def get_r_tikz_corr_plot(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: tikz code corresponding to an R plot
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
y_low = -1
y_high = 1
ylim = RUtil.mk_call_str("c", y_low, y_high)
print >> out, RUtil.mk_call_str(
"plot",
"my.table$t",
"my.table$corr.mi.diag.approx",
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"correlation"',
main='"correlation with mutual information"',
)
colors = ("red", "orange", "green", "blue", "black")
plot_indices = (7, 8, 9, 10, 11)
for c, plot_index in zip(colors, plot_indices):
header = g_time_stats_headers[plot_index]
print >> out, RUtil.mk_call_str("lines", "my.table$t", "my.table$%s" % header, col='"%s"' % c)
return out.getvalue()
def get_r_tikz_info_plot(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: tikz code corresponding to an R plot
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
y_low = 0
y_high = math.log(2)
ylim = RUtil.mk_call_str("c", y_low, y_high)
print >> out, RUtil.mk_call_str(
"plot",
"my.table$t",
"my.table$info.mi.diag.approx",
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"info"',
main='"informativeness with respect to MI"',
)
colors = ("red", "orange", "green", "blue", "black")
plot_indices = (17, 18, 19, 20, 21)
for c, plot_index in zip(colors, plot_indices):
header = g_time_stats_headers[plot_index]
print >> out, RUtil.mk_call_str("lines", "my.table$t", "my.table$%s" % header, col='"%s"' % c)
return out.getvalue()
def get_r_tikz_prop_plot(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: tikz code corresponding to an R plot
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
y_low = 0
y_high = 1
ylim = RUtil.mk_call_str("c", y_low, y_high)
print >> out, RUtil.mk_call_str(
"plot",
"my.table$t",
"my.table$prop.mi.diag.approx",
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"proportion"',
main='"proportion of same sign difference as MI"',
)
colors = ("red", "orange", "green", "blue", "black")
plot_indices = (12, 13, 14, 15, 16)
for c, plot_index in zip(colors, plot_indices):
header = g_time_stats_headers[plot_index]
print >> out, RUtil.mk_call_str("lines", "my.table$t", "my.table$%s" % header, col='"%s"' % c)
return out.getvalue()
def get_r_tikz_corr_plot(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: tikz code corresponding to an R plot
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
y_low = -1
y_high = 1
ylim = RUtil.mk_call_str('c', y_low, y_high)
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$corr.mi.diag.approx',
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"correlation"',
main='"correlation with mutual information"')
colors = ('red', 'orange', 'green', 'blue', 'black')
plot_indices = (7, 8, 9, 10, 11)
for c, plot_index in zip(colors, plot_indices):
header = g_time_stats_headers[plot_index]
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$%s' % header,
col='"%s"' % c)
return out.getvalue()
def get_r_tikz_mi_plot_script(nsels, time_stats):
"""
At each time point plot mutual information for all matrices.
@param time_stats: a list of stats for each time point
@return: tikz code corresponding to an R plot
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
mi_mut = time_stats_trans[1]
mi_min_sels = time_stats_trans[6]
mi_max_sels = time_stats_trans[2]
y_low = min(mi_min_sels + mi_mut)
y_high = max(mi_max_sels + mi_mut)
ylim = RUtil.mk_call_str('c', y_low, y_high)
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$mut',
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"MI"',
main='"MI for mut process and %d mut.sel processes"' % nsels)
colors = ('red', 'blue', 'green', 'black', 'green', 'blue')
plot_indices = (1, 2, 3, 4, 5, 6)
for c, plot_index in zip(colors, plot_indices):
header = g_time_stats_headers[plot_index]
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$%s' % header,
col='"%s"' % c)
return out.getvalue()
def get_r_tikz_prop_plot(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: tikz code corresponding to an R plot
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
y_low = 0
y_high = 1
ylim = RUtil.mk_call_str('c', y_low, y_high)
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$prop.mi.diag.approx',
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"proportion"',
main='"proportion of same sign difference as MI"')
colors = ('red', 'orange', 'green', 'blue', 'black')
plot_indices = (12, 13, 14, 15, 16)
for c, plot_index in zip(colors, plot_indices):
header = g_time_stats_headers[plot_index]
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$%s' % header,
col='"%s"' % c)
return out.getvalue()
def get_r_tikz_info_plot(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: tikz code corresponding to an R plot
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
y_low = 0
y_high = math.log(2)
ylim = RUtil.mk_call_str('c', y_low, y_high)
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$info.mi.diag.approx',
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"info"',
main='"informativeness with respect to MI"')
colors = ('red', 'orange', 'green', 'blue', 'black')
plot_indices = (17, 18, 19, 20, 21)
for c, plot_index in zip(colors, plot_indices):
header = g_time_stats_headers[plot_index]
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$%s' % header,
col='"%s"' % c)
return out.getvalue()
def get_r_tikz_mi_plot_script(nsels, time_stats):
"""
At each time point plot mutual information for all matrices.
@param time_stats: a list of stats for each time point
@return: tikz code corresponding to an R plot
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
mi_mut = time_stats_trans[1]
mi_min_sels = time_stats_trans[6]
mi_max_sels = time_stats_trans[2]
y_low = min(mi_min_sels + mi_mut)
y_high = max(mi_max_sels + mi_mut)
ylim = RUtil.mk_call_str("c", y_low, y_high)
print >> out, RUtil.mk_call_str(
"plot",
"my.table$t",
"my.table$mut",
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"MI"',
main='"MI for mut process and %d mut.sel processes"' % nsels,
)
colors = ("red", "blue", "green", "black", "green", "blue")
plot_indices = (1, 2, 3, 4, 5, 6)
for c, plot_index in zip(colors, plot_indices):
header = g_time_stats_headers[plot_index]
print >> out, RUtil.mk_call_str("lines", "my.table$t", "my.table$%s" % header, col='"%s"' % c)
return out.getvalue()
def get_response_content(fs):
# legend labels
label_a = 'N=%d mu=%f' % (fs.nstates_a, fs.mu_a)
label_b = 'N=%d mu=%f' % (fs.nstates_b, fs.mu_b)
arr, headers = make_table(fs)
# compute the max value
ymax = math.log(max(fs.nstates_a, fs.nstates_b))
nfifths = int(math.floor(ymax * 5.0)) + 1
ylim = RUtil.mk_call_str('c', 0, 0.2 * nfifths)
# write the R script body
out = StringIO()
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$alpha',
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"information"',
main='"comparison of an information criterion for two processes"',
)
# draw some horizontal lines
for i in range(nfifths+1):
print >> out, RUtil.mk_call_str(
'abline',
h=0.2*i,
col='"lightgray"',
lty='"dotted"')
colors = ('darkblue', 'darkred')
for c, header in zip(colors, headers[1:]):
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$%s' % header,
col='"%s"' % c,
)
legend_names = (label_a, label_b)
legend_name_str = 'c(' + ', '.join('"%s"' % s for s in legend_names) + ')'
legend_col_str = 'c(' + ', '.join('"%s"' % s for s in colors) + ')'
legend_lty_str = 'c(' + ', '.join('1' for s in colors) + ')'
print >> out, RUtil.mk_call_str(
'legend',
'"%s"' % fs.legend_placement,
legend_name_str,
col=legend_col_str,
lty=legend_lty_str,
)
script_body = out.getvalue()
# create the R plot image
table_string = RUtil.get_table_string(arr, headers)
device_name = Form.g_imageformat_to_r_function[fs.imageformat]
retcode, r_out, r_err, image_data = RUtil.run_plotter(
table_string, script_body, device_name)
if retcode:
raise RUtil.RError(r_err)
return image_data
def get_response_content(fs):
# legend labels
label_a = 'N=%d mu=%f' % (fs.nstates_a, fs.mu_a)
label_b = 'N=%d mu=%f' % (fs.nstates_b, fs.mu_b)
arr, headers = make_table(fs)
# compute the max value
ymax = math.log(max(fs.nstates_a, fs.nstates_b))
nfifths = int(math.floor(ymax * 5.0)) + 1
ylim = RUtil.mk_call_str('c', 0, 0.2 * nfifths)
# write the R script body
out = StringIO()
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$alpha',
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"information"',
main='"comparison of an information criterion for two processes"',
)
# draw some horizontal lines
for i in range(nfifths + 1):
print >> out, RUtil.mk_call_str('abline',
h=0.2 * i,
col='"lightgray"',
lty='"dotted"')
colors = ('darkblue', 'darkred')
for c, header in zip(colors, headers[1:]):
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$%s' % header,
col='"%s"' % c,
)
legend_names = (label_a, label_b)
legend_name_str = 'c(' + ', '.join('"%s"' % s for s in legend_names) + ')'
legend_col_str = 'c(' + ', '.join('"%s"' % s for s in colors) + ')'
legend_lty_str = 'c(' + ', '.join('1' for s in colors) + ')'
print >> out, RUtil.mk_call_str(
'legend',
'"%s"' % fs.legend_placement,
legend_name_str,
col=legend_col_str,
lty=legend_lty_str,
)
script_body = out.getvalue()
# create the R plot image
table_string = RUtil.get_table_string(arr, headers)
device_name = Form.g_imageformat_to_r_function[fs.imageformat]
retcode, r_out, r_err, image_data = RUtil.run_plotter(
table_string, script_body, device_name)
if retcode:
raise RUtil.RError(r_err)
return image_data
def get_response_content(fs):
distn_modes = [x for x in g_ordered_modes if x in fs.distribution]
if not distn_modes:
raise ValueError('no distribution mode was specified')
colors = [g_mode_to_color[m] for m in distn_modes]
arr, headers = make_table(fs, distn_modes)
distn_headers = headers[1:]
# Get the largest value in the array,
# skipping the first column.
arrmax = np.max(arr[:, 1:])
# write the R script body
out = StringIO()
ylim = RUtil.mk_call_str('c', 0, arrmax + 0.1)
sel_str = {
BALANCED: 'balanced',
HALPERN_BRUNO: 'Halpern-Bruno',
}[fs.selection]
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$%s' % distn_headers[0],
type='"n"',
ylim=ylim,
xlab='""',
ylab='"relaxation time"',
main='"Effect of selection (%s) on relaxation time for %d states"' %
(sel_str, fs.nstates),
)
for c, header in zip(colors, distn_headers):
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$%s' % header,
col='"%s"' % c,
)
mode_names = [s.replace('_', ' ') for s in distn_modes]
legend_name_str = 'c(' + ', '.join('"%s"' % s for s in mode_names) + ')'
legend_col_str = 'c(' + ', '.join('"%s"' % s for s in colors) + ')'
legend_lty_str = 'c(' + ', '.join(['1'] * len(distn_modes)) + ')'
print >> out, RUtil.mk_call_str(
'legend',
'"%s"' % fs.legend_placement,
legend_name_str,
col=legend_col_str,
lty=legend_lty_str,
)
script_body = out.getvalue()
# create the R plot image
table_string = RUtil.get_table_string(arr, headers)
device_name = Form.g_imageformat_to_r_function[fs.imageformat]
retcode, r_out, r_err, image_data = RUtil.run_plotter(
table_string, script_body, device_name)
if retcode:
raise RUtil.RError(r_err)
return image_data
def get_response_content(fs):
distn_modes = [x for x in g_ordered_modes if x in fs.distribution]
if not distn_modes:
raise ValueError('no distribution mode was specified')
colors = [g_mode_to_color[m] for m in distn_modes]
arr, headers = make_table(fs, distn_modes)
distn_headers = headers[1:]
# Get the largest value in the array,
# skipping the first column.
arrmax = np.max(arr[:,1:])
# write the R script body
out = StringIO()
ylim = RUtil.mk_call_str('c', 0, arrmax + 0.1)
sel_str = {
BALANCED : 'balanced',
HALPERN_BRUNO : 'Halpern-Bruno',
}[fs.selection]
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$%s' % distn_headers[0],
type='"n"',
ylim=ylim,
xlab='""',
ylab='"relaxation time"',
main='"Effect of selection (%s) on relaxation time for %d states"' % (sel_str, fs.nstates),
)
for c, header in zip(colors, distn_headers):
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$%s' % header,
col='"%s"' % c,
)
mode_names = [s.replace('_', ' ') for s in distn_modes]
legend_name_str = 'c(' + ', '.join('"%s"' % s for s in mode_names) + ')'
legend_col_str = 'c(' + ', '.join('"%s"' % s for s in colors) + ')'
legend_lty_str = 'c(' + ', '.join(['1']*len(distn_modes)) + ')'
print >> out, RUtil.mk_call_str(
'legend',
'"%s"' % fs.legend_placement,
legend_name_str,
col=legend_col_str,
lty=legend_lty_str,
)
script_body = out.getvalue()
# create the R plot image
table_string = RUtil.get_table_string(arr, headers)
device_name = Form.g_imageformat_to_r_function[fs.imageformat]
retcode, r_out, r_err, image_data = RUtil.run_plotter(
table_string, script_body, device_name)
if retcode:
raise RUtil.RError(r_err)
return image_data
def get_R_tick_cmd(axis, positions):
"""
@param axis: 1 for x, 2 for y
@param positions: a sequence of positions
@return: a single line R command to draw the ticks
"""
s = 'c(' + ', '.join(str(x) for x in positions) + ')'
return RUtil.mk_call_str('axis', axis, at=s)
def get_R_tick_cmd(axis, positions):
"""
@param axis: 1 for x, 2 for y
@param positions: a sequence of positions
@return: a single line R command to draw the ticks
"""
s = 'c(' + ', '.join(str(x) for x in positions) + ')'
return RUtil.mk_call_str('axis', axis, at=s)
def get_plot_scripts(sequence_lengths):
scripts = []
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'plot',
'my.table$sequence.length',
'my.table$mean.mean',
xlab="''",
ylab="'mean'",
xaxt="'n'",
main="'posterior statistics of rates among branches'",
#type='"n"',
)
print >> out, get_R_tick_cmd(1, sequence_lengths)
scripts.append(out.getvalue().rstrip())
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'plot',
'my.table$sequence.length',
'my.table$var.mean',
xlab="''",
ylab="'coeff of variation'",
xaxt="'n'",
#type='"n"',
)
print >> out, get_R_tick_cmd(1, sequence_lengths)
scripts.append(out.getvalue().rstrip())
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'plot',
'my.table$sequence.length',
'my.table$cov.mean',
xlab="'sequence length'",
ylab="'parent-child correlation'",
xaxt="'n'",
#type='"n"',
)
print >> out, get_R_tick_cmd(1, sequence_lengths)
scripts.append(out.getvalue().rstrip())
return scripts
def get_plot_scripts(sequence_lengths):
scripts = []
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'plot',
'my.table$sequence.length',
'my.table$mean.mean',
xlab="''",
ylab="'mean'",
xaxt="'n'",
main="'posterior statistics of rates among branches'",
#type='"n"',
)
print >> out, get_R_tick_cmd(1, sequence_lengths)
scripts.append(out.getvalue().rstrip())
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'plot',
'my.table$sequence.length',
'my.table$var.mean',
xlab="''",
ylab="'coeff of variation'",
xaxt="'n'",
#type='"n"',
)
print >> out, get_R_tick_cmd(1, sequence_lengths)
scripts.append(out.getvalue().rstrip())
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'plot',
'my.table$sequence.length',
'my.table$cov.mean',
xlab="'sequence length'",
ylab="'parent-child correlation'",
xaxt="'n'",
#type='"n"',
)
print >> out, get_R_tick_cmd(1, sequence_lengths)
scripts.append(out.getvalue().rstrip())
return scripts
def get_r_prop_script(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: R code
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
y_low = 0
y_high = 1
ylim = RUtil.mk_call_str('c', y_low, y_high)
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$prop.sel.vs.mut',
type='"l"',
ylim=ylim,
xlab='"time"',
ylab='"proportion"',
main='"proportion of mut-sel MI greater than mutation MI"')
return out.getvalue()
def get_r_prop_script(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: R code
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
y_low = 0
y_high = 1
ylim = RUtil.mk_call_str('c', y_low, y_high)
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$prop.sel.vs.mut',
type='"l"',
ylim=ylim,
xlab='"time"',
ylab='"proportion"',
main='"proportion of mut-sel MI greater than mutation MI"')
return out.getvalue()
def get_response_content(fs):
distn_modes = [x for x in g_ordered_modes if x in fs.distribution]
if not distn_modes:
raise ValueError("no distribution mode was specified")
colors = [g_mode_to_color[m] for m in distn_modes]
arr, headers = make_table(fs, distn_modes)
distn_headers = headers[1:]
# Get the largest value in the array,
# skipping the first column.
arrmax = np.max(arr[:, 1:])
# write the R script body
out = StringIO()
ylim = RUtil.mk_call_str("c", 0, arrmax + 0.1)
sel_str = {BALANCED: "f=1/2", HALPERN_BRUNO: "Halpern-Bruno"}[fs.selection]
print >> out, RUtil.mk_call_str(
"plot",
"my.table$t",
"my.table$%s" % distn_headers[0],
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"expected log L-ratio"',
main='"Effect of selection (%s) on log L-ratio for %d states"' % (sel_str, fs.nstates),
)
for c, header in zip(colors, distn_headers):
print >> out, RUtil.mk_call_str("lines", "my.table$t", "my.table$%s" % header, col='"%s"' % c)
mode_names = [s.replace("_", " ") for s in distn_modes]
legend_name_str = "c(" + ", ".join('"%s"' % s for s in mode_names) + ")"
legend_col_str = "c(" + ", ".join('"%s"' % s for s in colors) + ")"
legend_lty_str = "c(" + ", ".join(["1"] * len(distn_modes)) + ")"
print >> out, RUtil.mk_call_str(
"legend", '"%s"' % fs.legend_placement, legend_name_str, col=legend_col_str, lty=legend_lty_str
)
script_body = out.getvalue()
# create the R plot image
table_string = RUtil.get_table_string(arr, headers)
device_name = Form.g_imageformat_to_r_function[fs.imageformat]
retcode, r_out, r_err, image_data = RUtil.run_plotter(table_string, script_body, device_name)
if retcode:
raise RUtil.RError(r_err)
return image_data
def get_r_tikz_script(nsels, name):
"""
This is obsolete because I am now using pure R output.
@param nsels: the number of mutation-selection balance matrices
@param name: the name of the variable whose histogram should be plotted
@return: tikz code corresponding to an R plot
"""
out = StringIO()
print >> out, RUtil.mk_call_str('hist',
'my.table$%s' % name,
xlab='"%s"' % name,
ylab='"counts"',
main='"%s; N=%d"' % (name, nsels))
return out.getvalue()
def get_r_tikz_script(nsels, name):
"""
This is obsolete because I am now using pure R output.
@param nsels: the number of mutation-selection balance matrices
@param name: the name of the variable whose histogram should be plotted
@return: tikz code corresponding to an R plot
"""
out = StringIO()
print >> out, RUtil.mk_call_str(
'hist',
'my.table$%s' % name,
xlab = '"%s"' % name,
ylab = '"counts"',
main='"%s; N=%d"' % (name, nsels))
return out.getvalue()
def get_r_comboscript(nsels, names):
"""
Do all of the plots at once.
@param nsels: the number of mutation-selection balance matrices
@param names: the names of the variable whose histogram should be plotted
@return: tikz code corresponding to an R plot
"""
out = StringIO()
print >> out, 'par(mfrow=c(3,1))'
for name in names:
print >> out, RUtil.mk_call_str('hist',
'my.table$%s' % name,
xlab='"%s"' % name,
ylab='"counts"',
main='"%s; N=%d"' % (name, nsels))
return out.getvalue()
def get_r_comboscript(nsels, names):
"""
Do all of the plots at once.
@param nsels: the number of mutation-selection balance matrices
@param names: the names of the variable whose histogram should be plotted
@return: tikz code corresponding to an R plot
"""
out = StringIO()
print >> out, 'par(mfrow=c(3,1))'
for name in names:
print >> out, RUtil.mk_call_str(
'hist',
'my.table$%s' % name,
xlab = '"%s"' % name,
ylab = '"counts"',
main='"%s; N=%d"' % (name, nsels))
return out.getvalue()
def get_r_band_script(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: R code
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
mi_mut = time_stats_trans[1]
# set up the correctly sized plot
mi_min_sels = time_stats_trans[6]
mi_max_sels = time_stats_trans[2]
y_low = min(mi_min_sels + mi_mut)
y_high = max(mi_max_sels + mi_mut)
ylim = RUtil.mk_call_str('c', y_low, y_high)
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$mut',
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"MI"',
main='"MI for mut process (red) and %d mut-sel processes"' % nsels)
# draw a light gray polygon covering all selection mutual information
print >> out, RUtil.mk_call_str(
'polygon',
'c(my.table$t, rev(my.table$t))',
'c(my.table$mut.sel.max, rev(my.table$mut.sel.min))',
col='"gray80"',
border='NA')
# draw a darker gray polygon covering most of selection mutual information
print >> out, RUtil.mk_call_str(
'polygon',
'c(my.table$t, rev(my.table$t))',
'c(my.table$mut.sel.high, rev(my.table$mut.sel.low))',
col='"gray50"',
border='NA')
# draw the black line representing the mean selection mutual information
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$mut.sel.mean',
col='"black"')
# draw the red line representing the mutation mutual information
print >> out, RUtil.mk_call_str(
'lines',
'my.table$t',
'my.table$mut',
col='"red"')
return out.getvalue()
def get_response_content(fs):
# create the R table string and scripts
headers = [
'entropy',
'analog']
distributions = []
nstates = 4
npoints = 5000
arr = []
best_pair = None
for i in range(npoints):
weights = [random.expovariate(1) for j in range(nstates)]
total = sum(weights)
distn = [x / total for x in weights]
entropy = -sum(p * math.log(p) for p in distn)
sum_squares = sum(p*p for p in distn)
sum_cubes = sum(p*p*p for p in distn)
analog = math.log(sum_squares / sum_cubes)
row = [entropy, analog]
arr.append(row)
dist = (entropy - 1.0)**2 + (analog - 0.4)**2
if (best_pair is None) or (dist < best_pair[0]):
best_pair = (dist, distn)
# get the R table
table_string = RUtil.get_table_string(arr, headers)
# get the R script
out = StringIO()
title = ', '.join(str(x) for x in best_pair[1])
print >> out, RUtil.mk_call_str(
'plot',
'my.table$entropy',
'my.table$analog',
pch='20',
main='"%s"' % title)
script = out.getvalue()
# create the R plot image
device_name = Form.g_imageformat_to_r_function[fs.imageformat]
retcode, r_out, r_err, image_data = RUtil.run_plotter(
table_string, script, device_name)
if retcode:
raise RUtil.RError(r_err)
return image_data
def get_r_band_script(nsels, time_stats):
"""
@param time_stats: a list of stats for each time point
@return: R code
"""
out = StringIO()
time_stats_trans = zip(*time_stats)
mi_mut = time_stats_trans[1]
# set up the correctly sized plot
mi_min_sels = time_stats_trans[6]
mi_max_sels = time_stats_trans[2]
y_low = min(mi_min_sels + mi_mut)
y_high = max(mi_max_sels + mi_mut)
ylim = RUtil.mk_call_str('c', y_low, y_high)
print >> out, RUtil.mk_call_str(
'plot',
'my.table$t',
'my.table$mut',
type='"n"',
ylim=ylim,
xlab='"time"',
ylab='"MI"',
main='"MI for mut process (red) and %d mut-sel processes"' % nsels)
# draw a light gray polygon covering all selection mutual information
print >> out, RUtil.mk_call_str(
'polygon',
'c(my.table$t, rev(my.table$t))',
'c(my.table$mut.sel.max, rev(my.table$mut.sel.min))',
col='"gray80"',
border='NA')
# draw a darker gray polygon covering most of selection mutual information
print >> out, RUtil.mk_call_str(
'polygon',
'c(my.table$t, rev(my.table$t))',
'c(my.table$mut.sel.high, rev(my.table$mut.sel.low))',
col='"gray50"',
border='NA')
# draw the black line representing the mean selection mutual information
print >> out, RUtil.mk_call_str('lines',
'my.table$t',
'my.table$mut.sel.mean',
col='"black"')
# draw the red line representing the mutation mutual information
print >> out, RUtil.mk_call_str('lines',
'my.table$t',
'my.table$mut',
col='"red"')
return out.getvalue()
def get_r_cross_script(ncrossing_list):
"""
@param time_stats: a list of stats for each time point
@return: R code
"""
out = StringIO()
low = min(ncrossing_list)
high = max(ncrossing_list)
n_to_count = defaultdict(int)
for n in ncrossing_list:
n_to_count[n] += 1
counts = [n_to_count[i] for i in range(low, high+1)]
s = ', '.join('"%s"' % i for i in range(low, high+1))
print >> out, RUtil.mk_call_str(
'barplot',
'c(' + ', '.join(str(x) for x in counts) + ')',
'names.arg=c(' + s + ')',
xlab='"number of crossings"',
ylab='"frequency"',
main='"number of times mut-sel MI crosses mut MI"')
return out.getvalue()
def get_r_cross_script(ncrossing_list):
"""
@param time_stats: a list of stats for each time point
@return: R code
"""
out = StringIO()
low = min(ncrossing_list)
high = max(ncrossing_list)
n_to_count = defaultdict(int)
for n in ncrossing_list:
n_to_count[n] += 1
counts = [n_to_count[i] for i in range(low, high + 1)]
s = ', '.join('"%s"' % i for i in range(low, high + 1))
print >> out, RUtil.mk_call_str(
'barplot',
'c(' + ', '.join(str(x) for x in counts) + ')',
'names.arg=c(' + s + ')',
xlab='"number of crossings"',
ylab='"frequency"',
main='"number of times mut-sel MI crosses mut MI"')
return out.getvalue()
def get_response_content(fs):
# create the R table string and scripts
headers = ['entropy', 'analog']
distributions = []
nstates = 4
npoints = 5000
arr = []
best_pair = None
for i in range(npoints):
weights = [random.expovariate(1) for j in range(nstates)]
total = sum(weights)
distn = [x / total for x in weights]
entropy = -sum(p * math.log(p) for p in distn)
sum_squares = sum(p * p for p in distn)
sum_cubes = sum(p * p * p for p in distn)
analog = math.log(sum_squares / sum_cubes)
row = [entropy, analog]
arr.append(row)
dist = (entropy - 1.0)**2 + (analog - 0.4)**2
if (best_pair is None) or (dist < best_pair[0]):
best_pair = (dist, distn)
# get the R table
table_string = RUtil.get_table_string(arr, headers)
# get the R script
out = StringIO()
title = ', '.join(str(x) for x in best_pair[1])
print >> out, RUtil.mk_call_str('plot',
'my.table$entropy',
'my.table$analog',
pch='20',
main='"%s"' % title)
script = out.getvalue()
# create the R plot image
device_name = Form.g_imageformat_to_r_function[fs.imageformat]
retcode, r_out, r_err, image_data = RUtil.run_plotter(
table_string, script, device_name)
if retcode:
raise RUtil.RError(r_err)
return image_data
def get_ggplot2_x_tick_cmd(positions):
s = 'c(' + ', '.join(str(x) for x in positions) + ')'
return RUtil.mk_call_str('scale_x_discrete', breaks=s)
def get_ggplot2_scripts(nsamples, sequence_lengths, midpoints):
scripts = []
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str(
'aes',
x='midpoint',
y='mean.mean')), '+'
print >> out, RUtil.mk_call_str(
'geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='mean.low',
ymax='mean.high',
colour='factor(sequence.length)'),
width='20'), '+'
print >> out, "opts(title='mcmc chain length %d') +" % nsamples
print >> out, "geom_point() + xlab('midpoint') + ylab('mean of rates') +"
print >> out, "scale_color_discrete('length') +"
print >> out, get_ggplot2_x_tick_cmd(midpoints)
scripts.append(out.getvalue().rstrip())
# get the plot for the coefficient of variation
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str(
'aes',
x='midpoint',
y='var.mean')), '+'
print >> out, RUtil.mk_call_str(
'geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='var.low',
ymax='var.high',
colour='factor(sequence.length)'),
width='20'), '+'
print >> out, "geom_point() + xlab('midpoint') +"
print >> out, "ylab('coefficient of variation of rates') +"
print >> out, "scale_color_discrete('length') +"
print >> out, get_ggplot2_x_tick_cmd(midpoints)
scripts.append(out.getvalue().rstrip())
# get the plot for the correlation
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str(
'aes',
x='midpoint',
y='cov.mean')), '+'
print >> out, RUtil.mk_call_str(
'geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='cov.low',
ymax='cov.high',
colour='factor(sequence.length)'),
width='20'), '+'
print >> out, "geom_point() + xlab('midpoint') +"
print >> out, "ylab('parent child correlation of rates') +"
print >> out, "scale_color_discrete('length') +"
print >> out, get_ggplot2_x_tick_cmd(midpoints)
scripts.append(out.getvalue().rstrip())
return scripts
def get_ggplot2_legend_cmd():
s_labels = "c('57', '114', '228', '456')"
return RUtil.mk_call_str('scale_colour_discrete',
labels=s_labels)
def get_ggplot2_x_tick_cmd(positions):
s = 'c(' + ', '.join(str(x) for x in positions) + ')'
return RUtil.mk_call_str('scale_x_discrete', breaks=s)
def get_ggplot2_scripts(sequence_lengths):
scripts = []
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str(
'aes',
x='sequence.length',
y='mean.mean')), '+'
print >> out, RUtil.mk_call_str(
'geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='mean.low',
ymax='mean.high'),
width='20'), '+'
print >> out, "geom_point() + xlab('sequence length') + ylab('mean') +"
print >> out, get_ggplot2_x_tick_cmd(sequence_lengths)
scripts.append(out.getvalue().rstrip())
# get the plot for the coefficient of variation
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str(
'aes',
x='sequence.length',
y='var.mean')), '+'
print >> out, RUtil.mk_call_str(
'geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='var.low',
ymax='var.high'),
width='20'), '+'
print >> out, "geom_point() + xlab('sequence length') +"
print >> out, "ylab('coefficient of variation') +"
print >> out, get_ggplot2_x_tick_cmd(sequence_lengths)
scripts.append(out.getvalue().rstrip())
# get the plot for the correlation
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str(
'aes',
x='sequence.length',
y='cov.mean')), '+'
print >> out, RUtil.mk_call_str(
'geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='cov.low',
ymax='cov.high'),
width='20'), '+'
print >> out, "geom_point() + xlab('sequence length') +"
print >> out, "ylab('parent child correlation') +"
print >> out, get_ggplot2_x_tick_cmd(sequence_lengths)
scripts.append(out.getvalue().rstrip())
return scripts
def get_ggplot2_scripts(sequence_lengths):
scripts = []
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str('aes', x='sequence.length', y='mean.mean')), '+'
print >> out, RUtil.mk_call_str('geom_errorbar',
RUtil.mk_call_str('aes',
ymin='mean.low',
ymax='mean.high'),
width='20'), '+'
print >> out, "geom_point() + xlab('sequence length') + ylab('mean') +"
print >> out, get_ggplot2_x_tick_cmd(sequence_lengths)
scripts.append(out.getvalue().rstrip())
# get the plot for the coefficient of variation
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str('aes', x='sequence.length', y='var.mean')), '+'
print >> out, RUtil.mk_call_str('geom_errorbar',
RUtil.mk_call_str('aes',
ymin='var.low',
ymax='var.high'),
width='20'), '+'
print >> out, "geom_point() + xlab('sequence length') +"
print >> out, "ylab('coefficient of variation') +"
print >> out, get_ggplot2_x_tick_cmd(sequence_lengths)
scripts.append(out.getvalue().rstrip())
# get the plot for the correlation
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str('aes', x='sequence.length', y='cov.mean')), '+'
print >> out, RUtil.mk_call_str('geom_errorbar',
RUtil.mk_call_str('aes',
ymin='cov.low',
ymax='cov.high'),
width='20'), '+'
print >> out, "geom_point() + xlab('sequence length') +"
print >> out, "ylab('parent child correlation') +"
print >> out, get_ggplot2_x_tick_cmd(sequence_lengths)
scripts.append(out.getvalue().rstrip())
return scripts
def get_ggplot2_legend_cmd():
s_labels = "c('57', '114', '228', '456')"
return RUtil.mk_call_str('scale_colour_discrete', labels=s_labels)
def get_ggplot2_scripts(nsamples, sequence_lengths, midpoints):
scripts = []
# get the plot for the mean
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str('aes', x='midpoint', y='mean.mean')), '+'
print >> out, RUtil.mk_call_str('geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='mean.low',
ymax='mean.high',
colour='factor(sequence.length)'),
width='20'), '+'
print >> out, "opts(title='mcmc chain length %d') +" % nsamples
print >> out, "geom_point() + xlab('midpoint') + ylab('mean of rates') +"
print >> out, "scale_color_discrete('length') +"
print >> out, get_ggplot2_x_tick_cmd(midpoints)
scripts.append(out.getvalue().rstrip())
# get the plot for the coefficient of variation
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str('aes', x='midpoint', y='var.mean')), '+'
print >> out, RUtil.mk_call_str('geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='var.low',
ymax='var.high',
colour='factor(sequence.length)'),
width='20'), '+'
print >> out, "geom_point() + xlab('midpoint') +"
print >> out, "ylab('coefficient of variation of rates') +"
print >> out, "scale_color_discrete('length') +"
print >> out, get_ggplot2_x_tick_cmd(midpoints)
scripts.append(out.getvalue().rstrip())
# get the plot for the correlation
out = StringIO()
print >> out, RUtil.mk_call_str(
'ggplot', 'my.table',
RUtil.mk_call_str('aes', x='midpoint', y='cov.mean')), '+'
print >> out, RUtil.mk_call_str('geom_errorbar',
RUtil.mk_call_str(
'aes',
ymin='cov.low',
ymax='cov.high',
colour='factor(sequence.length)'),
width='20'), '+'
print >> out, "geom_point() + xlab('midpoint') +"
print >> out, "ylab('parent child correlation of rates') +"
print >> out, "scale_color_discrete('length') +"
print >> out, get_ggplot2_x_tick_cmd(midpoints)
scripts.append(out.getvalue().rstrip())
return scripts
