Course Content

Tweet Sentiment Analysis

Introduction Reading the Data Print out the Basic Info of our Dataset Data Preprocessing EDA Plot the Distribution Text Cleaning Words Count Generate a Word Cloud Text Sentiment Analysis Sentiment Classification

Words Count

Now we would like to explore the most represented number in our DataFrame. For this reason we will create a collection where we will store the most frequent words and then, plot it.

Methods description

from collections import Counter; import nltk: Imports the Counter class from the collections module and the nltk library;
from nltk.corpus import stopwords: Imports a list of common stopwords from NLTK;
nltk.download("stopwords"): Downloads the stopwords dataset from NLTK;
def remove_stopword(x): This defines a function named remove_stopword that takes a list x as input and returns a new list with stopwords removed;
return [y for y in x if y not in stopwords.words("english")]: This comprehension expression filters out stopwords from the input list x using the list of English stopwords from NLTK;
Counter: A class from the collections module used to count occurrences of elements in a list or iterable;
stopwords.words("english"): A method from NLTK that returns a list of stopwords for the English language;
temp.most_common(25): Returns the 25 most common elements (words) and their counts from the Counter object temp;
temp.iloc[1:,:]: Indexes a DataFrame temp to exclude the first row and select all columns;
temp.style.background_gradient(...): Applies a background gradient style to a DataFrame temp.

Task

Create a collection to count word occurrences using the Counter module:

Remove stopwords from our tweets texts.
Create a collection.
Create a DataFrame with the newly created list.
Change the background color to "Blues".

Mark tasks as Completed

Everything was clear?

Section 1. Chapter 8

AVAILABLE TO ULTIMATE ONLY

Methods description

from collections import Counter; import nltk: Imports the Counter class from the collections module and the nltk library;

from nltk.corpus import stopwords: Imports a list of common stopwords from NLTK;

nltk.download("stopwords"): Downloads the stopwords dataset from NLTK;

def remove_stopword(x): This defines a function named remove_stopword that takes a list x as input and returns a new list with stopwords removed;

return [y for y in x if y not in stopwords.words("english")]: This comprehension expression filters out stopwords from the input list x using the list of English stopwords from NLTK;

Counter: A class from the collections module used to count occurrences of elements in a list or iterable;

stopwords.words("english"): A method from NLTK that returns a list of stopwords for the English language;

temp.most_common(25): Returns the 25 most common elements (words) and their counts from the Counter object temp;

temp.iloc[1:,:]: Indexes a DataFrame temp to exclude the first row and select all columns;

temp.style.background_gradient(...): Applies a background gradient style to a DataFrame temp.