You're reading from Hands-On Financial Trading with Python A practical guide to using Zipline and other Python libraries for backtesting trading strategies

Product type Paperback

Published in Apr 2021

Publisher Packt

ISBN-13 9781838982881

Length 360 pages

Edition 1st Edition

Languages

Python

Tools

NumPy

Concepts

Data Analysis

Authors (2):

Sourav Ghosh

Jiri Pik

View More author details

Table of Contents (15) Chapters

Preface

1. Section 1: Introduction to Algorithmic Trading

2. Chapter 1: Introduction to Algorithmic Trading FREE CHAPTER

3. Section 2: In-Depth Look at Python Libraries for the Analysis of Financial Datasets

4. Chapter 2: Exploratory Data Analysis in Python

5. Chapter 3: High-Speed Scientific Computing Using NumPy

6. Chapter 4: Data Manipulation and Analysis with pandas

7. Chapter 5: Data Visualization Using Matplotlib

8. Chapter 6: Statistical Estimation, Inference, and Prediction

9. Section 3: Algorithmic Trading in Python

10. Chapter 7: Financial Market Data Access in Python

11. Chapter 8: Introduction to Zipline and PyFolio

12. Chapter 9: Fundamental Algorithmic Trading Strategies

13. Other Books You May Enjoy

Appendix A: How to Setup a Python Environment

Introduction to scikit-learn regression and classification

scikit-learn is a Python supervised and unsupervised machine learning library built on top of the numpy and scipy libraries.

Let's demonstrate how to forecast price changes on a dataset with RidgeCV regression and classification using scikit-learn.

Generating the dataset

Let's start by generating the dataset for the following examples—a Pandas DataFrame containing daily data for 20 years with BookPressure, TradePressure, RelativeValue, and Microstructure fields to represent some synthetic trading signals built on this dataset (also known as features or predictors). The PriceChange field represents the daily change in prices that we are trying to predict (also known as response or target variable). For simplicity, we make the PriceChange field a linear function of our predictors with random weights and some random noise. The Price field represents the actual price of the instrument generated using the...