Created
October 4, 2019 02:23
-
-
Save amitrani6/8c1ca16f1dc7c5e22a4826b96a8b8c73 to your computer and use it in GitHub Desktop.
Functions for processing raw text
This file contains 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
#Import the necessary libraries | |
import nltk | |
from nltk.stem import WordNetLemmatizer | |
#Initialize the Wordnet Lemmatizer | |
lemmatizer = WordNetLemmatizer() | |
#A function to lemmatize raw text, returns a list of lemmatized tokens | |
def lemmatize_text(tokenized_text): | |
return ' '.join([lemmatizer.lemmatize(w) for w in tokenized_text]) | |
#A function that ties all of the steps together | |
def process_text(file_name): | |
raw_episode_text = open_file(file_name) | |
clean_episode_text = cleaned_episode(raw_episode_text) | |
tokenize_episode_text = tokenize(clean_episode_text) | |
lemmatize_episode_text = lemmatize_text(tokenize_episode_text) | |
return lemmatize_episode_text | |
#Applies the text to the data frame | |
df['lemmatize_text'] = df.file_path.apply(lambda x: process_text(x)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment