We Keep Coding

Python adds a double entry at the end of output file

This is my code to create a hashtag file. The issue is it does not put the # for the first hashtag and at he end it puts a double hashtag like below.
passiveincome, #onlinemarketing, #wahmlife, #cash, #entrepreneurlifestyle, #makemoneyonline, #makemoneyfast, #entrepreneurlifestyle, #mlm, #mlm
How do I get the code to remove the double output and put the # at the beginning?
import random, os, sys
basepath = os.path.dirname(sys.argv[0]) + "/"
outputpath = "C:/Users/matth/OneDrive/Desktop/Create hashtags/"
paragraphsmin = 9
paragraphsmax = 9
sentencemin = 1
sentencemax = 1
keywords = []
for line in open(basepath + "/base.txt", "r"):
keywords.append(line.replace("\n",""))
keywordlist = []
keyword = open(basepath + "/text-original.txt", "r")
for line in keyword:
keywordlist.append(line.replace("\n", "\n"))
def type(name):
value = name[random.randint(0,len(name)-1)]
return value
"""
def xyz(num):
s1 = '' + type(keywordlist).strip()
return eval('s' + str(num))
"""
def s1():
return '' + type(keywordlist).strip()
def randomSentence():
sent = eval("s" + str(random.randint(1,1)) + "()")
return sent
for keyword in keywords:
outputfile = open(outputpath + keyword.replace(" ", " ") + ".txt", "w")
outputfile.write('')
for p in range(1,random.randint(paragraphsmin,paragraphsmax) + 1):
outputfile.write('')
for s in range(1,random.randint(sentencemin,sentencemax) + 1):
sentence = randomSentence()
if str(sentence)[0] == "\"":
outputfile.write("" + str(sentence)[0] + str(sentence)[1] + str(sentence)[2:] + " ")
else:
outputfile.write("" + str(sentence)[0] + str(sentence)[1:] + ", #")
outputfile.write('')
outputfile.write(sentence.replace("", "") + "")
outputfile.close()

Try replacing
outputfile.write("" + str(sentence)[0] + str(sentence)[1:] + ", #")
with
outputfile.write("#" + str(sentence)[0] + str(sentence)[1:] + ", ")

python files - who to open corectly

We have file with some math problems like: 46 + 19 (only + or - and it built up this way: number, space, sign, space, number) and we need to transform it into a new file and solve them (46 + 19 = 65). We don't know how many exercises there will be or the number of digits in every number. Here is my code:
enter code here
input_file = open(r'C:\try\bla.txt', 'r')
nums = input_file.read()
y = 0
dig1 = ''
dig2 = ''
sign = ''
x1 = nums.find(' ')
x2 = x1 + 1
def one(dig1, dig2, y):
for i in xrange(x1):
dig1 += nums[y]
y += 1
for m in xrange(abs(-x2)):
dig2 += nums[y + 1]
y += 1
sign = nums[x2]
if sign == '+':
sum = int(dig1) + int(dig2)
if sign == '-':
sum = int(dig1) - int(dig2)
print dig1, dig2, '=', sum
for a in xrange(0):
one(dig1, dig2, y)
one(dig1, dig2, y)
print 'f', nums[21]
#print dig1, dig2, '=', sum

Maybe you are want to get this(python3):
test.txt:
10 + 15
22 - 71
33 + 64
code:
import operator
op = {'+': operator.add, '-': operator.sub}
with open('test.txt', 'r') as f:
lines = f.readlines()
for i in lines:
args = i.split()
val = op[args[1]](int(args[0]), int(args[-1]))
r = f'{i.strip()} = {val}'
print(r)

how to equate unigram tfidf to 0 when bigram of related unigram is nonzero?

I am doing sentiment analysis of movie review using python with scikit-learn and nltk. i want to equate elements related to unigram to 0 (when they are having opposite polarity) when a bigram/ trigram related to those unigram are non zero.
for example:
movie is not bad
than feature vector is ['movie' 'is' 'not' 'bad' 'movie is' 'is not' 'not bad']=[3 3 1 1 4 2 4]
but i want [3 3 0 0 4 2 4] instead.
code:
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.svm import LinearSVC
import math
#######################Reading Training Review Phrases and Sentiments###################################
train_list = []
train_sentiment = []
with open('sentences.txt') as f:
content = f.readlines()
for sentence in content:
train_list.append(sentence.rstrip('\n').split("\t")[0])
train_sentiment.append(sentence.rstrip('\n').split("\t")[1])
#######################Number of phrases in each class###################################
ex_pos = pos = neu = neg = ex_neg = 0
ex_pos_phrases = pos_phrases = neu_phrases = neg_phrases = ex_neg_phrases = []
with open('ex_pos.txt', 'r') as ex_posF:
ex_pos_phrases = ex_posF.readlines()
ex_pos = len(ex_pos_phrases)
with open('pos.txt', 'r') as posF:
pos_phrases = posF.readlines()
pos = len(pos_phrases)
with open('neu.txt', 'r') as neuF:
neu_phrases = neuF.readlines()
neu = len(neu_phrases)
with open('neg.txt', 'r') as negF:
neg_phrases = negF.readlines()
neg = len(neg_phrases)
with open('ex_neg.txt', 'r') as ex_negF:
ex_neg_phrases = ex_negF.readlines()
ex_neg = len(ex_neg_phrases)
print(str(ex_neg) + "," + str(neg) + "," + str(neu) + "," + str(pos) + "," + str(ex_pos))
####################### Getting unique Words ###################################
unique_words = []
model = TfidfVectorizer(input=train_list)
train_tfidf = model.fit_transform(train_list)
unique_words = model.get_feature_names()
print("##### Word sentiment matrix ####")
########################## Word sentiment matrix ########################################
word_sentiment = [[0 for x in range(5)] for x in range(len(unique_words)) ]
wordcount = 0
for word in unique_words:
count = 0
for review in ex_neg_phrases:
review_words = review.rstrip('\n').split(" ")
for review_word in review_words:
if review_word == word:
count += 1
break
word_sentiment[wordcount][0] = count
count = 0
for review in neg_phrases:
review_words = review.rstrip('\n').split(" ")
for review_word in review_words:
if review_word == word:
count += 1
break
word_sentiment[wordcount][1] = count
count = 0
for review in neu_phrases:
review_words = review.rstrip('\n').split(" ")
for review_word in review_words:
if review_word == word:
count += 1
break
word_sentiment[wordcount][2] = count
count = 0
for review in ex_pos_phrases:
review_words = review.rstrip('\n').split(" ")
for review_word in review_words:
if review_word == word:
count += 1
break
word_sentiment[wordcount][4] = count
count = 0
for review in pos_phrases:
review_words = review.rstrip('\n').split(" ")
for review_word in review_words:
if review_word == word:
count += 1
break
word_sentiment[wordcount][3] = count
wordcount += 1
print("###The Training feature matrix###")
#################################The feature matrix#######################################
feature_matrix = [[0 for x in range(len(unique_words))] for x in range(len(train_list))]
print(len(feature_matrix))
print(len(feature_matrix[0]))
wordcount = 0
for unique_word in unique_words:
phrasecount = 0
ep = p = nu = en = n = 0
if word_sentiment[wordcount][4] != 0:
ep = .35 * math.log(word_sentiment[wordcount][4]/ex_pos)
if word_sentiment[wordcount][3] != 0:
p = .15 * math.log(word_sentiment[wordcount][3]/pos)
if word_sentiment[wordcount][2] != 0:
nu = 1 * math.log(word_sentiment[wordcount][2]/neu)
if word_sentiment[wordcount][0] != 0:
en = -.35 * math.log(word_sentiment[wordcount][0]/ex_neg)
if word_sentiment[wordcount][1] != 0:
n = -.15 * math.log(word_sentiment[wordcount][1]/neg)
for phrase in train_list:
words = phrase.split(" ")
docwordcount = 0
for word in words:
if word == unique_word:
docwordcount += 1
tfidf = (docwordcount * ep) + (docwordcount * p) + (docwordcount * nu) + (docwordcount * en) + (docwordcount * n)
feature_matrix[phrasecount][wordcount] = tfidf
phrasecount += 1
wordcount += 1
print("###The test feature matrix###")
test_list=[]
test_phraseid =[]
with open('sentences_test.txt') as f:
content = f.readlines()
for sentence in content:
test_list.append(sentence.rstrip('\n').split("\t")[0])
test_phraseid.append(sentence.rstrip('\n').split("\t")[1])
wordcount = 0
test_tfidf = [[0 for x in range(len(unique_words))] for x in range(len(test_list))]
for unique_word in unique_words:
phrasecount = 0
ep = p = nu = en = n = 0
if word_sentiment[wordcount][4] != 0:
ep = .35 * math.log(word_sentiment[wordcount][4]/ex_pos)
if word_sentiment[wordcount][3] != 0:
p = .15 * math.log(word_sentiment[wordcount][3]/pos)
if word_sentiment[wordcount][2] != 0:
nu = 1 * math.log(word_sentiment[wordcount][2]/neu)
if word_sentiment[wordcount][0] != 0:
en = -.35 * math.log(word_sentiment[wordcount][0]/ex_neg)
if word_sentiment[wordcount][1] != 0:
n = -.15 * math.log(word_sentiment[wordcount][1]/neg)
for phrase in test_list:
words = phrase.split(" ")
docwordcount = 0
for word in words:
if word == unique_word:
docwordcount += 1
tfidf = (docwordcount * ep) + (docwordcount * p) + (docwordcount * nu) + (docwordcount * en) + (docwordcount * n)
test_tfidf[phrasecount][wordcount] = tfidf
phrasecount += 1
wordcount += 1
print("###The Linear SVC ###")
self = LinearSVC()
self = LinearSVC.fit(self, feature_matrix, train_sentiment)
test_sentiment = LinearSVC.predict(self, test_tfidf)
with open('output_deltatfidf.csv', 'w') as fil:
fil.write("PhraseId,Sentiment\n")
for x in range(0, len(test_sentiment)):
fil.write(test_phraseid[x] + "," + test_sentiment[x] + "\n")

RC4 decryption with key in Python

I pulled this code from here for asp http://bytes.com/topic/access/insights/906671-rc4-encryption-algorithm-vba-vbscript, which i then run thru base64.
I am wonder if anyone can help me figure out how to write the decryption piece but in Python. As the decryption will happen on my Python Server Page.
Found this http://www.id-snippet.com/20801/python-rc4-cipher/, but it doesn't decrypt the RC4 asp from the first link.
-Jim
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
ASP page
'Base64
Function Base64Encode(inData)
Const Base64 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
Dim cOut, sOut, I
'For each group of 3 bytes
For I = 1 To Len(inData) Step 3
Dim nGroup, pOut, sGroup
'Create one long from this 3 bytes.
nGroup = &H10000 * Asc(Mid(inData, I, 1)) + _
&H100 * MyASC(Mid(inData, I + 1, 1)) + MyASC(Mid(inData, I + 2, 1))
'Oct splits the long To 8 groups with 3 bits
nGroup = Oct(nGroup)
'Add leading zeros
nGroup = String(8 - Len(nGroup), "0") & nGroup
'Convert To base64
pOut = Mid(Base64, CLng("&o" & Mid(nGroup, 1, 2)) + 1, 1) + _
Mid(Base64, CLng("&o" & Mid(nGroup, 3, 2)) + 1, 1) + _
Mid(Base64, CLng("&o" & Mid(nGroup, 5, 2)) + 1, 1) + _
Mid(Base64, CLng("&o" & Mid(nGroup, 7, 2)) + 1, 1)
'Add the part To OutPut string
sOut = sOut + pOut
'Add a new line For Each 76 chars In dest (76*3/4 = 57)
'If (I + 2) Mod 57 = 0 Then sOut = sOut + vbCrLf
Next
Select Case Len(inData) Mod 3
Case 1: '8 bit final
sOut = Left(sOut, Len(sOut) - 2) + "=="
Case 2: '16 bit final
sOut = Left(sOut, Len(sOut) - 1) + "="
End Select
Base64Encode = sOut
End Function
Function MyASC(OneChar)
If OneChar = "" Then MyASC = 0 Else MyASC = Asc(OneChar)
End Function
'RC4
Function RunRC4(sMessage, strKey)
Dim kLen, x, y, i, j, temp
Dim s(256), k(256)
'Init keystream
klen = Len(strKey)
For i = 0 To 255
s(i) = i
k(i) = Asc(Mid(strKey, (i Mod klen) + 1, 1))
Next
j = 0
For i = 0 To 255
j = (j + k(i) + s(i)) Mod 255
temp = s(i)
s(i) = s(j)
s(j) = temp
Next
'Drop n bytes from keystream
x = 0
y = 0
For i = 1 To 3072
x = (x + 1) Mod 255
y = (y + s(x)) Mod 255
temp = s(x)
s(x) = s(y)
s(y) = temp
Next
'Encode/Decode
For i = 1 To Len(sMessage)
x = (x + 1) Mod 255
y = (y + s(x)) Mod 255
temp = s(x)
s(x) = s(y)
s(y) = temp
RunRC4 = RunRC4 & Chr(s((s(x) + s(y)) Mod 255) Xor Asc(Mid(sMessage, i, 1)))
Next
End Function
encStr = Base64Encode(RunRC4(username,"1234"))
Python Server Page
def decode64(in_str):
import base64
decodedStr = base64.b64decode(in_str)
return decodedStr
def rc4crypt(data, key):
x = 0
box = range(256)
for i in range(256):
x = (x + box[i] + ord(key[i % len(key)])) % 256
box[i], box[x] = box[x], box[i]
x,y = 0, 0
out = []
for char in data:
x = (x + 1) % 256
y = (y + box[x]) % 256
box[x], box[y] = box[y], box[x]
out.append(chr(ord(char) ^ box[(box[x] + box[y]) % 256]))
return ''.join(out)
decStr = rc4crypt(decode64(encStr), "1234")
Can't figure out why python decrypt doesn't render the original string when using the same key "1234"

Error in python replace. (AttributeError: 'tuple' object has no attribute 'replace')

Environment
I am using Python 3 and my OS is Windows 7.
I understand that some commands have changed from the transition from python 2.7 to 3 (What I have used).
Problem
The variable is temporary but is this:
(((((0, 7), 7), 8), 4), 5)
Here is the code to get rid of the brackets:
randy = randy.replace(")", "")
randy = randy.replace("(", "")
randy = randy.replace(" ", "")
When it tries to execute the replace function, I get thrown an error:
Traceback (most recent call last):
File "<string>", line 248, in run_nodebug
File "Criptic.py", line 134, in <module>
randy = randy.replace(")", "")
AttributeError: 'tuple' object has no attribute 'replace'
Edit:
Here is all of the code:
#Import string
import string
import random
#Input user data
text = input("Enter your text to be converted: ")
#Test Print
print("-------------------------")
print("Your text is: ",text)
#Break up all the data
data = list(text)
#Lowercase
count = text.count("a")
count1 = text.count("b")
count2 = text.count("c")
count3 = text.count("d")
count4 = text.count("e")
count5 = text.count("f")
count6 = text.count("g")
count7 = text.count("h")
count8 = text.count("i")
count9 = text.count("j")
count10 = text.count("k")
count11 = text.count("l")
count12 = text.count("m")
count13 = text.count("n")
count14 = text.count("o")
count15 = text.count("p")
count16 = text.count("q")
count17 = text.count("r")
count18 = text.count("s")
count19 = text.count("t")
count20 = text.count("u")
count21 = text.count("v")
count22 = text.count("w")
count23 = text.count("x")
count24 = text.count("y")
count25 = text.count("z")
count26 = text.count("A")
#Uppercase
count27 = text.count("B")
count28 = text.count("C")
count29 = text.count("D")
count30 = text.count("E")
count31 = text.count("F")
count32 = text.count("G")
count33 = text.count("H")
count34 = text.count("I")
count35 = text.count("J")
count36 = text.count("K")
count37 = text.count("L")
count38 = text.count("M")
count39 = text.count("N")
count40 = text.count("O")
count41 = text.count("P")
count42 = text.count("Q")
count43 = text.count("R")
count44 = text.count("S")
count45 = text.count("T")
count46 = text.count("U")
count47 = text.count("V")
count48 = text.count("W")
count49 = text.count("X")
count50 = text.count("Y")
count51 = text.count("Z")
#Other Characters
count52 = text.count(" ")
count53 = text.count("?")
count54 = text.count("#")
count55 = text.count("(")
count56 = text.count(")")
count57 = text.count(".")
#Numbers
count58 = text.count("1")
count59 = text.count("2")
count60 = text.count("3")
count61 = text.count("4")
count62 = text.count("5")
count63 = text.count("6")
count64 = text.count("7")
count65 = text.count("8")
count66 = text.count("9")
count67 = text.count("0")
#Counting how many characters in the sentence
finalcount = count + count1 + count2 + count3 + count4 + count5 + count6 + count7 + count8 + count9 + count10 + count11 + count12 + count13 + count14 + count15 + count16 + count17 + count18 + count19 + count20 + count21 + count22 + count23 + count24 + count25 + count26 + count27 + count28 + count29 + count31 + count32 + count33 + count34 + count35 + count36 + count37 + count38 + count39 + count40 + count41 + count42 + count43 + count44 + count45 + count46 + count47 + count48 + count49 + count50 + count51 + count52 + count53 + count54 + count55 + count56 + count57 + count58 + count59 + count60 + count61 + count62 + count63 + count64 + count65 + count66 + count67
#Final count of Characters
print(" Chars: ",finalcount)
print("-------------------------")
char = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!##$%^&*()?_+-=1234567890 "
charnum = 74 + 11
list(char)
randy = 0
num = 0
while num < finalcount:
rand = random.randrange(1,9)
randy = randy,rand
finalcount = finalcount - 1
if rand == 1:
print(text[finalcount],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],",")
if rand == 2:
print(char[random.randrange(0,charnum)],text[finalcount],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],",")
if rand == 3:
print(char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],text[finalcount],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],",")
if rand == 4:
print(char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],text[finalcount],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],",")
if rand == 5:
print(char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],text[finalcount],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],",")
if rand == 6:
print(char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],text[finalcount],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],",")
if rand == 7:
print(char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],text[finalcount],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],",")
if rand == 8:
print(char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],text[finalcount],char[random.randrange(0,charnum)],",")
if rand == 9:
print(char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],char[random.randrange(0,charnum)],text[finalcount],",")
randy = randy.replace(")", "")
randy = randy.replace("(", "")
randy = randy.replace(" ", "")
print("-------------------------")
print("::::::::Completed::::::::")
print("-------------------------")
print(randy)
print("-This is your code unlock key. Without this code it will not decript!!!! ")
print("-------------------------")

You have a tuple (a sort of list) of numbers, and you want to make that a string. You can't replace the brackets, they aren't a part of the variable, they are just a part of its representation.
Instead you should use join() and str()
result = " ".join(str(x) for x in randy)
However, this probably will not give the right result either, as it is a nested list of tuples. You probably mean: randy = randy + (rand,) instead if randy = randy,rand.

randy = randy,rand
This notation creates a tuple of two elements, tuples do not have a method called replace.
If you just want to concatenate the numbers into a list representation separated by commas, you could do this in your loop:
randy = []
num = 0
while num < finalcount:
rand = random.randrange(1,9)
randy.append(rand)
Then you remove the replace lines, and instead do this
randy = ",".join(randy)
to get a string that has the values separated by commas.
You should maybe add the output that you would like to get to your question, because at the moment it's not quite clear what you want to do exactly.

exam_st_date = (11, 12, 2014)
# Sample Output : The examination will start from : 11 / 12 / 2014
newtup = str(exam_st_date).replace(',', ' /')
print(newtup)
look at mine example should give you some results

To delete a list of characters, you could use the string's translate method:
import string
name = "(((((0, 7), 7), 8), 4), 5)"
table = string.maketrans( '', '', )
print name.translate(table,"()")