Natural Language Processing, or NLP for short, is broadly defined as the automatic manipulation of natural language, like speech and text, by software. NLP is about taking raw text data and deriving insights and value from it--processing text data using standard techniques in Natural Language Processing and Machine Learning. Text data is available in abundance on the Internet, whether it be reviews, tweets, surveys, web pages or emails. Natural language processing is a powerful skill that helps us derive immense value from that data. In this course, you'll first learn about using the Natural Language Toolkit to pre-process raw text. Next, you'll learn how to auto-summarize text using machine learning. You'll wrap up the course by exploring how to classify text using machine learning. By the end of this course you'll be able to confidently process raw text data and apply machine learning algorithms to it.
You will also learn some of the most advanced techniques of Data Science like Deep learning using Tensor flow package. From self-driving cars to medical diagnoses, from face recognition to deep fakes, and from language translation to music generation, deep learning is spreading like wildfire throughout all areas of modern technology.
But deep learning is not only about super-fancy, cutting-edge, highly sophisticated applications. Deep learning is increasingly becoming a standard tool in machine-learning, data science, and statistics. Deep learning is used by small startups for data mining and dimension reduction, by governments for detecting tax evasion, and by scientists for detecting patterns in their research data. Deep learning is now used in most areas of technology, business, and entertainment. And it's becoming more important every year.
You will also learn the most advanced technique of tree based algorithm, Extreme Gradient Boosting. Sometimes, it’s debated whether XG Boost is better than Artificial Neural Network but the students are going to have both these advanced level algorithms in their arsenal.
We have also included Market Basket Analysis, and some of the popular linear and non-linear classification techniques like KNN, SVM, and Naïve Bayes. You will also get to learn one of the most popular variable reduction technique like Principal component analysis.
Introduction to Python Text Basics
Working with Text Files with Python - Part One
Working with Text Files with Python - Part Two
Introduction to Natural Language Processing
Spacy Setup and Overview
What is Natural Language Processing?
Spacy Basic
Tokenization
Stemming
Lemmatization
Stop Words
Phrase Matching and Vocabulary - Part One
Phrase Matching and Vocabulary - Part Two
Part of Speech Tagging and Entity Recognition
Introduction to POS & NER
Named Entity Recognition - Part One
Named Entity Recognition - Part Two
Sentence Segmentation
Introduction to semantics and sentiment analysis
Overview of Semantics and Word Vectors
Semantics and Word Vectors with Spacy
Sentiment Analysis Overview
Sentiment Analysis with NLTK
Sentiment Analysis Code Along Movie Review Project
Sentiment Analysis Code - Capstone Project
Topic Modeling
Introduction to Topic Modeling Section
Latent Dirichlet Allocation Overview
Latent Dirichlet Allocation with Python - Part One
Latent Dirichlet Allocation with Python - Part Two
Non-negative Matrix Factorization with Python
Topic Modeling Project - Capstone Project
Introduction to KNN
Theory of KNN
Using KNN to classify in Python
Validation of the model
Project work with KNN
Introduction to SVM
Theory of SVM
Using SVM to classify in Python
Validation of the model
Kernel trick of SVM to increase accuracy
Learn about different kernel
Project work with KNN
Introduction to Naïve Bayes
Theory of Naïve Bayes
Using Naïve Bayes to classify in Python
Validation of the model
Project work with Naïve Bayes
Introduction to MBA
Theory of MBA
Lift, support & confidence
Create recommendation with MBA
Project work with MBA
Introduction to PCA
Theory of PCA
How many components are considered?
Loading of components
Project work with PCA
Keras and Tensorflow
The neuron
The activation function
How do neural network learn
Gradient Descent
Backpropagation
ANN for regression
ANN for classification
Project work on ANN regression
Project work on ANN classification
XGBoost intuition
Create XGBoost matrices
Setting up parameters
Predicting with XGBoost
Validation of the model
Tuning of parameters
Cross validation
Driver importance
Project work on XGBoost