Encoding problem while running text summarization code - encoding

Question

Good Day
I was testing the functionality of a text summarization code published on the website: https://towardsdatascience.com/understand-text-summarization-and-create-your-own-summarizer-in-python-b26a9f09fc70.
The problem is that, when I call the function on a text file, the 'cp949' codec can't decode byte 0xe2 in position 205: illegal multibyte sequence error appears. I know, from other posts, that it is an error related to the encoding type of the file. Therefore, I changed the encoding type of the test2.txt file to UTF-8 (saving the file in Plain text format, then choosing UTF-8 on Text Encoding > Other Encoding), but I still get this error message.
Here is the code that I wrote:
Import libraries
from nltk.corpus import stopwords
from nltk.cluster.util import cosine_distance
import numpy as np
import networkx as nx
test_text_word = "test2.txt"
def read_article(test_text_word):
file = open(test_text_word, "r")
filedata = file.readlines()
article = filedata[0].split(". ")
sentences = []`
for sentence in article:
print(sentence)
sentences.append(sentence.replace("[^a-zA-Z]", " ").split(" "))
sentences.pop()
return sentences
def sentence_similarity(sent1, sent2, stopwords=None):
if stopwords is None:
stopwords = []
sent1 = [w.lower() for w in sent1]
sent2 = [w.lower() for w in sent2]
all_words = list(set(sent1 + sent2))
vector1 = [0] * len(all_words)
vector2 = [0] * len(all_words)
# build the vector for the first sentence
for w in sent1:
if w in stopwords:
continue
vector1[all_words.index(w)] += 1
# build the vector for the second sentence
for w in sent2:
if w in stopwords:
continue
vector2[all_words.index(w)] += 1
return 1 - cosine_distance(vector1, vector2)
def build_similarity_matrix(sentences, stop_words):
# Create an empty similarity matrix
similarity_matrix = np.zeros((len(sentences), len(sentences)))
for idx1 in range(len(sentences)):
for idx2 in range(len(sentences)):
if idx1 == idx2: #ignore if both are same sentences
continue
similarity_matrix[idx1][idx2] = sentence_similarity(sentences[idx1], sentences[idx2], stop_words)
return similarity_matrix
def generate_summary(test_text_word, top_n=5):
stop_words = stopwords.words('english')
summarize_text = []
# Step 1 - Read text anc split it
sentences = read_article(test_text_word)
# Step 2 - Generate Similary Martix across sentences
sentence_similarity_martix = build_similarity_matrix(sentences, stop_words)
# Step 3 - Rank sentences in similarity martix
sentence_similarity_graph = nx.from_numpy_array(sentence_similarity_martix)
scores = nx.pagerank(sentence_similarity_graph)
# Step 4 - Sort the rank and pick top sentences
ranked_sentence = sorted(((scores[i],s) for i,s in enumerate(sentences)), reverse=True)
print("Indexes of top ranked_sentence order are ", ranked_sentence)
for i in range(top_n):
summarize_text.append(" ".join(ranked_sentence[i][1]))
# Step 5 - Offcourse, output the summarize texr
print("Summarize Text: \n", ". ".join(summarize_text))
The problem is that, when I run the code, with the following command:
generate_summary("test2.txt", 2)
I receive this error message: 'cp949' codec can't decode byte 0xe2 in position 205: illegal multibyte sequence
Should I change something in the code?
Thanks for your support.