IndexError: list index out of range [ summarize_text.append(" ".join(ranked_sentence[i][1])) ]

Question

I have written some python code to generate an extractive summary of a txt file. I am getting a IndexError: list index out of range error for this line of my code ;

   for i in range(top_n):
      summarize_text.append(" ".join(ranked_sentence[i][1]))

I was following a tutorial to implement the process. https://towardsdatascience.com/understand-text-summarization-and-create-your-own-summarizer-in-python-b26a9f09fc70 I didn't find uch help from its reviews or comments. I tried searching for similar problems here with no avail.

My full code ;

from nltk.corpus import stopwords
from nltk.cluster.util import cosine_distance
import numpy as np
import networkx as nx

def read_article(file_name):
    file = open(file_name, "r+",encoding="utf-8")
    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(file_name, top_n=5):
    stop_words = stopwords.words('english')
    summarize_text = []

    # Step 1 - Read text anc split it
    sentences =  read_article(file_name)

    # 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)    

 # **THE ERROR**   
 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))

# let's begin
generate_summary( "F:\\Girivraaj\\tmp\\document8.txt", 2)

The error is being shown for ;

 for i in range(top_n):
      summarize_text.append(" ".join(ranked_sentence[i][1]))

( shown in bold in the full code )

The expected result would be a summary.

Answer 1

I noticed that this code will work with some texts but not others. The same error appeared for me but once I removed the whitespaces between the paragraphs, it ran with no problem. I think it might be sensitive to certain special characters.

Answer 2

There is a problem with your script, when it deals with regex and new line. Also, i didnt got the exact use if sentence.pop() ??

change the read_article function with below code..

def read_article(file_name):
    sentences = []
    file = open(file_name, 'r') 
    f_data = file.readlines()
    f_data = [x for x in f_data if x != '\n'] # it should remove any break present
    f_data = [x.replace('\n',' ') for x in f_data] #this would remove that end of line
    f_data = ''.join(f_data) 
    article = f_data.split('. ') 
    for sentence in article:
        sentences.append(sentence.replace("^[a-zA-Z0-9!@#$&()-`+,/\"]", " ").split(" "))
    return sentences