book

Hands-On Financial Trading with Python

by Jiri Pik, Sourav Ghosh

April 2021

Intermediate to advanced

360 pages

6h 24m

English

Packt Publishing

Read now

Unlock full access

ContributorsAbout the authorsAbout the reviewer
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesDownload the color imagesConventions usedGet in touchReviews
Walking through the evolution of algorithmic tradingUnderstanding financial asset classesGoing through the modern electronic trading exchangeOrder typesLimit order booksThe exchange matching engineUnderstanding the components of an algorithmic trading systemThe core infrastructure of an algorithmic trading systemThe quantitative infrastructure of an algorithmic trading systemSummary
Technical requirementsIntroduction to EDASteps in EDARevelation of the identity of A, B, and C and EDA's conclusionsSpecial Python libraries for EDASummary
Technical requirementsIntroduction to NumPyCreating NumPy ndarraysCreating 1D ndarraysCreating 2D ndarraysCreating any-dimension ndarraysCreating an ndarray with np.zeros(...)Creating an ndarray with np.ones(...)Creating an ndarray with np.identity(...)Creating an ndarray with np.arange(...)Creating an ndarray with np.random.randn(…)Data types used with NumPy ndarraysCreating a numpy.float64 arrayCreating a numpy.bool arrayndarrays' dtype attributeConverting underlying data types of ndarray with numpy.ndarrays.astype(...) Indexing of ndarraysDirect access to an ndarray's elementndarray slicingBoolean indexingIndexing with arraysBasic ndarray operationsScalar multiplication with an ndarrayLinear combinations of ndarraysExponentiation of ndarraysAddition of an ndarray with a scalarTransposing a matrixChanging the layout of an ndarrayFinding the minimum value in an ndarrayCalculating the absolute valueCalculating the mean of an ndarrayFinding the index of the maximum value in an ndarrayCalculating the cumulative sum of elements of an ndarrayFinding NaNs in an ndarrayFinding the truth values of x1>x2 of two ndarraysany and all Boolean operations on ndarraysSorting ndarraysSearching within ndarraysFile operations on ndarraysFile operations with text filesFile operations with binary filesSummary
Technical requirementsIntroducing pandas Series, pandas DataFrames, and pandas Indexespandas.Seriespandas.DataFramepandas.IndexLearning essential pandas.DataFrame operationsIndexing, selection, and filtering of DataFramesDropping rows and columns from a DataFrameSorting values and ranking the values' order within a DataFrameArithmetic operations on DataFramesMerging and combining multiple DataFrames into a single DataFrameHierarchical indexingGrouping operations in DataFramesTransforming values in DataFrames' axis indicesHandling missing data in DataFramesThe transformation of DataFrames with functions and mappingsDiscretization/bucketing of DataFrame valuesPermuting and sampling DataFrame values to generate new DataFramesExploring file operations with pandas.DataFramesCSV filesJSON filesSummary
Technical requirementsCreating figures and subplotsDefining figures' subplotsPlotting in subplotsEnriching plots with colors, markers, and line stylesEnriching axes with ticks, labels, and legendsEnriching data points with annotationsSaving plots to filesCharting a pandas DataFrame with MatplotlibCreating line plots of a DataFrame columnCreating bar plots of a DataFrame columnCreating histogram and density plots of a DataFrame columnCreating scatter plots of two DataFrame columnsPlotting time series dataSummary
Technical requirementsIntroduction to statsmodelsNormal distribution test with Q-Q plotsTime series modeling with statsmodelsETS analysis of a time seriesAugmented Dickey-Fuller test for stationarity of a time seriesAutocorrelation and partial autocorrelation of a time seriesARIMA time series modelUsing a SARIMAX time series model with pmdarimaTime series forecasting with Facebook's Prophet libraryIntroduction to scikit-learn regression and classificationGenerating the datasetRunning RidgeCV regression on the datasetRunning a classification method on the datasetSummary

Technical requirementsExploring the yahoofinancials Python librarySingle-ticker retrievalMultiple-tickers retrievalExploring the pandas_datareader Python libraryAccess to Yahoo FinanceAccess to EconDBAccess to the Federal Reserve Bank of St Louis' FREDCaching queriesExploring the Quandl data sourceExploring the IEX Cloud data sourceExploring the MarketStack data sourceSummary
Technical requirementsIntroduction to Zipline and PyFolioInstalling Zipline and PyFolioInstalling ZiplineInstalling PyFolioImporting market data into a Zipline/PyFolio backtesting systemImporting data from the historical Quandl bundleImporting data from the CSV files bundleImporting data from custom bundlesStructuring Zipline/PyFolio backtesting modulesTrading happens every dayTrading happens on a custom scheduleReviewing the key Zipline API referenceTypes of ordersCommission modelsSlippage modelsRunning Zipline backtesting from the command lineIntroduction to risk management with PyFolioMarket volatility, PnL variance, and PnL standard deviationTrade-level Sharpe ratioMaximum drawdownSummary
Technical requirements What is an algorithmic trading strategy?Learning momentum-based/trend-following strategiesRolling window mean strategySimple moving averages strategyExponentially weighted moving averages strategyRSI strategyMACD crossover strategyRSI and MACD strategiesTriple exponential average strategyWilliams R% strategyLearning mean-reversion strategiesBollinger band strategyPairs trading strategyLearning mathematical model-based strategiesMinimization of the portfolio volatility strategy with monthly tradingMaximum Sharpe ratio strategy with monthly tradingLearning time series prediction-based strategiesSARIMAX strategyProphet strategySummary
Technical requirementsInitial setupDownloading the complimentary Quandl data bundle
Other Books You May EnjoyPackt is searching for authors like youLeave a review - let other readers know what you think

Content preview from Hands-On Financial Trading with Python

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

This section will deep dive into the core Python libraries NumPy and pandas, which are used for the analysis and manipulation of large DataFrames. We will also cover the visualization library Matplotlib, which is closely linked to pandas. Finally, we will look at the statsmodels and scikit-learn libraries, which allow more advanced analysis of financial datasets.

This section comprises the following chapters: