>>>import nltk 

>>>nltk.download('wordnet') 
>>>quit()

from nltk.corpus import wordnet # WordNet is a lexical database for the English language, specifically designed for natural language processing.
"""Define a word using WordNet"""
def defineWordNet(word):
    try:
        syns = wordnet.synsets(word) # It looks up a word and returns a list of synsets (synonymous words that express the same concept, e.g. beloved) using wordnet.synsets().
        for syn in syns:
           print(syn.name(), ":", syn.definition(), ".", syn.examples()) # It prints the name, definition, and examples for each synset in the list.
        
    except:
        return "No definition found."
if __name__ == '__main__':
    defineWordNet("love")

from nltk.corpus import wordnet # WordNet is a lexical database for the English language, specifically designed for natural language processing.
def synonymsAntonyms(word):
    antonyms = []
    synonyms = []

    syns = wordnet.synsets(word) # It looks up a word and returns a list of synsets
    for syn in syns:
        for lemma in syn.lemmas(): # A lemma is the canonical or dictionary form of a word. It represents a specific sense of a word. 
            synonyms.append(lemma.name().lower()) # Since all the lemmas in our list of synsets have the same meaning, they can be treated as synonyms.
            if lemma.antonyms(): # We use the method antonyms() to find the antonyms for the lemmas. 
                antonyms.append(lemma.antonyms()[0].name().lower())
    
    print("\nantonyms(" + word + ")", set(antonyms)) # We use sets to remove duplicates.
    print("\nsynonyms(" + word + ")", set(synonyms))
if __name__ == '__main__':
    synonymsAntonyms("friend")

user@pc:~$ python
Python 3.9.5 (default, May 11 2021, 08:20:37) 
[GCC 10.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from nltk.tokenize import sent_tokenize, word_tokenize
>>> example = "I love cats and dogs very much. I like fluffy because they're cute."
>>> sent_tokenize(example) # We use sent_tokenize() to split up example into sentences.
['I love cats and dogs very much.', "I like fluffy because they're cute."]
>>> words = [word_tokenize(sentence) for sentence in sent_tokenize(example)] # We use word_tokenize() to split up sentences into words.
>>> words
[['I', 'love', 'cats', 'and', 'dogs', 'very', 'much', '.'], ['I', 'like', 'fluffy', 'because', 'they', "'re", 'cute', '.']]

>>> from nltk.corpus import stopwords # nltk.corpus has a list of stopwords stored in different languages
>>> stop_words = set(stopwords.words("english")) # {'from', "weren't", 'below', 'so', 'couldn', 'for', 'had', 'doing', "couldn't", 'now', 'shouldn', 'having', 'same', 'that', 'his', 'them', 'doesn', 'me', 'to', 'shan', 'our', 'own', 'yourselves', 'or', 'do'....}
>>> import itertools
word_list = list(itertools.chain.from_iterable(words)) # word_list is a simple list of words out of a list of lists (words)
content_words = []
filtered_words = []
>>> for word in word_list: # It iterates over word_list with a for loop
...     if word.lower() not in stop_words: # We use the method lower() to ignore whether the letters in word are uppercase or lowercase
...             content_words.append(word)
...     else:
...             filtered_words.append(word)
... 
>>> content_words
['love', 'cats', 'dogs', 'much', '.', 'like', 'fluffy', "'re", 'cute', '.']
>>> filtered_words
['I', 'and', 'very', 'I', 'because', 'they'] # We have filtered out a few words like "I" and "and".

>>> from nltk.stem import PorterStemmer # Stemmers remove morphological affixes from words, leaving only the word stem.
>>> stemmer = PorterStemmer() # It create a new Porter stemmer.
>>> stemmed_words = [stemmer.stem(word) for word in word_list]
>>> stemmed_words
['I', 'love', 'cat', 'and', 'dog', 'veri', 'much', '.', 'I', 'like', 'fluffi', 'becaus', 'they', "'re", 'cute', '.']

>>> import nltk # Previously, you need to use the NLTK Downloader to obtain averaged_perceptron_tagger:  >>> import nltk, >>> nltk.download('averaged_perceptron_tagger')
>>> nltp.pos_tag(word_list)
[('I', 'PRP'), ('love', 'VBP'), ('cats', 'NNS'), ('and', 'CC'), ('dogs', 'NNS'), ('very', 'RB'), ('much', 'RB'), ('.', '.'), ('I', 'PRP'), ('like', 'VBP'), ('fluffy', 'RB'), ('because', 'IN'), ('they', 'PRP'), ("'re", 'VBP'), ('cute', 'NN'), ('.', '.')]
``` python
nltk.help.upenn_tagset() (>>> import nltk, >>> nltk.download('tagsets')) gives you the list of tags and their meanings, e.g. VBP: verb, present tense, not 3rd person singular; NNS: noun, common, plural; CC: conjunction, coordinating.

>>> from nltk.book import * # It requires nltk.download("book"). It loads the text of several books.
*** Introductory Examples for the NLTK Book ***
Loading text1, ..., text9 and sent1, ..., sent9
Type the name of the text or sentence to view it.
Type: 'texts()' or 'sents()' to list the materials.
text1: Moby Dick by Herman Melville 1851
text2: Sense and Sensibility by Jane Austen 1811
text3: The Book of Genesis
text4: Inaugural Address Corpus
text5: Chat Corpus
text6: Monty Python and the Holy Grail
text7: Wall Street Journal
text8: Personals Corpus
text9: The Man Who Was Thursday by G . K . Chesterton 1908
>>> text3.count("multiply") # the method count() counts the total appearances of a given word in a text
18
>>> text3.concordance("multiply") # A concordance permits us to see words in context.

>>> text4.similar("liberty") # The similar method takes an input word and returns other words that appear in a similar range of contexts in the text. 
peace government freedom power life war duty congress all them it us
progress prosperity america history civilization which time men

>>> text4.common_contexts(["liberty", "constitution"]) # The method common_contexts allows us to examine the contexts that are shared by two or more words, such as liberty and constitution. 
our_and the_of # Liberty and constitution are usually surrounded by "our_and" and "the_of".
>>>> print(text2.generate()) # It prints random text, generated using a trigram language model.

>>> text3.dispersion_plot(
...     ["man", "woman", "Abraham", "Lord", "God", "love", "multiply", "created"] ) # You need to have Python's NumPy and Matplotlib packages installed.

>>> from nltk.corpus import stopwords # nltk.corpus has a list of stopwords stored in different languages
>>> import nltk
>>> from nltk.book import *
>>> stop_words = set(stopwords.words("english"))
>>> meaningful_words = []
>>> for word in text3: # It iterates over text3 with a for loop
...     if word.lower() not in stop_words and word.isalnum(): # We use the method lower() to ignore whether the letters in word are uppercase or lowercase, and the method isalnum() to remove all punctuation marks
...             meaningful_words.append(word)
>>> from nltk import FreqDist # A frequency distribution is used to study which words show up most frequently in a text.
>>> frequency_distribution = FreqDist(meaningful_words) # We are going to study the frequency distribution of words that are not stop words or punctuation marks. 
>>> frequency_distribution.most_common(20) # Furthermore, we are going to study the frequency distribution of the 20 most common words in Genesis that are not stop words or punctuation marks.
[('unto', 590), ('said', 476), ('thou', 272), ('thy', 267), ('thee', 257), ('shall', 253), ('God', 231), ('father', 198), ('land', 184), ('Jacob', 179), ('came', 177), ('LORD', 166), ('Joseph', 157), ('son', 152), ('sons', 142), ('upon', 139), ('Abraham', 129), ('man', 114), ('earth', 111), ('went', 110)]
>>> frequency_distribution.plot(20, cumulative=False) # We plot the frequency distribution of the 20 most common words in Genesis.

>>> text3.collocation_list() # A collocation is a sequence of words or terms that co-occur more often than would be expected by chance. The collocation_list method returns a list of collocation words with the default size of 2.
[('said', 'unto'), ('pray', 'thee'), ('thou', 'shalt'), ('thou', 'hast'), ('thy', 'seed'), ('years', 'old'), ('spake', 'unto'), ('thou', 'art'), ('LORD', 'God'), ('every', 'living'), ('God', 'hath'), ('begat', 'sons'), ('seven', 'years'), ('shalt', 'thou'), ('little', 'ones'), ('living', 'creature'), ('creeping', 'thing'), ('savoury', 'meat'), ('thirty', 'years'), ('every', 'beast')]
>>> len(text4) # It calculates the length of a text from start to finish
149797 # The Inaugural Address Corpus has 149797 words and punctuation symbols or tokens.
>>> len(set(text4)) # The vocabulary of a text is the set of tokens (or unique words) that it uses. The same result could have been obtained by: len(text4.vocab()) 
9913 # The Inaugural Address Corpus has 9913 distinct words and punctuation symbols.
>>> len(set(text4)) / len(text4) # It calculates a measure of the lexical richness of the text.
0.06617622515804722

>>> from nltk.sentiment import SentimentIntensityAnalyzer # It requires >>> nltk.download('vader_lexicon')
>>> sia = SentimentIntensityAnalyzer() # It creates an instance of a SentimentIntensityAnalyzer.
>>> sia.polarity_scores("Wow, this food is so tasty and yummy!")
{'neg': 0.0, 'neu': 0.436, 'pos': 0.564, 'compound': 0.8297}

>>> sia.polarity_scores("This is so yucky it makes me puke!")
{'neg': 0.549, 'neu': 0.451, 'pos': 0.0, 'compound': -0.8078}
>>> sia.polarity_scores("Cauliflower and broccoli are both cabbages")
{'neg': 0.0, 'neu': 1.0, 'pos': 0.0, 'compound': 0.0}