Created
May 27, 2019 06:23
-
-
Save aravindpai/c8364edf7c2d5083c97de71607d4bb25 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| stop_words = set(stopwords.words('english')) | |
| def text_cleaner(text): | |
| newString = text.lower() | |
| newString = BeautifulSoup(newString, "lxml").text | |
| newString = re.sub(r'\([^)]*\)', '', newString) | |
| newString = re.sub('"','', newString) | |
| newString = ' '.join([contraction_mapping[t] if t in contraction_mapping else t for t in newString.split(" ")]) | |
| newString = re.sub(r"'s\b","",newString) | |
| newString = re.sub("[^a-zA-Z]", " ", newString) | |
| tokens = [w for w in newString.split() if not w in stop_words] | |
| long_words=[] | |
| for i in tokens: | |
| if len(i)>=3: #removing short word | |
| long_words.append(i) | |
| return (" ".join(long_words)).strip() | |
| cleaned_text = [] | |
| for t in data['Text']: | |
| cleaned_text.append(text_cleaner(t)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment