def stats(self):
res = {}
for val in self.data.iteritems():
stat_report = {}
full_series = map(lambda x: x, val[1])
full_series = full_series[(len(full_series) / 4):] # Cut off first quarter to get more reliable data
full_series_sorted = full_series
full_series_sorted.sort()
steady_series = full_series[int(len(full_series) * 0.7):]
stat_report['mean'] = stats.mean(full_series)
try:
stat_report['stdev'] = stats.stdev(full_series)
except ZeroDivisionError:
stat_report['stdev'] = 0
stat_report['upper_0.1_percentile'] = self.percentile(full_series_sorted, 0.999)
stat_report['lower_0.1_percentile'] = self.percentile(full_series_sorted, 0.001)
stat_report['upper_1_percentile'] = self.percentile(full_series_sorted, 0.99)
stat_report['lower_1_percentile'] = self.percentile(full_series_sorted, 0.01)
stat_report['upper_5_percentile'] = self.percentile(full_series_sorted, 0.95)
stat_report['lower_5_percentile'] = self.percentile(full_series_sorted, 0.05)
stat_report['steady_mean'] = stats.mean(steady_series)
try:
stat_report['steady_stdev'] = stats.stdev(full_series)
except ZeroDivisionError:
stat_report['steady_stdev'] = 0
res[val[0]] = stat_report
return res
def getRMSEstd(res, nFolds):
"""
Method for calculating the std of RMSE of nFolds in a crossvalidation (returned).
res is the object containing the results from orngTest methods such as crossValidation.
"""
# Initialize a list to contain lists of errors for each fold.
errorList = []
for idx in range(nFolds):
errorList.append([])
# ex contains info on the fold number, prediction and actural responses for exah example used in the CV
# Append ex error to correct fold list
for ex in res.results:
error = (ex.classes[0] - ex.actualClass)**2
errorList[ex.iterationNumber].append(error)
# RMSE of the different folds
RMSElist = []
for idx in range(nFolds):
average = sum(errorList[idx]) / len(errorList[idx])
RMSElist.append(math.sqrt(average))
RMSEstd = stats.stdev(RMSElist)
RMSEmean = statc.mean(RMSElist)
if verbose > 0:
print str(RMSEmean) + "\t" + str(RMSEstd) + "\t" + string.join(
[str(x) for x in RMSElist], "\t")
return RMSEstd, RMSElist
def get_mean_times(data, buildtype, include_outliers):
return_data = defaultdict(lambda: defaultdict(float))
all_times = reduce(lambda x,y: x+y, reduce(lambda x,y: x+y, map(lambda d: d.values(), data.values())))
overall_mean = stats.mean(all_times)
overall_stdev = stats.stdev(all_times)
for (date, dateval) in data.iteritems():
typedict = {}
for (type, times) in dateval.iteritems():
mean = stats.mean(times)
if not include_outliers and len(times) > 1:
included_values = []
for time in times:
if abs(time - overall_mean) < 1.5*overall_stdev:
included_values.append(time)
if len(included_values) > 0:
mean = stats.mean(included_values)
else:
mean = None
typedict[type] = mean
if buildtype == "maximum" and max(typedict.values()):
return_data[date] = max(typedict.values())
elif typedict.get(buildtype):
return_data[date] = typedict.get(buildtype, 0)
return return_data
def set_quality_mean_and_variation_per_position(self):
self.read_all_quality_strings_by_position()
self.means = [mean(self.quality_string2score(s)) for s in self.quality_strings]
self.stdevs = [stdev(self.quality_string2score(s)) for s in self.quality_strings]
# relase the memory for quality_strings
self.quality_strings = None
def main():
(opts, args) = parser.parse_args()
if len(args) != 1:
print "\nPlease, select channel: 0/1\n"
parser.print_help()
else:
if opts.verbose:
verbose = True
print "connecting to ", opts.ip_addr
print "port number", opts.ip_port
message = args[0]
message = sendReceive(opts.ip_addr, opts.ip_port, opts.timeout,
message, opts.verbose)
#print "String:"
#print message
#print "Hex:"
hexMessage = b2a_hex(message)
#print hexMessage
print "No. bytes: ", len(message)
print "Done!"
#Unpacking message
msg_len = len(message)
num = unpack(str(msg_len) + 'B', message)
#print num
num = map(lambda x: x - 128, num)
#print num
print "Maximum: ", max(num), "Minimum: ", min(
num), "Mean: ", stats.mean(
num), "Standard deviation: ", stats.stdev(
num), "Variance: ", stats.var(num)
def main():
global qtimes,qerr
reps = int(sys.argv[1])
for j in range(reps):
jobs = [gevent.spawn(get_url, url) for url in urls]
#print("Size of jobs is {n}".format(n=len(jobs)))
gevent.joinall(jobs, timeout=30)
if not qerr.empty():
qerr.put(StopIteration)
for err in qerr:
print(err)
print("jobs size {s}".format(s=len(jobs)))
print("qstart size {n}".format(n=qstart.qsize()))
print("qtimes size {n}".format(n=qtimes.qsize()))
qtimes.put(StopIteration)
times = []
for item in qtimes:
times.append(item)
print("Min {t}".format(t=min(times)))
print("Max {t}".format(t=max(times)))
print("Mean {t}".format(t=stats.mean(times)))
print("StdDev {t}".format(t=stats.stdev(times)))
def getRMSEstd(res, nFolds):
"""
Method for calculating the std of RMSE of nFolds in a crossvalidation (returned).
res is the object containing the results from orngTest methods such as crossValidation.
"""
# Initialize a list to contain lists of errors for each fold.
errorList = []
for idx in range(nFolds):
errorList.append([])
# ex contains info on the fold number, prediction and actural responses for exah example used in the CV
# Append ex error to correct fold list
for ex in res.results:
error = (ex.classes[0]- ex.actualClass)**2
errorList[ex.iterationNumber].append(error)
# RMSE of the different folds
RMSElist = []
for idx in range(nFolds):
average = sum(errorList[idx])/len(errorList[idx])
RMSElist.append(math.sqrt(average))
RMSEstd = stats.stdev(RMSElist)
RMSEmean = statc.mean(RMSElist)
if verbose > 0: print str(RMSEmean)+"\t"+str(RMSEstd)+"\t"+string.join( [str(x) for x in RMSElist], "\t")
return RMSEstd, RMSElist
def main():
'''
this is the main section
{kernel: {machine : {[results]} } }
'''
scales = {}
data = send(template())
for kernel, results in data.iteritems():
for testid, run_data in results.iteritems():
machine = run_data.pop(0)
print "\n%s" % (kernel,)
for i in range(len(run_data)):
for single_bench in run_data[i].itervalues():
if type(single_bench) == dict:
value = [float(x) for x in
single_bench.get("RawString").split(":")]
val = stats.mean(value)
if len(value) > 1:
std = stats.stdev(value)
else:
std = float(0)
name = single_bench.get("Name")
attr = single_bench.get("Attributes")
scale = single_bench.get("Scale")
print "%s: %s (%s): %.2f %s (std %.2f)" % (machine,
name, attr, val, scale, std)
scales[scale] = scales.get(scale, "")
print scales
def histogram(self, out_fname, large = False):
assert self.data
# Hacky workaround in the case that a run had no data.
for x in self.data.values():
if len(x) == 0: x.extend([0,0])
if not large:
font = fm.FontProperties(family=['sans-serif'],size='small',fname=FONT_FILE)
mpl.rcParams['xtick.major.pad'] = 4
mpl.rcParams['ytick.major.pad'] = 4
mpl.rcParams['lines.linewidth'] = 1
else:
font = fm.FontProperties(family=['sans-serif'],size=36,fname=FONT_FILE)
mpl.rcParams['xtick.major.pad'] = 20
mpl.rcParams['ytick.major.pad'] = 20
mpl.rcParams['lines.linewidth'] = 5
fig = plt.figure()
# Set the margins for the plot to ensure a minimum of whitespace
ax = plt.axes([0.12,0.12,0.85,0.85])
data = map(lambda x: x[1], self.data.iteritems())
mean = stats.mean(map(lambda x: x, reduce(lambda x, y: x + y, data)))
stdev = stats.stdev(map(lambda x: x, reduce(lambda x, y: x + y, data)))
labels = []
hists = []
for series, color in zip(self.data.iteritems(), colors):
clipped_data = clip(series[1], 0, 3 * mean)
if clipped_data:
_, _, foo = ax.hist(clipped_data, bins=200, histtype='bar', facecolor = color, alpha = .5, label = series[0])
hists.append(foo)
labels.append(series[0])
else:
print "Tried to make a histogram of a series of size 0"
for tick in ax.xaxis.get_major_ticks():
tick.label1.set_fontproperties(font)
for tick in ax.yaxis.get_major_ticks():
tick.label1.set_fontproperties(font)
ax.set_ylabel('Frequency', fontproperties = font)
ax.set_xlabel('Latency (microseconds)', fontproperties = font) #simply should not be hardcoded but we want nice pictures now
ax.grid(True)
# Dirty hack to get around legend miscoloring: drop all the hists generated into the legend one by one
if hists:
plt.legend(map(lambda x: x[0], hists), labels, loc=1, prop = font)
if not large:
fig.set_size_inches(5,3.7)
fig.set_dpi(90)
plt.savefig(out_fname, bbox_inches="tight")
else:
ax.yaxis.LABELPAD = 40
ax.xaxis.LABELPAD = 40
fig.set_size_inches(20,14.8)
fig.set_dpi(300)
plt.savefig(out_fname, bbox_inches="tight")
def set_quality_mean_and_variation_per_position(self):
self.read_all_quality_strings_by_position()
self.means = [mean(self.quality_string2score(s))
for s in self.quality_strings]
self.stdevs = [stdev(self.quality_string2score(s))
for s in self.quality_strings]
# relase the memory for quality_strings
self.quality_strings = None
def weighSample():
listOfValues = []
weight = float(0.0)
count = 0
kcount = 0
averageWeight = 0.0
stdevWeight = 0.0
statustext = "Weighing sample"
STATUS.set(statustext)
statusWindow.update()
a = []
ACOUNT.set(0)
MCOUNT.set(0)
AVERAGEWEIGHT.set(0.0)
STDDEVWEIGHT.set(0.0)
STATUS.set("")
statusWindow.update()
weightArray = []
stopCheck = STOPPED.get()
averageWeight = 0.0
stdevWeight = 0.0
while STOPPED.get() < 1:
statusWindow.update()
result = []
weight = readStandardBalance()
#print "WEIGHT: ", weight
ACOUNT.set(ACOUNT.get() + 1)
statusWindow.update()
if weight is FALSE:
pass
elif weight > 0.0:
count += 1
weightArray.append(weight)
if (STOPPED.get() < 1 ):
if count > 4:
averageWeight = stats.mean(weightArray)
stdevWeight = stats.stdev(weightArray)
MCOUNT.set(count)
if count < 5:
statustext = " Count: %d the average weight of sample is <need at least 5 measurements>" % (count)
else:
statustext = "Count: %d the average weight of sample is: %f with stdev of: %f" % (
count, averageWeight, stdevWeight)
STATUS.set(statustext)
AVERAGEWEIGHT.set(averageWeight)
STDDEVWEIGHT.set(stdevWeight)
statusWindow.update()
stopCheck = STOPPED.get()
else:
is_there_a_sample()
sleep(1)
NEXTSTEP.set(1)
AVERAGEWEIGHT.set(averageWeight)
STDDEVWEIGHT.set(stdevWeight)
MCOUNT.set(count)
return count, averageWeight, stdevWeight
def letters_between_spaces(str):
#count the average word size
words = str.split()
wordCount = len(words)
ch = []
for word in words:
ch.append(len(word))
letterCountAverage = stats.mean(ch)
letterCountStdDev = stats.stdev(ch)
return None, {'letterAve/StdDev':letterCountAverage / letterCountStdDev}
def getmeanstdev(dist, center):
# find the mean and standard deviation of the distance of each tract in a district from its centroid
buildlist = []
for bginfo in attributes:
if attributes[bginfo][13] == dist:
buildlist.append(sqrt((center[0] - attributes[bginfo][1][0])**2 + (center[1] - attributes[bginfo][1][1])**2))
return stats.mean(buildlist), stats.stdev(buildlist)
def getmeanstdev(dist, center):
# find the mean and standard deviation of the distance of each tract in a district from its centroid
buildlist = []
for bginfo in attributes:
if attributes[bginfo][13] == dist:
buildlist.append(
sqrt((center[0] - attributes[bginfo][1][0])**2 +
(center[1] - attributes[bginfo][1][1])**2))
return stats.mean(buildlist), stats.stdev(buildlist)
def main():
if len(sys.argv) < 3:
print "Usage!"
exit(1)
database = sys.argv[2]
points = sys.argv[1]
boxData = csv.reader(open(points, "rb"))
boxes = []
for row in boxData:
if len(row) == 4:
boxes.append({"time": long(row[0]), "size": float(row[1]), "position": (int(row[2]), int(row[3]))})
else:
finishTime = long(row[0].split(":")[1])
conn = sqlite3.connect(database)
cur = conn.cursor()
cur.execute(
'select datetime,data from clues where kind="touch" and datetime between %d and %d'
% (boxes[0]["time"], finishTime)
)
touches = []
for touch in cur:
time = long(touch[0])
data = touch[1].split(",")
touches.append({"time": long(touch[0]), "position": (int(data[0]), int(data[1])), "pressure": float(data[2])})
timesForSize = {30: [], 60: [], 99: [], 129: []}
mmsizes = {30: 3, 60: 6, 99: 10, 129: 13}
deltas = []
for i, box in enumerate(boxes[:-1]):
delta = (boxes[i + 1]["time"] - box["time"]) / 1000.0
timesForSize[box["size"]].append(delta)
deltas.append(delta)
deltas.append((finishTime - boxes[-1]["time"]) / 1000.0)
for k, v in sorted(timesForSize.iteritems()):
print "%d: %.3f/%.3f/%.3f/%.3f (%.3f bps)" % (
mmsizes[k],
stats.mean(v),
min(v),
max(v),
stats.stdev(v),
1 / stats.mean(v),
)
def stats(self):
res = {}
for val in self.data.iteritems():
stat_report = {}
full_series = map(lambda x: x, val[1])
full_series = full_series[(
len(full_series) /
4):] # Cut off first quarter to get more reliable data
full_series_sorted = full_series
full_series_sorted.sort()
steady_series = full_series[int(len(full_series) * 0.7):]
stat_report['mean'] = stats.mean(full_series)
try:
stat_report['stdev'] = stats.stdev(full_series)
except ZeroDivisionError:
stat_report['stdev'] = 0
stat_report['upper_0.1_percentile'] = self.percentile(
full_series_sorted, 0.999)
stat_report['lower_0.1_percentile'] = self.percentile(
full_series_sorted, 0.001)
stat_report['upper_1_percentile'] = self.percentile(
full_series_sorted, 0.99)
stat_report['lower_1_percentile'] = self.percentile(
full_series_sorted, 0.01)
stat_report['upper_5_percentile'] = self.percentile(
full_series_sorted, 0.95)
stat_report['lower_5_percentile'] = self.percentile(
full_series_sorted, 0.05)
stat_report['steady_mean'] = stats.mean(steady_series)
try:
stat_report['steady_stdev'] = stats.stdev(full_series)
except ZeroDivisionError:
stat_report['steady_stdev'] = 0
res[val[0]] = stat_report
return res
def RMSE_obsolete(res=None):
"""
Calculates the Root Mean Squared Error of orngTest.ExperimentResults in res
The results res must be from a regressor
"""
# If Called without arguments, return the type of problems this method can be used for:
# 1 - Classification problems (Discrete Class)
# 2 - Regression problems (Continuous Class)
# 3 - Both Regression and Classification problems (Continuous or Discrete Class)
if res == None:
return {"type": REGRESSION}
if res.numberOfIterations > 1:
MSEs = [[0.0] * res.numberOfIterations
for i in range(res.numberOfLearners)]
nIter = [0] * res.numberOfIterations
for tex in res.results:
ac = float(tex.actualClass)
nIter[tex.iterationNumber] += 1
for i, cls in enumerate(tex.classes):
MSEs[i][tex.iterationNumber] += (float(cls) - ac)**2
MSEs = [[x / ni for x, ni in zip(y, nIter)] for y in MSEs]
MSEs = [[math.sqrt(x) for x in y] for y in MSEs]
# Print output from each fold to tem file
RMSEfoldList = MSEs
RMSE = [statc.mean(x) for x in RMSEfoldList]
RMSEstd = stats.stdev(RMSEfoldList[0])
#print str(RMSE[0])+"\t"+str(RMSEstd)+"\t"+string.join( [str(x) for x in RMSEfoldList[0]] , "\t")
return [round(statc.mean(x), 2) for x in MSEs]
else:
MSEs = [0.0] * res.numberOfLearners
for tex in res.results:
MSEs = map(lambda res, cls, ac=float(tex.actualClass): res +
(float(cls) - ac)**2,
MSEs,
tex.classes)
MSEs = [x / (len(res.results)) for x in MSEs]
return [round(math.sqrt(x), 2) for x in MSEs]
def CA_obsolete(res=None, returnFoldStat=False):
"""
Calculates the classification Accuracy of orngTest.ExperimentResults in res
The results res must be from a classifier
"""
# If Called without arguments, return the type of problems this method can be used for:
# 1 - Classification problems (Discrete Class)
# 2 - Regression problems (Continuous Class)
# 3 - Both Regression and Classification problems (Continuous or Discrete Class)
if res == None:
return {"type": CLASSIFICATION}
if res.numberOfIterations > 1:
CAs = [[0.0] * res.numberOfIterations
for i in range(res.numberOfLearners)]
nIter = [0] * res.numberOfIterations
for tex in res.results:
ac = tex.actualClass
nIter[tex.iterationNumber] += 1
for i, cls in enumerate(tex.classes):
if cls == ac:
CAs[i][tex.iterationNumber] += 1
CAs = [[x / ni for x, ni in zip(y, nIter)] for y in CAs]
CAfoldList = CAs
CA = [statc.mean(x) for x in CAs]
CAstd = stats.stdev(CAfoldList[0])
if returnFoldStat:
return [round(statc.mean(x), 3) for x in CAs], CAfoldList
else:
return [round(statc.mean(x), 3) for x in CAs]
else:
CAs = [0.0] * res.numberOfLearners
for tex in res.results:
CAs = map(lambda res, cls, ac=tex.actualClass: res + types.IntType(
cls == ac),
CAs,
tex.classes)
return [round(x / (len(res.results)), 3) for x in CAs]
def printStats(self):
"""
Print the stats for each of the hammers, and do some on the fly general stats
"""
allTimes = []
print "----------------------------\n Per Hammer stats:\n----------------------------"
#print out the stats for each hammer
i = 0
data = (datetime.timedelta(0), 0)
for history in self.histories:
point = self._printStat(i, history, allTimes)
data = (data[0] + point[0], data[1] + point[1])
print '\n'
i += 1
#print out general statistics
print "------------------------------\n General Stats:\n------------------------------"
print 'Total writes:\t', data[1]
print 'Total time spent writing:\t', str(data[0])
print 'Mean time spent writing:\t', str(data[0] / data[1])
#We could add more information here about the stats, now that all the times are gathered
print 'Standard deviation:\t\t', stats.stdev(allTimes)
def RMSE_obsolete(res = None):
"""
Calculates the Root Mean Squared Error of orngTest.ExperimentResults in res
The results res must be from a regressor
"""
# If Called without arguments, return the type of problems this method can be used for:
# 1 - Classification problems (Discrete Class)
# 2 - Regression problems (Continuous Class)
# 3 - Both Regression and Classification problems (Continuous or Discrete Class)
if res == None:
return {"type":REGRESSION}
if res.numberOfIterations > 1:
MSEs = [[0.0] * res.numberOfIterations for i in range(res.numberOfLearners)]
nIter = [0]*res.numberOfIterations
for tex in res.results:
ac = float(tex.actualClass)
nIter[tex.iterationNumber] += 1
for i, cls in enumerate(tex.classes):
MSEs[i][tex.iterationNumber] += (float(cls) - ac)**2
MSEs = [[x/ni for x, ni in zip(y, nIter)] for y in MSEs]
MSEs = [[math.sqrt(x) for x in y] for y in MSEs]
# Print output from each fold to tem file
RMSEfoldList = MSEs
RMSE = [statc.mean(x) for x in RMSEfoldList]
RMSEstd = stats.stdev(RMSEfoldList[0])
#print str(RMSE[0])+"\t"+str(RMSEstd)+"\t"+string.join( [str(x) for x in RMSEfoldList[0]] , "\t")
return [round(statc.mean(x),2) for x in MSEs]
else:
MSEs = [0.0]*res.numberOfLearners
for tex in res.results:
MSEs = map(lambda res, cls, ac = float(tex.actualClass):
res + (float(cls) - ac)**2, MSEs, tex.classes)
MSEs = [x/(len(res.results)) for x in MSEs]
return [round(math.sqrt(x),2) for x in MSEs]
def CA_obsolete(res = None, returnFoldStat = False):
"""
Calculates the classification Accuracy of orngTest.ExperimentResults in res
The results res must be from a classifier
"""
# If Called without arguments, return the type of problems this method can be used for:
# 1 - Classification problems (Discrete Class)
# 2 - Regression problems (Continuous Class)
# 3 - Both Regression and Classification problems (Continuous or Discrete Class)
if res == None:
return {"type":CLASSIFICATION}
if res.numberOfIterations > 1:
CAs = [[0.0] * res.numberOfIterations for i in range(res.numberOfLearners)]
nIter = [0]*res.numberOfIterations
for tex in res.results:
ac = tex.actualClass
nIter[tex.iterationNumber] += 1
for i, cls in enumerate(tex.classes):
if cls == ac:
CAs[i][tex.iterationNumber] += 1
CAs = [[x/ni for x, ni in zip(y, nIter)] for y in CAs]
CAfoldList = CAs
CA = [statc.mean(x) for x in CAs]
CAstd = stats.stdev(CAfoldList[0])
if returnFoldStat:
return [round(statc.mean(x),3) for x in CAs], CAfoldList
else:
return [round(statc.mean(x),3) for x in CAs]
else:
CAs = [0.0]*res.numberOfLearners
for tex in res.results:
CAs = map(lambda res, cls, ac = tex.actualClass:
res + types.IntType(cls == ac), CAs, tex.classes)
return [round(x/(len(res.results)),3) for x in CAs]
def final():
i = 0
iteracoes = zip(*totIteracoes)
print ' '
print ' '
print '******************************************************************'
print 'Media e desvio padrao das iteracoes:'
for prec in precs:
print '------------------------------------------------------------------'
print 'Precisao: %d' % prec
print 'Media: %d' % stats.mean(iteracoes[i])
print 'Maximo: %d' % max(iteracoes[i])
print 'Minimo: %d' % min(iteracoes[i])
print 'Desvio: %d' % stats.stdev(iteracoes[i])
i+=1
print '------------------------------------------------------------------'
ticks = range(1,i+1)
pylab.boxplot(iteracoes)
pylab.title('Distribuicao das Iteracoes')
pylab.xlabel('Precisao da raiz em casas decimais')
pylab.ylabel('Quantidade de Iteracoes')
pylab.xticks(ticks,precs)
pylab.show()
def main():
if (len(sys.argv) < 3):
print "Usage!"
exit(1)
points = sys.argv[1]
database = sys.argv[2]
boxData = csv.reader(open(points, 'rb'))
boxes = []
for row in boxData:
if (len(row) == 4):
boxes.append({"time":long(row[0]), "size":float(row[1]), "position":(int(row[2]),int(row[3]))})
else:
finishTime = long(row[0].split(':')[1])
conn = sqlite3.connect(database)
cur = conn.cursor()
cur.execute('select datetime,data from clues where kind="touch" and datetime between %d and %d' % (boxes[0]['time'],finishTime))
touches = []
for touch in cur:
time = long(touch[0])
data = touch[1].split(',')
touches.append({"time":long(touch[0]), "position":(int(data[0]),int(data[1])), "pressure":float(data[2])})
timesForSize = {30:[], 60:[], 99:[], 129:[]}
deltas = []
for i,box in enumerate(boxes[:-1]):
delta = (boxes[i+1]['time'] - box['time'])/1000.0
timesForSize[box['size']].append(delta)
deltas.append(delta)
deltas.append((finishTime - boxes[-1]['time'])/1000.0)
minimum = min(deltas)
maximum = max(deltas)
mean = stats.mean(deltas)
stddev = stats.stdev(deltas)
for k,v in sorted(timesForSize.iteritems()):
print "%d: %.3f/%.3f/%.3f/%.3f (%.3f bps)" % (k, min(v), stats.mean(v), max(v), stats.stdev(v), 1/stats.mean(v))
print "Avg: %.3f/%.3f/%.3f/%.3f (%.3f boxes per second)" % (minimum, mean, maximum, stddev, 1/mean)
boxesWithTouches = []
for i,box in enumerate(boxes[:-1]):
time = box['time']
nextTime = boxes[i+1]['time']
def f(x): return x['time'] > time and x['time'] < nextTime
associatedTouches = filter(f, touches)
boxesWithTouches.append({'size': box['size'], 'position': box['position'], 'touches':associatedTouches})
mags = []
magsPerSize = []
sizes = [30, 60, 99, 129]
for buttonSize in sizes:
def sizeOfBox(t): return t['size'] == buttonSize
boxes = filter(sizeOfBox, boxesWithTouches)
for boxWithTouch in boxes:
center = boxWithTouch['position']
for touch in boxWithTouch['touches']:
tapPos = touch['position']
deltaX = center[0] - tapPos[0]
deltaY = center[1] - tapPos[1]
mags.append(math.sqrt(pow(deltaX, 2) + pow(deltaY, 2)))
magsPerSize = magsPerSize + mags
mags = []
magsPerSize = []
def mean_stdev(vals, null_val=-1):
vals2 = [i for i in vals if i != null_val]
return int(round(mean(vals2), 0)), stdev(vals2), len(vals2)
def adc_var ( ip_addr, ip_port, timeout, channel, packetNumber, buffer_size, verbose):
s_adc = socket.socket( socket.AF_INET, socket.SOCK_STREAM )
s_adc.settimeout( int(timeout) )
# try connection
try:
s_adc.connect( (ip_addr, int( ip_port ) ) )
except:
print "adc_var(): Error, no ADC connection, port: ", ip_port,
s_adc.close()
sys.exit()
# open connection
message = sendReceive ( s_adc, channel, packetNumber,
buffer_size, verbose )
# close connection
s_adc.close()
# unpacking message
msg_len = len(message)
if msg_len > 0:
num = unpack(str(msg_len)+'B', message)
# add offset, [0 255] -> [-128 128]
num = map(lambda x: x-128, num)
if verbose:
print "Min=", min(num), "Max=", max(num), "Mean=", stats.mean(num), "Var=", stats.var(num), "Std=", stats.stdev(num)
var = stats.var(num)
else:
var = "N/A"
return var
#if qerrors.qsize():
#for err in qerrors:
#print(err)
#if qstart.qsize():
#print("START: {e}".format(e=qstart.qsize()))
print("Build times")
bstart = time.time()
times = []
#i =0
if qtimes.qsize():
qtimes.put(StopIteration)
#print(qtimes.qsize())
for item in qtimes:
#i += 1
#print(i, item)
times.append(item)
# The len of times[] indicates the number or successful responses.
# The len should equal max_connections * iterations from the command line.
print("Time spent building time[]: {t} len={l}".format(t=time.time() - bstart, l=len(times)))
print("Round trip time:")
print("Min {t}".format(t=min(times)))
print("Max {t}".format(t=max(times)))
if sys.version[0] == "2":
print("Mean {t}".format(t=stats.mean(times)))
print("StdDev {t}".format(t=stats.stdev(times)))
#print("Invalid responses={i}".format(i=invalid_responses))
print '\nVARIATION' print 'obrientransform:' l = range(1,21) a = N.array(l) ll = [l]*5 aa = N.array(ll) print stats.obrientransform(l,l,l,l,l) print stats.obrientransform(a,a,a,a,a) print 'samplevar:',stats.samplevar(l),stats.samplevar(a) print 'samplestdev:',stats.samplestdev(l),stats.samplestdev(a) print 'var:',stats.var(l),stats.var(a) print 'stdev:',stats.stdev(l),stats.stdev(a) print 'sterr:',stats.sterr(l),stats.sterr(a) print 'sem:',stats.sem(l),stats.sem(a) print 'z:',stats.z(l,4),stats.z(a,4) print 'zs:' print stats.zs(l) print stats.zs(a) print '\nTRIMMING' print 'trimboth:' print stats.trimboth(l,.2) print stats.trimboth(lf,.2) print stats.trimboth(a,.2) print stats.trimboth(af,.2) print 'trim1:' print stats.trim1(l,.2)
def standard_deviation(values):
try:
return stats.stdev(values)
except ZeroDivisionError:
return None
def compare_test_durations(tree1, revision1, tree2, revision2, submitter):
revision_count = 10
if revision1:
control_revision = revision1
else:
if DEBUG:
print 'finding the most recent changeset with all tests completed'
control_revision = get_range_of_recent_commits(find_most_recent_completed_commit(),
count=revision_count)
if not control_revision:
return None
if DEBUG:
print 'getting durations from ES for changeset', control_revision
if isinstance(control_revision, list):
control = get_median_duration_for_ES_commit_list(control_revision)
else:
control = [get_durations_for_ES_commit(control_revision)]
if tree2 == 'try':
trylogs = get_list_of_try_logs('%s-%s' % (submitter, revision2))
if DEBUG:
print "parsing try logs"
test = get_durations_from_trylogs(trylogs)
elif tree2 == 'mozilla-central':
if not revision2:
revision2 = find_most_recent_completed_commit()
test = get_durations_for_ES_commit(revision2)
else:
raise Exception("Unsupported tree %s" % tree2)
results = defaultdict(lambda: defaultdict(list))
totals = [0 for x in range(0, len(control))]
test_total = 0
for plat in test:
test_suites = test.get(plat, {})
for suite in test_suites:
testtime = int(test[plat][suite])
timelist = [int(x.get(plat, {}).get(suite)) for x in control if x.get(plat, {}).get(suite)]
results[plat][suite] = {'mean': stats.mean(timelist),
'stdev': stats.stdev(timelist) if len(timelist) > 1 else 0,
'testtime': testtime
}
totallist = [int(x.get(plat, {}).get(suite)) if x.get(plat, {}).get(suite) else testtime for x in control]
totals = [y + totals[x] for x,y in enumerate(totallist)]
test_total += testtime
return { 'durations': results,
'totals': {
'mean': stats.mean(totals),
'stdev': stats.stdev(totals) if len(totals) > 1 else 0,
'testtime': test_total
},
'revisions': [
{ 'tree': 'mozilla-central',
'revision': control_revision },
{ 'tree': tree2,
'revision': revision2 }
]}
output = "Pathway analysis. Result dir: %s. Performed at %s" % (RESULT_DIR, str(datetime.now()))
output += "\n1. Statistics\n"
output += "----------------------------------------------------------------------------------------------------------------------------\n"
output += " Interaction_component_counts CoulombEnergy_Contribution \n"
output += " Box Sum_of_interacting_atoms CloseContact Hydrophobic HydrogenBond Electrostatic mean stddev \n"
output += "----------------------------------------------------------------------------------------------------------------------------\n"
pattern1= " %s %4s %s %s %s %s %10.3f %10.3f \n"
for i in range(len(p)):
elec_energies = p[i].statistics['coulomb_energies']
output += pattern1 % (i+1, p[i].statistics['sum'],
p[i].statistics['closecontact'],
p[i].statistics['hydrophobic'],
p[i].statistics['hydrogen'],
p[i].statistics['electrostatic'],
(stats.mean(elec_energies),0.0)[len(elec_energies) == 0],
(stats.stdev(elec_energies),0.0)[len(elec_energies) == 0]
)
OFILE = open('pathway_analysis.txt','w')
OFILE.write(output)
output = "\n2.Details. List of residues with high-frequency (>= 40%) of interactions in each box\n"
output += "---------------------------------------------------------------------------------------------\n"
output += " Box Residue Interaction_frequency Receptor_states\n"
output += " CloseContact Hydrophobic HydrogenBond Electrostatic All \n"
output += "---------------------------------------------------------------------------------------------\n"
pattern2= " %s %s %7.3f %7.3f %7.3f %7.3f %7.3f %s\n"
residue_set = []
for i in range(len(p)):
residue_set.append( [] )
for res in p[i].all_residues:
if p[i].frequency(res) >= 0.4:
def main(): townSize = 100 duration = 100 if debugMode == 1: iterations = 1 trials = 1 else: iterations = 100 trials = 35 fPercentBase = 0 fPercentDelta = 0 tPercentBase = 0 tPercentDelta = 1 deathHungerBase = 2 deathHungerDelta = 0 maxHarvestBase = 5 maxHarvestDelta = 0 previousMean = 0 previousStDev = 0 for iteration in range(iterations): fPercent = fPercentBase + (fPercentDelta * iteration) tPercent = tPercentBase + (tPercentDelta * iteration) deathHunger = deathHungerBase + (deathHungerDelta * iteration) maxHarvest = maxHarvestBase + (maxHarvestDelta * iteration) numFishers = int(fPercent * (townSize / 100)) numTeachers = int(tPercent * (townSize / 100)) survivingPops = [] for trial in range(trials): Canvas = [] # Create first two towns Canvas.append(Town()) for i in range(numFishers): Canvas[0].Home.add(Man(i, 1)) if numTeachers > 1: for i in range(numTeachers): Canvas[0].Home.add(Man(i, 2)) for i in range(townSize - numFishers - numTeachers): Canvas[0].Home.add(Man(i, 0)) for day in range(duration): Canvas[day].morningCommute() Canvas[day].stockMarket() Canvas[day].sellMarket() Canvas[day].fishingDay(maxHarvest) Canvas[day].returnHome() if debugMode == 1: print "Before deathHunger on day " + str(day) + ", home population is " + str(len(Canvas[day].Home)) + " and there are " + str(len(Canvas[day].Market)) + " people hungry in the market" Canvas[day].assessHunger(deathHunger) if debugMode == 1: print "At the end of day " + str(day) + ", home population is " + str(len(Canvas[day].Home)) + " and there are " + str(len(Canvas[day].Market)) + " people hungry in the market" Canvas.append(Town()) Canvas[day + 1].clone(Canvas[day]) survivingPops.append(len(Canvas[day].Home)) if displayPops == 1: print survivingPops currentMean = stats.mean(survivingPops) currentStDev = stats.stdev(survivingPops) if displayPops == 1: print str(currentMean) + ", " + str(currentStDev) else: print str(currentMean) + ", " previousMean = currentMean previousStDev = currentStDev
def main(argv):
global sqlitefile
global csvfilename
csvfilename = None # need to set this to some sane default because ensureValidTestID() won't work without it
try:
sqlitefile = 'resultdb.sqlite'
opts, args = getopt.getopt(argv, 'hf:e:', ('help', 'db=', 'csv='))
except getopt.GetoptError:
usage()
for opt, arg in opts:
if opt in ('-h', '--help'):
usage()
elif opt in ('-f', '--db='):
sqlitefile = arg
ensureValidTestID()
elif opt in ('-e', '--csv='):
csvfilename = arg
ensureValidTestID()
writecsv(csvfilename, sometestid)
sys.exit(0)
# ---- INIT ----
# dbconn = sqlite3.connect(sqlitefile)
# dbconn.row_factory = sqlite3.Row
# c = dbconn.cursor()
getSQLiteConn()
myquery = 'SELECT test_id, date, hits, up, time, data, resptime, trans, bw, concur, ok, fail, long, short FROM siege WHERE test_id LIKE \'' + str(
sometestid) + '%\''
#todo = ['hits', 'up', 'time', 'data', 'resptime', 'trans', 'bw', 'concur', 'ok', 'fail', 'long', 'short']
floats = ('up', 'time', 'data', 'resptime', 'trans', 'bw', 'concur',
'long', 'short')
ints = ('hits', 'ok', 'fail')
# todo is a dict with each key as the col name and each val as a list containing all the vals
"""
Siege example return and var types
(u'mysql-1-1', u'1303101006.08', u'6830', u'85.88', u'352.12', u'48.83', u'5.05', u'19.40', u'0.14', u'97.88', u'6840', u'1123', u'15.41', u'0.56')
str(test_id)
int(date)
int(hits)
float(up)
float(time)
float(data)
float(resptime)
float(trans)
float(bw)
float(concur)
int(ok)
int(fail)
float(long)
float(short)
"""
mydict = {}
# create empty lists
for i in floats + ints:
mydict[i] = []
# we can now just map keys in our dict to results in the DB query since the names are 1:1
data = c.execute(myquery)
numrows = c.fetchone()
if numrows is None:
print "No tests found when using test ID selector:", sometestid
print "Displaying a list of test IDs in", sqlitefile
for row in c.execute('select test_id from siege'):
print row[0]
print '(For help / usage info, see', sys.argv[0], '--help)'
sys.exit(2)
for row in data:
for key in floats:
mydict[key].append(float(row[key]))
for key in ints:
mydict[key].append(int(row[key]))
meandict = {}
mediandict = {}
stdevdict = {}
for key, val in mydict.iteritems():
meandict[key] = stats.mean(val)
stdevdict[key] = stats.stdev(val)
mediandict[key] = getMedian(val)
print 'Test ID selector: ' + sometestid
print "Raw dump of dataset to parse: "
print mydict
print '\r\nMean: '
print meandict
print '\r\nMedian: '
print mediandict
print '\r\nStandard Deviation: '
print stdevdict
# select test_id, datetime(date, 'unixepoch') from siege where test_id = 'mysql-1-1';
#print mydict['trans']
# ---- MAIN ----
return
print '\nVARIATION' print 'obrientransform:' l = range(1, 21) a = N.array(l) ll = [l] * 5 aa = N.array(ll) print stats.obrientransform(l, l, l, l, l) print stats.obrientransform(a, a, a, a, a) print 'samplevar:', stats.samplevar(l), stats.samplevar(a) print 'samplestdev:', stats.samplestdev(l), stats.samplestdev(a) print 'var:', stats.var(l), stats.var(a) print 'stdev:', stats.stdev(l), stats.stdev(a) print 'sterr:', stats.sterr(l), stats.sterr(a) print 'sem:', stats.sem(l), stats.sem(a) print 'z:', stats.z(l, 4), stats.z(a, 4) print 'zs:' print stats.zs(l) print stats.zs(a) print '\nTRIMMING' print 'trimboth:' print stats.trimboth(l, .2) print stats.trimboth(lf, .2) print stats.trimboth(a, .2) print stats.trimboth(af, .2) print 'trim1:' print stats.trim1(l, .2)
output = "Pathway analysis. Result dir: %s. Performed at %s" % (RESULT_DIR, str(datetime.now()))
output += "\n1. Statistics\n"
output += "----------------------------------------------------------------------------------------------------------------------------\n"
output += " Interaction_component_counts CoulombEnergy_Contribution \n"
output += " Box Sum_of_interacting_atoms CloseContact Hydrophobic HydrogenBond Electrostatic mean stddev \n"
output += "----------------------------------------------------------------------------------------------------------------------------\n"
pattern1= " %s %4s %s %s %s %s %10.3f %10.3f \n"
for i in range(len(p)):
elec_energies = p[i].statistics['coulomb_energies']
output += pattern1 % (i+1, p[i].statistics['sum'],
p[i].statistics['closecontact'],
p[i].statistics['hydrophobic'],
p[i].statistics['hydrogen'],
p[i].statistics['electrostatic'],
(stats.mean(elec_energies),0.0)[len(elec_energies) == 0],
(stats.stdev(elec_energies),0.0)[len(elec_energies) == 0]
)
OFILE = open('pathway_analysis.txt','w')
OFILE.write(output)
output = "\n2.Details. List of residues with high-frequency (>= 40%) of interactions in each box\n"
output += "---------------------------------------------------------------------------------------------\n"
output += " Box Residue Interaction_frequency Receptor_states\n"
output += " CloseContact Hydrophobic HydrogenBond Electrostatic All \n"
output += "---------------------------------------------------------------------------------------------\n"
pattern2= " %s %s %7.3f %7.3f %7.3f %7.3f %7.3f %s\n"
residue_set = []
for i in range(len(p)):
residue_set.append( [] )
for res in p[i].all_residues:
if p[i].frequency(res) >= 0.3:
def test_stdev(self):
"Testing stdev"
data = [ self.L, self.A ]
for d in data:
self.EQ( stats.stdev( d ), 5.9160797831 )
def cull_outliers(data, n_sigma):
mean = stats.mean(map(lambda x: x, data))
sigma = stats.stdev(map(lambda x: x, data))
return filter(lambda x: abs(x - mean) < n_sigma * sigma, data)
def main():
if (len(sys.argv) < 3):
print "Usage!"
exit(1)
database = sys.argv[2]
points = sys.argv[1]
boxData = list(csv.reader(open(points, 'rb')))
boxes = [{"time":long(row[0]), "size":float(row[1]), "position":(int(row[2]),int(row[3]))} for row in boxData[:-1]]
finishTime = long(boxData[-1][0].split(':')[1])
conn = sqlite3.connect(database)
cur = conn.cursor()
cur.execute('select datetime,data from clues where kind="touch" and datetime between %d and %d' % (boxes[0]['time'],finishTime))
touches = [{'time':long(t[0]), 'position':(int(t[1].split(',')[0]), int(t[1].split(',')[1])), 'pressure':float(t[1].split(',')[2])} for t in cur]
boxesWithTouches = []
for i,box in enumerate(boxes[:-1]):
time = box['time']
nextTime = boxes[i+1]['time']
def f(x): return x['time'] > time and x['time'] < nextTime
associatedTouches = filter(f, touches)
numTaps = 1
for j,touch in enumerate(associatedTouches[:-1]):
currentTouchTime = touch['time']
nextTouchTime = associatedTouches[j+1]['time']
if (nextTouchTime - currentTouchTime) > 100:
numTaps += 1
boxesWithTouches.append({'size': box['size'], 'position': box['position'], 'touches':associatedTouches, 'attempts':numTaps})
numTaps = 0
# Finish up with the last box
box = boxes[-1]
time = boxes[-1]['time']
nextTime = finishTime
def f(x): return x['time'] > time and x['time'] < nextTime
associatedTouches = filter(f, touches)
numTaps = 1
for j,touch in enumerate(associatedTouches[:-1]):
currentTouchTime = touch['time']
nextTouchTime = associatedTouches[j+1]['time']
if (nextTouchTime - currentTouchTime) > 100:
numTaps += 1
boxesWithTouches.append({'size': box['size'], 'position': box['position'], 'touches':associatedTouches, 'attempts':numTaps})
sizes = [30, 60, 99, 129]
mmsizes = [3,6,10,13]
for buttonSize in sizes:
def sizeOfBox(t): return t['size'] == buttonSize
filteredBoxes = filter(sizeOfBox, boxesWithTouches)
listOfAttempts = [box['attempts'] for box in filteredBoxes]
print "%d: %.3f/%.3f/%.3f/%.3f" % (mmsizes[sizes.index(buttonSize)], stats.mean(listOfAttempts), min(listOfAttempts), max(listOfAttempts), stats.stdev(listOfAttempts))
#!/usr/bin/python
import sys
import re
from statlib import stats
if __name__ == '__main__':
a = []
for i in xrange(501):
a.append([])
m = re.compile("(?P<l>\d+)\s(?P<m>\d+)")
L = sys.stdin.readlines()
for l in L:
s = m.match(l)
length = int(s.group("l"))
length -= length%10 +5
a[length].append(int(s.group("m")))
b = []
for i in xrange(200,501):
if (a[i] != []):
print i, stats.mean(a[i]), stats.stdev(a[i])
# b.append(len(a[i]))
# print stats.mean(b), stats.stdev(b)
def cull_outliers(data, n_sigma):
mean = stats.mean(map(lambda x: x, data))
sigma = stats.stdev(map(lambda x: x, data))
return filter(lambda x: abs(x - mean) < n_sigma * sigma, data)
def test_stdev(self):
"Testing stdev"
data = [self.L, self.A]
for d in data:
self.EQ(stats.stdev(d), 5.9160797831)
def mean_stdev(vals, null_val=-1): vals2 = [i for i in vals if i != null_val] return int(round(mean(vals2), 0)), stdev(vals2), len(vals2)
if delta_flag:
return delta
if __name__ == "__main__":
start_date = datetime.strptime(raw_input("Start date: "), '%Y%m%d')
day_range = int(raw_input("Day Range: "))
sample_days = int(raw_input("Sample days: "))
company_list = CompanyList(raw_input("Company List: "))
stocks_per_day = int(raw_input("Stocks per day: "))
percents_correct = [
float(p) for p in raw_input("Percents correct: ").split(",")
]
results = {}
for trial in range(len(percents_correct)):
deltas = run_experiment(company_list=company_list,
sample_days=sample_days,
start_date=start_date,
day_range=day_range,
percent_correct=percents_correct[trial],
stocks_per_day=stocks_per_day)
print "Percent correct: %f, %s" % (percents_correct[trial],
str(deltas))
print "\t (%f, %f)" % (stats.mean(deltas), stats.stdev(deltas))
results[percents_correct[trial]] = deltas
print results
def main(argv):
global sqlitefile
global csvfilename
csvfilename = None # need to set this to some sane default because ensureValidTestID() won't work without it
try:
sqlitefile = 'resultdb.sqlite'
opts, args = getopt.getopt(argv, 'hf:e:', ('help', 'db=', 'csv='))
except getopt.GetoptError:
usage()
for opt, arg in opts:
if opt in ('-h', '--help'):
usage()
elif opt in ('-f', '--db='):
sqlitefile = arg
ensureValidTestID()
elif opt in ('-e','--csv='):
csvfilename = arg
ensureValidTestID()
writecsv(csvfilename, sometestid)
sys.exit(0)
# ---- INIT ----
# dbconn = sqlite3.connect(sqlitefile)
# dbconn.row_factory = sqlite3.Row
# c = dbconn.cursor()
getSQLiteConn()
myquery = 'SELECT test_id, date, hits, up, time, data, resptime, trans, bw, concur, ok, fail, long, short FROM siege WHERE test_id LIKE \'' + str(sometestid) + '%\''
#todo = ['hits', 'up', 'time', 'data', 'resptime', 'trans', 'bw', 'concur', 'ok', 'fail', 'long', 'short']
floats = ('up', 'time', 'data', 'resptime', 'trans', 'bw', 'concur', 'long', 'short')
ints = ('hits', 'ok', 'fail')
# todo is a dict with each key as the col name and each val as a list containing all the vals
"""
Siege example return and var types
(u'mysql-1-1', u'1303101006.08', u'6830', u'85.88', u'352.12', u'48.83', u'5.05', u'19.40', u'0.14', u'97.88', u'6840', u'1123', u'15.41', u'0.56')
str(test_id)
int(date)
int(hits)
float(up)
float(time)
float(data)
float(resptime)
float(trans)
float(bw)
float(concur)
int(ok)
int(fail)
float(long)
float(short)
"""
mydict = {}
# create empty lists
for i in floats + ints:
mydict[i] = []
# we can now just map keys in our dict to results in the DB query since the names are 1:1
data = c.execute(myquery)
numrows = c.fetchone()
if numrows is None:
print "No tests found when using test ID selector:", sometestid
print "Displaying a list of test IDs in", sqlitefile
for row in c.execute('select test_id from siege'):
print row[0]
print '(For help / usage info, see', sys.argv[0], '--help)'
sys.exit(2)
for row in data:
for key in floats:
mydict[key].append(float(row[key]))
for key in ints:
mydict[key].append(int(row[key]))
meandict = {}
mediandict = {}
stdevdict = {}
for key, val in mydict.iteritems():
meandict[key] = stats.mean(val)
stdevdict[key] = stats.stdev(val)
mediandict[key] = getMedian(val)
print 'Test ID selector: ' + sometestid
print "Raw dump of dataset to parse: "
print mydict
print '\r\nMean: '
print meandict
print '\r\nMedian: '
print mediandict
print '\r\nStandard Deviation: '
print stdevdict
# select test_id, datetime(date, 'unixepoch') from siege where test_id = 'mysql-1-1';
#print mydict['trans']
# ---- MAIN ----
return
def histogram(self, out_fname, large=False):
assert self.data
# Hacky workaround in the case that a run had no data.
for x in self.data.values():
if len(x) == 0: x.extend([0, 0])
if not large:
font = fm.FontProperties(family=['sans-serif'],
size='small',
fname=FONT_FILE)
mpl.rcParams['xtick.major.pad'] = 4
mpl.rcParams['ytick.major.pad'] = 4
mpl.rcParams['lines.linewidth'] = 1
else:
font = fm.FontProperties(family=['sans-serif'],
size=36,
fname=FONT_FILE)
mpl.rcParams['xtick.major.pad'] = 20
mpl.rcParams['ytick.major.pad'] = 20
mpl.rcParams['lines.linewidth'] = 5
fig = plt.figure()
# Set the margins for the plot to ensure a minimum of whitespace
ax = plt.axes([0.12, 0.12, 0.85, 0.85])
data = map(lambda x: x[1], self.data.iteritems())
mean = stats.mean(map(lambda x: x, reduce(lambda x, y: x + y, data)))
stdev = stats.stdev(map(lambda x: x, reduce(lambda x, y: x + y, data)))
labels = []
hists = []
for series, color in zip(self.data.iteritems(), colors):
clipped_data = clip(series[1], 0, 3 * mean)
if clipped_data:
_, _, foo = ax.hist(clipped_data,
bins=200,
histtype='bar',
facecolor=color,
alpha=.5,
label=series[0])
hists.append(foo)
labels.append(series[0])
else:
print "Tried to make a histogram of a series of size 0"
for tick in ax.xaxis.get_major_ticks():
tick.label1.set_fontproperties(font)
for tick in ax.yaxis.get_major_ticks():
tick.label1.set_fontproperties(font)
ax.set_ylabel('Frequency', fontproperties=font)
ax.set_xlabel(
'Latency (microseconds)', fontproperties=font
) #simply should not be hardcoded but we want nice pictures now
ax.grid(True)
# Dirty hack to get around legend miscoloring: drop all the hists generated into the legend one by one
if hists:
plt.legend(map(lambda x: x[0], hists), labels, loc=1, prop=font)
if not large:
fig.set_size_inches(5, 3.7)
fig.set_dpi(90)
plt.savefig(out_fname, bbox_inches="tight")
else:
ax.yaxis.LABELPAD = 40
ax.xaxis.LABELPAD = 40
fig.set_size_inches(20, 14.8)
fig.set_dpi(300)
plt.savefig(out_fname, bbox_inches="tight")
def evaluate(self, *args, **params):
return _stats.stdev(*args, **params)
print('\nVARIATION')
print('obrientransform:')
l = list(range(1, 21))
a = N.array(l)
ll = [l] * 5
aa = N.array(ll)
print(stats.obrientransform(l, l, l, l, l))
print(stats.obrientransform(a, a, a, a, a))
print('samplevar:', stats.samplevar(l), stats.samplevar(a))
print('samplestdev:', stats.samplestdev(l), stats.samplestdev(a))
print('var:', stats.var(l), stats.var(a))
print('stdev:', stats.stdev(l), stats.stdev(a))
print('sterr:', stats.sterr(l), stats.sterr(a))
print('sem:', stats.sem(l), stats.sem(a))
print('z:', stats.z(l, 4), stats.z(a, 4))
print('zs:')
print(stats.zs(l))
print(stats.zs(a))
print('\nTRIMMING')
print('trimboth:')
print(stats.trimboth(l, .2))
print(stats.trimboth(lf, .2))
print(stats.trimboth(a, .2))
print(stats.trimboth(af, .2))
print('trim1:')
print(stats.trim1(l, .2))
# run in wt/visual-cluster
from statlib import stats
OFILE = open("stats.txt",'w')
for i in range(1,8):
BEs = []
IFILE = open("visual_cluster-%s.pdb" % i, 'r')
for l in IFILE:
values = l.split()
BEs.append(float(values[9]) / 0.7) # if given BEs are weighted
OFILE.write("visual_cluster-%s: %s, stddev %s, lower %s, upper %s, min %s, max %s, median %s \n" % (i,stats.mean(BEs),
stats.stdev(BEs),
stats.scoreatpercentile(BEs,25),
stats.scoreatpercentile(BEs,75),
min(BEs), max(BEs),
stats.median(BEs) ))
OFILE.close()
def stdev(self):
return stats.stdev(self.deltas)
output = "Pathway analysis. Result dir: %s. Performed at %s" % (
RESULT_DIR, str(datetime.now()))
output += "\n1. Statistics\n"
output += "----------------------------------------------------------------------------------------------------------------------------\n"
output += " Interaction_component_counts CoulombEnergy_Contribution \n"
output += " Box Sum_of_interacting_atoms CloseContact Hydrophobic HydrogenBond Electrostatic mean stddev \n"
output += "----------------------------------------------------------------------------------------------------------------------------\n"
pattern1 = " %s %4s %s %s %s %s %10.3f %10.3f \n"
for i in range(len(p)):
elec_energies = p[i].statistics['coulomb_energies']
output += pattern1 % (
i + 1, p[i].statistics['sum'], p[i].statistics['closecontact'],
p[i].statistics['hydrophobic'], p[i].statistics['hydrogen'],
p[i].statistics['electrostatic'],
(stats.mean(elec_energies), 0.0)[len(elec_energies) == 0],
(stats.stdev(elec_energies), 0.0)[len(elec_energies) == 0])
OFILE = open('pathway_analysis.txt', 'w')
OFILE.write(output)
output = "\n2.Details. List of residues with high-frequency (>= 40%) of interactions in each box\n"
output += "---------------------------------------------------------------------------------------------\n"
output += " Box Residue Interaction_frequency Receptor_states\n"
output += " CloseContact Hydrophobic HydrogenBond Electrostatic All \n"
output += "---------------------------------------------------------------------------------------------\n"
pattern2 = " %s %s %7.3f %7.3f %7.3f %7.3f %7.3f %s\n"
residue_set = []
for i in range(len(p)):
residue_set.append([])
for res in p[i].all_residues:
if p[i].frequency(res) >= 0.4:
# get list of receptors by specified residue
def standard_deviation(values):
try:
return stats.stdev(values)
except ZeroDivisionError:
return None
def stdev(self):
return stats.stdev(self.deltas)
