How can i complete this project ? it about sentmental classification - python-3.x

Question

I was trying to write code for sentmental classifier for twitter csv file.
The code is working but in the coursera platform it gets stuck it did not work. It show me some errors; it is coursera pyhton function dictionaries and files specialization course.
projectTwitterDataFile = open("project_twitter_data.csv","r")
resultingDataFile = open("resulting_data.csv","w")
punctuation_chars = ["'", '"', ",", ".", "!", ":", ";", '#', '#']
# lists of words to use
positive_words = []
with open("positive_words.txt") as pos_f:
for lin in pos_f:
if lin[0] != ';' and lin[0] != '\n':
positive_words.append(lin.strip())
def get_pos(strSentences):
strSentences = strip_punctuation(strSentences)
listStrSentences= strSentences.split()
count=0
for word in listStrSentences:
for positiveWord in positive_words:
if word == positiveWord:
count+=1
return count
negative_words = []
with open("negative_words.txt") as pos_f:
for lin in pos_f:
if lin[0] != ';' and lin[0] != '\n':
negative_words.append(lin.strip())
def get_neg(strSentences):
strSentences = strip_punctuation(strSentences)
listStrSentences = strSentences.split()
count=0
for word in listStrSentences:
for negativeWord in negative_words:
if word == negativeWord:
count+=1
print(count)
return count
def strip_punctuation(strWord):
for charPunct in punctuation_chars:
strWord = strWord.replace(charPunct, "")
return strWord
def writeInDataFile(resultingDataFile):
resultingDataFile.write("Number of Retweets, Number of Replies,
positive Score, Negative Score, Net Score")
resultingDataFile.write("\n")
linesPTDF = projectTwitterDataFile.readlines()
headerDontUsed= linesPTDF.pop(0)
for linesTD in linesPTDF:
listTD = linesTD.strip().split(',')
resultingDataFile.write("{}, {}, {}, {}, {}".format(listTD[1],
listTD[2], get_pos(listTD[0]), get_neg(listTD[0]),
(get_pos(listTD[0])- get_neg(listTD[0]))))
resultingDataFile.write("\n")
writeInDataFile(resultingDataFile)
projectTwitterDataFile.close()
resultingDataFile.close())
Error
TimeLimitError: Program exceeded run time limit. on line 37
Description
Your program is running too long. Most programs in this book should
run in less than 10 seconds easily. This probably indicates your
program is in an infinite loop.
To Fix
Add some print statements to figure out if your program is in an
infinte loop. If it is not you can increase the run time with
sys.setExecutionLimit(msecs)

Answer 1

It's not very clear to me what you're trying to do. Your code isn't very well-formatted, so besides the fact that your line indentation is off, it's not immediately clear where your functions end and where new commands begin. In fact, you have commands put in between your definitions/functions. The typical convention in Python is to put your callable functions at the top, then the flow of actual code at the bottom after your functions.
I take it that positive_words.txt and negative_words.txt are just two text files where each line is either a word (with punctuation marks such as apostrophes already stripped out), something starting with a semicolon, or a blank line? If so, you can probably just do something like this to extract the lists:
with open("positive_words") as f:
positive_words = [ c.strip() for c in f.readlines() if c[0] not in [';', '\n'] ]
Also, instead opening files and passing the instances of their openings into your functions, only to not use that file in any other functions, maybe you should just pass in the name of the file, then do all of the opening and closing from within the function.

Answer 2

punctuation_chars = ["'", '"', ",", ".", "!", ":", ";", '#', '#']
def strip_punctuation(oldS):
for i in punctuation_chars:
oldS = str(oldS).replace('%s' % i, '')
return oldS
def strip_punctuation(oldS):
for i in punctuation_chars:
oldS = str(oldS).replace('%s' % i, '')
return oldS
punctuation_chars = ["'", '"', ",", ".", "!", ":", ";", '#', '#']
# list of positive words to use
positive_words = []
with open("positive_words.txt") as pos_f:
for lin in pos_f:
if lin[0] != ';' and lin[0] != '\n':
positive_words.append(lin.strip())
def get_pos(str):
str = strip_punctuation(str).split()
j = 0
for i in str:
if i in positive_words:
j += 1
return j
def strip_punctuation(oldS):
for i in punctuation_chars:
oldS = str(oldS).replace('%s' % i, '')
return oldS
punctuation_chars = ["'", '"', ",", ".", "!", ":", ";", '#', '#']
negative_words = []
with open("negative_words.txt") as pos_f:
for lin in pos_f:
if lin[0] != ';' and lin[0] != '\n':
negative_words.append(lin.strip())
def get_neg(str):
str = strip_punctuation(str).split()
k = 0
for i in str:
if i in negative_words:
k += 1
return k
def run(file):
csvFile = open(file, 'r')
lines = csvFile.readlines()
lines = lines[1:]
neg_count = []
pos_count = []
wordList = []
for i in lines:
i = i.strip()
i = i.split(",")[0]
wordList.append(i)
for i in wordList:
neg_count.append(get_neg(i))
pos_count.append(get_pos(i))
res = ['retweet_count,reply_count,pos_count,neg_count,score']
res = []
for i in lines:
i = i.strip()
i = i.split(",")[1:]
res.append(i)
temp = []
for i in res:
i = list(map(int, i))
temp.append(i)
res = temp
for i in range(len(res)):
res[i].append(pos_count[i])
res[i].append(neg_count[i])
res[i].append(pos_count[i] - neg_count[i])
temp = []
for i in res:
temp.append(','.join('%s' %id for id in i))
res = temp
res.insert(0, "Number of Retweets, Number of Replies, Positive Score, Negative Score, Net Score")
print(res)
res = '\n'.join('%s' % id for id in res)
with open("resulting_data.csv", 'w') as csvFile:
write = csvFile.write(res)
if __name__ == '__main__':
run('project_twitter_data.csv')