def getRate(aUrl):
irUrl = mainUrl + aUrl
i = 1
yes = 0
no = 0
yesarr = []
try:
while True: #traveling pages
pageSoup = BeautifulSoup(urlopen(irUrl+"&page="+str(i)), 'html.parser', from_encoding='cp932')
pageTables = pageSoup.body.div.div.find_all('table')
pageTable = pageTables[len(pageTables)-1].find_all('tr')
# kinda dangerous part. check whether it's players' data table or not
if len(pageTable[0].find_all('th'))!=17:
break
for j in range(1, len(pageTable),2):
dataRow = pageTable[j]
commentRow = pageTable[j+1]
#check black list
playerID = re.search('[0-9]+',dataRow.a['href']).group(0)
if playerID in blackList:
continue
#replace fullwidth(Em-size) characters with halfwidth characters
comment = unicodedata.normalize("NFKC", commentRow.td.string or "")
checkVal = checkComment(comment)
if checkVal[1]==-1:
no = no+1
elif checkVal[1]>0:
yes = yes+1
yesarr.append(checkVal)
i = i+1
med = -1
if len(yesarr):
yesarr = sorted(yesarr)
temparr = []
resarr = []
for i in range(0, len(yesarr)):
if i>0 and yesarr[i][0] > yesarr[i-1][0]:
med = statistics.median_high(temparr)
if len(resarr)==0 or med != resarr[-1][1]:
resarr.append( (yesarr[i-1][0], med))
temparr.append(yesarr[i][1])
med = statistics.median_high(temparr)
if len(resarr)==0 or med != resarr[-1][1]:
resarr.append( (yesarr[-1][0], med))
return (yes, no, med, resarr)
except:
print("Failed to load the IR page: " + aUrl)
def get_overall_stats(results_dict):
average = statistics.mean(results_dict)
median = statistics.median(results_dict)
median_low = statistics.median_low(results_dict)
median_high = statistics.median_high(results_dict)
mode = calc_mode(results_dict)
return {'avg': average, 'med': median, 'medlo': median_low, 'medhi': median_high, 'mode': mode}
def stats_helper(list):
"""
https://docs.python.org/3/library/statistics.html#statistics.pvariance
:param list:
:return:
"""
mean = statistics.mean(list)
mode = None
try:
mode = statistics.mode(list)
except statistics.StatisticsError:
# no unique mode
pass
return {
'mean': mean,
'variance': statistics.pvariance(list, mu=mean),
'standard_deviation': statistics.pstdev(list, mu=mean),
'median': statistics.median(list),
'median_low': statistics.median_low(list),
'median_high': statistics.median_high(list),
'median_grouped': statistics.median_grouped(list),
'mode': mode
}
def __init__(self, values):
values = [eval(i) for i in values]
super().__init__(values)
self.min = min(values)
self.max = max(values)
self.mean = Decimal(mean(values)).quantize(Decimal('.00000'))
self.median_low = median_low(values)
self.median = median(values)
self.median_high = median_high(values)
def web_dataset_reader(url):
'''
:param url: Input a web address.
:return: This algorithm returns a dataseet and its descriptive statistics.
Example:
>>> url='http://robjhyndman.com/tsdldata/ecology1/hopedale.dat'
>>> import web_dataset_reader_program as wbd
>>> print(wbd.web_dataset_reader(url))
>>> .
.
.
'''
from urllib import request as ur
import web_skip_header_program as wh
import statistics as st
highvalue=0
count=0
with ur.urlopen(url) as webpage:
first_data=wh.webpage_skip_head(webpage)
first_data=first_data.split()
dataset=first_data
for data in webpage: # This reads the remaining lines of the webpage
data=data.decode('utf-8')
data=data.split()
dataset+=data # For each iteration, the data transformed into
# list append to dataset with first_data as its first list
# #print(dataset)
data_float=dataset
for i in range(len(dataset)):
data=float(dataset[i])
data_float[i]=float(dataset[i]) # Elements in the list 'dataset' are transformed to
# float for additional operations such as min, max, range, sum
count+= 1 # This counts the number of elements in the list
highvalue =max(highvalue,data) # Zero is assigned to highvalue for its start value.
# The data changes for each loop and compared with each element in the list
lowvalue = min(data_float)
totalvalue =sum(data_float)
rangevalue = highvalue - lowvalue
#print(count)
observation=len(dataset)
average=totalvalue/observation
mean=st.mean(data_float)
median=st.median(data_float)
median_high=st.median_high(data_float)
median_low=st.median_low(data_float)
#mode=st.mode(data_float)# If there is more than one mode, it will return Stat Error
stdev=st.pstdev(data_float)
variance=st.pvariance(data_float)
return print('The Dataset in List form is:\n',data_float,'\n',
'=============================================\n',' DIAGNOSTIC ANALYTICS \n',
'=============================================\n','The Descriptive Statistics of the Dataset are:',
'\nTotal:\t\t{3}\nMaximum:\t{0}\nMinimum:\t{1}\nRange:\t\t{2}\nAverage:\t{5:.2f}\nMedian:\t\t{6}'
'\nMedianHigh:\t{7}\nMedian Low:\t{8}\nVariance:\t{10:.2f}\nStd.Dev:\t{9:.2f}\nCounts:\t\t{4}'
.format(highvalue,lowvalue,rangevalue,totalvalue,observation,mean,median,median_high,
median_low,stdev,variance),'\n','=============================================')
def connected_components(matrix, author_to_int):
#convert matrix to adj_list
v = len(matrix)
adj_list = convert_matrix_to_adj_list(matrix, v)
#using dfs to find connected components
metavisited, list_of_ints = [False for _ in range(v)], []
for vertex in range(v):
if not metavisited[vertex]:
ret = dfs(metavisited, vertex, adj_list)
list_of_ints.append(ret[0])
metavisited = ret[1]
largest = largest_connected(list_of_ints)
max_cc_size, max_cc, sizes = largest[0], largest[1], sorted(largest[2])
#convert ints into authors
inverse_author_dict = {v: k for k, v in author_to_int.items()}
list_of_strings, max_cc_string = [], []
for cc in list_of_ints:
string_cc = [inverse_author_dict[i] for i in cc]
if cc == max_cc:
max_cc_string = string_cc
list_of_strings.append(string_cc)
#statistics of cc sizes
average = statistics.mean(sizes)
median = statistics.median(sizes)
median_low = statistics.median_low(sizes)
median_high = statistics.median_high(sizes)
mode = calc_mode(sizes)
#density per connected component
d_per_component = density_per_component(list_of_ints, matrix, author_to_int)
#saving info into a text file
with open('connected_components.txt', 'w') as f:
f.write('Connected authors: ' + '\n')
for cc in list_of_strings:
f.write('\n' + str(len(cc)) + ' ' + str(cc) + '\n')
f.write('Density : ' + str(d_per_component[str(cc)]) + '\n')
f.write('\n')
f.write('Connected components: ' + '\n')
for cc in list_of_ints:
f.write(str(len(cc)) + ' ' + str(cc) + '\n')
f.write('\n')
f.write('Number of connected components: ' + str(len(list_of_ints)) + '\n')
f.write('Largest component size: ' + str(max_cc_size) + '\n')
f.write('Largest connected component: ' + str(max_cc_string) + '\n')
f.write('Component sizes: ' + str(sizes) + '\n')
f.write('Average component size: ' + str(average) + '\n')
f.write('Median: ' + str(median) + '\n')
f.write('Low median: ' + str(median_low) + '\n')
f.write('High median: ' + str(median_high) + '\n')
f.write('Mode: ' + str(mode))
pickle.dump(adj_list, open("adj_list.p", "wb"))
pickle.dump(list_of_ints, open("list_of_ints.p", "wb"))
def main():
print(stats.mean(range(6)))
print(stats.median(range(6)))
print(stats.median_low(range(6)))
print(stats.median_high(range(6)))
print(stats.median_grouped(range(6)))
try:
print(stats.mode(range(6)))
except Exception as e:
print(e)
print(stats.mode(list(range(6)) + [3]))
print(stats.pstdev(list(range(6)) + [3]))
print(stats.stdev(list(range(6)) + [3]))
print(stats.pvariance(list(range(6)) + [3]))
print(stats.variance(list(range(6)) + [3]))
def __init__(self, values, stdDevs):
new_values = []
for i in values:
if i != '':
try:
if "." in i:
new_values.append(float(i))
else:
new_values.append(int(i))
except:
pass #already picked up by error checks
values = new_values
super().__init__(values)
self.stDevOutliers = []
standardDeviations = Decimal(stdDevs)
if len(values) >= 8:
self.pval = mstats.normaltest(array(values))[1]
else:
self.pval = 100
self.min = min(values)
self.max = max(values)
self.mean = Decimal(mean(values)).quantize(Decimal('.00000'))
self.median_low = median_low(values)
self.median = median(values)
self.median_high = median_high(values)
self.stdev = Decimal(stdev(values)).quantize(Decimal('.00'))
self.normDist = 'No'
if(self.pval > 0.055):
self.normDist = 'Yes'
elif self.pval == 100:
self.normDist = 'N/A'
if self.normDist == 'Yes':
outlier_count = 0
for x, value in enumerate(values):
if value < (self.mean - standardDeviations * self.stdev) or \
value > (self.mean + standardDeviations * self.stdev):
if outlier_count > max_Outliers:
self.stDevOutliers = ">%d outliers" % max_Outliers
break
self.stDevOutliers.append("Row: %d Value: %s" % (x, value))
outlier_count += 1
def __init__(self, values, stdDevs):
standardDeviations = stdDevs
new_values = []
for i in values:
if i != '':
try:
new_values.append(float(i))
except:
pass #already picked up in error checks
values = new_values
super().__init__(values)
self.stDevOutliers = []
if len(values) >= 8:
self.pval = mstats.normaltest(array(values))[1]
else:
self.pval = 100
if self.mode != 'N/A':
self.mode = self.int_to_sci(self.mode)
self.min = self.int_to_sci(min(values))
self.max = self.int_to_sci(max(values))
self.mean = self.int_to_sci(mean(values))
self.median_low = self.int_to_sci(median_low(values))
self.median = self.int_to_sci(median(values))
self.median_high = self.int_to_sci(median_high(values))
self.stdev = self.int_to_sci(stdev(values))
self.normDist = 'No'
if(self.pval < 0.055):
self.normDist = 'Yes'
elif(self.pval == 100):
self.normDist = 'N/A'
if self.normDist == 'Yes':
outlier_count = 0
for x, value in enumerate(values):
if value < (float(self.mean) - standardDeviations * float(self.stdev)) or \
value > (float(self.mean) + standardDeviations * float(self.stdev)):
if outlier_count > max_Outliers:
self.stDevOutliers = ">%d outliers" % max_Outliers
break
self.stDevOutliers.append("Row: %d Value: %s" % (x, value))
outlier_count += 1
m2 = {}
l1 = []
l2 = []
while n <= end:
c += 1
h = intHash32(n)
#Extract left most 12 bits
x1 = (h >> 20) & 0xfff
m1[x1] = 1
z1 = m - len(m1)
#Linear counting formula
u1 = int(m * math.log(float(m) / float(z1)))
e1 = abs(100*float(u1 - c)/float(c))
l1.append(e1)
print("%d %d %d %f" % (n, c, u1, e1))
#Extract right most 12 bits
x2 = h & 0xfff
m2[x2] = 1
z2 = m - len(m2)
u2 = int(m * math.log(float(m) / float(z2)))
e2 = abs(100*float(u2 - c)/float(c))
l2.append(e2)
print("%d %d %d %f" % (n, c, u2, e2))
n += 1
print("Left 12 bits error: min=%f max=%f avg=%f median=%f median_low=%f median_high=%f" % (min(l1), max(l1), stat.mean(l1), stat.median(l1), stat.median_low(l1), stat.median_high(l1)))
print("Right 12 bits error: min=%f max=%f avg=%f median=%f median_low=%f median_high=%f" % (min(l2), max(l2), stat.mean(l2), stat.median(l2), stat.median_low(l2), stat.median_high(l2)))
while(j > left and A[j - 1] > A[j]):
swap(A,j,j - 1)
j -= 1
return left + int(math.ceil((right - left) / 2))
def swap(A,i,j):
A[i],A[j] = A[j],A[i]
def partition(A,lo,hi,pivot):
pivotVal = A[pivot]
swap(A,hi,pivot)
i = lo
for j in range(lo,hi):
if( A[j] <= pivotVal ):
swap(A,i,j)
i += 1
swap(A,hi,i)
return i
N = 1000
for i in range(1,N+1):
A = [random.randint(0,100) for j in range(0,i)]
myMed = median(A)
theirMed = median_high(A)
if(myMed != theirMed):
print("ERROR! our median algorithm found %d while theirs found %d. Dump of A:\n%s" % (myMed, theirMed, str(A)))
else:
continue
print("done! ran through %d test cases." % N)
print(num) a = [1, 2, 3, 4] num = statistics.median(a) print(num) a = [1, 2, 3, 4, 5] num = statistics.median(a) print(num) a = [1, 2, 3, 4] num = statistics.median_low(a) print(num) a = [1, 2, 3, 4, 5] num = statistics.median_high(a) print(num) a = [1, 2, 3, 4] num = statistics.median_grouped(a) print(num) a = [1, 2, 3, 4, 5, 4] num = statistics.mode(a) print(num) a = [1, 2, 3, 4, 5, 1] num = statistics.mode(a) print(num) a = [1, 2, 3, 4]
def calcular_dados():
"""
Calcula as estatisticas de idade:
1. Mostrar a menor idade calculada
2. Mostrar a maior idade calculada
3. Mostrar a média de idade dos adultos
4. Mostrar a quantidade de nascimentos por década
O que temos: [ 1970, 1981, 1998, 2002, 1990, 1970 ]
O que queremos: { 1980: 10, 1990: 15, 2000: 5 }
1o passo: converter anos em decadas:
1985 / 10 = 198,5 int -> 198 x10 = 1980
2o passo: criar uma lista nova (set_decadas) com as decadas sem repetir
3o passo: contar as decadas na lista original (lista_decadas) usando a lista nova
Para cada decada dentro da lista nova (set_decadas) contar qtas vezes
ela aparece na lista original (lista_decadas)
"""
# Lista por Compreensão
# lista = [ <expressão para valor> <loop> <expressão para loop> ]
menor_idade = min([ objeto.idade for objeto in lista_entrevistados ])
maior_idade = max([ objeto.idade for objeto in lista_entrevistados ])
media_adultos = statistics.median_high(
[ objeto.idade for objeto in lista_entrevistados if objeto.idade >= 18 ]
)
lista_decadas = [ int(objeto.ano_informado/10)*10 for objeto in lista_entrevistados]
set_decadas = set(lista_decadas)
# Dicionário por Compreensão
# dicionario = { <expressao para chave>:<expressao para valor> <loop> <expressao pro loop>}
qtd_nascimentos = { decada:lista_decadas.count(decada) for decada in set_decadas }
print("\nResultados:")
print('-----------------------------------------')
print("Quantidade de Entrevistas: {}".format(len(lista_entrevistados)))
print("Menor Idade Informada: {}".format(menor_idade))
print("Maior Idade Informada: {}".format(maior_idade))
print("Média de Idade dos Adultos Informados: {}".format(media_adultos))
print("\nNascimentos por Década")
print('-----------------------------------------')
for decada, quantidade in qtd_nascimentos.items():
print("{}: {} nascimentos".format(decada, quantidade))
print('\n\n')
resposta_ok = False
while resposta_ok == False:
try:
resposta = input("Deseja mostrar os dados num arquivo? (s/n)")
resposta = resposta[0].lower()
if resposta == 's' or resposta == 'n':
resposta_ok = True
except:
continue
if resposta == 's':
sh.gedit("dados.json")
def doCalc(G, counter, results):
print("start calculations")
fh = open("hamster.edgelist", 'rb')
Ginit = nx.read_edgelist(fh, create_using=nx.DiGraph())
fh.close()
pr = nx.pagerank(G, alpha=0.85)
prtwo = nx.pagerank(Ginit, alpha=0.85)
avg = float(1) / float(number_of_nodes(G))
isavg = 0
underavg = 0
aboveavg = 0
minv = 1
maxv = 0
work = 0
for key, value in pr.items():
#print(key, 'corresponds to', value)
g = str(value)
a = str(key) + ": " + g
#print(a)
work = work + value
if (value < avg):
underavg = underavg + 1
if (minv > value):
minv = value
elif (value == avg):
isavg = isavg + 1
else:
aboveavg = aboveavg + 1
if (maxv < value):
maxv = value
onemin = 0
onemax = 0
items = []
for k, l in pr.items():
items.append(l)
if (l == minv):
onemin = onemin + 1
elif (l == maxv):
onemax = onemax + 1
m = str(onemin)
n = str(onemax)
b = str(work)
c = str(isavg)
d = str(underavg)
e = str(aboveavg)
h = str(minv)
i = str(maxv)
f = str(avg)
o = str(statistics.median(items))
p = str(statistics.median_low(items))
q = str(statistics.median_high(items))
s = str(statistics.median_grouped(items))
#t = str(statistics.mode(items))
u = str(statistics.pstdev(items))
v = str(statistics.pvariance(items))
w = str(statistics.stdev(items))
x = str(statistics.variance(items))
#y= str(statistics.StatisticsError(items))
if (os.stat(os.getcwd() + "/results/testResults" + str(counter) +
".txt").st_size >= 5000000):
results.close()
counter = counter + 1
results = open(
os.getcwd() + "/results/testResults" + str(counter) + ".txt", 'w')
print(counter)
results.write('\n')
results.write('testdata \n')
results.write(json.dumps(pr) + '\n')
print("start new pagerank")
one = pagerankCalc(G, pr, False)
print("start init pagerank")
two = pagerankCalc(Ginit, prtwo, False)
results.write("average: " + f + '\n')
results.write("total: " + b + '\n')
results.write("isavg: " + c + '\n')
results.write("underavg: " + d + '\n')
results.write("aboveavg: " + e + '\n')
results.write("minimum: " + h + '\n')
results.write("maximum: " + i + '\n')
results.write("nrminimum: " + m + '\n')
results.write("nrmaximum: " + n + '\n')
results.write("median: " + o + '\n')
results.write("low median: " + p + '\n')
results.write("high median: " + q + '\n')
results.write("grouped median: " + s + '\n')
#results.write("mode: "+t+'\n')
results.write("pstdev: " + u + '\n')
results.write("pvariance: " + v + '\n')
results.write("stdev: " + w + '\n')
results.write("variance: " + x + '\n')
print("start pagerank calc")
results.write("rank list: " + json.dumps(one) + '\n')
results.write("rank list init: " + json.dumps(two) + '\n')
#results.write("error: "+y+'\n') # too much data, only if actually test
print("start eroor calc")
results.write("rank list error : " + json.dumps(one) + '\n')
results.write("rank list init error: " + json.dumps(two) + '\n')
print("start error calc")
error = calcrankError(two, one)
pr = nx.pagerank(G, alpha=0.85)
prtwo = nx.pagerank(Ginit, alpha=0.85)
errorvalue = calcvalueError(two, one, prtwo, pr)
results.write("rank based error: " + str(error) + '\n')
results.write("value based error: " + str(errorvalue) + '\n')
print("succes writing to test " + str(counter) + " result")
return counter, results
atexit.register(lambda: p.terminate())
time.sleep(1) # Wait for the server to launch.
"""
def test_runserver():
import requests
requests.get('http://localhost:8000/')
if __name__ == '__main__':
for cmd in ['runserver', 'gunserver']:
t = timeit.Timer('test_runserver()', setup_code.format(cmd=cmd))
loop, repeat = 1000, 3
results = t.repeat(repeat, loop)
print()
print(cmd, 'loop of', loop, 'repeated', repeat, 'times')
print('=============')
print('Average: {mean:.2f}'.format(mean=statistics.mean(results)))
print('Medians: {me:.2f} {lo:.2f} {hi:.2f}'.format(
me=statistics.median(results),
lo=statistics.median_low(results),
hi=statistics.median_high(results),
))
print('Min/Max: {min:.2f} {max:.2f}'.format(
min=min(results),
max=max(results),
))
print()
for slice2 in range(0,200):
ymean = input[slice2]
popt, pcov = curve_fit(func, x, ymean,[1000, 3, 1])
k = func(0,*popt)
if k > 800:
densmean2[i2] = k
i2 = i2 + 1
print 'length of densmap2', len(densmean2)
plt.plot(zcoord,densmean,'k.')
import statistics
print mean(densmean2)
print median(densmean2)
print statistics.median_low(densmean2)
print statistics.median_high(densmean2)
#print statistics.mode(densmean2)
# <codecell>
## DELETE THIS CELL, IT GIVES ONLY HOW MANY TIMES DOES EACH VALUE OF densmean APPEAR -> NOT USEFUL
from collections import Counter
c = Counter(densmean)
#print densmean
#list(c)
c += Counter()
#print c.most_common() # n least common elements
#print c[-3.2638837653955745e-17]
#sum(c.values())
# <codecell>
def findMedian(self):
return (statistics.median_high(self.x_list),
statistics.median_high(self.y_list))
import statistics lista1 = [3,5,3,12,13,3,7,8] lista2 = [3,3,3,5,7,8,12,13] print(statistics.median(lista1)) print(lista1) print(statistics.median_low(lista1)) print(statistics.median(lista2)) print(lista2) print(statistics.median_low(lista2)) print(statistics.median_high(lista1)) print(lista2[(statistics.median_high(lista2))]) l2 = ["bla", "aga"] l2[0] = 0 print(l2)
import pandas as pd
import matplotlib.pyplot as plt
dane = np.loadtxt("MDR_RR_TB_burden_estimates_2020-10-29.csv", delimiter=',', skiprows=1, usecols=12)
# print(dane)
print(np.max(dane))
print(dane.max())
print(np.median(dane))
dane1 = np.loadtxt("Wzrost.csv", delimiter=',', skiprows=0)
# print(dane1)
print("odchylenie standardowe:", st.stdev(dane1))
print("odchylenie standardowe 2", st.pstdev(dane1))
print("median high:", st.median_high(dane1))
print("median low:", st.median_low(dane1))
print("pstdev:", st.pstdev(dane1))
print("stdev:", st.stdev(dane1))
print("pvariance:", st.pvariance(dane1))
print("variance:", st.variance(dane1))
print("mode:", st.mode(dane1))
print(sc.ttest_1samp(dane, 0))
df = pd.read_csv("brain_size.csv", delimiter=";", skiprows=0)
# print(df)
print(np.mean(df['VIQ']))
print(df['Gender'].value_counts())
# using Python statistics functions
import statistics
import csv
import array
# simple statistics operations
sample_data1 = [1, 3, 5, 7]
sample_data2 = [2, 3, 5, 4, 3, 5, 3, 2, 5, 6, 4, 3]
# TODO: Use the mean function - calculates an average value
print(statistics.mean(sample_data1))
# TODO: Use the different median functions
print(statistics.median(sample_data1))
print(statistics.median_high(sample_data1))
print(statistics.median_low(sample_data1))
print(statistics.median_grouped(sample_data1))
# TODO: The mode function indicates which data item occurs
# most frequently
print(statistics.mode(sample_data2))
# Read data from a CSV file and calculate statistics
def readData():
with open("StockQuotes.csv") as dataFile:
data = array.array('f', [])
reader = csv.reader(dataFile)
curLine = 0
for row in reader:
#Медиана
n = len(x)
if n % 2:
median_ = sorted(x)[round(0.5 * (n - 1))]
else:
x_ord, index = sorted(x), round(0.5 * n)
median_ = 0.5 * (x_ord[index - 1] + x_ord[index])
print(f'Расчет медианы: {median_}')
median_2 = statistics.median(x)
print(f'Расчет медианы с помощью statistics.median(): {median_2}')
statistics.median_low(x[:-1])
print(
f'Расчет медианы с помощью statistics.median_low: {statistics.median_low(x[:-1])}'
)
statistics.median_high(x[:-1])
print(
f'Расчет медианы с помощью statistics.median_high {statistics.median_high(x[:-1])}'
)
median_2 = np.median(y)
print(f'Расчет медианы с помощью np.median: {median_2}')
#Мода
u = [2, 3, 2, 8, 12]
mode_ = max((u.count(item), item) for item in set(u))[1]
print(f'Вычисление моды: {mode_}')
mode_2 = statistics.mode(u)
print(f'Вычисление моды с помощью statistics.mode(): {mode_2}')
mode_3 = statistics.multimode(u)
print(f'Вычисление моды с помощью statistics.multimode(): {mode_3}')
mode_4 = scipy.stats.mode(u)
''' Created on 2016. 12. 8. @author: lsh ''' import statistics as sta data = [1, 2, 3, 4, 5, 6] print(sta.mean(data)) print(sta.median(data)) print(sta.median_low(data)) print(sta.median_high(data)) print(sta.pvariance(data)) print(sta.pstdev(data)) print(sta.variance(data)) print(sta.stdev(data))
def update_event(self, inp=-1):
self.set_output_val(0, statistics.median_high(self.input(0)))
import statistics
n = int(input())
a = list(map(int, input().split()))
p = int(int(n * (n + 1) / 2) / 2 + 1)
ans = a
flg = False
for i in range(2, n):
for j in range(n - i):
t = statistics.median_high(a[j:i + j])
ans.append(t)
if (ans.count(t) >= p):
flg = True
break
if (flg):
break
print(statistics.median_high(ans))
import statistics as s olst = [1, 2, 3, 5, 6, 9, 4, 2, 10] elst = [0, 1, 4, 5, 6, 6, 8, 6] print(s.mean(olst)) print(s.mean(elst)) print(s.median(olst)) print(s.median(elst)) print(s.median_low(olst)) print(s.median_high(elst)) print(s.mode(olst), s.mode(elst), sep=' And ') print(s.stdev(olst), s.stdev(elst)) print(s.variance(olst), s.variance(elst), sep=' And ') print(s.pvariance(olst), s.pvariance(elst), sep=' And ') print(s.pstdev(olst), s.pstdev(elst), sep=' And ')
import statistics
score = [30, 40, 60, 70, 80, 90]
print(statistics.mean(score))
print(statistics.harmonic_mean(score))
print(statistics.median(score))
print(statistics.median_low(score))
print(statistics.median_high(score))
import time
print(time.time())
t = time.time()
print(time.ctime(t))
import time
now = time.localtime()
print("%d년 %d월 %d일" % (now.tm_year, now.tm_mon, now.tm_mday))
print("%d:%d;%d" % (now.tm_hour, now.tm_min, now.tm_sec))
import time
start = time.time()
for a in range(1000):
print(a)
end = time.time()
print(end - start)
print("안녕하세요.")
time.sleep(1)
median = statistics.median(l)
print(median)
# 3
#%%
l_even = [10, 1, 3, 7, 1, 6]
median = statistics.median(l_even)
print(median)
# 4.5
median_low = statistics.median_low(l_even)
print(median_low)
# 3
median_high = statistics.median_high(l_even)
print(median_high)
# 6
print(
statistics.median_high(l) == statistics.median_low(l) == statistics.median(
l))
# True
#%%
mode = statistics.mode(l)
print(mode)
# 1
l_mode_error = [1, 2, 3, 4, 5]
# mode = statistics.mode(l_mode_error)
import random,statistics print(random) print(help(statistics)) #print(help(random)) print(random.randrange(1000000)) ra=random.choice(['apple','banana','greps']) print(ra) data=(2,4,5,3,5,7) print(data) print(statistics.mean(data)) print(statistics.median_high(data)) print(statistics.median(data))
h = intHash32(n)
#Extract left most 12 bits
x1 = (h >> 20) & 0xfff
m1[x1] = 1
z1 = m - len(m1)
#Linear counting formula
u1 = int(m * math.log(float(m) / float(z1)))
e1 = abs(100 * float(u1 - c) / float(c))
l1.append(e1)
print("%d %d %d %f" % (n, c, u1, e1))
#Extract right most 12 bits
x2 = h & 0xfff
m2[x2] = 1
z2 = m - len(m2)
u2 = int(m * math.log(float(m) / float(z2)))
e2 = abs(100 * float(u2 - c) / float(c))
l2.append(e2)
print("%d %d %d %f" % (n, c, u2, e2))
n += 1
print(
"Left 12 bits error: min=%f max=%f avg=%f median=%f median_low=%f median_high=%f"
% (min(l1), max(l1), stat.mean(l1), stat.median(l1), stat.median_low(l1),
stat.median_high(l1)))
print(
"Right 12 bits error: min=%f max=%f avg=%f median=%f median_low=%f median_high=%f"
% (min(l2), max(l2), stat.mean(l2), stat.median(l2), stat.median_low(l2),
stat.median_high(l2)))
import statistics as s
l1 = [4, 6, 2, 5, 7, 7]
x = s.median_high(l1)
print(f'Median_high is {x}')
'''
Output:
Median_high is 6
'''
def display_patches(n_patches,
imageset,
filestr=None,
display=False,
figsize=(8, 8),
patch_dims=(16, 16),
pcobject=None,
center=False,
labels=True,
title=None,
cmap='gray',
acts=None,
sample=False):
'''
Function that takes in batch major data (must be a list)
'''
fs = factors(n_patches)
if len(fs) % 2 == 0:
dims = [statistics.median_low(fs), statistics.median_high(fs)]
else:
dims = [statistics.median(fs), statistics.median(fs)]
fig = plt.figure(figsize=(8, 8))
axs = [fig.add_subplot(dims[0], dims[1], i + 1) for i in range(n_patches)]
if labels == True:
cols = ['{}'.format(col + 1) for col in range(dims[1])]
rows = ['{}'.format(row + 1) for row in range(dims[0])]
for ax, col in zip(np.array(axs).reshape(dims)[0], cols):
ax.set_title(col, fontweight="bold", size=30, pad=15)
for ax, row in zip(np.array(axs).reshape(dims)[:, 0], rows):
# ax.set_ylabel(row, rotation=0, size='large', labelpad=10)
ax.set_ylabel(row,
fontweight="bold",
size=30,
rotation=0,
verticalalignment='center',
labelpad=25)
if title is not None:
# fig.suptitle(title, fontsize=18, y=1.00)
# fig.suptitle(title,fontweight ="bold",fontsize=20)
fig.suptitle(title, fontweight="bold", fontsize=50)
if type(imageset) != list:
imageset = [imageset[i, :] for i in range(imageset.shape[0])]
if acts is not None:
sorted_idxs = np.argsort(
np.linalg.norm(acts[:n_patches, :], ord=1, axis=1))[::-1]
imageset = [imageset[:n_patches][idx] for idx in sorted_idxs]
if sample == False:
imagelist = zip(axs, imageset)
else:
imagelist = zip(axs, random.sample(imageset, n_patches))
for ax, image in imagelist:
if center == True:
vmax = np.max(np.abs([image.min(), image.max()]))
vmin = -vmax
else:
vmax = None
vmin = None
if pcobject:
image = np.reshape(pcobject.inverse_transform(image), patch_dims)
else:
image = np.reshape(image, patch_dims)
ax.imshow(image,
cmap=cmap,
interpolation='nearest',
vmin=vmin,
vmax=vmax)
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_ticks([])
fig.subplots_adjust(wspace=0, hspace=0)
fig.set_figheight(dims[0])
fig.set_figwidth(dims[1])
fig.tight_layout(rect=[0, 0, 1, 0.98])
figure = plt.gcf()
if filestr is not None:
figure.savefig(filestr, dpi='figure')
if display == False:
plt.close()
return (fig, axs)
percent = [
2.606255012, 1.222935044, 1.283079391, 3.628708901, 6.856455493,
4.911788292, 2.886928629, 0.781876504, 0.962309543, 2.265437049,
6.816359262, 3.688853248, 3.468323978, 5.633520449, 4.530874098,
1.984763432, 0.922213312, 3.327987169, 4.190056135, 5.493183641,
1.864474739, 10.60545309, 2.425821973, 2.726543705, 8.740978348,
6.174819567
]
percent.sort()
print(percent)
#this ends with error
#print(median(percent))
#print(median_low(percent))
#print(median_high(percent))
#this succeeds
import statistics
print(statistics.median(percent))
print(statistics.median_low(percent))
print(statistics.median_high(percent))
#this also succeeds
##from statistics import *
##print(median(percent))
##print(median_low(percent))
##print(median_high(percent))
662, 4, 26, 10, 13, 15, 21, 17, 123, 643, 1, 95, 20, 256, 2048, 1116, 5, 6,
1, 52, 6, 931, 83, 7, 9, 80, 99, 136, 18, 24, 14, 123, 5
]
print("Mean", statistics.mean(data))
print("Median", statistics.median(data))
try:
print("Mode", statistics.mode(data))
except statistics.StatisticsError:
print("No unique mode.")
print("Standard deviation:", statistics.stdev(data))
print("Variance:", statistics.variance(data))
odd_data = [4, 7, 3, 9, 12]
even_data = [4, 7, 3, 9, 12, 2]
print(odd_data)
print(even_data)
print("Median odd data", statistics.median(odd_data))
print("Median even data", statistics.median(even_data))
print("Median low of even data", statistics.median_low(even_data))
print("Median high of even data", statistics.median_high(even_data))
print("Standard deviation:", statistics.stdev(odd_data))
print("Variance:", statistics.variance(odd_data))
# Simple plot to look for outliers
import seaborn as sns
import matplotlib.pyplot as plt
sns.boxplot(x=even_data)
plt.show()
sns.boxplot(x=data)
plt.show()
import statistics nums = [44, 62, 11, 22, 155, 22, 3333, 444] z = statistics.median_high(nums) print(z)
import statistics
from sys import stdin
message = stdin.readline().strip()
N = len(message)
rc = []
for i in range(1, N + 1):
if N % i == 0:
rc.append(i)
N_rc = len(rc)
if N_rc % 2 == 1:
r = statistics.median(rc)
c = statistics.median(rc)
else:
r = statistics.median_low(rc)
c = statistics.median_high(rc)
matrix = [[0 for _ in range(r)] for _ in range(c)]
for i in range(c):
for j in range(r):
matrix[i][j] = message[(i * r) + j]
for i in range(r):
for j in range(c):
print(matrix[j][i], end="")
y.append(float(val[4])) print(len(x),len(y)) peak = 49.9378768165 + 1399.2004138 #print(statistics.mean(y)) #print(statistics.stdev(y)) for val in y: if val >peak: z.append(val) print(len(z)) import matplotlib.pyplot as plt import numpy as np spread = z flier_high = [statistics.median_high(z)] flier_low = [statistics.median_low(z)] print(flier_high, flier_low) data = np.concatenate((spread, flier_high, flier_low), 0) plt.boxplot(data,1) plt.figure() plt.show() ''' for i in range(1,len(x)): x[i-1] = float(x[i])-float(x[i-1]) ll = []
def median_high(self):
return stats.median_high(self.values())
__author__ = 'luowen' """ the statisic demo """ import statistics list1 = [1, 2, 3, 4, 5, 6] midNum = statistics.mean(list1) print(midNum) # get the average data of list1 medianNum = statistics.median(list1) print(medianNum) # get median data of list1 medianNumLow = statistics.median_low(list1) print(medianNumLow) # get median lower data of list1 medianNumHigh = statistics.median_high(list1) print(medianNumHigh) # get median hight data of list1 medianNumGroup = statistics.median_grouped(list1, 10) print(medianNumGroup) # get detail information from https://docs.python.org/3/library/statistics.html
def log_graph(G,
identify_self=True,
nodecolor="label",
epoch=0,
fig_size=(4, 3),
dpi=300,
label_node_feat=False,
edge_vmax=None,
args=None):
"""
Args:
nodecolor: the color of node, can be determined by 'label', or 'feat'. For feat, it needs to
be one-hot'
"""
cmap = plt.get_cmap("Set1")
plt.switch_backend("agg")
fig = plt.figure(figsize=fig_size, dpi=dpi)
node_colors = []
# edge_colors = [min(max(w, 0.0), 1.0) for (u,v,w) in G.edges.data('weight', default=1)]
edge_colors = [w for (u, v, w) in G.edges.data("weight", default=1)]
# maximum value for node color
vmax = 8
for i in G.nodes():
if nodecolor == "feat" and "feat" in G.nodes[i]:
num_classes = G.nodes[i]["feat"].size()[0]
if num_classes >= 10:
cmap = plt.get_cmap("tab20")
vmax = 19
elif num_classes >= 8:
cmap = plt.get_cmap("tab10")
vmax = 9
break
feat_labels = {}
for i in G.nodes():
if identify_self and "self" in G.nodes[i]:
node_colors.append(0)
elif nodecolor == "label" and "label" in G.nodes[i]:
node_colors.append(G.nodes[i]["label"] + 1)
elif nodecolor == "feat" and "feat" in G.nodes[i]:
# print(G.nodes[i]['feat'])
feat = G.nodes[i]["feat"].detach().numpy()
# idx with pos val in 1D array
feat_class = 0
for j in range(len(feat)):
if feat[j] == 1:
feat_class = j
break
node_colors.append(feat_class)
feat_labels[i] = feat_class
else:
node_colors.append(1)
if not label_node_feat:
feat_labels = None
plt.switch_backend("agg")
fig = plt.figure(figsize=fig_size, dpi=dpi)
#pos_layout = nx.kamada_kawai_layout(G, weight=None)
pos_layout = nx.fruchterman_reingold_layout(G)
if G.number_of_nodes() == 0 or G.number_of_edges() == 0:
edge_vmax = 1
edge_vmin = 0
else:
weights = [d for (u, v, d) in G.edges(data="weight", default=1)]
if edge_vmax is None:
edge_vmax = statistics.median_high(
[d for (u, v, d) in G.edges(data="weight", default=1)])
min_color = min([d for (u, v, d) in G.edges(data="weight", default=1)])
# color range: gray to black
edge_vmin = 2 * min_color - edge_vmax
nx.draw(
G,
pos=pos_layout,
arrows=True,
with_labels=True,
font_size=4,
labels=feat_labels,
node_color=node_colors,
vmin=0,
vmax=vmax,
cmap=cmap,
edge_color=edge_colors,
edge_cmap=plt.get_cmap("Greys"),
edge_vmin=edge_vmin,
edge_vmax=edge_vmax,
width=1.0,
node_size=120,
alpha=0.8,
)
fig.axes[0].xaxis.set_visible(False)
fig.canvas.draw()
print("Arithmetischer Mittelwert: ", statistics.mean(probe1))
# Mitterlwert = mean = Summe der Werte geteilt durch ihre Anzahl
print("Harmonischer Mittelwert: ", statistics.harmonic_mean(probe1))
# harmonischer Mitterlwert = mean = Summe der Werte geteilt durch ihre Kehrwerte
print()
# Median
# Mitte der Zahlenmenge
print("Median: ", statistics.median(probe1))
probe2 = [5, 2, 4, 17, 3]
print("Median: ", statistics.median(probe2))
print()
# Unterer Median
# Mitte der Zahlenmenge, low wertet nach unteren Wert ab
print("Unterer Median: ", statistics.median_low(probe1))
print("Unterer Median: ", statistics.median_low(probe2))
print()
# Oberer Median
# Mitte der Zahlenmenge, high wertet nach oberen Wert auf
print("Oberer Median: ", statistics.median_high(probe1))
print("Oberer Median: ", statistics.median_high(probe2))
print()
# Tupel, Werte eines Dictionary
probe3 = (5, 2, 4, 17)
print("aus Tupel: ", statistics.mean(probe3))
probe4 = {'D': 5, 'NL': 2, 'CH': 4, 'F': 17}
print("aus Dictionary: ", statistics.mean(probe4.values()))
#Arithmetic mean of data:
print("data mean =", statistics.mean(data))
#Middle value (median) of data:
print("data median =",statistics.median(data))
#Low median: is always a member of the data set. When the number of data points is odd the middle value is returned. When it is even,
#the smaller of the two data points is returned:
print("data low median =",statistics.median_low(data))
#Example with a dataset with even number of data points:
print("even data set = ", (1,3,5,7))
print("even data set low median =",statistics.median_low([1,3,5,7]))
#Median high: when the number of points in the data set is odd, this function will return the middle value. When the number of data points
#is even, it will return the highest of the two middle points.
print("data high median =",statistics.median_high(data))
#Example with a dataset with even number of data points:
print("even data set high median =",statistics.median_high([1,3,5,7]))
#MEASURES OF SPREAD:
#Sample standard deviation
print("data standard deviation =", statistics.stdev(data))
#Variance
print("data variance =",statistics.variance(data))
#There is also another measurement of standard deviation, the population standard deviation:
print("data population standard deviation = ",statistics.pstdev(data,mu=None))
#And the population variance of data. In this function there is also the argument mu, that corresponds to the mean of data. If mu is
#not assigned or is 'None', than the men is also calculated by this function.
def __init__(self, pi, gpio, measurement_time=120):
self.pi = pi
self.gpio = gpio
self.period = 1 / 910 * 1000000
self.tick_high = None
self.duty_cycle = None
self.duty_scale = 1000
self.list_duty_cycles = []
self.duty_cycle_min = None
self.duty_cycle_max = None
#http://abyz.me.uk/rpi/pigpio/python.html#set_mode
self.pi.set_mode(gpio=self.gpio, mode=pigpio.INPUT)
#http://abyz.me.uk/rpi/pigpio/python.html#callback
self.cb = self.pi.callback(user_gpio=self.gpio,
edge=pigpio.EITHER_EDGE,
func=self.cbf)
print('{}{}{}'.format('Starting measurements for: ', measurement_time,
' seconds.'))
print('----------------------------------------------------------')
time.sleep(measurement_time)
#stop callback before sorting list to avoid getting added new elements unintended
#http://abyz.me.uk/rpi/pigpio/python.html#callback
self.cb.cancel()
time.sleep(1)
self.list_duty_cycles = sorted(self.list_duty_cycles)
#some analyzis of the dc values
sorted_set = list(sorted(set(self.list_duty_cycles)))
print('{} {}'.format('Ascending sorted distinct duty cycle values:',
sorted_set))
print('----------------------------------------------------------')
differences_list = [
sorted_set[i + 1] - sorted_set[i]
for i in range(len(sorted_set) - 1)
]
rounded_differences_list = [
round(differences_list[i], 2)
for i in range(len(differences_list) - 1)
]
counted_sorted_list = collections.Counter(rounded_differences_list)
print('{} {}'.format(
'Ascending counted, sorted and rounded distinct differences between duty cycle values:',
counted_sorted_list))
print('----------------------------------------------------------')
#Median and median_high/median_low are chosen, because the biggest
#and smallest values are needed, and not an avarage of the smallest
#and biggest values of the selection.
#https://docs.python.org/3/library/statistics.html#statistics.median
print('{} {}'.format('Smallest 250 values:',
self.list_duty_cycles[:250]))
self.duty_cycle_min = statistics.median_high(
self.list_duty_cycles[:20])
print('----------------------------------------------------------')
print('{} {}'.format('Biggest 250 values:',
self.list_duty_cycles[-250:]))
self.duty_cycle_max = statistics.median_low(
self.list_duty_cycles[-20:])
print('----------------------------------------------------------')
print('duty_cycle_min:', round(self.duty_cycle_min, 2))
print('duty_cycle_max:', round(self.duty_cycle_max, 2))
#CHAPTER 8 # 1. Call a different function from the statistics module # 2. Create a module named cubed with a function that takes a number as a parameter, # and returns the number cubed. Import and call the function from another module. import statistics import cubed numbers = [1, 2, 3, 4, 5, 6, 7, 8] print(statistics.median_high(numbers)) print(cubed.cubed(4))
import statistics as st
x = [3,1.5,4.5,6.75,2.25,5.75,2.25]
print("_________Question1__________")
print(st.mean(x))
print(st.harmonic_mean(x))
print(st.median(x))
print(st.median_low(x))
print(st.median_high(x))
print(st.median_grouped(x))
print(st.mode(x))
print(st.pstdev(x))
print(st.pvariance(x))
print(st.stdev(x))
print(st.variance(x))
print("_________Question2__________")
import random
print(random.random())
print(random.randrange(10))
print(random.choice(["Ali","Khalid","Hussam"]))
print(random.sample(range(1000),10))
print(random.choice("Orange Academy"))
y = [1,5,8,9,2,4]
random.shuffle(y)
print(y)
def median(self):
return statistics.median_high(self._salaries)
import statistics as s
sales = [111, 222, 444, 222, 444, 222, 444, 222, 4455, 222]
#
print(s.mean(sales)) #avg
print(max(sales)) #return max
print(min(sales)) #return min
print(sum(sales)) #return total
print(len(sales)) #return count of items
##
print(s.median(sales)) #return mid value (if even count : sum or mid 2 val/2)
print(s.median_high(sales))
print(s.median_low(sales))
print(s.variance(sales)) #return var
print(s.stdev(sales)) #return sqrt() for var
print(s.median_high(sales))
print(s.mode(sales)) #return value which has highest freq/count
'''
stats function:
count/len
min
max
sum
mean/avv
mode
def log_graph(
writer,
Gc,
name,
identify_self=True,
nodecolor="label",
epoch=0,
fig_size=(4, 3),
dpi=300,
label_node_feat=False,
edge_vmax=None,
args=None,
):
"""
Args:
nodecolor: the color of node, can be determined by 'label', or 'feat'. For feat, it needs to
be one-hot'
"""
cmap = plt.get_cmap("Set1")
plt.switch_backend("agg")
fig = plt.figure(figsize=fig_size, dpi=dpi)
node_colors = []
# edge_colors = [min(max(w, 0.0), 1.0) for (u,v,w) in Gc.edges.data('weight', default=1)]
edge_colors = [w for (u, v, w) in Gc.edges.data("weight", default=1)]
# maximum value for node color
vmax = 8
for i in Gc.nodes():
if nodecolor == "feat" and "feat" in Gc.nodes[i]:
num_classes = Gc.nodes[i]["feat"].size()[0]
if num_classes >= 10:
cmap = plt.get_cmap("tab20")
vmax = 19
elif num_classes >= 8:
cmap = plt.get_cmap("tab10")
vmax = 9
break
feat_labels = {}
for i in Gc.nodes():
if identify_self and "self" in Gc.nodes[i]:
node_colors.append(0)
elif nodecolor == "label" and "label" in Gc.nodes[i]:
node_colors.append(Gc.nodes[i]["label"] + 1)
elif nodecolor == "feat" and "feat" in Gc.nodes[i]:
# print(Gc.nodes[i]['feat'])
feat = Gc.nodes[i]["feat"].detach().numpy()
# idx with pos val in 1D array
feat_class = 0
for j in range(len(feat)):
if feat[j] == 1:
feat_class = j
break
node_colors.append(feat_class)
feat_labels[i] = feat_class
else:
node_colors.append(1)
if not label_node_feat:
feat_labels = None
plt.switch_backend("agg")
fig = plt.figure(figsize=fig_size, dpi=dpi)
if Gc.number_of_nodes() == 0:
raise Exception("empty graph")
if Gc.number_of_edges() == 0:
raise Exception("empty edge")
# remove_nodes = []
# for u in Gc.nodes():
# if Gc
pos_layout = nx.kamada_kawai_layout(Gc, weight=None)
# pos_layout = nx.spring_layout(Gc, weight=None)
weights = [d for (u, v, d) in Gc.edges(data="weight", default=1)]
if edge_vmax is None:
edge_vmax = statistics.median_high(
[d for (u, v, d) in Gc.edges(data="weight", default=1)])
min_color = min([d for (u, v, d) in Gc.edges(data="weight", default=1)])
# color range: gray to black
edge_vmin = 2 * min_color - edge_vmax
nx.draw(
Gc,
pos=pos_layout,
with_labels=False,
font_size=4,
labels=feat_labels,
node_color=node_colors,
vmin=0,
vmax=vmax,
cmap=cmap,
edge_color=edge_colors,
edge_cmap=plt.get_cmap("Greys"),
edge_vmin=edge_vmin,
edge_vmax=edge_vmax,
width=1.0,
node_size=50,
alpha=0.8,
)
fig.axes[0].xaxis.set_visible(False)
fig.canvas.draw()
if args is None:
save_path = os.path.join("log/", name + ".pdf")
else:
save_path = os.path.join(
"log",
name + gen_explainer_prefix(args) + "_" + str(epoch) + ".pdf")
print("log/" + name + gen_explainer_prefix(args) + "_" + str(epoch) +
".pdf")
os.makedirs(os.path.dirname(save_path), exist_ok=True)
plt.savefig(save_path, format="pdf")
img = tensorboardX.utils.figure_to_image(fig)
writer.add_image(name, img, epoch)
# = (2 * 2)/3
# = 1.333
#
# Input : arr[] = {13.5, 14.5, 14.8, 15.2, 16.1}
# Output : 14.7707
# =============================================================================
#harmonic mean
print("Harmonic Mean")
print(statistics.harmonic_mean([2.5, 3, 10]))
print("Median")
#median
print(statistics.median([1, 3, 4, 5]))
#median high
print(statistics.median_high([1, 3, 5, 7]))
#median high
print(statistics.median_low([1, 3, 5, 7]))
print("Statistics Grouped Median...")
print(statistics.median_grouped([52, 52, 53, 54]))
#mode
print(statistics.mode(["red", "blue", "blue", "red", "green", "red", "red"]))
print(statistics.mode([1, 1, 2, 2, 2]))
data = [4, 5, 7, 1, 3, 6, 7]
print(statistics.stdev(data))
print(statistics.variance(data))
