def naive_bayes_guess(lines, hockey, baseball):
line_words = lines.split()
total_count_H = count_all(hockey)
total_count_B = count_all(baseball)
PH = float(hockey[0])/(float(baseball[0]+hockey[0]))
PB = 1-PH
h = 0
b = 0
for i in range(1, len(line_words)):
word = line_words[i]
try:
wh = hockey[word]
except:
wh = 0
try:
wb = baseball[word]
except:
wb = 0
p_word = l(float(wh+wb+1)/float(total_count_B+total_count_H+2))
p_h_word = l(float(wh+1)/float(2+total_count_H))+l(PH) - p_word
p_b_word = l(float(wb+1)/float(2+total_count_B))+l(PB) - p_word
h += p_h_word
b += p_b_word
if h>b :
return "rec.sport.hockey"
else:
return "rec.sport.baseball"
def isBeaut():
if 0 in A:
return True
h = set()
for i in xrange(N):
t = l(abs(A[i])) / l(2)
A[i] = t if A[i] > 0 else -t
# log tables prepared
print A
for i in A:
val, sgn = abs(i), i > 0
if (val, sgn) in h:
return True
else:
h.add((val, sgn))
print h
return False
def compute_document_density(data):
global tech_file, business_file, sport_file, entertainment_file, politics_file
count = 0
if data in politics_file:
count += 1
if data in entertainment_file:
count += 1
if data in sport_file:
count += 1
if data in tech_file:
count += 1
if data in politics_file:
count += 1
if count == 0:
return 0
else:
return l(5 / count)
def getMayor(n):
digitos = int(l(n)) + 1
arr_digitos = []
aux = n
for i in range(digitos):
arr_digitos.append(int(aux % 10))
aux = aux / 10
metodo_burbuja(arr_digitos)
numero = 0
var = 1
aux = 0
i = 0
while (i < digitos):
aux = arr_digitos[i] * var
numero = numero + aux
var = var * 10
i = i + 1
return numero
maxa = max(tbu, tent, tpol, tspo, ttec)
# if maxa != 0.0:
# if tbu == maxa:
# print (w, document_density, maxa, "business")
# elif tent == maxa:
# print (w, document_density, maxa, "entertainment")
# elif tpol == maxa:
# print (w, document_density, maxa, "politics")
# elif tspo == maxa:
# print (w, document_density, maxa, "sports")
# else:
# print (w, document_density, maxa, "tech")
if document_density == l(5 / 1):
t1 += maxa
elif document_density == l(5 / 2):
t2 += maxa
elif document_density == l(5 / 3):
t3 += maxa
elif document_density == l(5 / 4):
t4 += maxa
else:
t5 += maxa
bu += tbu
ent += tent
pol += tpol
spo += tspo
tec += ttec
#----------------------------------- # 引入包 #----------------------------------- # 直接调用时 # print(sqrt(5)) # NameError: name 'sqrt' is not defined # 直接导入包中所有 import math print(math.sqrt(2)) # 导入包中某个函数 from math import log10 print(log10(100)) # 导入包时重命名 import math as m print(m.log(5, 2)) # 导入包中函数时重命名 from math import log as l print(l(2, 5))
from math import log as l
i = 1
c = 0
while True:
d = 1
for j in range(1, 10):
if int(l(j**i, 10)) + 1 == i:
c += 1
d = 0
print(j, i)
if d == 1:
break
i += 1
print(c)
def categorizeApi(text):
stop_words = stopwords.words('english') + ['said' + 'v']
ps = PorterStemmer()
business_file = entertainment_file = politics_file = sport_file = tech_file = []
business = getFreqDist("business")
print("Classifing data")
entertainment = getFreqDist("entertainment")
# print ("entertainment")
politics = getFreqDist("politics")
# print ("politics")
sport = getFreqDist("sport")
# print ("sport")
tech = getFreqDist("tech")
# print ("tech")
a = text[:]
a = [w for w in word_tokenize(proc(a)) if w not in stop_words]
bu = ent = pol = spo = tec = 1e-19
#indicates the count of the document density
t1 = t2 = t3 = t4 = t5 = 0
for w in a:
#included document density
tbu = tent = tpol = tspo = ttec = 1e-19
w = ps.stem(w)
document_density = compute_document_density(w)
if w in business:
tbu = business.freq(w) * document_density
if w in entertainment:
tent = entertainment.freq(w) * document_density
if w in politics:
tpol = politics.freq(w) * document_density
if w in sport:
tspo = sport.freq(w) * document_density
if w in tech:
ttec = tech.freq(w) * document_density
maxa = max(tbu, tent, tpol, tspo, ttec)
# if maxa != 0.0:
# if tbu == maxa:
# # print (w, document_density, maxa, "business")
# elif tent == maxa:
# # print (w, document_density, maxa, "entertainment")
# elif tpol == maxa:
# # print (w, document_density, maxa, "politics")
# elif tspo == maxa:
# # print (w, document_density, maxa, "sports")
# else:
# # print (w, document_density, maxa, "tech")
if document_density == l(5 / 1):
t1 += maxa
elif document_density == l(5 / 2):
t2 += maxa
elif document_density == l(5 / 3):
t3 += maxa
elif document_density == l(5 / 4):
t4 += maxa
else:
t5 += maxa
bu += tbu
ent += tent
pol += tpol
spo += tspo
tec += ttec
print()
tsum = t1 + t2 + t3 + t4 + t5
if tsum != 0:
t1 = t1 * 100 / tsum
t2 = t2 * 100 / tsum
t3 = t3 * 100 / tsum
t4 = t4 * 100 / tsum
t5 = t5 * 100 / tsum
maxa = max(bu, ent, pol, spo, tec)
if maxa != 1e-19:
if bu == maxa:
return "business"
elif ent == maxa:
return "entertainment"
elif pol == maxa:
return "politics"
elif spo == maxa:
return "sports"
elif tec == maxa:
return "tech"
else:
return "business"
from math import log as l n=input() N=n*int(l(n)+l(l(n))) a=range(2,N) for i in range(int(n**.5)+1): a=filter(lambda x:x%a[i] or x==a[i],a) print a[:n]
m(6) # In[39]: from math import fmod as f f(9, 3) # In[45]: from math import log as sq sq(4) # In[46]: from math import log10 as l l(4) # In[48]: import random print(random.choice([1, 2, 3, 4]), end=" ") # In[52]: import random print(random.randrange(20, 40, 2), end=" ") # In[55]: import random
def ln(b):
try:
assert b > 0
return l(b)
except:
print('Error!')
def log(a, b):
try:
assert (a > 0) and (a != 1) and (b > 0)
return l(b, a)
except:
print('Error!')
def lg(b):
try:
assert b > 0
return l(b, 10)
except:
print('Error!')
def super_root(n):
f = lambda w, x: w if (e(w) * w - x) / (w * e(w) + e(w)) <= 10e-15 else f(
w - (e(w) * w - x) / (w * e(w) + e(w)), x)
return e(f(*[l(n)] * 2))
from math import log as l
d = 1
n = 1
c = 0
for i in range(1000):
if int(l(n, 10)) > int(l(d, 10)):
c += 1
tmp = d
d += n
n += 2 * tmp
print(c)