d_widths = [.5] * len(densities)
d_labels = []
for density in densities:
d_labels.append(str(density))
#################################################################################
#graph subplot for u = 2
A2 = makeA(1)
mycolorlistu2 = [(0.9769448735268946, 0.6468696110452877, 0.2151452804329661),
(0.37645505989354233, 0.6875228836084111,
0.30496111115768654),
(0.39140782566655674, 0.7613012099948101, 0.7475874114794775)]
ax1 = plt.subplot2grid((20, 7), (0, 0), rowspan=5, colspan=7)
SBG = StackedBarGrapher()
SBG.stackedBarPlot(ax1,
A2,
mycolorlistu2,
xLabels=d_labels,
yTicks=3,
widths=d_widths,
gap=0.005,
scale=False)
for i in range(len(A2)):
Ai = [x for x in A2[i] if x > 0]
y = [x / 2.0 for x in Ai]
for j in range(len(Ai)):
if j > 0:
yy = y[j] + np.sum(Ai[0:j])
def plot_gene_usage(geneusage_data, columns, pic_type, germline_gene_list,
germline_type):
detected_genes = [x.split('*')[0] for x in columns]
SBG = StackedBarGrapher()
d = np.array(geneusage_data)
total_number = np.sum(d)
if total_number == 0:
print "There is no %s" % germline_type
else:
line_numbers = np.sum(d, axis=1)
line_number_percent_list = []
for line_number in line_numbers:
#line_number_percent = format((float(line_number)/float(total_number)), '.2%')
line_number_percent = float(line_number) / float(
total_number) * 100
line_number_percent_list.append(line_number_percent)
#print len(line_number_percent_list), len(columns)
zip_gene_number = zip(columns, line_number_percent_list)
#print zip_gene_number
gene_number_dict = {}
for item in zip_gene_number:
gene_number_dict.setdefault(item[0].split('*')[0],
[]).append(item[1])
max_len_value = 0
for key, value in gene_number_dict.items():
if max_len_value < len(value):
max_len_value = len(value)
#print gene_number_dict
gene_names = get_all_gene_name(germline_gene_list)
data = np.zeros((len(gene_names), max_len_value))
for index, gene in enumerate(gene_names):
try:
gene_number = gene_number_dict[gene]
#print gene_number
for n_index, number in enumerate(
sorted(gene_number, reverse=True)):
data[index][n_index] = number
except KeyError:
pass
d_labels = gene_names
d_colors = [
'#2166ac', '#fee090', '#fdbb84', '#fc8d59', '#e34a33', '#b30000',
'#777777', '#2166ac', '#fee090', '#fdbb84', '#fc8d59', '#e34a33',
'#b30000', '#777777', '#2166ac', '#fee090', '#fdbb84', '#fc8d59',
'#e34a33', '#b30000', '#777777'
]
rows = ['%d%%' % x for x in range(75, 101)]
#rows.insert(0, "<75%")
colors = plt.cm.rainbow(np.linspace(0, 1, 10))
#d_colors = colors
fig = plt.figure()
max_y_tick = math.ceil(max(np.sum(data, axis=1)))
y_ticks_tick, y_ticks_label, tick_log = [0], [0], 0
while max_y_tick % 2 != 0:
max_y_tick += 1
while tick_log <= max_y_tick:
tick_log += 2
y_ticks_tick.append(tick_log * 1)
y_ticks_label.append(tick_log * 1)
while len(y_ticks_tick) > 14:
if len(y_ticks_tick) % 2 == 0:
y_ticks_tick, y_ticks_label = y_ticks_tick[
1:][::2], y_ticks_label[1:][::2]
y_ticks_tick.insert(0, 0), y_ticks_label.insert(0, 0)
else:
y_ticks_tick, y_ticks_label = y_ticks_tick[::
2], y_ticks_label[::
2]
y_ticks = [y_ticks_tick, y_ticks_label]
ax = fig.add_subplot(111)
SBG.stackedBarPlot(ax,
data,
d_colors,
xLabels=d_labels,
edgeCols=['#000000'] * len(d_colors),
yTicks=y_ticks,
ylabel='Percent of reads (%)',
gap=.2,
endGaps=True)
plt.title("%s %s %s gene usage" %
(prj_name, chain_type, germline_type))
fig.subplots_adjust(bottom=0.4)
plt.tight_layout()
for t in ax.xaxis.get_ticklabels():
t.set_horizontalalignment('center')
if str(t).split("'")[1] in detected_genes:
t.set_color('blue')
plt.savefig(
'%s/%s_%s_%s_gene_usage_identity%s.png' %
(prj_tree.figure, prj_name, chain_type, germline_type, pic_type),
dpi=300)
del fig
plt.close()
#Plot black percentage gene usage
black_colors = ['#000000'] * len(d_colors)
fig = plt.figure()
ax = fig.add_subplot(111)
SBG.stackedBarPlot(
ax,
data,
#d_colors,
black_colors,
xLabels=d_labels,
edgeCols=['#000000'] * len(d_colors),
yTicks=y_ticks,
ylabel='Percent of reads (%)',
gap=.2,
endGaps=True)
plt.title("%s %s %s gene usage" %
(prj_name, chain_type, germline_type))
fig.subplots_adjust(bottom=0.4)
plt.tight_layout()
for t in ax.xaxis.get_ticklabels():
t.set_horizontalalignment('center')
#if str(t).split("'")[1] in detected_genes:
# t.set_color('blue')
plt.savefig(
'%s/%s_%s_%s_gene_usage_percentage%s.png' %
(prj_tree.figure, prj_name, chain_type, germline_type, pic_type),
dpi=300)
del fig
plt.close()
#Write down gene usage percentage info
record_gene_usage_percent(gene_number_dict, germline_type, pic_type)
post_A_2 = []
for i in pre_A_2:
total = sum(i)
post_A_partial = []
for j in i:
post_A_partial.append((j/float(total))*100)
post_A_2.append(post_A_partial)
my_color_list_2 = [
(0.9769448735268946, 0.6468696110452877, 0.2151452804329661),
(0.7645505989354233, 0.4875228836084111, 0.30496111115768654),
(0.1562085876188265, 0.44786703170340336, 0.9887241674046707), ]
ax1 = plt.subplot2grid((20,7), (0,0), rowspan = 4, colspan=7)
SBG = StackedBarGrapher()
SBG.stackedBarPlot(ax1,
post_A_2,
my_color_list_2,
xLabels=d_labels,
yTicks=3,
widths=d_widths,
gap = 0.005,
scale=False
)
for i in range(len(post_A_2)):
Ai = [x for x in post_A_2[i] if x>0]
y = [x/2.0 for x in Ai]
for j in range(len(Ai)):
if j>0:
import seaborn as sb
from matplotlib import pyplot as plt
import matplotlib as mpl
import seaborn as sns
import numpy as np
SBDIR = '~/soft/src/dev/tools/stackedBarGraph/'
GFDIR = '/na/home/splis/soft/src/dev/craft/gunfolds/tools/'
import sys, os
sys.path.append(os.path.expanduser(SBDIR))
sys.path.append(os.path.expanduser(GFDIR))
import zickle as zkl
from stackedBarGraph import StackedBarGrapher
SBG = StackedBarGrapher()
def gettimes(d):
t = [x['ms'] for x in d]
time = map(lambda x: x/1000./60., t)
return time
l = [(0.15, 'leibnitz_nodes_15_density_0.1_newp_.zkl'),
(0.20, 'leibnitz_nodes_20_density_0.1_newp_.zkl'),
(0.25, 'leibnitz_nodes_25_density_0.1_newp_.zkl'),
(0.30, 'leibnitz_nodes_30_density_0.1_newp_.zkl'),
(0.35, 'leibnitz_nodes_35_density_0.1_newp_.zkl')]
fig = pl.figure(figsize=[10,3])
#Read in data & create total column
(0.39140782566655674, 0.761012099948101, 0.7475874114794775),
(0.0965359591761811, 0.43566457484639054, 0.9375581594394308),
(0.859944654091911, 0.208070821188862, 0.8893517695418856),
(0.022700048163251885, 0.658455757390323, 0.45194508876647577),
(0.5934259725250017, 0.6259544064286037, 0.8943937276483482),
(0.1248759682295419, 0.1286185769691658, 0.6973677590395778),
(0.1834548561930609, 0.8625908063396674, 0.2808367027257399),
(0.7072265637451247, 0.795648339142106, 0.4662593453344923),
(0.9522043509564118, 0.8383482335114356, 0.04624824811210648),
(0.2509444122476855, 0.723665792376911, 0.1685356796751546)]
d_widths = [.5]*len(['2','3','4'])
ax1 = plt.subplot2grid((7,7), (0,0), rowspan = 6, colspan=7)
SBG = StackedBarGrapher()
SBG.stackedBarPlot(ax1,
A,
my_color_list,
xLabels=['2','3','4'],
yTicks=3,
widths=d_widths,
gap = 0.005,
scale=False
)
for i in range(len(A)):
Ai = [x for x in A[i] if x>0]
y = [x/2.0 for x in Ai]
for j in range(len(Ai)):
if j>0:
total = sum(i)
post_A_partial = []
for j in i:
post_A_partial.append((j / float(total)) * 100)
post_A_2.append(post_A_partial)
my_color_list_2 = [
(0.9769448735268946, 0.6468696110452877, 0.2151452804329661),
(0.7645505989354233, 0.4875228836084111, 0.30496111115768654),
(0.6151274326753975, 0.496189476149738, 0.75244053646953548),
(0.1562085876188265, 0.44786703170340336, 0.9887241674046707),
(0.4210506028639077, 0.2200011667972023, 0.37841949185273394)
]
ax1 = plt.subplot2grid((20, 7), (0, 0), rowspan=4, colspan=7)
SBG = StackedBarGrapher()
SBG.stackedBarPlot(ax1,
post_A_2,
my_color_list_2,
xLabels=d_labels,
yTicks=3,
widths=d_widths,
gap=0.005,
scale=False)
for i in range(len(post_A_2)):
Ai = [x for x in post_A_2[i] if x > 0]
y = [x / 2.0 for x in Ai]
for j in range(len(Ai)):
if j > 0:
yy = y[j] + np.sum(Ai[0:j])
def main():
#sys.exit(0)
germline_fasta = SeqIO.index(
"/zzh_gpfs02/yanmingchen/HJT-PGM/Naive/Naive_IgM/Igblast_database/20150429-human-gl-vdj.fasta",
"fasta")
mutation_patterns_files = glob.glob('%s/%s_*_mutation_patterns.txt' %
(prj_tree.data, prj_name))
mean_list = []
ploy_gene_position_dict = {}
for mutation_patterns_file in mutation_patterns_files:
print mutation_patterns_file
ref_seq_id_name = mutation_patterns_file.split("_")[-3]
print ref_seq_id_name
#if ref_seq_id_name == "IGHV1-18":
mutation_patterns_file = open(mutation_patterns_file, "rU")
if os.fstat(mutation_patterns_file.fileno()).st_size:
mutation_patterns_reader = np.loadtxt(mutation_patterns_file)
print mutation_patterns_reader, len(mutation_patterns_reader)
mutation_patterns_reader = copy.deepcopy(
mutation_patterns_reader[:10])
if mutation_patterns_reader.ndim == 2:
#print mutation_patterns_reader
#print len(mutation_patterns_reader)
#print mutation_patterns_reader.shape, mutation_patterns_reader.ndim
line_numbers = np.sum(mutation_patterns_reader, axis=1)
#print line_numbers
line_number_percent_list = []
elif mutation_patterns_reader.ndim == 1:
#print mutation_patterns_reader
mutation_patterns_reader = mutation_patterns_reader.reshape(
1, len(mutation_patterns_reader))
#print mutation_patterns_reader
#print len(mutation_patterns_reader)
#print mutation_patterns_reader.shape, mutation_patterns_reader.ndim
line_numbers = np.sum(mutation_patterns_reader, axis=1)
#print line_numbers
line_numbers = [
x / (index + 1) for (index, x) in enumerate(line_numbers)
]
third_quartile = scist.scoreatpercentile(line_numbers, 75)
interquartile_range = scist.scoreatpercentile(
line_numbers, 75) - scist.scoreatpercentile(line_numbers, 25)
#print mutation_patterns_reader, len(mutation_patterns_reader)
print third_quartile, interquartile_range, line_numbers
start_bin = 0
for bin_index in sorted(range(1, 6), reverse=True):
#print bin_index, mutation_patterns_reader[bin_index]
try:
bin_numbers = line_numbers[bin_index]
print bin_numbers, third_quartile, interquartile_range, (
bin_numbers - third_quartile) - (1.5 *
interquartile_range)
if (bin_numbers - third_quartile) > (
1.5 * interquartile_range): #0.4 Naive :0.3
print "yes"
print bin_numbers, third_quartile, interquartile_range, (
bin_numbers -
third_quartile) - (1.5 * interquartile_range)
mutation_patterns_reader = copy.deepcopy(
mutation_patterns_reader[bin_index:])
start_bin = bin_index
break
except IndexError:
continue
#if ref_seq_id_name == "IGHV1-69":
# sys.exit(0)
for line_index, line in enumerate(mutation_patterns_reader):
for row_index, row in enumerate(line):
if line_numbers[line_index] != 0:
#print line_index, line_index + start_bin, line_numbers[line_index + start_bin], line_numbers
mutation_patterns_reader[
line_index, row_index] = mutation_patterns_reader[
line_index,
row_index] / line_numbers[line_index +
start_bin] * 100
#print mutation_patterns_reader, mutation_patterns_reader.shape
mutation_patterns_reader = mutation_patterns_reader.T
#print mutation_patterns_reader, mutation_patterns_reader.shape
if mutation_patterns_reader.shape[1] == 1:
ploy_gene_position_dict[ref_seq_id_name] = [0]
else:
ploy_gene_position_dict[ref_seq_id_name] = [0]
left, width = .45, .5
bottom, height = .5, .5
right = left + width
top = bottom + height
fig = plt.figure(figsize=(8, 6))
ax = fig.add_subplot(111)
line_flag = 1
for index, line in enumerate(mutation_patterns_reader):
Yi = line
Xi = np.arange(start_bin + 1, start_bin + len(line) + 1)
#print Xi, Yi, type(Xi), type(Yi), len(Xi), len(Yi)
X = sm.add_constant(Xi)
est = sm.OLS(Yi, X)
est = est.fit()
if est.params[0] >= 12.5:
if est.pvalues[0] <= 0.05:
ploy_gene_position_dict.setdefault(
ref_seq_id_name, []).append(index + 1)
#print est.summary()
print est.params[0]
#print est.tvalues
print est.pvalues[0]
#print help(sm.regression.linear_model.OLSResults)
#sys,exit(0)
X_prime = np.linspace(X.min(), X.max(),
100)[:, np.newaxis]
X_prime = sm.add_constant(X_prime)
y_hat = est.predict(X_prime)
plt.plot(Xi, Yi, 'g', alpha=0.9, linewidth=2)
plt.scatter(Xi,
Yi,
c='g',
marker="o",
alpha=0.9,
linewidth=2)
plt.plot(X_prime[:, 1], y_hat, 'r')
ax.text(.2,
top - (0.05 * line_flag),
"Nt postition: " + str(index + 1),
horizontalalignment='right',
verticalalignment='top',
transform=ax.transAxes)
ax.text(.2,
top - (0.05 * line_flag) - 0.05,
"P-value: " +
str(round(est.pvalues[0], 3)),
horizontalalignment='right',
verticalalignment='top',
transform=ax.transAxes)
line_flag += 2
else:
plt.plot(Xi, Yi, 'b', alpha=0.3, linewidth=2)
plt.scatter(Xi,
Yi,
c='b',
marker="o",
alpha=0.3,
linewidth=2)
plt.xlabel("Mutation Count (Sequence)")
plt.ylabel("Mutation Freq. (position)")
plt.ylim(ymin=0)
plt.ylim(0, 100)
#plt.xlim(start_bin , start_bin + len(line))
plt.xlim(0, 10)
#plt.xticks(range(0,len(line),1), ('0','1', '2', '3', '4', '5', '6', '7', '8', '9', '10'))
plt.title(ref_seq_id_name)
fig.savefig("%s/%s_%s_mutation_patterns0.4.png" %
(prj_tree.figure, prj_name, ref_seq_id_name),
dpi=300)
plt.close(fig)
else:
print "yes"
ploy_gene_position_dict[ref_seq_id_name] = [0]
#output
print ploy_gene_position_dict
pickle_file = '%s/%s_ploy_gene_position_dict_dump' % (prj_tree.tmp,
prj_name)
pickle_file_handle = open(pickle_file, 'wb')
dump_tuple = (ploy_gene_position_dict)
pickle.dump(dump_tuple, pickle_file_handle)
pickle_file_handle.close()
#Step 2: get PLOY position nucl and plot stack bar
for germline_type in ('V', 'J'):
pickle_file = '%s/%s_gene_usage_info_dump_%s_%s%s' % (
prj_tree.tmp, prj_name, germline_type, chain_type, pic_type)
f_IgH = open(pickle_file, 'rb')
pickle_tuple_IgH = pickle.load(f_IgH)
columns_IgH, geneusage_data_IgH, gene_usage_ids_IgH = pickle_tuple_IgH[
0], pickle_tuple_IgH[1], pickle_tuple_IgH[2]
f_IgH.close()
geneusage_dict = {}
for i in range(len(pickle_tuple_IgH[0])):
geneusage_dict.setdefault(columns_IgH[i].split("*")[0],
[]).append(sum(geneusage_data_IgH[i]))
for (key, value) in geneusage_dict.items():
geneusage_dict[key] = sum(value)
result_file_name = open(
'%s/%s_%s_%s_right_allele_usage%s.txt' %
(prj_tree.data, prj_name, chain_type, germline_type, pic_type),
"rU")
result_file = csv.reader(result_file_name, delimiter="\t")
max_freq_allele_dict = {}
for line in result_file:
max_freq_allele_dict[line[0]] = line[0] + "*" + line[1]
print max_freq_allele_dict
pickle_files = glob.glob(
'%s/%s_mutation_pattrens_dump_%s_%s_*' %
(prj_tree.tmp, prj_name, germline_type, chain_type))
for pickle_file in pickle_files:
print pickle_file
ref_seq_id_name = pickle_file.split('_')[-1]
outfile = open(
'%s/%s_mutation_spectrum_%s_%s_%s_all' %
(prj_tree.data, prj_name, germline_type, chain_type,
ref_seq_id_name), "w")
writer = csv.writer(outfile, delimiter="\t")
pickle_file_handle = open(pickle_file, 'rb')
pickle_tuple = pickle.load(pickle_file_handle)
mutation_patterns_group = pickle_tuple
#print mutation_patterns_group
pickle_file_handle.close()
try:
max_freq_allele = max_freq_allele_dict[ref_seq_id_name]
except KeyError:
continue
germline_fasta_seq = germline_fasta[max_freq_allele].seq.upper()
mutation_spectrum_array = np.zeros((len(germline_fasta_seq), 5))
for (key, value) in mutation_patterns_group.items():
#if key <= 10:
for record in value:
read_id = record[0]
position_records = record[1]
for position_record_item in position_records:
position = position_record_item[0]
ref_nucl = position_record_item[1]
query_nucl = position_record_item[2]
if query_nucl == "A":
mutation_spectrum_array[position - 1][0] += 1
elif query_nucl == "C":
mutation_spectrum_array[position - 1][1] += 1
elif query_nucl == "-":
mutation_spectrum_array[position - 1][2] += 1
elif query_nucl == "T":
mutation_spectrum_array[position - 1][3] += 1
elif query_nucl == "G":
mutation_spectrum_array[position - 1][4] += 1
for index, nucl in enumerate(germline_fasta_seq):
if nucl == "A":
print "mutation_spectrum_array[index][0]", mutation_spectrum_array[
index][0]
#mutation_spectrum_array[index][0] = 0#-sum(mutation_spectrum_array[index])
if nucl == "C":
print "mutation_spectrum_array[index][1]", mutation_spectrum_array[
index][1]
#mutation_spectrum_array[index][1] = 0#-sum(mutation_spectrum_array[index])
if nucl == "T":
print "mutation_spectrum_array[index][3]", mutation_spectrum_array[
index][3]
#mutation_spectrum_array[index][3] = 0#-sum(mutation_spectrum_array[index])
if nucl == "G":
print "mutation_spectrum_array[index][4]", mutation_spectrum_array[
index][4]
#mutation_spectrum_array[index][4] = 0#-sum(mutation_spectrum_array[index])
for index, line in enumerate(mutation_spectrum_array):
writer.writerow([germline_fasta_seq[index]] + list(line))
outfile.close()
#Plot mutation spectrum
d_colors = [
'#2166ac', '#fee090', '#fdbb84', '#fc8d59', '#e34a33',
'#b30000', '#777777'
]
#gap = 0.2
SBG = StackedBarGrapher()
fig = plt.figure()
ax5 = fig.add_subplot(111)
SBG.stackedBarPlot(ax5,
mutation_spectrum_array,
d_colors,
edgeCols=d_colors,
ylabel='Number of reads')
plt.title("%s %s" %
(ref_seq_id_name, geneusage_dict[ref_seq_id_name]))
#plt.xticks(range(0,10,1), ('1', '2', '3', '4', '5', '6', '7', '8', '9', '10'))
plt.savefig('%s/%s_%s_%s_%s_nutation_spectrum_all.png' %
(prj_tree.figure, prj_name, chain_type, germline_type,
ref_seq_id_name),
dpi=300)
del fig
plt.close()
# ploy_nucl_position_draw
poly_nucl_positions = ploy_gene_position_dict[ref_seq_id_name]
if len(poly_nucl_positions) > 1:
for poly_nucl_position in poly_nucl_positions[1:]:
poly_nucl_position_array = np.zeros((10, 4))
for (key, value) in mutation_patterns_group.items():
if key <= 10:
for record in value:
read_id = record[0]
position_records = record[1]
for position_record_item in position_records:
position = position_record_item[0]
if position == poly_nucl_position:
ref_nucl = position_record_item[1]
query_nucl = position_record_item[2]
if query_nucl == "A":
poly_nucl_position_array[key -
1][0] += 1
elif query_nucl == "T":
poly_nucl_position_array[key -
1][1] += 1
elif query_nucl == "C":
poly_nucl_position_array[key -
1][2] += 1
elif query_nucl == "G":
poly_nucl_position_array[key -
1][3] += 1
#print poly_nucl_position_array
#d_colors = ['#2166ac', '#fee090', '#fdbb84', '#fc8d59', '#e34a33', '#b30000', '#777777']
d_colors = ['red', 'yellow', 'blue', 'green']
gap = 0.2
SBG = StackedBarGrapher()
fig = plt.figure()
ax5 = fig.add_subplot(111)
SBG.stackedBarPlot(ax5,
poly_nucl_position_array,
d_colors,
edgeCols=['#000000'] * 7,
ylabel='Number of reads',
gap=gap)
plt.title("%s %s %s" %
(ref_seq_id_name, poly_nucl_position, ref_nucl))
plt.xticks(
range(0, 10, 1),
('1', '2', '3', '4', '5', '6', '7', '8', '9', '10'))
plt.savefig(
'%s/%s_%s_%s_%s_position%s_all.png' %
(prj_tree.figure, prj_name, chain_type, germline_type,
ref_seq_id_name, poly_nucl_position),
dpi=300)
del fig
plt.close()
def draw_graph(Holes_Objects, Processes_Objects, Block_List):
SBG = StackedBarGrapher()
Memory_List = []
for each in Holes_Objects:
Memory_List.append([float(each.address), float(each.size), 1])
if (Block_List == []):
for x in range(len(Holes_Objects)):
Block_List.append([
float(Holes_Objects[x].address + Holes_Objects[x].size),
float(Holes_Objects[x + 1].address - Holes_Objects[x].address -
Holes_Objects[x].size)
if x < len(Holes_Objects) - 1 else 0, 0
])
for each in Block_List:
Memory_List.append(each)
for each in Processes_Objects:
if (each.allocated_to != -1):
Memory_List.append(
[float(each.allocated_to.address),
float(each.size), 2])
print Memory_List
Memory_List.sort(key=lambda x: x[0])
print Memory_List
np_array = []
d_colors = []
for each in Memory_List:
np_array.append(each[1])
if (each[2] == 0):
d_colors.append('#aaaaaa')
elif (each[2] == 1):
d_colors.append('#0000bb')
elif (each[2] == 2):
d_colors.append('#bb0000')
d = np.array([np_array])
print d
d_widths = [1]
d_labels = ["Memory"]
fig = plt.figure()
ax = fig.add_subplot(111)
SBG.stackedBarPlot(
ax,
d,
d_colors,
xLabels=d_labels,
yTicks=7,
widths=d_widths,
)
plt.title("Memory Allocation")
fig.subplots_adjust(bottom=0.4)
plt.tight_layout()
plt.show()
plt.close(fig)
del fig
def plot_gene_usage(result_dict, pic_type, germline_gene_list, germline_type):
SBG = StackedBarGrapher()
gene_number_dict = {}
total_number = sum(result_dict.values())
for (key, value) in result_dict.items():
gene_number_dict.setdefault(key.split('*')[0], []).append(
float(value) / total_number * 100)
max_len_value = 0
for key, value in gene_number_dict.items():
if max_len_value < len(value):
max_len_value = len(value)
gene_names = get_all_gene_name(germline_gene_list)
data = np.zeros((len(gene_names), max_len_value))
for index, gene in enumerate(gene_names):
try:
gene_number = gene_number_dict[gene]
print gene_number
for n_index, number in enumerate(sorted(gene_number,
reverse=True)):
data[index][n_index] = number
except KeyError:
pass
d_labels = gene_names
d_colors = [
'#2166ac', '#fee090', '#fdbb84', '#fc8d59', '#e34a33', '#b30000',
'#777777', '#2166ac', '#fee090', '#fdbb84', '#fc8d59', '#e34a33',
'#b30000', '#777777', '#2166ac', '#fee090', '#fdbb84', '#fc8d59',
'#e34a33', '#b30000', '#777777'
]
rows = ['%d%%' % x for x in range(75, 101)]
#rows.insert(0, "<75%")
colors = plt.cm.rainbow(np.linspace(0, 1, 10))
#d_colors = colors
fig = plt.figure()
max_y_tick = math.ceil(max(np.sum(data, axis=1)))
y_ticks_tick, y_ticks_label, tick_log = [0], [0], 0
while max_y_tick % 2 != 0:
max_y_tick += 1
while tick_log <= max_y_tick:
tick_log += 2
y_ticks_tick.append(tick_log * 1)
y_ticks_label.append(tick_log * 1)
while len(y_ticks_tick) > 14:
if len(y_ticks_tick) % 2 == 0:
y_ticks_tick, y_ticks_label = y_ticks_tick[1:][::2], y_ticks_label[
1:][::2]
y_ticks_tick.insert(0, 0), y_ticks_label.insert(0, 0)
else:
y_ticks_tick, y_ticks_label = y_ticks_tick[::2], y_ticks_label[::2]
y_ticks = [y_ticks_tick, y_ticks_label]
ax = fig.add_subplot(111)
SBG.stackedBarPlot(ax,
data,
d_colors,
xLabels=d_labels,
edgeCols=['#000000'] * len(d_colors),
yTicks=y_ticks,
ylabel='Percent of reads (%)',
gap=.2,
endGaps=True)
plt.title("%s %s %s gene usage" % (prj_name, chain_type, germline_type))
fig.subplots_adjust(bottom=0.4)
plt.tight_layout()
for t in ax.xaxis.get_ticklabels():
t.set_horizontalalignment('center')
if str(t).split("'")[1] in list(gene_number_dict.keys()):
t.set_color('blue')
plt.savefig(
'/zzh_gpfs02/yanmingchen/HJT-PGM/Naive/%s/%s_%s_%s_gene_usage%s.png' %
(prj_name, prj_name, chain_type, germline_type, pic_type),
dpi=300)
del fig
plt.close()
(0.6151274326753975, 0.496189476149738, 0.75244053646953548),
(0.1562085876188265, 0.44786703170340336, 0.9887241674046707),
(0.4210506028639077, 0.2200011667972023, 0.37841949185273394),
(0.7728656344058752, 0.17367399916287833, 0.026245548153039366),
(0.904005064928743, 0.3038725882767085, 0.9399279068775889),
(0.39140782566655674, 0.761012099948101, 0.7475874114794775),
(0.0965359591761811, 0.43566457484639054, 0.9375581594394308),
(0.859944654091911, 0.208070821188862, 0.8893517695418856),
(0.5934259725250017, 0.6259544064286037, 0.8943937276483482),
(0.1834548561930609, 0.8625908063396674, 0.2808367027257399),
(0.9522043509564118, 0.8383482335114356, 0.04624824811210648),
(0.2509444122476855, 0.723665792376911, 0.1685356796751546)]
ax1 = plt.subplot2grid((7,7), (0,0), rowspan = 6, colspan=7)
SBG = StackedBarGrapher()
SBG.stackedBarPlot(ax1,
post_A,
my_color_list,
xLabels=d_labels,
yTicks=3,
widths=d_widths,
gap = 0.005,
scale=False
)
for i in range(len(post_A)):
Ai = [x for x in post_A[i] if x>0]
y = [x/2.0 for x in Ai]
for j in range(len(Ai)):
if j>0:
(0.39140782566655674, 0.761012099948101, 0.7475874114794775),
(0.0965359591761811, 0.43566457484639054, 0.9375581594394308),
(0.859944654091911, 0.208070821188862, 0.8893517695418856),
(0.022700048163251885, 0.658455757390323, 0.45194508876647577),
(0.5934259725250017, 0.6259544064286037, 0.8943937276483482),
(0.1248759682295419, 0.1286185769691658, 0.6973677590395778),
(0.1834548561930609, 0.8625908063396674, 0.2808367027257399),
(0.7072265637451247, 0.795648339142106, 0.4662593453344923),
(0.9522043509564118, 0.8383482335114356, 0.04624824811210648),
(0.2509444122476855, 0.723665792376911, 0.1685356796751546)]
d_widths = [.5]*len(['2','3','4'])
ax1 = plt.subplot2grid((7,7), (0,0), rowspan = 6, colspan=7)
SBG = StackedBarGrapher()
SBG.stackedBarPlot(ax1,
A,
my_color_list,
xLabels=['2','3','4'],
yTicks=3,
widths=d_widths,
gap = 0.005,
scale=False
)
for i in range(len(A)):
Ai = [x for x in A[i] if x>0]
y = [x/2.0 for x in Ai]
for j in range(len(Ai)):
if j>0:
import numpy as np
from matplotlib import pyplot as plt
from stackedBarGraph import StackedBarGrapher
SBG = StackedBarGrapher()
d = np.array([[101., 0., 0., 0., 0., 0., 0.], [92., 3., 0., 4., 5., 6., 0.],
[56., 7., 8., 9., 23., 4., 5.], [81., 2., 4., 5., 32., 33., 4.],
[0., 45., 2., 3., 45., 67., 8.], [99., 5., 0., 0., 0., 43.,
56.]])
d_widths = [.5, .5, .5, .5, .5, .5]
d_labels = ["fred", "julie", "sam", "peter", "rob", "baz"]
d_colors = [
'#2166ac', '#fee090', '#fdbb84', '#fc8d59', '#e34a33', '#b30000', '#777777'
]
fig = plt.figure()
ax = fig.add_subplot(111)
SBG.stackedBarPlot(ax,
d,
d_colors,
xLabels=d_labels,
yTicks=7,
widths=d_widths,
scale=True,
gap=1)
plt.title("Scaled bars with set widths")
fig.subplots_adjust(bottom=0.4)
plt.tight_layout()
import pandas as pd
import pylab as pl
from matplotlib import pyplot as plt
import matplotlib as mpl
import seaborn as sns
import numpy as np
import sys
sys.path.append('/na/home/splis/soft/src/dev/craft/gunfolds/tools/')
sys.path.append('/na/homes/splis/soft/src/dev/tools/stackedBarGraph/')
import zickle as zkl
from stackedBarGraph import StackedBarGrapher
SBG = StackedBarGrapher()
fig = pl.figure(figsize=[10,1.3])
#Read in data & create total column
d = zkl.load("hooke_nodes_6_g32g1_.zkl")#hooke_nodes_35_newp_.zkl")
densities = np.sort(d.keys())
def get_counts(d):
eqc = [len(x['eq']) for x in d]
keys = np.sort(np.unique(eqc))
c = {}
for k in keys:
c[k] = len(np.where(eqc == k)[0])
return c
# unique size
usz = set()
dc = {}
