PL.subplots_adjust(left=0.25,right=0.95,top=0.95, bottom=0.25)
    PL.show(block=False) 
    saveFig('median_kl_heatmap_cell_lines') 

def plotBoxPlotSummary(all_result_outputs, label='', data_label='', y_label='', plot_label='', cl_order=[]):
    data_values = [x[0][data_label][0].values for x in all_result_outputs]
    #sample_names = [getSimpleName(x[1]) + '\n(Median reads = %d)' % x[0][data_label][1] for x in all_result_outputs]
    sample_names = [getSimpleName(x[1]) for x in all_result_outputs]
    if len(cl_order)>0:
        cell_lines = [' '.join(x.split()[:-2]) for x in sample_names]
        print(cell_lines)
        reordered_data, reordered_sample_names = [],[]
        for cell_line in cl_order:
            for i, cline in enumerate(cell_lines):
                if cline == cell_line:
                      reordered_data.append(data_values[i])
                      reordered_sample_names.append(sample_names[i])
        sample_names = reordered_sample_names
        data_values = reordered_data

    PL.figure(figsize=(5,5))
    for i,dvs in enumerate(data_values):
        print(np.median(dvs))
        PL.boxplot([dvs], positions=[i], showfliers=True, sym='.', widths=0.8)
    PL.xticks(range(len(sample_names)), sample_names, rotation='vertical')
    PL.xlim((-0.5,len(sample_names)-0.5))
    PL.ylim((0,5))
    PL.ylabel(y_label)   
    PL.title(label)
    PL.subplots_adjust(bottom=0.3)
    PL.show(block=False)
    saveFig( '%s_%s' % (plot_label, sanitizeLabel(label))) 

def plot_confusion_matrix(cm, title='Confusion matrix', cmap=plt.cm.Blues):
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(iris.target_names))
    plt.xticks(tick_marks, iris.target_names, rotation=45)
    plt.yticks(tick_marks, iris.target_names)
    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label') 

def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
    """Helper function to plot a gallery of portraits"""
    pl.figure(figsize=(1.8 * n_col, 2.4 * n_row))
    pl.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35)
    for i in range(n_row * n_col):
        pl.subplot(n_row, n_col, i + 1)
        pl.imshow(images[i].reshape((h, w)), cmap=pl.cm.gray)
        pl.title(titles[i], size=12)
        pl.xticks(())
        pl.yticks(())


# plot the result of the prediction on a portion of the test set 

def plot_sensor_data_and_label(self, title, timestamp, x, y, z, label_timestamp, label=None):
        if not self.to_save and not self.to_show:
            return

        self.big_figure()

        pylab.plot(timestamp, x, color='r', label='x')
        pylab.plot(timestamp, y, color='g', label='y')
        pylab.plot(timestamp, z, color='b', label='z')

        for i in range(0, len(label_timestamp)):
            if label is not None:
                if i != 0:
                    pylab.axvline(label_timestamp[i], color="k", ls='dashed')
                else:
                    pylab.axvline(label_timestamp[i], color="k", label="keystroke", ls='dashed')
            else:
                pylab.axvline(label_timestamp[i], color="k", ls='dashed')

        pylab.legend()

        pylab.title(title)
        pylab.xlabel('Time')
        pylab.ylabel('Amplitude')
        if label:
            pylab.xticks(label_timestamp, label) 

def plot(self):
        import pylab as plt

        q_ticks_int = [self.q_dist[i] for i in self.q_ticks]
        q_ticks_label = self.q_labels
        for i, q in enumerate(q_ticks_label):
            if q in self.translate_to_pylab:
                q_ticks_label[i] = self.translate_to_pylab[q]
        plt.plot(self.q_dist, self.ew_list)
        plt.xticks(q_ticks_int, q_ticks_label)
        for x in q_ticks_int:
            plt.axvline(x, color="black")
        return plt 

def plot(self, filename=None, vmin=None, vmax=None, cmap='jet_r'):
        import pylab
        pylab.clf()
        pylab.imshow(-np.log10(self.results[self._start_y:,:]), 
            origin="lower",
            aspect="auto", cmap=cmap, vmin=vmin, vmax=vmax)
        pylab.colorbar()

        # Fix xticks
        XMAX = float(self.results.shape[1])  # The max integer on xaxis
        xpos = list(range(0, int(XMAX), int(XMAX/5)))
        xx = [int(this*100)/100 for this in np.array(xpos) / XMAX * self.duration]
        pylab.xticks(xpos, xx, fontsize=16)

        # Fix yticks
        YMAX = float(self.results.shape[0])  # The max integer on xaxis
        ypos = list(range(0, int(YMAX), int(YMAX/5)))
        yy = [int(this) for this in np.array(ypos) / YMAX * self.sampling]
        pylab.yticks(ypos, yy, fontsize=16)

        #pylab.yticks([1000,2000,3000,4000], [5500,11000,16500,22000], fontsize=16)
        #pylab.title("%s echoes" %  filename.replace(".png", ""), fontsize=25)
        pylab.xlabel("Time (seconds)", fontsize=25)
        pylab.ylabel("Frequence (Hz)", fontsize=25)
        pylab.tight_layout()
        if filename:
            pylab.savefig(filename) 

def plot_confusion_matrix(self, label_test, fn_test):

        fn_preds = self.clf.predict(fn_test)
        acc = accuracy_score(label_test, fn_preds)

        cm_ = CM(label_test, fn_preds)
        cm = normalize(cm_.astype(np.float), axis=1, norm='l1')

        fig = pl.figure()
        ax = fig.add_subplot(111)
        cax = ax.matshow(cm)
        fig.colorbar(cax)
        for x in range(len(cm)):
            for y in range(len(cm)):
                ax.annotate(str("%.3f(%d)"%(cm[x][y], cm_[x][y])), xy=(y,x),
                            horizontalalignment='center',
                            verticalalignment='center',
                            fontsize=10)
        cm_cls =np.unique(np.hstack((label_test,fn_preds)))

        cls = []
        for c in cm_cls:
            cls.append(mapping[c])
        pl.yticks(range(len(cls)), cls)
        pl.ylabel('True label')
        pl.xticks(range(len(cls)), cls)
        pl.xlabel('Predicted label')
        pl.title('Mn Confusion matrix (%.3f)'%acc)

        pl.show() 

def plot_word_freq_dist(text):
    fd = text.vocab()

    samples = fd.keys()[:50]
    values = [fd[sample] for sample in samples]
    values = [sum(values[:i+1]) * 100.0/fd.N() for i in range(len(values))]
    pylab.title(text.name)
    pylab.xlabel("Samples")
    pylab.ylabel("Cumulative Percentage")
    pylab.plot(values)
    pylab.xticks(range(len(samples)), [str(s) for s in samples], rotation=90)
    pylab.show() 

def malt_demo(nx=False):
    """
    A demonstration of the result of reading a dependency
    version of the first sentence of the Penn Treebank.
    """
    dg = DependencyGraph("""Pierre  NNP     2       NMOD
Vinken  NNP     8       SUB
,       ,       2       P
61      CD      5       NMOD
years   NNS     6       AMOD
old     JJ      2       NMOD
,       ,       2       P
will    MD      0       ROOT
join    VB      8       VC
the     DT      11      NMOD
board   NN      9       OBJ
as      IN      9       VMOD
a       DT      15      NMOD
nonexecutive    JJ      15      NMOD
director        NN      12      PMOD
Nov.    NNP     9       VMOD
29      CD      16      NMOD
.       .       9       VMOD
""")
    tree = dg.tree()
    print tree.pprint()
    if nx:
        #currently doesn't work
        import networkx as NX
        import pylab as P

        g = dg.nx_graph()
        g.info()
        pos = NX.spring_layout(g, dim=1)
        NX.draw_networkx_nodes(g, pos, node_size=50)
        #NX.draw_networkx_edges(g, pos, edge_color='k', width=8)
        NX.draw_networkx_labels(g, pos, dg.nx_labels)
        P.xticks([])
        P.yticks([])
        P.savefig('tree.png')
        P.show() 

def graph(text,text2=''): 
    pl.xticks(())
    pl.yticks(())
    pl.xlim(0,30)
    pl.ylim(0,20) 
    pl.plot([x,x],[0,3])
    pl.text(x,-2,"X");
    pl.text(0,x,"X")
    pl.text(x,x*1.7, text, ha='center', va='center',size=10, alpha=.5) 
    pl.text(-5,10,text2,size=25) 

def plot(self, *args, **kwargs):
        """
        Plot the given samples from the conditional frequency distribution.
        For a cumulative plot, specify cumulative=True.
        (Requires Matplotlib to be installed.)

        :param samples: The samples to plot
        :type samples: list
        :param title: The title for the graph
        :type title: str
        :param conditions: The conditions to plot (default is all)
        :type conditions: list
        """
        try:
            import pylab
        except ImportError:
            raise ValueError('The plot function requires the matplotlib package (aka pylab).'
                             'See http://matplotlib.sourceforge.net/')

        cumulative = _get_kwarg(kwargs, 'cumulative', False)
        conditions = _get_kwarg(kwargs, 'conditions', self.conditions())
        title = _get_kwarg(kwargs, 'title', '')
        samples = _get_kwarg(kwargs, 'samples',
                             sorted(set(v for c in conditions for v in self[c])))  # this computation could be wasted
        if not "linewidth" in kwargs:
            kwargs["linewidth"] = 2

        for condition in conditions:
            if cumulative:
                freqs = list(self[condition]._cumulative_frequencies(samples))
                ylabel = "Cumulative Counts"
                legend_loc = 'lower right'
            else:
                freqs = [self[condition][sample] for sample in samples]
                ylabel = "Counts"
                legend_loc = 'upper right'
            # percents = [f * 100 for f in freqs] only in ConditionalProbDist?
            kwargs['label'] = str(condition)
            pylab.plot(freqs, *args, **kwargs)

        pylab.legend(loc=legend_loc)
        pylab.grid(True, color="silver")
        pylab.xticks(range(len(samples)), [unicode(s) for s in samples], rotation=90)
        if title:
            pylab.title(title)
        pylab.xlabel("Samples")
        pylab.ylabel(ylabel)
        pylab.show() 

def plot(self, *args, **kwargs):
        """
        Plot samples from the frequency distribution
        displaying the most frequent sample first.  If an integer
        parameter is supplied, stop after this many samples have been
        plotted.  If two integer parameters m, n are supplied, plot a
        subset of the samples, beginning with m and stopping at n-1.
        For a cumulative plot, specify cumulative=True.
        (Requires Matplotlib to be installed.)

        :param title: The title for the graph
        :type title: str
        :param cumulative: A flag to specify whether the plot is cumulative (default = False)
        :type title: bool
        """
        try:
            import pylab
        except ImportError:
            raise ValueError('The plot function requires the matplotlib package (aka pylab). '
                         'See http://matplotlib.sourceforge.net/')

        if len(args) == 0:
            args = [len(self)]
        samples = list(islice(self, *args))

        cumulative = _get_kwarg(kwargs, 'cumulative', False)
        if cumulative:
            freqs = list(self._cumulative_frequencies(samples))
            ylabel = "Cumulative Counts"
        else:
            freqs = [self[sample] for sample in samples]
            ylabel = "Counts"
        # percents = [f * 100 for f in freqs]  only in ProbDist?

        pylab.grid(True, color="silver")
        if not "linewidth" in kwargs:
            kwargs["linewidth"] = 2
        if "title" in kwargs:
            pylab.title(kwargs["title"])
            del kwargs["title"]
        pylab.plot(freqs, **kwargs)
        pylab.xticks(range(len(samples)), [unicode(s) for s in samples], rotation=90)
        pylab.xlabel("Samples")
        pylab.ylabel(ylabel)
        pylab.show() 

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')