Python for Finance Cookbook: Over 80 powerful recipes for effective financial data analysis. 2 Ed

Table of Contents....2

Preface....3

Acquiring Financial Data....14

Getting data from Yahoo Finance....16

Getting data from Nasdaq Data Link....21

Getting data from Intrinio....26

Getting data from Alpha Vantage....35

Getting data from CoinGecko....42

Summary....46

Data Preprocessing....48

Converting prices to returns....48

Adjusting the returns for inflation....52

Changing the frequency of time series data....58

Different ways of imputing missing data....62

Converting currencies....69

Different ways of aggregating trade data....73

Summary....82

Visualizing Financial Time Series....83

Basic visualization of time series data....84

Visualizing seasonal patterns....92

Creating interactive visualizations....99

Creating a candlestick chart....106

Summary....113

Exploring Financial Time Series Data....114

Outlier detection using rolling statistics....115

Outlier detection with the Hampel filter....120

Detecting changepoints in time series....126

Detecting trends in time series....133

Detecting patterns in a time series using the Hurst exponent....136

Investigating stylized facts of asset returns....142

Summary....157

Technical Analysis and Building Interactive Dashboards....159

Calculating the most popular technical indicators....160

Downloading the technical indicators....167

Recognizing candlestick patterns....172

Building an interactive web app for technical analysis using Streamlit....179

Deploying the technical analysis app....193

Summary....197

Time Series Analysis and Forecasting....198

Time series decomposition....199

Testing for stationarity in time series....211

Correcting for stationarity in time series....219

Modeling time series with exponential smoothing methods....228

Modeling time series with ARIMA class models....241

Finding the best-fitting ARIMA model with auto-ARIMA....258

Summary....274

Machine Learning-Based Approaches to Time Series Forecasting....275

Validation methods for time series....276

Feature engineering for time series....293

Time series forecasting as reduced regression....312

Forecasting with Meta’s Prophet....329

AutoML for time series forecasting with PyCaret....347

Summary....361

Multi-Factor Models....364

Estimating the CAPM....365

Estimating the Fama-French three-factor model....374

Estimating the rolling three-factor model on a portfolio of assets....382

Estimating the four- and five-factor models....386

Estimating cross-sectional factor models using the Fama-MacBeth regression....393

Summary....401

Modeling Volatility with GARCH Class Models....402

Modeling stock returns’ volatility with ARCH models....403

Modeling stock returns’ volatility with GARCH models....412

Forecasting volatility using GARCH models....420

Multivariate volatility forecasting with the CCC-GARCH model....430

Forecasting the conditional covariance matrix using DCC-GARCH....436

Summary....447

Monte Carlo Simulations in Finance....448

Simulating stock price dynamics using a geometric Brownian motion....449

Pricing European options using simulations....459

Pricing American options with Least Squares Monte Carlo....467

Pricing American options using QuantLib....473

Pricing barrier options....478

Estimating Value-at-Risk using Monte Carlo....482

Summary....490

Asset Allocation....491

Evaluating an equally-weighted portfolio’s performance....493

Finding the efficient frontier using Monte Carlo simulations....505

Finding the efficient frontier using optimization with SciPy....515

Finding the efficient frontier using convex optimization with CVXPY....525

Finding the optimal portfolio with Hierarchical Risk Parity....536

Summary....546

Backtesting Trading Strategies....547

Vectorized backtesting with pandas....550

Event-driven backtesting with backtrader....557

Backtesting a long/short strategy based on the RSI....569

Backtesting a buy/sell strategy based on Bollinger bands....579

Backtesting a moving average crossover strategy using crypto data....588

Backtesting a mean-variance portfolio optimization....596

Summary....603

Applied Machine Learning: Identifying Credit Default....605

Loading data and managing data types....606

Exploratory data analysis....617

Splitting data into training and test sets....637

Identifying and dealing with missing values....643

Encoding categorical variables....653

Fitting a decision tree classifier....663

Organizing the project with pipelines....682

Tuning hyperparameters using grid searches and cross-validation....694

Summary....711

Advanced Concepts for Machine Learning Projects....713

Exploring ensemble classifiers....715

Exploring alternative approaches to encoding categorical features....728

Investigating different approaches to handling imbalanced data....740

Leveraging the wisdom of the crowds with stacked ensembles....755

Bayesian hyperparameter optimization....764

Investigating feature importance....784

Exploring feature selection techniques....800

Exploring explainable AI techniques....819

Summary....846

Deep Learning in Finance....849

Exploring fastai’s Tabular Learner....850

Exploring Google’s TabNet....866

Time series forecasting with Amazon’s DeepAR....880

Time series forecasting with NeuralProphet....896

Summary....915

Other Books You May Enjoy....920

Index....923

Python is one of the most popular programming languages in the financial industry, with a huge collection of accompanying libraries. In this new edition of the Python for Finance Cookbook, you will explore classical quantitative finance approaches to data modeling, such as GARCH, CAPM, factor models, as well as modern machine learning and deep learning solutions.

You will use popular Python libraries that, in a few lines of code, provide the means to quickly process, analyze, and draw conclusions from financial data. In this new edition, more emphasis was put on exploratory data analysis to help you visualize and better understand financial data. While doing so, you will also learn how to use Streamlit to create elegant, interactive web applications to present the results of technical analyses.

Using the recipes in this book, you will become proficient in financial data analysis, be it for personal or professional projects. You will also understand which potential issues to expect with such analyses and, more importantly, how to overcome them.

What you will learn

• Preprocess, analyze, and visualize financial data
• Explore time series modeling with statistical (exponential smoothing, ARIMA) and machine learning models
• Uncover advanced time series forecasting algorithms such as Meta's Prophet
• Use Monte Carlo simulations for derivatives valuation and risk assessment
• Explore volatility modeling using univariate and multivariate GARCH models
• Investigate various approaches to asset allocation
• Learn how to approach ML-projects using an example of default prediction
• Explore modern deep learning models such as Google's TabNet, Amazon's DeepAR and NeuralProphet

Who this book is for

This book is intended for financial analysts, data analysts and scientists, and Python developers with a familiarity with financial concepts. You'll learn how to correctly use advanced approaches for analysis, avoid potential pitfalls and common mistakes, and reach correct conclusions for a broad range of finance problems.

Working knowledge of the Python programming language (particularly libraries such as pandas and NumPy) is necessary.