Develop-Packt's repositories
Hotspot-Analysis
We will visualize the results of hotspot analysis and use kernel density estimation, which is the most popular algorithm for building distributions using a collection of observations. By the end of the course, you should be able to leverage Python libraries to build multi-dimensional density estimation models and work with geo-spatial data.
Topic-Modeling-and-Theme-Extraction
In this module you will learn how to analyze topic modeling output from Amazon Comprehend, then perform topic modeling on two documents with a known topic structure.
Analyzing-Documents-and-Text-with-Natural-Language-Processing
In this module you will look at AWS AI services and examine an emerging computing paradigm – the Serverless Computing. We will then proceed to applying NLP and the Amazon Comprehend service to analyze documents.
Analyzing-the-Bank-Marketing-Dataset
Analyze marketing campaign data related to new financial products. Discover linear and logistic regression models, and explore the relationships between the different features in the data
Analyzing-the-Heart-Disease-Dataset
Identify missing values, outliers and trends in medical data. Create bar charts, heatmaps and other visualizations to understand how the features impact the target column of the data set
Analyzing-the-Sequence-of-Data-with-RNNs-Using-PyTorch
Understand the learning process of RNNs and discover the LSTM network architecture. Solve problems and perform Natural Language Processing using sequences of data
Autoencoders
This course will take a look at autoencoders and their applications will help you see how autoencoders are used in dimensionality reduction and denoising. You will implement an artificial neural network and an autoencoder using the Keras framework. By the end of this course, you will be able to implement an autoencoder model using convolutional neural networks.
Building-A-Trained-Model
This module will cover the key stages involved in building a comprehensive program. It also explains how to build and save a model such that you get the same results every time it is run and call a saved model to use it for predictions on unseen data.
Clustering
This module covers the concept of clustering in machine learning. It explains three of the most common clustering algorithms, with a hands-on approximation to solve a real-life data problem. The three clustering algorithms covered are k-means, mean-shift and DBSCAN algorithms.
Discovering-the-Building-Blocks-of-Neural-Networks-with-PyTorch
Discover the main building blocks of neural networks and understand the three main neural network architectures. Explore the process of solving a regression data problem
Evaluating-the-Bitcoin-Model
This module covers you can improve the performance by modifying the network's hyperparameters. It also covers different functions and techniques to evaluate the model
Exploring-Absenteeism-at-Work
Estimate conditional probabilities, compare data distributions, and perform data transformations to analyze employee absences
Exploring-the-Online-Retail-Dataset
Search for and deal with missing values, outliers, and anomalies in an online retail dataset. Create new columns from existing data and design visualizations to demonstrate your findings
Hierarchical-Clustering
You will learn to use hierarchical clustering to build stronger groupings which make more logical sense. This course teaches you how to build a hierarchy, apply linkage criteria, and implement hierarchical clustering
Identifying-Online-Shoppers-Purchase-Intentions
Perform univariate and bivariate analysis to analyze the behavior of online shoppers. Learn how to implement clustering and make recommendations based on the prediction
Introduction-to-AWS
This chapter will introduce you to the Amazon Web Service interface and will teach you how to store and retrieve data with Amazon Simple Storage Service (S3).
Introduction-to-Clustering
This course teaches you how to calculate distance metrics, form and identify clusters in a dataset, implement k-means clustering from scratch and analyze clustering performance by calculating the silhouette score
Introduction-to-Convolutional-Neural-Networks-with-PyTorch
Use CNNs to solve image classification problems using PyTorch. Improve your model's performance by applying data augmentation and batch normalization.
Introduction-to-Deep-Learning-and-PyTorch
Explore some of the most popular applications of deep learning, understand what PyTorch is, and use PyTorch to build a simple single-layer network.
Introduction-to-Scikit-Learn
This module covers scikit-learn's syntax to solve simple data problem, which will be the starting point to develop machine learning solutions
Investigating-Air-Quality-in-Beijing
Perform EDA on an air quality dataset. Identify relationships in the data and discover trends in pollutant levels over time
Key-Concepts-of-Supervised-Learning
This module covers the main steps for working on a supervised machine learning problems, classification and regression. It will also cover how to effectively create unbiased models that perform well over unseen data.
Market-Basket-Analysis
Market basket analysis unlocks the underlying relationships between the items that customers purchase. By the end of this course, you should have a solid grasp of transaction data, the basic metrics that define the relationship between two items, the Apriori algorithm, and associations rules.
Performing-Bike-Sharing-Analysis
Analyze data from bike sharing services to identify usage patterns. Implement visual analysis, hypothesis testing, and time series analysis
Performing-Style-Transfer-with-PyTorch
Perform style transfer using pretrained models. Create well-performing algorithms without having to gather large quantities of data.
Predicting-the-Energy-Usage-of-Household-Appliances
Analyze the energy consumed by household appliances. Explore individual features to assess whether the data is skewed and perform feature engineering to create new features
Predicting-the-Price-of-Bitcoin
This module covers how to assemble a complete deep learning system, from gathering data to prediction. We will use Keras make predictions with the trained model
Solving-a-Classification-Problem-with-DNNs-Using-PyTorch
Make use of PyTorch's custom modules to define a network architecture and train a model. Investigate how to improve a model's performance and deploy your model for wider use.
Supervised-Learning-Algorithms
This module explores three different supervised learning algorithms used for classification. It also takes a step-by-step approach to solve a supervised learning classification problem using these algorithms and perform error analysis by comparing the results of the three different algorithms.
Topic-Modeling
You will evaluate latent Dirichlet allocation models and execute non-negative matrix factorization models. Finally, you will interpret the results of topic models and identify the best topic model for the given scenario. You will see how topic modelling provides insights into the underlying structure of documents. By the end of this course, you will be able to build fully functioning topic models to derive value and insights for your business