def testMean(self):
"""
Check that mean works as expected.
"""
self.assertAlmostEqual(stats.mean(self.dataA), self.meanA, 5)
self.assertAlmostEqual(stats.mean(self.dataB), self.meanB, 5)
return
def least_squares_fit(x, y):
"""given training values for x and y,
find the least-squares values of alpha and beta"""
beta = stats.correlation(x, y) * \
stats.standard_deviation(y) / stats.standard_deviation(x)
alpha = stats.mean(y) - beta * stats.mean(x)
return alpha, beta
def sync_check():
# print 'Checking sync...'
max_mcnt_difference=4
mcnts=dict()
mcnts_list=[]
mcnt_tot=0
for f,fpga in enumerate(fpgas):
mcnts[f]=dict()
try:
hdr_index=bram_oob[f]['hdr'].index(1)
except:
print 'ERR: No headers found in BRAM. Are the F engines properly connected?'
exit()
pkt_64bit = struct.unpack('>Q',bram_dmp['bram_msb'][f]['data'][(4*hdr_index):(4*hdr_index)+4]+bram_dmp['bram_lsb'][f]['data'][(4*hdr_index):(4*hdr_index)+4])[0]
mcnts[f]['mcnt'] =(pkt_64bit&((2**64)-(2**16)))>>16
mcnts_list.append(mcnts[f]['mcnt'])
# print '[%s] MCNT: %i'%(servers[f],mcnts[f]['mcnt'])
mcnts['mean']=stats.mean(mcnts_list)
mcnts['median']=stats.median(mcnts_list)
mcnts['mode']=stats.mode(mcnts_list)
mcnts['modalmean']=stats.mean(mcnts['mode'][1])
# print 'mean: %i, median: %i, modal mean: %i mode:'%(mcnts['mean'],mcnts['median'],mcnts['modalmean']),mcnts['mode']
for f,fpga in enumerate(fpgas):
if mcnts[f]['mcnt']>(mcnts['modalmean']+max_mcnt_difference) or mcnts[f]['mcnt'] < (mcnts['modalmean']-max_mcnt_difference):
print '%s OUT OF SYNC!!'%servers[f]
mcnts[f]['sync_status']='FAIL with error of %i'%(mcnts[f]['mcnt']-mcnts['modalmean'])
else:
mcnts[f]['sync_status']='PASS'
return mcnts
def least_squares_fit(x, y):
"""given training values for x and y,
find the least-squares values of alpha and beta"""
beta = stats.correlation(x, y) * \
stats.standard_deviation(y) / stats.standard_deviation(x)
alpha = stats.mean(y) - beta * stats.mean(x)
return alpha, beta
def compute_stats(te_diffs, gene_diffs, plot_dir):
pvals = []
table_lines = []
for te_or in te_diffs:
rep, fam, orient = te_or
for sample_key in te_diffs[te_or]:
sample1, sample2 = sample_key
# if enough data
if len(te_diffs[te_or][sample_key]) >= 10:
wo_te = list((gene_diffs[sample_key] - te_diffs[te_or][sample_key]).elements())
w_te = list(te_diffs[te_or][sample_key].elements())
wo_mean = stats.mean(wo_te)
w_mean = stats.mean(w_te)
z, p = stats.mannwhitneyu(w_te, wo_te)
cols = (rep, fam, orient, sample1, sample2, len(w_te), w_mean, wo_mean, z, p)
table_lines.append('%-17s %-17s %1s %-10s %-10s %6d %9.2f %9.2f %8.2f %10.2e' % cols)
pvals.append(p)
# plot ...
if rep in ['*'] and fam in ['*','LINE/L1','SINE/Alu','LTR/ERV1','LTR/ERVL-MaLR','LINE/L2','LTR/ERVL','SINE/MIR','DNA/hAT-Charlie','LTR/ERVK','DNA/TcMar-Tigger']:
out_pdf = '%s/%s_%s_%s_%s-%s.pdf' % (plot_dir,rep.replace('/','-'),fam.replace('/','-'),orient,sample1,sample2)
cdf_plot(te_or, w_te, wo_te, out_pdf)
return table_lines, pvals
def fit(self, X, y):
n = len(X)
# _x e _y serao as medias de x e y.
_x = st.mean(X)
_y = st.mean(y)
self.__class__.b1 = np.sum((X - _x) * (y - _y)) / np.sum((X - _x)**2)
self.__class__.b0 = _y - (self.__class__.b1 * _x)
def statsex(self, objects):
"""
Do some statistics on a source list
Return dictionary
"""
import stats, pstat
# Return if we have no objects
if len(objects) == 0:
return 0
# Define dictionary to hold statistics
stat = {}
# Get number of objects
stat['N'] = str(len(objects))
# Define list (float) of FWHM values
fwhm = [ float(obj[7]) for obj in objects ]
# Define list (float) of ELLIPTICITY values
el = [ float(obj[6]) for obj in objects ]
# Define list (float) of THETA_IMAGE values
pa = [ float(obj[5]) for obj in objects ]
# Define list (float) of 'Stella-like' values
stella = [ float(obj[9]) for obj in objects ]
# Create a histogram of FWHM values of binsize 1 pixel
hfwhm = stats.histogram(fwhm,40,[0,40])[0]
stat['medianFWHM'] = "%.2f" % stats.median(fwhm)
stat['meanFWHM'] = "%.2f" % stats.mean(fwhm)
stat['modeFWHM'] = "%.2f" % float(hfwhm.index(max(hfwhm))+0.5)
try:
stat['stdevFWHM'] = "%.2f" % stats.stdev(fwhm)
except ZeroDivisionError:
stat['stdevFWHM'] = '0.00';
stat['medianEL'] = "%.2f" % stats.median(el)
stat['meanEL'] = "%.2f" % stats.mean(el)
try:
stat['stdevEL'] = "%.2f" % stats.stdev(el)
except ZeroDivisionError:
stat['stdevEL'] = '0.00'
# Histogram of Ellipticity PA (-180 to 180, bins of 45 deg)
#stat['histoTHETA'] = stats.histogram(pa,8,[-180,180])[0]
# Histogram of Stellarity (0 to 1, bins of 0.05)
#stat['histoStella'] = stats.histogram(stella,20,[0,1.01])[0]
return stat
def statsex(self, objects):
"""
Do some statistics on a source list
Return dictionary
"""
import stats, pstat
# Return if we have no objects
if len(objects) == 0:
return 0
# Define dictionary to hold statistics
stat = {}
# Get number of objects
stat['N'] = str(len(objects))
# Define list (float) of FWHM values
fwhm = [ float(obj[7]) for obj in objects ]
# Define list (float) of ELLIPTICITY values
el = [ float(obj[6]) for obj in objects ]
# Define list (float) of THETA_IMAGE values
pa = [ float(obj[5]) for obj in objects ]
# Define list (float) of 'Stella-like' values
stella = [ float(obj[9]) for obj in objects ]
# Create a histogram of FWHM values of binsize 1 pixel
hfwhm = stats.histogram(fwhm,40,[0,40])[0]
stat['medianFWHM'] = "%.2f" % stats.median(fwhm)
stat['meanFWHM'] = "%.2f" % stats.mean(fwhm)
stat['modeFWHM'] = "%.2f" % float(hfwhm.index(max(hfwhm))+0.5)
try:
stat['stdevFWHM'] = "%.2f" % stats.stdev(fwhm)
except ZeroDivisionError:
stat['stdevFWHM'] = '0.00';
stat['medianEL'] = "%.2f" % stats.median(el)
stat['meanEL'] = "%.2f" % stats.mean(el)
try:
stat['stdevEL'] = "%.2f" % stats.stdev(el)
except ZeroDivisionError:
stat['stdevEL'] = '0.00'
# Histogram of Ellipticity PA (-180 to 180, bins of 45 deg)
#stat['histoTHETA'] = stats.histogram(pa,8,[-180,180])[0]
# Histogram of Stellarity (0 to 1, bins of 0.05)
#stat['histoStella'] = stats.histogram(stella,20,[0,1.01])[0]
return stat
def testOnTuples(self):
"""
Checks that methods also work on tuples.
"""
self.assertAlmostEqual(stats.mean(tuple(self.dataA)), self.meanA, 5)
self.assertAlmostEqual(stats.mean(tuple(self.dataB)), self.meanB, 5)
self.assertAlmostEqual(stats.stddev(tuple(self.dataA)), self.stddevA, 5)
self.assertAlmostEqual(stats.stddev(tuple(self.dataB)), self.stddevB, 5)
return
def least_squares_fit(xs: Vector, ys: Vector) -> Tuple[float, float]:
"""
Given a dataset represented by xs and ys, return the alpha, beta that provide the least squared error fit for a
function y_i = alpha * x_i + beta
"""
alpha = correlation(xs,
ys) * standard_deviation(ys) / standard_deviation(xs)
beta = mean(ys) - alpha * mean(xs)
return alpha, beta
def test_validator_working_correct_negativa(self):
with self.assertRaises(TypeError) as raised_exception:
stats.missing_data(2, 3.5)
self.assertEqual(raised_exception.exception.args[0],
"input type must be list")
with self.assertRaises(ValueError) as raised_exception:
stats.mean([1, 2, (2, 3.5)], [3.5, 2, 1])
self.assertEqual(raised_exception.exception.args[0],
"value in x must be numeric")
def findLSRline(dp):
if !checkDPFormat(dp):
print "ERROR: invalid dotplot format in findLSRline"
return "invalid dotplot format"
r = CorrCoef(dp)
x = [i[0] for i in dp]
sx = stats.stdDev(x)
y = [i[1] for i in dp]
sy = stats.stdDev(y)
b = (r * sy) / sx
a = stats.mean(y) - b * stats.mean(x)
def corr(xdata, ydata):
"""corr(xydata) -> float
corr(xdata, ydata) -> float
Return the sample Pearson's Correlation Coefficient of (x,y) data.
If ydata is None or not given, then xdata must be an iterable of (x, y)
pairs. Otherwise, both xdata and ydata must be iterables of values, which
will be truncated to the shorter of the two.
>>> corr([(0.1, 2.3), (0.5, 2.7), (1.2, 3.1), (1.7, 2.9)])
... #doctest: +ELLIPSIS
0.827429009335...
The Pearson correlation is +1 in the case of a perfect positive
correlation (i.e. an increasing linear relationship), -1 in the case of
a perfect anti-correlation (i.e. a decreasing linear relationship), and
some value between -1 and 1 in all other cases, indicating the degree
of linear dependence between the variables.
>>> xdata = [1, 2, 3, 4, 5, 6]
>>> ydata = [2*x for x in xdata] # Perfect correlation.
>>> corr(xdata, ydata)
1.0
>>> corr(xdata, [5-y for y in ydata]) # Perfect anti-correlation.
-1.0
If there are not at least two data points, or if either all the x values
or all the y values are equal, StatsError is raised.
"""
n = len(xdata)
assert n == len(ydata)
if n < 2:
raise StatsError(
'correlation requires at least two data points, got %d' % n)
# First pass is to determine the means.
mx = stats.mean(xdata)
my = stats.mean(ydata)
# Second pass to determine the standard deviations.
sx = stats.stdev(xdata, mx)
sy = stats.stdev(ydata, my)
if sx == 0:
raise StatsError('all x values are equal')
if sy == 0:
raise StatsError('all y values are equal')
# Third pass to calculate the correlation coefficient.
ap = add_partial
total = []
for x, y in zip(xdata, ydata):
term = ((x-mx)/sx) * ((y-my)/sy)
ap(term, total)
r = math.fsum(total)/(n-1)
assert -1 <= r <= r
return r
def muestroEspeYVar(valores, esperanzaTeorica, alfa):
print("El calculo de la Esperanza en la muestra es:", stats.mean(valores))
print("Teoricamente la Esperanza es:", esperanzaTeorica)
print("El calculo de la Varianza en la muestra es:", numpy.var(valores))
print("Teoricamente la Varianza es:", calcularVarianza(alfa))
print("El calculo del Desvio Estandar en la muestra es:",
math.sqrt(numpy.var(valores)))
print("Teoricamente es:", math.sqrt(calcularVarianza(alfa)))
print("El parametro alfa de la muestra es :", 1 / (stats.mean(valores)))
print("Teoricamente es :", alfa)
print("\n")
def get_modules(self, cutoff=.05):
modules = []
for e in self:
if e.val < min(e.lo_min, e.hi_min, cutoff):
if self.datatype=="continuous":
e.desc = "lo" if mean(e.a) < mean(e.b) else "hi"
else:
e.desc = "enriched"
modules.append(e)
else:
modules += e.get_modules(cutoff=cutoff)
return modules
def collect_mean(input_list):
""" Collect time execution of mean of each module """
begin_py_mean = clock()
py_mean(input_list)
end_py_mean = clock()
begin_mean = clock()
mean(input_list)
end_mean = clock()
times = format_times(end_py_mean - begin_py_mean, end_mean - begin_mean)
save_times(times, logs['mean'])
def _SP(xdata, mx, ydata, my):
"""SP = sum of product of deviations.
Helper function for calculating covariance directly.
"""
if mx is None:
# Two pass algorithm.
xdata = as_sequence(xdata)
mx = stats.mean(xdata)
if my is None:
# Two pass algorithm.
ydata = as_sequence(ydata)
my = stats.mean(ydata)
return _generalised_sum(zip(xdata, ydata), lambda t: (t[0]-mx)*(t[1]-my))
def corr(x, y):
N = len(x)
if len(y) != N:
raise Exception(
"Sequences must be of the same length. X length: {0} ; Y length {1}"
.format(N, len(y)))
else:
sum = 0
for index, xi in enumerate(x):
sum += xi * y[index]
r = (sum - N * stats.mean(x) * stats.mean(y)) / (
(N - 1) * stats.stdev(x) * stats.stdev(y))
return r
def check_basic(self):
a = [3,4,5,10,-3,-5,6]
af = [3.,4,5,10,-3,-5,-6]
Na = len(a)
Naf = len(af)
mn1 = 0.0
for el in a:
mn1 += el / float(Na)
assert_almost_equal(stats.mean(a),mn1,11)
mn2 = 0.0
for el in af:
mn2 += el / float(Naf)
assert_almost_equal(stats.mean(af),mn2,11)
def _getRatingStarsAverages():
android_ratings = []
ios_ratings = []
android_stars = []
ios_stars = []
global android_ratings_average
global android_stars_average
global ios_ratings_average
global ios_stars_average
print collection_ios.count(
{
'android_ratings_float': {
'$gte': 1
},
'ios_ratings_float': {
'$gte': 1
}
},
no_cursor_timeout=True)
for app in collection_ios.find(
{
'android_ratings_float': {
'$gte': 1
},
'ios_ratings_float': {
'$gte': 1
}
},
no_cursor_timeout=True):
android_ratings.append(app['android_ratings_float'])
android_stars.append(app['android_stars_float'])
#ios stats
ios_ratings.append(app['ios_ratings_float'])
ios_stars.append(app['ios_stars_float'])
android_ratings_average = stats.mean(android_ratings)
android_stars_average = stats.mean(android_stars)
ios_ratings_average = stats.mean(ios_ratings)
ios_stars_average = stats.mean(ios_stars)
print "android"
print android_ratings_average
print android_stars_average
print "ios"
print ios_ratings_average
print ios_stars_average
def check_2d(self):
a = [[1.0, 2.0, 3.0],
[2.0, 4.0, 6.0],
[8.0, 12.0, 7.0]]
A = array(a,'d')
N1,N2 = (3,3)
mn1 = zeros(N2,'d')
for k in range(N1):
mn1 += A[k,:] / N1
allclose(stats.mean(a),mn1,rtol=1e-13,atol=1e-13)
mn2 = zeros(N1,'d')
for k in range(N2):
mn2 += A[:,k] / N2
allclose(stats.mean(a,axis=0),mn2,rtol=1e-13,atol=1e-13)
def parameter_cedo_meanmean(self, TTL):
""" Computes the CEDO distribution parameter with the mean of the mean IMT per each pair of meeting nodes. """
raise Exception() #deprecated
logger.debug("Estimating CEDO mean of means parameter.")
imts = []
for timestamp, l in self._all_im.values():
if l:
imts.append(mean(l))
m = imts and mean(imts) or sys.maxsize
return self.apply_ndp(TTL, m)
def _getCollection():
print "Sanity Check"
print "android"
print android_ratings_average
print android_stars_average
print "ios"
print ios_ratings_average
print ios_stars_average
ratings_combined_average = stats.mean(
[android_ratings_average, ios_ratings_average])
stars_combined_average = stats.mean(
[android_stars_average, ios_stars_average])
print "average:"
print ratings_combined_average
print stars_combined_average
for post in collection_ios.find(
{
'android_ratings_float': {
'$gte': 1
},
'ios_ratings_float': {
'$gte': 1
}
},
no_cursor_timeout=True):
android_app_id = post['android_app_id']
android_app_rating = post['android_ratings_float']
android_app_star = post['android_stars_float']
ios_app_rating = post['ios_ratings_float']
ios_app_star = post['ios_stars_float']
successAndroid = (float(
_sucess(android_app_rating, android_app_star,
ratings_combined_average, stars_combined_average)) /
5) * 100
successIos = (float(
_sucess(ios_app_rating, ios_app_star, ratings_combined_average,
stars_combined_average)) / 5) * 100
collection_ios.find_one_and_update(
{"android_app_id": android_app_id}, {
'$set': {
'android_success_average': successAndroid,
'ios_success_average': successIos
}
})
def calculateDividingLine(gestures, maybeGestures, nonGestures): numFolds = min(TESTING_FOLDS, len(gestures)) allGestureDistances = [] allNonGestureDistances = [] for foldNum in range(numFolds): trainingGestures = [gesture for i, gesture in enumerate(gestures) if i % numFolds != foldNum] testingGestures = [localTimeGestures for i, localTimeGestures in enumerate(maybeGestures) if i % numFolds == foldNum] #print 'train, test #s: ', len(trainingGestures), len(testingGestures) #make a distance calculator based on the subset of hte training data distanceCalculator = gestureDistanceCalculator.GestureDistanceCalculator(trainingGestures) #each localTimeGestures is a list of the closest times to when a gesture was identified in training #since the output can be triggered at slightly different times, we should look for a minimum near where #the gesture is known to have happened, compared to the training gestures gestureDistances = [] #print testingGestures for localTimeGestureSet in testingGestures: closestDistance = min(map(distanceCalculator.getDistance, localTimeGestureSet)) gestureDistances.append(closestDistance) #gestureDistances = map(distanceCalculator.getDistance, testingGestures) #print gestureDistances nonGestureDistances = map(distanceCalculator.getDistance, nonGestures) #print gestureDistances allGestureDistances += gestureDistances allNonGestureDistances += nonGestureDistances #break #print len(allGestureDistances), len(allNonGestureDistances) print 'means: ', stats.mean(allGestureDistances), stats.mean(allNonGestureDistances) print 'std devs: ', stats.stdDev(allGestureDistances), stats.stdDev(allNonGestureDistances) meanGesture = stats.mean(allGestureDistances) meanNon = stats.mean(allNonGestureDistances) devGesture = stats.stdDev(allGestureDistances) devNon = stats.stdDev(allNonGestureDistances) line = (meanGesture * devNon + meanNon * devGesture) / ( devGesture + devNon) #print line return line
def liver(request):
expressLevelsNishi = naturallysortedexpressionlist(Expression.objects.filter(organ='Liver', experiment='Nishimura'))
expressLevelsPMT = naturallysortedexpressionlist(Expression.objects.filter(organ='Liver', experiment__startswith='PMT Sample'))
expressBiotroveTransporters = naturallysortedtransporterlist(Transporter.objects.filter(expression__organ='Liver',expression__experiment__startswith='PMT Biotrove').distinct())
important = Transporter.objects.filter(organ__name='Liver')
importantNames = []
for x in important:
importantNames.append(str(x.symbol))
synquery = Transporter.objects.all()
syns = {}
for x in synquery:
syns[x.symbol] = x.synonyms
#Calculate mean expression across all PMT samples
pmtTableValues = []
for x in range(len(expressLevelsPMT)/3):
build = []
for y in range(3):
build.append(expressLevelsPMT[x*3+y].value)
avg = stats.mean(build)
stdev = stats.stdev(build)
id = expressLevelsPMT[x*3].trans
pmtTableValues.append([id] + build + [avg, stdev])
#Calculate median and quartiles across biotrove samples
biotroveTableValues = []
for x in expressBiotroveTransporters:
values = Expression.objects.filter(organ='Liver', experiment__startswith='PMT Biotrove', trans=x).values_list('value',flat='True').order_by('value')
build = []
build.append(x.symbol)
build.append(quartiles(values,1))
build.append(quartiles(values,2))
build.append(quartiles(values,3))
biotroveTableValues.append(build)
return render_to_response('liver.html', {'expressionNishi': expressLevelsNishi, 'expressionPMT': pmtTableValues, 'organ': 'Liver', 'syns': syns, 'important': importantNames, 'expressionBiotrove': biotroveTableValues})
def linear_regression(x, y): """ See: https://www.khanacademy.org/math/probability/regression/regression-correlation/v/regression-line-example """ xy_mean = s.xy_mean(x, y) print xy_mean x_mean = s.mean(x) y_mean = s.mean(y) x_squared_mean = s.mean([xi ** 2 for xi in x]) # Slope. a = (x_mean * y_mean - xy_mean) / (x_mean ** 2 - x_squared_mean) # Intercept. b = y_mean - a * x_mean return (a, b)
def ttest_1samp(a, popmean):
t = (stats.mean(a) - popmean) / (stats.stddev(a) / len(a) ** 0.5)
v = len(a) - 1.0
p = gamma((v + 1) / 2) / ((v * pi) ** 0.5 * gamma(v / 2)) * (1 + t ** 2 / v) ** (-(v + 1) / 2)
return (
[t, None],
[p, None])
def main():
[(stat, first), (stat, second)] = load_stats(sys.argv[1:])
# Attempt to increase robustness by dropping the outlying 10% of values.
first = trim(first, 0.1)
second = trim(second, 0.1)
fmean = stats.mean(first)
smean = stats.mean(second)
p = 1 - ttest_1samp(second, fmean)[1][0]
if p >= 0.95:
# rejected the null hypothesis
print sys.argv[1], 'mean of', fmean, 'differs from', sys.argv[2], 'mean of', smean, '(%2.0f%%)' % (p * 100,)
else:
# failed to reject the null hypothesis
print 'cannot prove means (%s, %s) differ (%2.0f%%)' % (fmean, smean, p * 100,)
def circvar(samples, high=2*pi, low=0):
"""Compute the circular variance for samples assumed to be in the range [low to high]
"""
ang = (samples - low)*2*pi / (high-low)
res = stats.mean(exp(1j*ang))
V = 1-abs(res)
return ((high-low)/2.0/pi)**2 * V
def circstd(samples, high=2*pi, low=0):
"""Compute the circular standard deviation for samples assumed to be in the range [low to high]
"""
ang = (samples - low)*2*pi / (high-low)
res = stats.mean(exp(1j*ang))
V = 1-abs(res)
return ((high-low)/2.0/pi) * sqrt(V)
def integrate_box_1d(self, low, high):
"""Computes the integral of a 1D pdf between two bounds.
Parameters
----------
low : scalar
lower bound of integration
high : scalar
upper bound of integration
Returns
-------
value : scalar
the result of the integral
Raises
------
ValueError if the KDE is over more than one dimension.
"""
if self.d != 1:
raise ValueError("integrate_box_1d() only handles 1D pdfs")
stdev = ravel(sqrt(self.covariance))[0]
normalized_low = ravel((low - self.dataset) / stdev)
normalized_high = ravel((high - self.dataset) / stdev)
value = stats.mean(
special.ndtr(normalized_high) - special.ndtr(normalized_low))
return value
def diff_fpkm(diff_file, pseudocount):
gene_fpkms = {}
diff_in = open(diff_file)
diff_in.readline()
for line in diff_in:
a = line.split('\t')
gene_id = a[0]
sample1 = a[4]
sample2 = a[5]
status = a[6]
fpkm1 = float(a[7])
fpkm2 = float(a[8])
if status == 'OK':
if gene_id in gene_fpkms:
gene_fpkms[gene_id] += [fpkm1, fpkm2]
else:
gene_fpkms[gene_id] = [fpkm1, fpkm2]
diff_in.close()
gene_fpkm = {}
for gene_id in gene_fpkms:
log_fpkms = [math.log(fpkm+pseudocount,2) for fpkm in gene_fpkms[gene_id]]
gene_fpkm[gene_id] = stats.mean(log_fpkms)
return gene_fpkm
def muestroEsperanzayVar(valores,alfa,ka):
print("El calculo de la esperanza en la muestra es:",stats.mean(valores))
print("Teoricamente la Esperanza es = ",ka/alfa)
print("El calculo de la Varianza es = ",numpy.var(valores))
print("Teoricamente la Varianza es = ",ka/(alfa**2))
print("El Desvio estandar es =",math.sqrt(numpy.var(valores)))
print("Teoricamente es =",math.sqrt(ka/(alfa**2)))
def scale(data_matrix):
num_rows, num_cols = shape(data_matrix)
means = [mean(get_column(data_matrix,j))
for j in range(num_cols)]
stdevs = [standard_deviation(get_column(data_matrix,j))
for j in range(num_cols)]
return means, stdevs
def sample_stats(n):
"""
Compute mean and standard deviation on a bunch of
random numbers
"""
sample = tuple(random.random() for i in range(n))
return mean(sample), sd(sample)
def main():
[(_ignore_stat, first), (_ignore_stat, second)] = load_stats(sys.argv[1:])
# Attempt to increase robustness by dropping the outlying 10% of values.
first = trim(first, 0.1)
second = trim(second, 0.1)
fmean = stats.mean(first)
smean = stats.mean(second)
p = ttest_1samp(second, fmean)[1]
if p >= 0.95:
# rejected the null hypothesis
print(sys.argv[1], 'mean of', fmean, 'differs from', sys.argv[2], 'mean of', smean, '(%2.0f%%)' % (p * 100,))
else:
# failed to reject the null hypothesis
print('cannot prove means (%s, %s) differ (%2.0f%%)' % (fmean, smean, p * 100,))
def _test_mem_bounded_golden_values_fields(activeGpuCount, memUsageTS,
tailStart):
goldenVal = 1148 # 1 KB plus some swag per field instance (Global, GPU). This is based off of the keyed vector block size and default number of blocks
tolerance = 0.10 # low tolerance, amount of records stored is bounded
for fieldId, series in memUsageTS.fieldVals.items():
seriesTail = series[tailStart:]
# skip fields that are not implemented
if sum(seriesTail) == 0:
continue
#Don't check the size of binary fields since it's arbitrary per fieldId
if helper_field_has_variable_size(fieldId):
logger.info("Skipping variable-sized fieldId %d" % fieldId)
continue
mean = stats.mean(seriesTail)
lowLimit = (1 - tolerance) * goldenVal
highLimit = (1 + tolerance) * goldenVal * activeGpuCount
assert lowLimit < mean < highLimit, \
'Expected field "%d" memory usage to be between %s and %s but got %s' % \
(fieldId, lowLimit, highLimit, mean) \
+ 'If this new value is expected, change the golden value used for comparison.'
def ttest_1samp(a, popmean):
# T statistic - http://mathworld.wolfram.com/Studentst-Distribution.html
t = (stats.mean(a) - popmean) / (stats.stddev(a) / len(a)**0.5)
v = len(a) - 1.0
p = gamma((v + 1) / 2) / (
(v * pi)**0.5 * gamma(v / 2)) * (1 + t**2 / v)**(-(v + 1) / 2)
return (t, p)
def wordSummary(db, table):
f = open("wordSummary_%s.txt" % table, 'w')
d = {}
header = "word, length, rtAVG, rtSTD, total, percCorrect\n"
f.write(header)
wordList = []
sql = "SELECT DISTINCT(word) FROM %s" % table
for w in db.query(sql):
wordList.append(w[0])
for word in wordList:
sql = "SELECT RT FROM %s WHERE word = '%s' AND incorrect = 0" % (table,
word)
wordLen = len(word)
rtList = []
zList = []
for rt in db.query(sql):
rtList.append(rt[0])
rtAVG = stats.mean(rtList)
rtSTD = stats.samplestdev(rtList)
total = db.query("SELECT COUNT(*) FROM %s WHERE word = '%s'" %
(table, word))[0][0]
percCorrect = float(len(rtList)) / float(total) * 100.0
print len(rtList), total
myString = "%s, %i, %f, %f, %i, %f\n" % (word, wordLen, rtAVG, rtSTD,
total, percCorrect)
print myString
f.write(myString)
f.close()
def wordSummary(db, table):
f = open("wordSummary_%s.txt" % table, 'w')
d = {}
header = "word, length, rtAVG, rtSTD, total, percCorrect\n"
f.write(header)
wordList = []
sql = "SELECT DISTINCT(word) FROM %s" % table
for w in db.query(sql):
wordList.append(w[0])
for word in wordList:
sql = "SELECT RT FROM %s WHERE word = '%s' AND incorrect = 0" % (table, word)
wordLen = len(word)
rtList = []
zList = []
for rt in db.query(sql):
rtList.append(rt[0])
rtAVG = stats.mean(rtList)
rtSTD = stats.samplestdev(rtList)
total = db.query("SELECT COUNT(*) FROM %s WHERE word = '%s'" % (table, word))[0][0]
percCorrect = float(len(rtList)) / float(total) * 100.0
print len(rtList), total
myString = "%s, %i, %f, %f, %i, %f\n" % (word, wordLen, rtAVG, rtSTD, total, percCorrect)
print myString
f.write(myString)
f.close()
def optimal_discard_6(hand):
# loop over all possible discard options
possible_hands_scores = {}
for i in range(6):
for j in range(6):
if j > i:
possible_hand = []
counter = -1
for card in hand['hand6']:
counter += 1
if counter == i or counter == j:
continue
possible_hand.append(card)
# get total list of possible scores for that hand
point_list = check_all_cuts(possible_hand)
possible_hands_scores[tuple(possible_hand)] = point_list
max_expected_points = 0
best_hand = []
for poss_hand, point_list in possible_hands_scores.iteritems():
expected_points = mean(point_list)
# print hand, expected_points
if expected_points > max_expected_points:
max_expected_points = expected_points
best_hand = poss_hand
discard = list(set(hand['hand6']) - set(best_hand))
# print("Best Hand = {} for {} points".format(best_hand, max_expected_points))
return list(best_hand), discard
def print_latex_stats(diffs, label): print '%s & %.3f & %.3f & %.3f & %.3f \\\\' % ( label, min(diffs) / 1000.0, max(diffs) / 1000.0, stats.mean(diffs) / 1000.0, stats.stdev(diffs) / 1000.0)
def print_stats(L):
""" Display some information about the lists """
print "Let's compute some statistics..."
print "\tMean: %d" % mean(L)
print "\tStandard deviation: %d" % std(L)
print "\t# of outliers: %d" % (len(L) - len(remove_outliers(L,1)))
def test_mean1():
obs = mean([0, 0, 0, 0])
exp = 0
assert_equal(obs, exp)
obs = mean([0, 200])
exp = 100
assert_equal(obs, exp)
obs = mean([0, -200])
exp = -100
assert_equal(obs, exp)
obs = mean([0])
exp = 0
assert_equal(obs, exp)
def integrate_box_1d(self, low, high):
"""Computes the integral of a 1D pdf between two bounds.
Parameters
----------
low : scalar
lower bound of integration
high : scalar
upper bound of integration
Returns
-------
value : scalar
the result of the integral
"""
if self.d != 1:
raise ValueError("integrate_box_1d() only handles 1D pdfs")
stdev = ravel(sqrt(self.covariance))[0]
normalized_low = ravel((low - self.dataset)/stdev)
normalized_high = ravel((high - self.dataset)/stdev)
value = stats.mean(special.ndtr(normalized_high) -
special.ndtr(normalized_low))
return value
def testVariance(self):
data = [1, 2, 3]
assert stats.mean(data) == 2
self.assertEqual(stats.pvariance(data), 2/3)
self.assertEqual(stats.variance(data), 1.0)
self.assertEqual(stats.pstdev(data), math.sqrt(2/3))
self.assertEqual(stats.stdev(data), 1.0)
def circvar(samples, high=2*pi, low=0):
"""Compute the circular variance for samples assumed to be in the range [low to high]
"""
ang = (samples - low)*2*pi / (high-low)
res = stats.mean(exp(1j*ang))
V = 1-abs(res)
return ((high-low)/2.0/pi)**2 * V
def circstd(samples, high=2*pi, low=0):
"""Compute the circular standard deviation for samples assumed to be in the range [low to high]
"""
ang = (samples - low)*2*pi / (high-low)
res = stats.mean(exp(1j*ang))
V = 1-abs(res)
return ((high-low)/2.0/pi) * sqrt(V)
def test_mean1():
obs = mean([0, 0, 0, 0])
exp = 0
assert_equal(obs, exp)
obs = mean([0, 200])
exp = 100
assert_equal(obs, exp)
obs = mean([0, -200])
exp = -100
assert_equal(obs, exp)
obs = mean([0])
exp = 0
assert_equal(obs, exp)
def diff_fpkm(diff_file, pseudocount):
gene_fpkms = {}
diff_in = open(diff_file)
diff_in.readline()
for line in diff_in:
a = line.split('\t')
gene_id = a[0]
sample1 = a[4]
sample2 = a[5]
status = a[6]
fpkm1 = float(a[7])
fpkm2 = float(a[8])
if status == 'OK':
if gene_id in gene_fpkms:
gene_fpkms[gene_id] += [fpkm1, fpkm2]
else:
gene_fpkms[gene_id] = [fpkm1, fpkm2]
diff_in.close()
gene_fpkm = {}
for gene_id in gene_fpkms:
log_fpkms = [
math.log(fpkm + pseudocount, 2) for fpkm in gene_fpkms[gene_id]
]
gene_fpkm[gene_id] = stats.mean(log_fpkms)
return gene_fpkm
def default_score_set(expression, primer_set, primer_locs, max_dist, bg_dist_mean):
"""Evaluate an expression using the provided values and a set of metrics.
:returns: the score and the metrics used to calculate it
"""
# Calculate various metrics
binding_distances = stats.seq_diff(primer_locs)
namespace = {
'set_size': len(primer_set),
'fg_dist_mean': stats.mean(binding_distances),
'fg_dist_std': stats.stdev(binding_distances),
'fg_dist_gini': stats.gini(binding_distances),
'bg_dist_mean': bg_dist_mean,
'fg_max_dist': max_dist,
'__builtins__': None}
permitted_var_str = ", ".join(
[key for key in namespace.keys() if key is not "__builtins__"])
score = None
try:
score = eval(expression, namespace, {'__builtins__': {}})
except NameError as e:
raise NameError(
e.message +
'. Permitted variables are %s. Refer to README or docs for help.'
% permitted_var_str)
del namespace['__builtins__']
return score, namespace
def scaleTestMinFinding(): xs = range(10) distances = [] noise = 3.5 n = 1000000 for i in range(n): a = random() b = random() c = random() ys = [x*x*a + x*b + c + random() * noise for x in xs] #print a, b, c, polynomialFit(xs, ys)[::-1] minExp, unc = polynomialFindMinimum(xs, ys, returnErrors = True) minCalc = -b/(2.0*a) dist = (minCalc - minExp) / unc #print minCalc, minExp, unc, dist distances.append(dist) print 'mean: %f' % stats.mean(distances) print 'stdDev: %f' % stats.stdDev(distances) for sigma in [1, 2, 3]: print 'With %d sigma: %f%%' % (sigma, 100.0 * sum([int(abs(d) < sigma) for d in distances]) / n) pylab.hist(distances, bins = 50, range = (-5, 5)) pylab.show()
def cuff_fpkm(fpkm_file, pseudocount):
cuff = cufflinks.fpkm_tracking(fpkm_tracking_file)
gene_fpkm = {}
for gene_id in cuff.genes:
gene_fpkm[gene_id] = stats.mean([math.log(pseudocount+e,2) for e in cuff.gene_expr(gene_id, not_found=0, fail=0)])
return gene_fpkm
def circmean(samples, high=2*pi, low=0):
"""Compute the circular mean for samples assumed to be in the range [low to high]
"""
ang = (samples - low)*2*pi / (high-low)
res = angle(stats.mean(exp(1j*ang)))
if (res < 0):
res = res + 2*pi
return res*(high-low)/2.0/pi + low
def scale(data_matrix):
"""returns means and standard deviations of each column"""
num_rows, num_columns = la.shape(data_matrix)
means = [stats.mean(la.get_c(data_matrix, j)) for j in range(num_columns)]
stdevs = [
stats.std_dev(la.get_c(data_matrix, j)) for j in range(num_columns)
]
return means, stdevs
def circmean(samples, high=2*pi, low=0):
"""Compute the circular mean for samples assumed to be in the range [low to high]
"""
ang = (samples - low)*2*pi / (high-low)
res = angle(stats.mean(exp(1j*ang)))
if (res < 0):
res = res + 2*pi
return res*(high-low)/2.0/pi + low
def _getRatingAverages():
count = 0
android_rating_total = 0
ios_rating_total = 0
android_ratings = []
ios_ratings = []
global android_rating_average
global ios_rating_average
global android_rating_median
global ios_rating_median
global android_rating_q1
global ios_rating_q1
global android_rating_q3
global ios_rating_q3
for app in collection_ios.find().batch_size(30):
# count=count+1
# android_rating_total=android_rating_total+float(app['android_ratingsAllVersions'].replace(',',''))
# ios_rating_total=ios_rating_total+float(app['ios_ratingsAllVersions_new'].replace(',',''))
android_ratings.append(float(app["android_ratingsAllVersions"].replace(",", "")))
ios_ratings.append(float(app["ios_ratingsAllVersions_new"].replace(",", "")))
android_rating_average = stats.mean(android_ratings)
ios_rating_average = stats.mean(ios_ratings)
android_rating_median = stats.median(android_ratings)
ios_rating_median = stats.median(ios_ratings)
android_rating_q1 = stats.quartiles(android_ratings)[0]
ios_rating_q1 = stats.quartiles(ios_ratings)[0]
android_rating_q3 = stats.quartiles(android_ratings)[1]
ios_rating_q3 = stats.quartiles(ios_ratings)[1]
print "ios stats"
print ios_rating_q1
print ios_rating_median
print ios_rating_q3
print "Android stats"
print android_rating_q1
print android_rating_median
print android_rating_q3
def scale(data_matrix):
#各列の平均と標準偏差を返す
num_rows, num_cols = shape(data_matrix)
means = [mean(get_column(data_matrix, j)) for j in range(num_cols)]
stdevs = [
standard_deviation(get_column(data_matrix, j)) for j in range(num_cols)
]
return means, stdevs