1-liners reference

nlp.load('ner').predict('Angela Merkel from Germany and the American Donald Trump dont share many opinions')

nlp.load('ner.conll').predict('Angela Merkel from Germany and the American Donald Trump dont share many opinions')

nlp.load('pos').predict('Part of speech assigns each token in a sentence a grammatical label')

nlp.load('emotion').predict('I love NLU!')

nlp.load('sentiment').predict("I hate this guy Sami")

nlp.load('en.classify.trec50').predict('How expensive is the Watch?')

nlp.load('en.classify.fakenews').predict('Unicorns have been sighted on Mars!')

nlp.load('en.classify.cyberbullying').predict('Women belong in the kitchen.') # sorry we really don't mean it

nlp.load('en.classify.spam').predict('Please sign up for this FREE membership it costs $$NO MONEY$$ just your mobile number!')

nlp.load('en.classify.sarcasm').predict('gotta love the teachers who give exams on the day after halloween')

nlp.load('en.sentiment.imdb').predict('The Matrix was a pretty good movie')

nlp.load('en.sentiment.twitter').predict('@elonmusk Tesla stock price is too high imo')

nlp.load('lang').predict(['NLU is an open-source text processing library for advanced natural language processing for the Python.','NLU est une bibliothèque de traitement de texte open source pour le traitement avancé du langage naturel pour les langages de programmation Python.'])

nlp.load('e2e').predict('E2E is a dataset for training generative models')

nlp.load('en.classify.toxic').predict('You are to stupid')

nlp.load('yake').predict("NLU is a Python Library for beginners and experts in NLP")

nlp.load('bert').predict('NLU offers the latest embeddings in one line ')

nlp.load('biobert').predict('Biobert was pretrained on a medical dataset')

nlp.load('covidbert').predict('Albert uses a collection of many berts to generate embeddings')

nlp.load('albert').predict('Albert uses a collection of many berts to generate embeddings')

nlp.load('electra').predict('He was suprised by the diversity of NLU')

nlp.load('elmo').predict('Elmo was trained on Left to right masked to learn its embeddings')

nlp.load('xlnet').predict('XLNET computes contextualized word representations using combination of Autoregressive Language Model and Permutation Language Model')

nlp.load('glove').predict('Glove embeddings are generated by aggregating global word-word co-occurrence matrix from a corpus')

#This takes around 10GB RAM, watch out!
nlp.load('bert albert electra elmo xlnet use glove').predict('Get all of them at once! Watch your RAM tough!')

nlp.load('embed_sentence.electra').predict('He was suprised by the diversity of NLU')

nlp.load('use').predict('USE is designed to encode whole sentences and documents into vectors that can be used for text classification, semantic similarity, clustering or oder NLP tasks')

nlp.load('spell').predict('I liek pentut buttr ant jely')

nlp.load('dep.untyped').predict('Untyped Dependencies represent a grammatical tree structure.md')

nlp.load('dep').predict('Typed Dependencies represent a grammatical tree structure.md where every edge has a label')

nlp.load('tokenize').predict('Each word and symbol in a sentence will generate token.')

nlp.load('stem').predict('NLU can get you the stem of a word')

nlp.load('stopwords').predict('I want you to remove stopwords from this sentence please')

nlp.load('lemma').predict('Lemmatizing generates a less noisy version of the inputted tokens')

nlp.load('norm').predict('@CKL_IT says that #normalizers are pretty useful to clean #structured_strings in #NLU like tweets')

nlp.load('ngram').predict('Wht a wondful day!')

nlp.load('match.datetime').predict('In the years 2000/01/01 to 2010/01/01 a lot of things happened')

# First we load the pipeline
pipe = nlp.load('match.chunks')
# Now we print the info to see at which index which com,ponent is and what parameters we can configure on them 
pipe.generate_class_metadata_table()
# Lets set our Chunker to only match NN
pipe['default_chunker'].setRegexParsers(['<NN>+', '<JJ>+'])
# Now we can predict with the configured pipeline
pipe.predict("Jim and Joe went to the big blue market next to the town hall")

nlp.load('sentence_detector').predict('NLU can detect things. Like beginning and endings of sentences. It can also do much more!', output_level ='sentence')  

pipe = nlp.load('norm_document')
data = '<!DOCTYPE html> <html> <head> <title>Example</title> </head> <body> <p>This is an example of a simple HTML page with one paragraph.</p> </body> </html>'
df = pipe.predict(data,output_level='document')
df

pipe = nlp.load('ja.segment_words')
# japanese for 'Donald Trump and Angela Merkel dont share many opinions'
ja_data = ['ドナルド・トランプとアンゲラ・メルケルは多くの意見を共有していません']
df = pipe.predict(ja_data, output_level='token')
df

translate_pipe = nlp.load('xx.en.translate_to.de')
df = translate_pipe.predict('Billy likes to go to the mall every sunday')
df

# Let's download an audio file 
!wget https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/resources/en/audio/samples/wavs/ngm_12484_01067234848.wav
FILE_PATH = "ngm_12484_01067234848.wav"

asr_df = nlp.load('en.speech2text.hubert').predict('ngm_12484_01067234848.wav')
asr_df

# Let's download an audio file 
!wget https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/resources/en/audio/samples/wavs/ngm_12484_01067234848.wav
FILE_PATH = "ngm_12484_01067234848.wav"

asr_df = nlp.load('en.speech2text.wav2vec2.v2_base_960h').predict('ngm_12484_01067234848.wav')
asr_df

import pandas as pd 

context_df = pd.DataFrame({
    'name':['Donald Trump','Elon Musk'], 
    'money': ['$100,000,000','$20,000,000,000,000'], 
    'married': ['yes','no'], 
    'age' : ['75','55'] })
context_df

questions = [
    "Who earns less than 200,000,000?",
    "Who earns more than 200,000,000?",
    "Who earns 100,000,000?",
    "How much money has Donald Trump?",
    "Who is the youngest?",
]
questions

import nlu
# Now we combine both to a tuple and we are done! We can now pass this to the .predict() method
tapas_data  = (context_df, questions)
# Lets load a TAPAS QA model and predict on (context,question). 
# It will give us an aswer for every question in the questions array, based on the context in context_df
answers = nlu.load('en.answer_question.tapas.wtq.large_finetuned').predict(tapas_data)
answers

!wget -q https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/resources/en/images/images.zip
import shutil
shutil.unpack_archive("images.zip", "images", "zip")
! ls /content/images/images/

nlu.load('en.classify_image.base_patch16_224').predict('/content/images/images')

!wget -q https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/resources/en/images/images.zip
import shutil
shutil.unpack_archive("images.zip", "images", "zip")
! ls /content/images/images/

nlu.load('en.classify_image.convnext.tiny').predict('/content/images/images')

!wget -q https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/resources/en/images/images.zip
import shutil
shutil.unpack_archive("images.zip", "images", "zip")
! ls /content/images/images/

nlu.load('en.classify_image.swin.tiny').predict('/content/images/images')

# Set the task on T5
pipe = nlp.load('summarize')

# define Data, add additional tags between sentences
data = [
'''
The belgian duo took to the dance floor on monday night with some friends . manchester united face newcastle in the premier league on wednesday . red devils will be looking for just their second league away win in seven . louis van gaal’s side currently sit two points clear of liverpool in fourth .
''',
'''  Calculus, originally called infinitesimal calculus or "the calculus of infinitesimals", is the mathematical study of continuous change, in the same way that geometry is the study of shape and algebra is the study of generalizations of arithmetic operations. It has two major branches, differential calculus and integral calculus; the former concerns instantaneous rates of change, and the slopes of curves, while integral calculus concerns accumulation of quantities, and areas under or between curves. These two branches are related to each other by the fundamental theorem of calculus, and they make use of the fundamental notions of convergence of infinite sequences and infinite series to a well-defined limit.[1] Infinitesimal calculus was developed independently in the late 17th century by Isaac Newton and Gottfried Wilhelm Leibniz.[2][3] Today, calculus has widespread uses in science, engineering, and economics.[4] In mathematics education, calculus denotes courses of elementary mathematical analysis, which are mainly devoted to the study of functions and limits. The word calculus (plural calculi) is a Latin word, meaning originally "small pebble" (this meaning is kept in medicine – see Calculus (medicine)). Because such pebbles were used for calculation, the meaning of the word has evolved and today usually means a method of computation. It is therefore used for naming specific methods of calculation and related theories, such as propositional calculus, Ricci calculus, calculus of variations, lambda calculus, and process calculus.'''
]


#Predict on text data with T5
pipe.predict(data)

t5 = nlp.load('en.t5.base')
# Set the task on T5
t5['t5'].setTask('stsb ') 

# define Data, add additional tags between sentences
data = [
             
              ''' sentence1:  What attributes would have made you highly desirable in ancient Rome?  
                  sentence2:  How I GET OPPERTINUTY TO JOIN IT COMPANY AS A FRESHER?'
              '''
             ,
             '''  
              sentence1: What was it like in Ancient rome?
              sentence2: 	What was Ancient rome like?
              ''',
              '''  
              sentence1: What was live like as a King in Ancient Rome??
              sentence2: 	What was Ancient rome like?
              '''

             ]



#Predict on text data with T5
t5.predict(data)

pipe = nlp.load('grammar_correctness')
# Set the task on T5
pipe['t5'].setTask('cola sentence: ')
# define Data
data = ['Anna and Mike is going skiing and they is liked is','Anna and Mike like to dance']
#Predict on text data with T5
pipe.predict(data)

model = nlu.load('en.seq2seq.distilbart_cnn_12_6')
# Set the task on T5
model['bart_transformer'].setTask("summarize: ")
model['bart_transformer'].setMaxOutputLength(200)
# define Data
data = '''LONDON, England (Reuters) -- Harry Potter star Daniel Radcliffe gains access to a reported £20 million ($41.1 million) fortune as he turns 18 on Monday, but he insists the money won't cast a spell on him. Daniel Radcliffe as Harry Potter in "Harry Potter and the Order of the Phoenix" To the disappointment of gossip columnists around the world, the young actor says he has no plans to fritter his cash away on fast cars, drink and celebrity parties. "I don't plan to be one of those people who, as soon as they turn 18, suddenly buy themselves a massive sports car collection or something similar," he told an Australian interviewer earlier this month. "I don't think I'll be particularly extravagant. "The things I like buying are things that cost about 10 pounds -- books and CDs and DVDs." At 18, Radcliffe will be able to gamble in a casino, buy a drink in a pub or see the horror film "Hostel: Part II," currently six places below his number one movie on the UK box office chart. Details of how he'll mark his landmark birthday are under wraps. His agent and publicist had no comment on his plans. "I'll definitely have some sort of party," he said in an interview. "Hopefully none of you will be reading about it." Radcliffe's earnings from the first five Potter films have been held in a trust fund which he has not been able to touch. Despite his growing fame and riches, the actor says he is keeping his feet firmly on the ground. "People are always looking to say 'kid star goes off the rails,'" he told reporters last month. "But I try very hard not to go that way because it would be too easy for them." His latest outing as the boy wizard in "Harry Potter and the Order of the Phoenix" is breaking records on both sides of the Atlantic and he will reprise the role in the last two films. Watch I-Reporter give her review of Potter's latest » . There is life beyond Potter, however. The Londoner has filmed a TV movie called "My Boy Jack," about author Rudyard Kipling and his son, due for release later this year. He will also appear in "December Boys," an Australian film about four boys who escape an orphanage. Earlier this year, he made his stage debut playing a tortured teenager in Peter Shaffer's "Equus." Meanwhile, he is braced for even closer media scrutiny now that he's legally an adult: "I just think I'm going to be more sort of fair game," he told Reuters. E-mail to a friend . Copyright 2007 Reuters. All rights reserved.This material may not be published, broadcast, rewritten, or redistributed.'''
#Predict on text data with T5
df = model.predict(data)

nlp.load('answer_question').predict("""
Where did Jebe die?
context: Ghenkis Khan recalled Subtai back to Mongolia soon afterwards,
 and Jebe died on the road back to Samarkand""")
>>> Output: Samarkand

question ='''
What does increased oxygen concentrations in the patient’s lungs displace? 
context: Hyperbaric (high-pressure) medicine uses special oxygen chambers to increase the partial pressure of O 2 around the patient and, when needed, the medical staff. 
Carbon monoxide poisoning, gas gangrene, and decompression sickness (the ’bends’) are sometimes treated using these devices. Increased O 2 concentration in the lungs helps to displace carbon monoxide from the heme group of hemoglobin.
 Oxygen gas is poisonous to the anaerobic bacteria that cause gas gangrene, so increasing its partial pressure helps kill them. Decompression sickness occurs in divers who decompress too quickly after a dive, resulting in bubbles of inert gas, mostly nitrogen and helium, forming in their blood. Increasing the pressure of O 2 as soon as possible is part of the treatment.
'''


#Predict on text data with T5
nlp.load('answer_question').predict(question)
>>> Output: carbon monoxide	

question1 = 'Who is Jack ma?'
question2 = 'Who is founder of Alibaba Group?'
question3 = 'When did Jack Ma re-appear?'
question4 = 'How did Alibaba stocks react?'
question5 = 'Whom did Jack Ma meet?'
question6 = 'Who did Jack Ma hide from?'

# from https://www.bbc.com/news/business-55728338 
news_article_snippet = """ context:
Alibaba Group founder Jack Ma has made his first appearance since Chinese regulators cracked down on his business empire.
His absence had fuelled speculation over his whereabouts amid increasing official scrutiny of his businesses.
The billionaire met 100 rural teachers in China via a video meeting on Wednesday, according to local government media.
Alibaba shares surged 5% on Hong Kong's stock exchange on the news.
"""
# join question with context, works with Pandas DF aswell!
questions = [
             question1+ news_article_snippet,
             question2+ news_article_snippet,
             question3+ news_article_snippet,
             question4+ news_article_snippet,
             question5+ news_article_snippet,
             question6+ news_article_snippet,]
nlp.load('answer_question').predict(questions)

nlp.load('en.t5').predict('Who is president of Nigeria?')
>>> Muhammadu Buhari 

nlp.load('en.t5').predict('What is the most spoken language in India?')
>>> Hindi

nlp.load('en.t5').predict('What is the capital of Germany?')
>>> Berlin