def sample(text):
# converts text to histogram
histo = histogram(text)
# print("histogram: ")
# print(histogram)
# returns number of tokens in histogram
# tokens = 0
# for word in histo:
# tokens += histo[word]
tokens = unique_words(histo)
# print("tokens: ")
# print(tokens)
# cumulative_probability
cum_prob = 0
# random number
ranum = random.uniform(0, 1)
# print("random number: ")
# print(ranum)
# randomly picks one word based on word frequency
for word in histo:
cum_prob += (float(histo[word]) / float(tokens))
# print("cumulative prob: ")
# print(cum_prob)
if cum_prob >= ranum:
return word
def stochastic(histo):
''' Stochastic sampling means taking an element from a given collection at random '''
total_unique = unique_words(histo) # number of unique words
print(unique)
rand_num = random.randint(1, total_unique) # random number in range of number of unique words
print(rand_num)
percentages = []
total_wc = 0
for item in histo:
total_wc += item[0]
for item in histo:
freq = freq(item[0], histo)
perc = freq / total_wc
instance = [item[0], perc]
counter = 0
word = None
# count until we hit the random number
for item in histo:
if counter < rand_num:
counter += 1
word = item
print(word[0])
return word[0]
def stochastic(histo):
''' Stochastic sampling means taking an element from a given collection at random '''
unique = histogram.unique_words(histo)
rand_num = random.randint(1, unique)
counter = 0
while counter < rand_num:
for item in histo:
counter += 1
def stochastic(histo):
''' Stochastic sampling means taking an element from a given collection at random '''
unique = histogram.unique_words(histo) # number of unique words
rand_num = random.randint(
1, unique) # random number in range of number of unique words
counter = 0
word = None
while counter < rand_num: # count until we hit the random number
for item in histo:
counter += 1
word = item
print(word[1])
return word[1]
def stochastic(histo):
''' Stochastic sampling means taking an element from a given collection at random '''
total_unique = unique_words(histo) # number of unique words
print(unique)
rand_num = random.randint(
1, total_unique) # random number in range of number of unique words
print(rand_num)
counter = 0
word = None
# count until we hit the random number
for item in histo:
if counter < rand_num:
counter += 1
word = item
print(word[0])
return word[0]
def stochastic(histo):
''' Stochastic sampling means taking an element from a given collection at random '''
total_unique = unique_words(histo) # number of unique words
print(total_unique)
rand_num = random.randint(1, total_unique) # random number in range of number of unique words
print(rand_num)
percentages = []
total_wc = 0
for item in histo:
total_wc += item[0]
for item in histo:
freq = freq(item[0], histo)
perc = freq / total_wc
instance = [item[0], perc]
percentages.append(instance)
return percentages
def stochastic(histo):
''' Stochastic sampling means taking an element from a given collection at random '''
unique = histogram.unique_words(histo)
rand_num = random.randint(0, unique)
