Effective Prediction with Machine Learning – Second Edition

Effective Prediction with Machine Learning – Second Edition

English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 1h 32m | 376 MB

A one-stop solution to quickly program fast Machine Learning algorithms with NumPy and scikit-learn

Scikit-learn has evolved as a robust library for machine learning applications in Python with support for a wide range of supervised and unsupervised learning algorithms.

This course begins by taking you through videos on evaluating the statistical properties of data and generating synthetic data for machine learning modeling. As you progress through the sections, you will come across videos that will teach you to implement techniques such as data pre-processing, linear regression, logistic regression, and K-NN. You will also look at Pre-Model and Pre-Processing workflows, to help you choose the right models.

Finally, you’ll explore dimensionality reduction with various parameters.

This course consists of practical videos on scikit-learn that target novices as well as intermediate users. It explores technical issues in depth, covers additional protocols, and supplies many more real-life examples so that you are able to implement scikit-learn in your daily life.

What You Will Learn

  • Build predictive models in minutes by using scikit-learn
  • Understand the differences and relationships between Classification and Regression
  • Use distance metrics to predict in Clustering
  • Find points with similar characteristics with Nearest Neighbors
  • Use automation and cross-validation to find the best model and focus on it for a data product
Table of Contents

01 The Course Overview
02 NumPy Basics
03 Loading and Viewing the Iris Dataset
04 Viewing the Iris Dataset with Pandas
05 Plotting with NumPy and Matplotlib
06 SVM Classification
07 Cross-Validation Using Various Algorithms
08 Classification versus Regression
09 Creating Sample Data for Toy Analysis
10374_Code Bundle.zip
10 Scaling Data to the Standard Normal Distribution
11 Working with Categorical Variables
12 Creating Binary Features and Imputing Missing Values
13 A Linear Model in the Presence of Outliers
14 Using Gaussian Processes for Regression
15 Using SGD for Regression
16 Reducing Dimensionality with PCA
17 Using Decomposition to Classify with DictionaryLearning
18 Dimensionality Reduction with Manifolds
19 Testing Methods to Reduce Dimensionality with Pipelines