NATURAL LANGUAGE PROCESSING RECIPES : unlocking text data with machine learning and deep... learning using python

Focus on implementing end-to-end projects using Python and leverage state-of-the-art algorithms. This book teaches you to efficiently use a wide range of natural language processing (NLP) packages to: implement text classification, identify parts of speech, utilize topic modeling, text summarization, sentiment analysis, information retrieval, and many more applications of NLP. The book begins with text data collection, web scraping, and the different types of data sources. It explains how to clean and pre-process text data, and offers ways to analyze data with advanced algorithms. You then explore semantic and syntactic analysis of the text. Complex NLP solutions that involve text normalization are covered along with advanced pre-processing methods, POS tagging, parsing, text summarization, sentiment analysis, word2vec, seq2seq, and much more. The book presents the fundamentals necessary for applications of machine learning and deep learning in NLP. This second edition goes over advanced techniques to convert text to features such as Glove, Elmo, Bert, etc. It also includes an understanding of how transformers work, taking sentence BERT and GPT as examples. The final chapters explain advanced industrial applications of NLP with solution implementation and leveraging the power of deep learning techniques for NLP problems. It also employs state-of-the-art advanced RNNs, such as long short-term memory, to solve complex text generation tasks. After reading this book, you will have a clear understanding of the challenges faced by different industries and you will have worked on multiple examples of implementing NLP in the real world. **What You Will Learn*** Know the core concepts of implementing NLP and various approaches to natural language processing (NLP), including NLP using Python libraries such as NLTK, textblob, SpaCy, Standford CoreNLP, and more * Implement text pre-processing and feature engineering in NLP, including advanced methods of feature engineering * Understand and implement the concepts of information retrieval, text summarization, sentiment analysis, text classification, and other advanced NLP techniques leveraging machine learning and deep learning **Who This Book Is For** Data scientists who want to refresh and learn various concepts of natural language processing (NLP) through coding exercises Table of Contents About the Authors About the Technical Reviewer Acknowledgments Introduction Chapter 1: Extracting the Data Introduction Client Data Free Sources Web Scraping Recipe 1-1. Collecting Data Problem Solution How It Works Step 1-1. Log in to the Twitter developer portal Step 1-2. Execute query in Python Recipe 1-2. Collecting Data from PDFs Problem Solution How It Works Step 2-1. Install and import all the necessary libraries Step 2-2. Extract text from a PDF file Recipe 1-3. Collecting Data from Word Files Problem Solution How It Works Step 3-1. Install and import all the necessary libraries Step 3-2. Extract text from a Word file Recipe 1-4. Collecting Data from JSON Problem Solution How It Works Step 4-1. Install and import all the necessary libraries Step 4-2. Extract text from a JSON file Recipe 1-5. Collecting Data from HTML Problem Solution How It Works Step 5-1. Install and import all the necessary libraries Step 5-2. Fetch the HTML file Step 5-3. Parse the HTML file Step 5-4. Extract a tag value Step 5-5. Extract all instances of a particular tag Step 5-6. Extract all text from a particular tag Recipe 1-6. Parsing Text Using Regular Expressions Problem Solution How It Works Tokenizing Extracting Email IDs Replacing Email IDs Extracting Data from an eBook and Performing regex Recipe 1-7. Handling Strings Problem Solution How It Works Replacing Content Concatenating Two Strings Searching for a Substring in a String Recipe 1-8. Scraping Text from the Web Problem Solution How It Works Step 8-1. Install all the necessary libraries Step 8-2. Import the libraries Step 8-3. Identify the URL to extract the data Step 8-4. Request the URL and download the content using Beautiful Soup Step 8-5. Understand the website’s structure to extract the required information Step 8-6. Use Beautiful Soup to extract and parse the data from HTML tags Step 8-7. Convert lists to a data frame and perform an analysis that meets business requirements Step 8-8. Download the data frame Chapter 2: Exploring and Processing Text Data Recipe 2-1. Converting Text Data to Lowercase Problem Solution How It Works Step 1-1. Read/create the text data Step 1-2. Execute the lower() function on the text data Recipe 2-2. Removing Punctuation Problem Solution How It Works Step 2-1. Read/create the text data Step 2-2. Execute the replace() function on the text data Recipe 2-3. Removing Stop Words Problem Solution How It Works Step 3-1. Read/create the text data Step 3-2. Remove punctuation from the text data Recipe 2-4. Standardizing Text Problem Solution How It Works Step 4-1. Create a custom lookup dictionary Step 4-2. Create a custom function for text standardization Step 4-3. Run the text_std function Recipe 2-5. Correcting Spelling Problem Solution How It Works Step 5-1. Read/create the text data Step 5-2. Execute spelling correction on the text data Recipe 2-6. Tokenizing Text Problem Solution How It Works Step 6-1. Read/create the text data Step 6-2. Tokenize the text data Recipe 2-7. Stemming Problem Solution How It Works Step 7-1. Read the text data Step 7-2. Stem the text Recipe 2-8. Lemmatizing Problem Solution How It Works Step 8-1. Read the text data Step 8-2. Lemmatize the data Recipe 2-9. Exploring Text Data Problem Solution How It Works Step 9-1. Read the text data Step 9-2. Import necessary libraries Step 9-3 Check the number of words in the data Step 9-4. Compute the frequency of all words in the reviews Step 9-5. Consider words with length greater than 3 and plot Step 9-6. Build a word cloud Recipe 2-10. Dealing with Emojis and Emoticons Problem Solution How It Works Step 10-A1. Read the text data Step 10-A2. Install and import necessary libraries Step 10-A3. Write a function that coverts emojis into words Step 10-A4. Pass text with an emoji to the function Problem Solution How It Works Step 10-B1. Read the text data Step 10-B2. Install and import necessary libraries Step 10-B3. Write a function to remove emojis Step 10-B4. Pass text with an emoji to the function Problem Solution How It Works Step 10-C1. Read the text data Step 10-C2. Install and import necessary libraries Step 10-C3. Write function to convert emoticons into word Step 10-C4. Pass text with emoticons to the function Problem Solution How It Works Step 10-D1 Read the text data Step 10-D2. Install and import necessary libraries Step 10-D3. Write function to remove emoticons Step 10-D4. Pass text with emoticons to the function Problem Solution How It Works Step 10-E1. Read the text data Step 10-E2. Install and import necessary libraries Step 10-E3. Find all emojis and determine their meaning Recipe 2-11. Building a Text Preprocessing Pipeline Problem Solution How It Works Step 11-1. Read/create the text data Step 11-2. Process the text Chapter 3: Converting Text to Features Recipe 3-1. Converting Text to Features Using One-Hot Encoding Problem Solution How It Works Step 1-1. Store the text in a variable Step 1-2. Execute a function on the text data Recipe 3-2. Converting Text to Features Using a Count Vectorizer Problem Solution How It Works Recipe 3-3. Generating n-grams Problem Solution How It Works Step 3-1. Generate n-grams using TextBlob Step 3-2. Generate bigram-based features for a document Recipe 3-4. Generating a Co-occurrence Matrix Problem Solution How It Works Step 4-1. Import the necessary libraries Step 4-2. Create function for a co-occurrence matrix Step 4-3. Generate a co-occurrence matrix Recipe 3-5. Hash Vectorizing Problem Solution How It Works Step 5-1. Import the necessary libraries and create a document Step 5-2. Generate a hash vectorizer matrix Recipe 3-6. Converting Text to Features Using TF-IDF Problem Solution How It Works Step 6-1. Read the text data Step 6-2. Create the features Recipe 3-7. Implementing Word Embeddings Problem Solution How It Works skip-gram Continuous Bag of Words (CBOW) Recipe 3-8. Implementing fastText Problem Solution How It Works Recipe 3-9. Converting Text to Features Using State-of-the-Art Embeddings Problem Solution ELMo Sentence Encoders doc2vec Sentence-BERT Universal Encoder InferSent Open-AI GPT How It Works Step 9-1. Import a notebook and data to Google Colab Step 9-2. Install and import libraries Step 9-3. Read text data Step 9-4. Process text data Step 9-5. Generate a feature vector Sentence-BERT Universal Encoder Infersent Open-AI GPT Step 9-6. Generate a feature vector function automatically using a selected embedding method Chapter 4: Advanced Natural Language Processing Recipe 4-1. Extracting Noun Phrases Problem Solution How It Works Recipe 4-2. Finding Similarity Between Texts Solution How It Works Step 2-1. Create/read the text data Step 2-2. Find similarities Phonetic Matching Recipe 4-3. Tagging Part of Speech Problem Solution How It Works Step 3-1. Store the text in a variable Step 3-2. Import NLTK for POS Recipe 4-4. Extracting Entities from Text Problem Solution How It Works Step 4-1. Read/create the text data Step 4-2. Extract the entities Using NLTK Using spaCy Recipe 4-5. Extracting Topics from Text Problem Solution How It Works Step 5-1. Create the text data Step 5-2. Clean and preprocess the data Step 5-3. Prepare the document term matrix Step 5-4. Create the LDA model Recipe 4-6. Classifying Text Problem Solution How It Works Step 6-1. Collect and understand the data Step 6-2. Text processing and feature engineering Step 6-3. Model training Recipe 4-7. Carrying Out Sentiment Analysis Problem Solution How It Works Step 7-1. Create the sample data Step 7-2. Clean and preprocess the data Step 7-3. Get the sentiment scores Recipe 4-8. Disambiguating Text Problem Solution How It Works Step 8-1. Import libraries Step 8-2. Disambiguate word sense Recipe 4-9. Converting Speech to Text Problem Solution How It Works Step 9-1. Define the business problem Step 9-2. Install and import necessary libraries Step 9-3. Run the code Recipe 4-10. Converting Text to Speech Problem Solution How It Works Step 10-1. Install and import necessary libraries Step 10-2. Run the code with the gTTs function Recipe 4-11. Translating Speech Problem Solution How It Works Step 11-1. Install and import necessary libraries Step 11-2. Input text Step 11-3. Run the goslate function Chapter 5: Implementing Industry Applications Recipe 5-1. Implementing Multiclass Classification Problem Solution How It Works Step 1-1. Get the data from Kaggle Step 1-2. Import the libraries Step 1-3. Import the data Step 1-4. Analyze the date Step 1-5. Split the data Step 1-6. Use TF-IDF for feature engineering Step 1-7. Build the model and evaluate Recipe 5-2. Implementing Sentiment Analysis Problem Solution How It Works Step 2-1. Define the business problem Step 2-2. Identify potential data sources and extract insights Step 2-3. Preprocess the data Step 2-4. Analyze data Step 2-5. Use a pre-trained model Step 2-6. Do sentiment analysis Step 2-7. Get business insights Recipe 5-3. Applying Text Similarity Functions Problem Solution How It Works Step 3a-1. Read and understand the data Step 3a-2. Extract a blocking key Step 3a-3. Do similarity matching and scoring Step 3a-4. Predict if records match using ECM classifier Records of same customers from multiple tables Step 3b-1. Read and understand the data Step 3b-2. Block to reduce the comparison window and create record pairs Step 3b-3. Do similarity matching Step 3b-4. Predict if records match using ECM classifier Recipe 5-4. Summarizing Text Data Problem Solution How It Works Step 4-1. Use TextRank Step 4-2. Use feature-based text summarization Recipe 5-5. Clustering Documents Problem Solution How It Works Step 5-1. Import data and libraries Step 5-2. Preprocess and use TF-IDF feature engineering Step 5-3. Cluster using k-means Step 5-4. Identify cluster behavior Step 5-5. Plot the clusters on a 2D graph Recipe 5-6. NLP in a Search Engine Problem Solution How It Works Step 6-1. Preprocess Step 6-2. Use the entity extraction model Step 6-3. Do query enhancement/expansion Step 6-4. Use a search platform Step 6-5. Learn to rank Recipe 5-7. Detecting Fake News Problem Solution How It Works Step 7-1. Collect data Step 7-2. Install libraries Step 7-3. Analyze the data Step 7-4. Do exploratory data analysis Step 7-5. Preprocess the data Step 7-6. Use train_test_split Step 7-7. Do feature engineering Step 7-8. Build a model Model Evaluation Step 7-9. Tune hyperparameters Step 7-10. Validate Summary Recipe 5-8. Movie Genre Tagging Problem Solution Approach Flow How It Works Step 8-1. Collect data Step 8-2. Install libraries Step 8-3. Analyze the data Step 8-4. Do exploratory data analysis Step 8-5. Preprocess the data Step 8-6. Use train_test_split Step 8-7. Do feature engineering Step 8-8. Do model building and prediction Problem Transformation Binary Relevance Classifier Chains Label Powerset Adapted Algorithm Chapter 6: Deep Learning for NLP Introduction to Deep Learning Convolutional Neural Networks Data Architecture Convolution Nonlinearity (ReLU) Pooling Flatten, Fully Connected, and Softmax Layers Backpropagation: Training the Neural Network Recurrent Neural Networks Training RNN: Backpropagation Through Time (BPTT) Long Short-Term Memory (LSTM) Recipe 6-1. Retrieving Information Problem Solution How It Works Step 1-1. Import the libraries Step 1-2. Create or import documents Step 1-3. Download word2vec Step 1-4. Create an IR system Step 1-5. Results and applications Recipe 6-2. Classifying Text with Deep Learning Problem Solution How It Works Step 2-1. Define the business problem Step 2-2. Identify potential data sources and collect Step 2-3. Preprocess text Step 2-4. Prepare the data for model building Step 2-5. Model building and predicting Recipe 6-3. Next Word Prediction Problem Solution How It Works Step 3-1. Define the business problem Step 3-2. Identify potential data sources and collect Step 3-3. Import and install necessary libraries Step 3-4. Process the data Step 3-5. Prepare data for modeling Step 3-6. Build the model Step 3-7. Predict the next word Recipe 6-4. Stack Overflow question recommendation Problem Solution How It Works Step 4-1. Collect data Step 4-2. Import Notebook and data to Google Colab Step 4-3. Import the libraries Step 4-4. Import the data and EDA Step 4-5. Clean the text data Step 4-6. Use TFIDF for feature engineering Step 4-7. Use GloVe embeddings for feature engineering Step 4-8. Use GPT for feature engineering Step 4-9. Use Sentence-BERT for feature engineering Step 4-10. Create functions to fetch top questions Step 4-11. Preprocess user input Step 4-12. Find similar questions Chapter 7: Conclusion and Next-Gen NLP Recipe 7-1. Recent advancements in text to features or distributed representations Problem Solution Recipe 7-2. Advanced deep learning for NLP Problem Solution Recursive Neural Networks Deep Generative Models Recipe 7-3. Reinforcement learning applications in NLP Problem Solution Exploration vs. Exploitation Trade-off Temporal Difference Recipe 7-4. Transfer learning and pre-trained models Problem Solution Why Do We Need to Transfer Learning NLP? A New Era of Embeddings ULMFiT: Transfer Learning in NLP Transformers: Beyond LSTM flair Why BERT? BERT and RNN BERT vs. LSTM BERT vs. OpenAI GPT Recipe 7-5. Meta-learning in NLP Problem Solution Recipe 7-6. Capsule networks for NLP Problem Solution Multitasking in NLP Index