def test_variance(self):
"""Assume degree of freedom = 0"""
l = [1, 2, 3, 4, 5, 5, 4, 3, 3, 1, 2]
my_value = st.variance(l)
numpy_value = np.var(l)
self.assertEquals(my_value, numpy_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 directional_variance(data: List[Vector], w: Vector) -> float:
"""
Given a dataset and a vector w from which to take a direction, return the variance in the data along that direction
"""
dir_w = direction(w)
# key insight: the dot product of two orthogonal vectors is zero. dot product against a magnitude vector is the portion
# of the magnitude of the query vector in THAT direction
dot_projections: Vector = [dot(v, dir_w) for v in data]
return variance(dot_projections) # books code doesn't center mean but that should be ok, we already centered it
def clustered_mismatch_variance(self, cluster_count: int) -> float:
"""
Returns the variance between the mismatch clusters. The
raw cluster mismatches can be retrieved with the
`clustered_mismatches` method. `cluster_count` controls
the number of clusters used.
"""
return variance(
np.array(self.clustered_mismatches(cluster_count=cluster_count)),
sample=False,
)
def print_testcase(variablePrefix, i, count, values_mean, values_stdDev,
values_ordering, weights_mean, weights_stdDev,
weights_ordering):
from stats import mean, variance, sqrt_float
# calculate values
values = generate_numbers(count, values_mean, values_stdDev,
values_ordering)
weights = generate_weights(count, weights_mean, weights_stdDev,
weights_ordering)
m = mean(values, weights)
v = variance(values, weights, m)
stdDev = sqrt_float(v)
weightedValues = []
for value, weight in zip(values, weights):
weightedValues.append(value)
weightedValues.append(weight)
# output values
print("// Generated values with parameters:")
print("// Count = {}".format(count))
print("// values_mean = {:e}; values_stdDev = {:e}; values_ordering = {}".
format(values_mean, values_stdDev, values_ordering))
print(
"// weights_mean = {:e}; weights_stdDev = {:e}; weights_ordering = {}".
format(weights_mean, weights_stdDev, weights_ordering))
print("private static final long {}Mean{} = {}; // approx ~ {:e}".format(
variablePrefix, i, export(float(m)), float(m)))
print("private static final long {}StdDev{} = {}; // approx ~ {:e}".format(
variablePrefix, i, export(stdDev), stdDev))
print("private static final long[] {}WeightedValues{} = {};".format(
variablePrefix, i, export_series(weightedValues)))
print("")
def print_testcase(variablePrefix, i, count, values_mean, values_stdDev,
values_ordering, weights_mean, weights_stdDev, weights_ordering):
from stats import mean, variance, sqrt_float
# calculate values
values = generate_numbers(count, values_mean,
values_stdDev, values_ordering)
weights = generate_weights(count, weights_mean,
weights_stdDev, weights_ordering)
m = mean(values, weights)
v = variance(values, weights, m)
stdDev = sqrt_float(v)
weightedValues = []
for value, weight in zip(values, weights):
weightedValues.append(value)
weightedValues.append(weight)
# output values
print("// Generated values with parameters:")
print("// Count = {}".format(count))
print("// values_mean = {:e}; values_stdDev = {:e}; values_ordering = {}"
.format(values_mean, values_stdDev, values_ordering))
print("// weights_mean = {:e}; weights_stdDev = {:e}; weights_ordering = {}"
.format(weights_mean, weights_stdDev, weights_ordering))
print("private static final long {}Mean{} = {}; // approx ~ {:e}"
.format(variablePrefix, i, export(float(m)), float(m)))
print("private static final long {}StdDev{} = {}; // approx ~ {:e}"
.format(variablePrefix, i, export(stdDev), stdDev))
print("private static final long[] {}WeightedValues{} = {};"
.format(variablePrefix, i, export_series(weightedValues)))
print("")
def getSignalCoherenceError(downSampledFrequency, rawData = rawData): downSampled = fftDataExtraction.downSample(rawData, rawSps, downSampledFrequency, interpolate = True)#[int(random()*100):] #downSampled = downSampled[:int(downSampledFrequency)/2] #downSampled = downSampled[:40] highSamples = downSampled[::2] lowSamples = downSampled[1::2] times = map(lambda x: x/downSampledFrequency, range(len(downSampled))) highTimes = times[::2] lowTimes = times[1::2] differences = map(lambda x: (x[0]-x[1])**1.0, zip(highSamples, lowSamples)) slope, yint = stats.lineOfBestFit(highTimes, differences) #return slope #return abs(slope) #return 1.0 / slope #return max(differences) - min(differences) #derivSquared = sum([(differences[i+1] - differences[i])**2.0 for i in range(len(differences)-1)]) #return derivSquared return stats.variance(differences)
median = st.median(A)
print("A's median = ", median)
quantile = st.quantile(A, 0.2)
print("A's 20% quantile = ", quantile)
quantile = st.quantile(A, 0.9)
print("A's 90% quantile = ", quantile)
mode = st.mode(A)
print("A's mode = ", mode)
data_range = st.data_range(A)
print("A's range = ", data_range)
variance = st.variance(A)
print("A's variance = ", variance)
standard_deviation = st.standard_deviation(A)
print("A's standard deviation = ", standard_deviation)
interquartile_range = st.interquartile_range(A)
print("A's interquartile range of 25% ~ 75% = ", interquartile_range)
x = [-2, -1, 0, 1, 2]
y = [2, 1, 0, 1, 2]
correlation = st.correlation(x, y)
print("correlation = ", correlation)
def test_variance_single_value_is_zero(self):
self.assertEqual(0.0, variance([0.0]))
self.assertEqual(0.0, variance([99.999]))
import random
import matplotlib.pyplot as plt
import stats
import numpy
import math
def generoValoresEmpiricos(matrizValores):
x = random.random()
for i in range(0, len(matrizValores)):
if (matrizValores[i][3] >= x):
x = matrizValores[i][0]
return x
cantNum = 1000
matrizValores = [[1, 15, 0.15, 0.15], [2, 15, 0.15, 0.3], [3, 17, 0.17, 0.52],
[4, 12, 0.12, 0.64], [5, 20, 0.2, 0.84], [6, 16, 0.16, 1]]
for j in range(0, 2):
valores = []
for i in range(0, cantNum):
valores.append(generoValoresEmpiricos(matrizValores))
print("\nMuestra Nro ", j + 1)
print("La Esperanza de la muestra es =", stats.mean(valores))
print("La Varianza es = ", stats.variance(valores))
plt.hist(valores, edgecolor='black', linewidth=1, alpha=0.5)
plt.show()
covariances = []
for i in range(1, sampleCount):
covariance = 0
X1 = sampleList[i - 1] #list of values in the first sample
X2 = sampleList[i] #list of values in the second sample
u1 = sampleMeans[i - 1] #mean of the first sample
u2 = sampleMeans[i] #mean of the second sample
for index in range(0, sampleLength):
covariance += ((X1[index] - u1) *
(X2[index] - u2)) / sampleLength
covariances = covariances + [covariance]
#Now we calculate correlations between each sample to see if they approach zero.
#If they approach zero the initial transient is vanished
correlations = []
for i in range(1, sampleCount):
X1_variance = stats.variance(sampleList[i - 1])
X2_variance = stats.variance(sampleList[i])
try:
correlation = covariances[i - 1] / math.sqrt(
X1_variance * X2_variance)
correlations = correlations + [correlation]
except:
#Division with zero has occured, so correlation set to zero
correlations = correlations + [0]
print(correlations)
"""
Here we look at the average queue lengths with each of the configurations.
"""
"""
interarrival_time is either exp(25) or exp(22.5)
def test_variance_typical_values(self):
"""variance of some typical values"""
self.assertEqual(0.0, variance([10.0, 10.0, 10.0, 10.0, 10.0]))
self.assertEqual(2.0, variance([1, 2, 3, 4, 5]))
self.assertEqual(8.0, variance([10, 2, 8, 4, 6]))
def testVar(self):
sx2 = stats.variance(self.xdata)
sy2 = stats.variance(self.ydata)
self.assertAlmostEqual(sx2, 11004687 / 983040, places=self.places)
self.assertAlmostEqual(sy2, 4647 / 3840, places=self.places)
don't have to write lots of code over and over for each problem.
"""
# CONFIG
PROJECT_ROOT = '..' # relative location pointing to utils/ and stats.py
# REST OF FILE
import sys
# allows import of project files (idk how else to do this)
sys.path.insert(1, PROJECT_ROOT)
from utils.webassign import array_from_shitstring
from stats import variance, standard_deviation
data = array_from_shitstring(
"85 105 130 160 180 195 134 145 214 105 145 151 153 135 87 99 94 119 129"
) # put your data here
data.sort()
print("Oxidation induction time (min): {}".format(data))
data_variance = variance(data)
data_standard_deviation = standard_deviation(data)
print("Sample variance: {}".format(data_variance))
print("Standard deviation: {}".format(data_standard_deviation))
data_to_hours = [value / 60 for value in data]
data_variance_in_hours = variance(data_to_hours)
standard_deviation_in_hours = standard_deviation(data_to_hours)
print("Sample variance (hrs): {}".format(data_variance_in_hours))
print("Standard deviation (hrs): {}".format(standard_deviation_in_hours))
def test_variance_single_value_is_zero(self):
"""variance of a singleton list should be zero"""
self.assertEqual(0.0, variance([0.0]))
self.assertEqual(0.0, variance([99.999]))
def testVariance(self):
self.assertEquals(self.population_variance,
stats.variance(self.data, True))
self.assertEquals(self.sample_variance,
stats.variance(self.data[:len(self.data) / 2]))
def register_sample (app, app_id, tag, day_of_the_week = None): user = User.objects.filter(app = app, app_id = app_id).first() ## Clear all the events of that tag ## Then recreate them from the new data events = Event.objects.filter(user = user, tag = tag) if day_of_the_week is not None: events = events.filter(day_of_week = day_of_the_week) for event in events: event.is_active = False event.save() app = importlib.import_module(user.app + "." + user.app) event_times = getattr(app, "%s_times" % tag)(app_id, day_of_the_week = day_of_the_week) if len(event_times) < 2: return if len(event_times[0]) < 2: return pmf = stats.event_pmf(event_times, 1440) pmf_average = stats.average(pmf) if pmf_average < minimum_pmf_mean(tag): ## All weak probabilities. Only outlier events. return pmf_variance = stats.variance(pmf, average = pmf_average) pmf_std = stats.standard_deviation(pmf, variance = pmf_variance) in_event = False event_start_minutes = [] event_end_minutes = [] event_probabilites = [] for minute in range(0,1440): if pmf[minute] > pmf_average + pmf_variance: if in_event is False: event_start_minutes.append(minute) in_event = True else: if in_event is True: event_end_minutes.append(minute) in_event = False if len(event_start_minutes) > len(event_end_minutes): ## Assume the last event started at night and ends in the morning event_start_minutes[0] = event_start_minutes[len(event_start_minutes) - 1] del event_start_minutes[len(event_start_minutes) - 1] ## If events are too close together, combined them. for index in range(0, len(event_end_minutes)): if index + 1 >= len(event_start_minutes): break event_end_time = event_end_minutes[index] next_event_start_time = event_start_minutes[index + 1] time_between_event = next_event_start_time - event_end_time if time_between_event < minimum_time_between_event(tag): del event_end_minutes[index] del event_start_minutes[index + 1] for index in range(0, len(event_start_minutes)): start_minute = event_start_minutes[index] end_minute = event_end_minutes[index] if start_minute < end_minute: event_probability_set = pmf[start_minute:end_minute] else: event_probability_set = pmf[start_minute:1439] event_probability_set.extend(pmf[0:end_minute]) event_average_probablity = stats.average(event_probability_set) event_probability_variance = stats.variance(event_probability_set, average = event_average_probablity) fringe_start_time = start_minute - fringe_time_for_event(tag) if fringe_start_time < 0: fringe_start_time = 1440 + fringe_start_time fringe_end_time = end_minute + fringe_time_for_event(tag) if fringe_end_time > 1440: fringe_end_time = fringe_end_time - 1440 if fringe_end_time > fringe_start_time: fringe_pmf = pmf[fringe_start_time:fringe_end_time] else: fringe_pmf = pmf[fringe_start_time:1439] fringe_pmf.extend(pmf[0:fringe_end_time]) fringe_average_probability = stats.average(fringe_pmf) fringe_variance = stats.variance(fringe_pmf, average = fringe_average_probability) start_hour = float(start_minute)/60.0 end_hour = float(end_minute)/60.0 e = Event.objects.create(user = user, tag = tag, start_time = start_hour, end_time = end_hour, day_of_week = day_of_the_week, probability = event_average_probablity, probability_variance = event_probability_variance, fringe_probability = fringe_average_probability, fringe_variance = fringe_variance) e.save()
d1 = Dog('fido', 3, 'male')
d2 = Dog('sally', 5, 'female')
print('before', d1)
d1.eat()
print('after eating', d1)
d1.play()
print('after playing', d1)
# instructions
# read in dogs.txt
# create a dog for
# every entry
# add all dogs
# to a dogs array
# find the average age
# of these dogs
# and the standard deviation
doglist = []
dogages = []
with open('dogs.txt') as f:
for line in f:
dog = line.strip().split(',')
doglist.append(Dog(dog[0], int(dog[1]), dog[2]))
dogages.append(int(dog[1]))
avg_age = s.mean(dogages)
age_std_dev = s.variance(dogages)**(1 / 2)
print(doglist, avg_age, age_std_dev)
import stats
def cargoArchivos():
datos1=pd.read_excel("Datos 01.xlsx",header=None)
listaDatos1={col:datos1[col].dropna().tolist() for col in datos1.columns}[0]
datos2=pd.read_excel("Datos 02.xlsx",header=None)
listaDatos2={col:datos2[col].dropna().tolist() for col in datos2.columns}[0]
datos3=pd.read_excel("Datos 03.xlsx",header=None)
listaDatos3={col:datos3[col].dropna().tolist() for col in datos3.columns}[0]
return listaDatos1,listaDatos2,listaDatos3
datos1,datos2,datos3=cargoArchivos()
print("\nDatos Muestra 1")
esperanzaDatos1 = stats.mean(datos1)
varianzaDatos1 = stats.variance(datos1)
lambdaa=esperanzaDatos1
print("La Esperanza Matematica de la muestra es = ",esperanzaDatos1)
print("La Varianza Matematica de la muestra es = ",varianzaDatos1)
print("El lambda de la muestra es = ",lambdaa)
plt.hist(datos1, edgecolor='black', linewidth=1,density=1,label=(f'Lambda = {round(lambdaa,0)}'))
y = [((math.exp(-6) * (6 ** x)) / (math.factorial(x))) for x in datos1]
plt.plot(datos1,y,'o')
plt.grid(True)
plt.ylim(0,0.25)
plt.text(9,0.15,"Amarrilo Dist.Poisson Lambda=6",color='black')
plt.legend(title="Parametros")
plt.title("Datos Muestra 1 - Distribucion Poisson")
plt.xlabel("Intervalos")
plt.ylabel("Frecuencia")
plt.show()
def testVariance(self):
self.assertEquals(self.population_variance, stats.variance(self.data, True))
self.assertEquals(self.sample_variance, stats.variance(self.data[:len(self.data)/2]))
def test_variance_throws_exception(self):
with self.assertRaises(TypeError):
var = variance([])
def test_variance(self):
self.assertEqual(stats.variance([1, 2, 3, 4, 5]), 2.5)
"""
This file contains some default imports and commonly used functions so that you
don't have to write lots of code over and over for each problem.
"""
# CONFIG
PROJECT_ROOT = '..' # relative location pointing to utils/ and stats.py
# REST OF FILE
import sys
# allows import of project files (idk how else to do this)
sys.path.insert(1, PROJECT_ROOT)
from utils.webassign import array_from_shitstring_floats
from stats import get_range, variance, standard_deviation
o2_consumption = array_from_shitstring_floats(
'29.6 49.4 31.0 28.4 28.8 25.4 34.0 29.8 23.8 30.1')
print("O2 Consumption: {}".format(o2_consumption))
print("Sample range: {}".format(get_range(o2_consumption)))
print("Sample variance: {}".format(variance(o2_consumption)))
print("Standard deviation: {}".format(standard_deviation(o2_consumption)))
import numpy as np
import stats
# Load the column at the ith column, at the i-1 index
def load_col(fname, i):
return np.loadtxt(fname, usecols=(i-1,))
y = load_col("ludoarray.txt", 3)
print("Column 3 (y) is: {}".format(y))
# Calculate the mean, variance, and std_dev of y
mean = stats.mean(y)
variance = stats.variance(y)
std_dev = stats.std_dev(y)
# Print the result of the calculations
print("The mean of y is {:f} \nThe variance of y is {:f} \nThe std deviation of \
y is {:f}".format(mean,variance,std_dev))
def test_variance_throws_exception(self):
"""variance of an empty list should raise an exception"""
with self.assertRaises(ValueError):
var = variance([])
#내가 만든 directory에 path만들기
import sys
sys.path.append('C:\\mypython')
sys.path
#잘못된 path 지우기
sys.path.remove('C:\\mypython')
#########################################
[문제84] stats 모듈에 평균, 분산, 표준편차함수를 사용할수 있는 프로그램을 생성하세요.
>>> import stats
>>> stats.mean(1,2,3,4,5)
3.0
>>> stats.variance(1,2,3,4,5)
2.5
>>> stats.stddev(1,2,3,4,5)
1.5811388300841898
#stats에 각 함수를 포함하도록 하기
########## c:\python\stats.py 답
import math
def mean (*arg):
return sum(arg)/len(arg)
def variance(*arg):
total = 0
m = mean(*arg)
import sys
# allows import of project files (idk how else to do this)
sys.path.insert(1, '..')
from utils.webassign import array_from_shitstring
from stats import mean, deviation_from_mean, variance, standard_deviation
youngs_mod = array_from_shitstring(" 116.6 115.8 114.9 115.3 115.6 ")
youngs_mod.sort()
print("Young's Mod: {}".format(youngs_mod))
sample_mean = mean(youngs_mod)
print("Young's Mod (mean): {}".format(sample_mean))
print("Deviation from mean:")
deviation_list = deviation_from_mean(youngs_mod)
for data_point, deviation in zip(youngs_mod, deviation_list):
print("Sample: {0}, deviation from mean: {1}".format(
data_point, deviation))
my_variance = variance(youngs_mod)
print("Sample variance: {}".format(my_variance))
print("Standard deviation: {}".format(standard_deviation(youngs_mod)))
import stats stats = stats.Stats() list1 = [1,3,5,6] list2 = [1,3,4,5] total1 = stats.total(list1) total2 = stats.total(list2) mean1 = stats.mean(list1) mean2 = stats.mean(list2) mode1 = stats.mode(list1) mode2 = stats.mode(list2) median1 = stats.median(list1) median2 = stats.median(list2) variance1 = stats.variance(list1) variance2 = stats.variance(list2) standard_deviation1 = stats.SD(list1) standard_deviation2 = stats.SD(list2) covariance_pop = stats.covariance(list1, list2) covariance_sample = stats.covariance(list1, list2, True) correlation = stats.correlation(list1, list2) skewness_pop1 = stats.skewness(list1) skewness_pop2 = stats.skewness(list2) skewness_sample1 = stats.skewness(list1, True) skewness_sample2 = stats.skewness(list2, True) kurtosis_pop1 = stats.kurtosis(list1) kurtosis_pop2 = stats.kurtosis(list2) kurtosis_sample1 = stats.kurtosis(list1, True) kurtosis_sample2 = stats.kurtosis(list2, True)
