and the new code:
input2 = open('lc.txt', 'r', encoding='latin-1').read()
preword1words = []
preword2words = []
preword1counts = []
preword2counts = []
betterbe10timesseenatleast1 = 0
betterbe10timesseenatleast2 = 0
for count2 in range(1000000000):
window = input2[count2: count2 + 12]
searchfor = 'computer'
sl = len(searchfor) + 1
if window[-(sl-1):] == searchfor:
if window[-sl] == ' ' or window[-sl] == ',' or window[-sl] == '.' or
window[-sl] == '[' or window[-sl] == ']' or window[-sl] == '(' or window[-sl]
== ')' or window[-sl] == ':' or window[-sl] == ';' or window[-sl] == '\n' or
window[-sl] == '\t' or window[-sl] == '\r':
if input2[count2 + 12] == ' ' or input2[count2 + 12] == ',' or
input2[count2 + 12] == '.' or input2[count2 + 12] == '[' or input2[count2 + 12]
== ']' or input2[count2 + 12] == '(' or input2[count2 + 12] == ')' or
input2[count2 + 12] == ':' or input2[count2 + 12] == ';' or input2[count2 + 12]
== '\n' or input2[count2 + 12] == '\t' or input2[count2 + 12] == '\r':
betterbe10timesseenatleast1 += 1
word = ''
passed = 0
for i in range(50):
if passed == 1:
if input2[count2 + 12 + i] == ' ' or input2[count2 + 12 + i] == ','
or input2[count2 + 12 + i] == '.' or input2[count2 + 12 + i] == '[' or
input2[count2 + 12 + i] == ']' or input2[count2 + 12 + i] == '(' or
input2[count2 + 12 + i] == ')' or input2[count2 + 12 + i] == ':' or
input2[count2 + 12 + i] == ';' or input2[count2 + 12 + i] == '\n' or
input2[count2 + 12 + i] == '\t' or input2[count2 + 12 + i] == '\r':
break
word = word + input2[count2 + 12 + i]
if passed == 0 and input2[count2 + 12 + i] == ' ':
passed = 1
elif passed == 0:
break
found = 0
if len(word) > 0:
for i in range(len(preword1words)):
if word == preword1words[i]:
preword1counts[i] += 1
found = 1
if found == 0:
preword1words.append(word)
preword1counts.append(1)
word = ''
passed = 0
for i in range(len(window) - sl+1):
if passed == 1:
if window[-sl - i] == ' ' or window[-sl - i] == ',' or window[-sl -
i] == '.' or window[-sl - i] == '[' or window[-sl - i] == ']' or window[-sl -
i] == '(' or window[-sl - i] == ')' or window[-sl - i] == ':' or window[-sl -
i] == ';' or window[-sl - i] == '\n' or window[-sl - i] == '\t' or window[-sl -
i] == '\r':
break
word = window[-sl-i] + word
if passed == 0 and window[-sl-i] == ' ':
passed = 1
elif passed == 0:
break
found = 0
if len(word) > 0:
for i in range(len(preword1words)):
if word == preword1words[i]:
preword1counts[i] += 1
found = 1
if found == 0:
preword1words.append(word)
preword1counts.append(1)
else:
searchfor = 'table'
sl = len(searchfor) + 1
if window[-(sl-1):] == searchfor:
if window[-sl] == ' ' or window[-sl] == ',' or window[-sl] == '.' or
window[-sl] == '[' or window[-sl] == ']' or window[-sl] == '(' or window[-sl]
== ')' or window[-sl] == ':' or window[-sl] == ';' or window[-sl] == '\n' or
window[-sl] == '\t' or window[-sl] == '\r':
if input2[count2 + 12] == ' ' or input2[count2 + 12] == ',' or
input2[count2 + 12] == '.' or input2[count2 + 12] == '[' or input2[count2 + 12]
== ']' or input2[count2 + 12] == '(' or input2[count2 + 12] == ')' or
input2[count2 + 12] == ':' or input2[count2 + 12] == ';' or input2[count2 + 12]
== '\n' or input2[count2 + 12] == '\t' or input2[count2 + 12] == '\r':
betterbe10timesseenatleast2 += 1
word = ''
passed = 0
for i in range(50):
if passed == 1:
if input2[count2 + 12 + i] == ' ' or input2[count2 + 12 + i] ==
',' or input2[count2 + 12 + i] == '.' or input2[count2 + 12 + i] == '[' or
input2[count2 + 12 + i] == ']' or input2[count2 + 12 + i] == '(' or
input2[count2 + 12 + i] == ')' or input2[count2 + 12 + i] == ':' or
input2[count2 + 12 + i] == ';' or input2[count2 + 12 + i] == '\n' or
input2[count2 + 12 + i] == '\t' or input2[count2 + 12 + i] == '\r':
break
word = word + input2[count2 + 12 + i]
if passed == 0 and input2[count2 + 12 + i] == ' ':
passed = 1
elif passed == 0:
break
found = 0
if len(word) > 0:
for i in range(len(preword2words)):
if word == preword2words[i]:
preword2counts[i] += 1
found = 1
if found == 0:
preword2words.append(word)
preword2counts.append(1)
word = ''
passed = 0
for i in range(len(window) - sl+1):
if passed == 1:
if window[-sl - i] == ' ' or window[-sl - i] == ',' or window[-sl
- i] == '.' or window[-sl - i] == '[' or window[-sl - i] == ']' or window[-sl -
i] == '(' or window[-sl - i] == ')' or window[-sl - i] == ':' or window[-sl -
i] == ';' or window[-sl - i] == '\n' or window[-sl - i] == '\t' or window[-sl -
i] == '\r':
break
word = window[-sl - i] + word
if passed == 0 and window[-sl - i] == ' ':
passed = 1
elif passed == 0:
break
found = 0
if len(word) > 0:
for i in range(len(preword2words)):
if word == preword2words[i]:
preword2counts[i] += 1
found = 1
if found == 0:
preword2words.append(word)
preword2counts.append(1)
if betterbe10timesseenatleast1 < 10 or betterbe10timesseenatleast2 < 10:
print('should use words that both have a minimum of 10 counts at least')
for i in range(len(preword1counts)):
if preword1counts[i] > 180:
preword1counts[i] = 180
for i in range(len(preword2counts)):
if preword2counts[i] > 180:
preword2counts[i] = 180
tree = ['',[]]
for count2 in range(10000000):
window = input2[count2: count2 + 15]
node = 0
for i in range(len(window)):
char_index = tree[node].find(window[i]) + 1
if char_index == 0:
tree[node] += window[i]
tree[node + 1].insert(len(tree[node])-1,1)
tree[node + 1].append(len(tree))
tree.extend(('',[]))
break
tree[node + 1][char_index - 1] += 1
node = tree[node + 1][len(tree[node]) + char_index - 1]
word1words = []
word1counts = []
for i in range(len(preword1words)):
window = ' ' + preword1words[i]
node = 0
try:
for ii in range(len(window)):
char_index = tree[node].find(window[ii]) + 1
node = tree[node + 1][len(tree[node]) + char_index - 1]
char_index = tree[node].find(' ') + 1
if tree[node+1][char_index - 1] < 270:
word1words.append(preword1words[i])
word1counts.append(preword1counts[i])
except:
word1words.append(preword1words[i])
word1counts.append(preword1counts[i])
word2words = []
word2counts = []
for i in range(len(preword2words)):
window = ' ' + preword2words[i]
node = 0
try:
for ii in range(len(window)):
char_index = tree[node].find(window[ii]) + 1
node = tree[node + 1][len(tree[node]) + char_index - 1]
char_index = tree[node].find(' ') + 1
if tree[node+1][char_index - 1] < 270:
word2words.append(preword2words[i])
word2counts.append(preword2counts[i])
except:
word2words.append(preword2words[i])
word2counts.append(preword2counts[i])
wordsum1 = sum(word1counts)
wordsum2 = sum(word2counts)
if wordsum1 > wordsum2:
normcreator = wordsum1 / wordsum2
for i in range(len(word2counts)):
word2counts[i] = word2counts[i] * normcreator
biggersum = wordsum1
else:
normcreator = wordsum2 / wordsum1
for i in range(len(word1counts)):
word1counts[i] = word1counts[i] * normcreator
biggersum = wordsum2
shared = 0
for i in range(len(word1words)):
for ii in range(len(word2words)):
if word1words[i] == word2words[ii]:
if word1counts[i] < word2counts[ii]:
smallernumber = word1counts[i]
biggernumber = word2counts[ii]
else:
smallernumber = word2counts[ii]
biggernumber = word1counts[i]
shared += (biggernumber * (smallernumber / biggernumber))
print(shared / biggersum)
# get the amount of words that follow and the amount of types of words that
follow, confidence = total / (types * 10) + another such averaged
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T01fa5e447808d368-M3763f7b3473400334eae7e7c
Delivery options: https://agi.topicbox.com/groups/agi/subscription
