def update_plot(gkey, graph_conf, plot, plot_data):
"""Determine x axis breaks and add rolled dice symbols to plot."""
# Determine x axis breaks
x_breaks = plot_data.copy()
x_breaks = x_breaks[graph_conf["xlab"]].drop_duplicates().tolist()
x_breaks.sort()
x_labels = [" "] + [abs(x) for x in x_breaks] + [" "]
x_breaks = [x_breaks[0] - 0.5] + x_breaks + [x_breaks[-1] + 0.5]
plot += ggplot.scale_x_discrete(breaks=x_breaks, labels=x_labels)
# Add rolled dice symbols
top0 = graph_conf["limits"][1] - 1
top1 = top0 - 1.2
left0 = x_breaks[1]
left1 = left0
colors = {"b": "#000000", "B": "#87CEFA", "c": "#ff0000", "d": "#4B0082", "C": "#ffff00", "D": "#008000"}
pad = len(x_breaks) * 0.0235
for letter in graphs[gkey]["dice_key"]:
if letter in "CDB":
color = colors[letter]
plot += ggplot.geom_text(
label=[letter.lower()], x=[left0, left0 + 1], y=[top0, top0 - 1], color=color, family="EotE Symbol"
)
left0 += pad
else:
color = colors[letter]
plot += ggplot.geom_text(
label=[letter.lower()], x=[left1, left1 + 1], y=[top1, top1 - 1], color=color, family="EotE Symbol"
)
left1 += pad
return plot
def plot_outcomes(self, chart_title=None, use_ggplot=False):
""" Plot the outcomes of patients observed.
:param chart_title: optional chart title. Default is fairly verbose
:type chart_title: str
:param use_ggplot: True to use ggplot, else matplotlib
:type use_ggplot: bool
:return: a plot of patient outcomes
"""
if not chart_title:
chart_title="Each point represents a patient\nA circle indicates no toxicity, a cross toxicity"
chart_title = chart_title + "\n"
if use_ggplot:
if self.size() > 0:
from ggplot import (ggplot, ggtitle, geom_text, aes, ylim)
import numpy as np
import pandas as pd
patient_number = range(1, self.size()+1)
symbol = np.where(self.toxicities(), 'X', 'O')
data = pd.DataFrame({'Patient number': patient_number,
'Dose level': self.doses(),
'DLT': self.toxicities(),
'Symbol': symbol})
p = ggplot(data, aes(x='Patient number', y='Dose level', label='Symbol')) \
+ ggtitle(chart_title) + geom_text(aes(size=20, vjust=-0.07)) + ylim(1, 5)
return p
else:
if self.size() > 0:
import matplotlib.pyplot as plt
import numpy as np
patient_number = np.arange(1, self.size()+1)
doses_given = np.array(self.doses())
tox_loc = np.array(self.toxicities()).astype('bool')
if sum(tox_loc):
plt.scatter(patient_number[tox_loc], doses_given[tox_loc], marker='x', s=300,
facecolors='none', edgecolors='k')
if sum(~tox_loc):
plt.scatter(patient_number[~tox_loc], doses_given[~tox_loc], marker='o', s=300,
facecolors='none', edgecolors='k')
plt.title(chart_title)
plt.ylabel('Dose level')
plt.xlabel('Patient number')
plt.yticks(self.dose_levels())
p = plt.gcf()
phi = (np.sqrt(5)+1)/2.
p.set_size_inches(12, 12/phi)
def plot(self, inputs):
"""Plot the given X and Y axes on a scatter plot"""
if inputs.year not in self.dat.Year.values:
return
if inputs.xvar not in self.dat or inputs.yvar not in self.dat:
return
subdat = self.dat[self.dat.Year == inputs.year]
p = ggplot(subdat, aes(x=inputs.xvar, y=inputs.yvar))
p = p + geom_point()
if inputs.shownames:
p = p + geom_text(aes(label=self.ID_col), vjust=1, hjust=1)
if inputs.linear:
p = p + stat_smooth(color="red", method="lm")
return p
def plot(self, inputs):
"""Plot the given X and Y axes on a scatter plot"""
if inputs.year not in self.dat.Year.values:
return
if inputs.xvar not in self.dat or inputs.yvar not in self.dat:
return
subdat = self.dat[self.dat.Year == inputs.year]
p = ggplot(subdat, aes(x=inputs.xvar, y=inputs.yvar))
p = p + geom_point()
if inputs.shownames:
p = p + geom_text(aes(label=self.ID_col), vjust=1, hjust=1)
if inputs.linear:
p = p + stat_smooth(color="red", method="lm")
return p
m=1,
alpha=alpha))
#save results to results folder, with plot and printing to screen.
metadata = datetime.datetime.now().strftime(
"%Y-%m-%d %H:%M:%S") + "test_mode==" + str(test_mode)
f = open("results/LSH_vs_KDT_%s.pkl" % metadata, mode='w')
pkl.dump(obj=results, file=f)
logtimes = [math.log(r.avg_time, 2) for r in results]
distances = [r.avg_distance for r in results]
methods = [r.method[0:3] for r in results]
alpha = [r.alpha for r in results]
m = [r.m for r in results]
results_df = pd.DataFrame(
data={
"logtimes": logtimes,
"distances": distances,
"methods": methods,
"m": m,
"alpha": alpha
})
print results_df
p = gg.ggplot(data = results_df, aesthetics = gg.aes(x = "logtimes",
y = "distances",
label = "methods")) + \
gg.geom_text() + \
gg.ggtitle("LSH and KD trees: tradeoffs") + \
gg.xlab("Log2 average query time ") + gg.ylab("Average L2 distance from query point)")
gg.ggsave(filename="results/LSH_vs_KDT_%s.png" % metadata, plot=p)
#Testing
results = []
for m in mvals:
results.append(test_approx_nn(method = "hashing", traindata=docdata, testdata = testdata, m=m, alpha=1))
for alpha in avals:
results.append(test_approx_nn(method = "kdtree" , traindata=docdata, testdata = testdata, m=1, alpha=alpha))
#save results to results folder, with plot and printing to screen.
metadata = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S") + "test_mode==" + str(test_mode)
f = open("results/LSH_vs_KDT_%s.pkl" % metadata, mode = 'w')
pkl.dump(obj=results, file=f)
logtimes = [math.log(r.avg_time, 2) for r in results]
distances = [r.avg_distance for r in results]
methods = [r.method[0:3] for r in results]
alpha = [r.alpha for r in results]
m = [r.m for r in results]
results_df = pd.DataFrame(data = {"logtimes" : logtimes,
"distances" : distances,
"methods" : methods,
"m":m,
"alpha": alpha})
print results_df
p = gg.ggplot(data = results_df, aesthetics = gg.aes(x = "logtimes",
y = "distances",
label = "methods")) + \
gg.geom_text() + \
gg.ggtitle("LSH and KD trees: tradeoffs") + \
gg.xlab("Log2 average query time ") + gg.ylab("Average L2 distance from query point)")
gg.ggsave(filename="results/LSH_vs_KDT_%s.png" % metadata, plot = p)
def main():
global args, ruleset
# Arguments Parser
argparser, subparser = parser_setup()
register_rules(subparser)
args = argparser.parse_args()
rulemod = sys.modules["rpgdice.rulesets.%s" % args.ruleset]
rulemod.prepare(args, srand)
if args.debug:
print "DEBUG: args", args
print
results = list()
pool = multiprocessing.Pool()
try:
for result in pool.map(rulemod.simulate_rolls, rulemod.variables):
results.extend(result)
pool.close()
pool.join()
except KeyboardInterrupt:
sys.exit(130)
if args.debug:
print "DEBUG: results:"
pprint(results)
print
conf = dict()
conf = {"vlab": "Variables", "xlab": "Outcome", "ylab": "Probability %"}
for item in conf:
try:
conf[item] = getattr(rulemod, item)
except:
pass
columns = ("Graph", conf["vlab"], conf["xlab"], "Count", conf["ylab"])
data = pandas.DataFrame.from_records(results, columns=columns)
# Create and save graphs
for gkey in rulemod.graphs:
# Graph Defaults
graph_conf = conf.copy()
graph_conf["file_prefix"] = "%s%02d" % (args.ruleset, gkey)
graph_conf["file_suffix"] = str()
# colors
colors_lower = ["#ff0000", "#cc0000", "#993300", "#666600"]
colors_upper = ["#006666", "#003399", "#0000cc", "#0000ff"]
colors_mid = ["#000000"]
color_count = len(rulemod.variables) - 1
if color_count % 2 == 0:
lower_slice = (color_count / 2) * -1
upper_slice = color_count / 2
else:
lower_slice = ((color_count - 1) / 2) * -1
upper_slice = (color_count + 1) / 2
graph_conf["color_list"] = colors_lower[lower_slice:] + colors_mid + colors_upper[0:upper_slice]
# graph_conf from graph
graph_items = (
"color_list",
"file_prefix",
"file_suffix",
"graph_type",
"limits",
"x_breaks",
"x_labels",
"title",
"vlab",
"xlab",
"ylab",
)
for item in graph_items:
try:
graph_conf[item] = rulemod.graphs[gkey][item]
except:
try:
graph_conf[item] = getattr(rulemod, item)
except:
if item not in graph_conf:
graph_conf[item] = None
if args.debug:
print "DEBUG: graph_conf:"
pprint(graph_conf)
print
# plot_data
plot_data = data.copy()
plot_data = plot_data[plot_data["Graph"] == gkey]
plot_data.rename(
columns={
conf["vlab"]: graph_conf["vlab"],
conf["xlab"]: graph_conf["xlab"],
conf["ylab"]: graph_conf["ylab"],
},
inplace=True,
)
plot_data.index = range(1, len(plot_data) + 1)
if args.debug:
print "DEBUG: plot_data:"
pprint(plot_data)
print
# Create plot
if args.graph:
plot = (
ggplot.ggplot(
ggplot.aes(x=graph_conf["xlab"], y=graph_conf["ylab"], color=graph_conf["vlab"]), data=plot_data
)
+ ggplot.ggtitle(graph_conf["title"])
+ ggplot.theme_gray()
+ ggplot.scale_colour_manual(values=graph_conf["color_list"])
)
plot.rcParams["font.family"] = "monospace"
if graph_conf["x_breaks"] and graph_conf["x_labels"]:
plot += ggplot.scale_x_discrete(breaks=graph_conf["x_breaks"], labels=graph_conf["x_labels"])
if graph_conf["limits"]:
plot += ggplot.ylim(graph_conf["limits"][0], graph_conf["limits"][1])
if graph_conf["graph_type"] == "bars":
plot += ggplot.geom_line(size=20)
text_data = plot_data[plot_data["Count"] > 0]
text_data.index = range(0, len(text_data))
outcomes = dict(text_data[graph_conf["xlab"]])
percents = dict(text_data[graph_conf["ylab"]])
for k in outcomes:
percent = "%4.1f%%" % percents[k]
x = outcomes[k]
y = percents[k] + 4
color = graph_conf["color_list"][k]
plot += ggplot.geom_text(label=[percent], x=[x, x + 1], y=[y, y - 1], color=color)
else:
plot += ggplot.geom_line()
plot += ggplot.geom_point(alpha=0.3, size=50)
if hasattr(rulemod, "update_plot"):
plot = rulemod.update_plot(gkey, graph_conf, plot, plot_data)
if args.dumpsave:
filename = "/dev/null"
else:
filename = "%s%s.png" % (graph_conf["file_prefix"], graph_conf["file_suffix"])
ggplot.ggsave(filename, plot, format="png", dpi=300)
return 0
