Tag: python

bitcoin and ethereum futures spread dynamics

Here we will download and display calendar futures spread on btc and eth from binance. We will use the following code to get the data via http API. We will look into september / december 2020 calendar spread for coin

Posted in crypto Tagged with: ,

how to quickly get new crypto api points for new products

When new products are introduced on crypto exchanges, the python api’s and docuementation sometime is not complete, and it’s difficult to find exact symbol names and other paramters.To quickly find out symbol names and other paramters for api calls, we

Posted in crypto Tagged with: , ,

How to save order book and trades data for crypto futures

To save data in text format for crypto futures order book and trades from binance we can use the following python snippet: (if you are interested to have -10% on binance trading fees you can use the following code: WFH7DYED

Posted in crypto Tagged with: ,

Python structure for machine learning experiments

Here we will present the setup for single machine to run time consuming machine learning experiments like feature selection using different machine learning models. First we will create python program which runs single experiment. We will use argparse library to

Posted in machine learning Tagged with: ,

Feature selection

Feature selection in low signal-to-noise environments like finance. In the following we will create a feature selection function which would work on XGBoost models as well as Tensorflow and simple sklearn models. We will use univariate as well as other

Posted in machine learning Tagged with: ,

How to display candle stick bars from binance futures in jupyter notebook

In order to download and display binance candlestick bars in jupyter notebook we will need the following packages: pip install mplfinance pip install python-binance pip install plotly Also you would need to get API keys from binance Binance API management

Posted in crypto Tagged with: , ,

How to check time-series for abnormality

In many time series machine learning problems the with large number of features the raw data might contain – abnormal / extreme points – discontinuities – stale data To help with determining quickly abnormal or extreme points we can use

Posted in machine learning Tagged with: ,

How to add feature interactions

Sometimes it is preferable to use simple machine learning algorithms such as logistic regression due to speed and explainability. But usually these simple algorithms do not incorporate interactions of the features (in contrary to , say, neural networks, where sum/difference

Posted in machine learning Tagged with: ,

time series feature transformations – quantiles

For machine learning algorithms to work well, it’s usually useful to remove noise from features.For time-series this can be achieved in several ways, such as moving averages, applying sign transform, or applying low pass filter. Other, more simple way is

Posted in machine learning Tagged with: ,

python and derivatives pricing tutorial

Tutorial objective: write and understand simple minimal programs in python for pricing financial derivatives topics: Brownian motion objective: draw and calculate properties of brownian motion using python Black scholes pricing objective: calculate call option price Heston model objective: draw forward

Posted in OTC derivatives valuation, quant finance coding course Tagged with: , ,