marketsimulation's People
marketsimulation's Issues
Save settings.py with the dataset whenever a new simulation is started.
graph for realistic and unrealistic behavior
Make overview of experiments
Which parameters are kept fixed, and why.
d6: Run ga with varied ssmm minspread
make library function for pickling generations data
Try affinity propagation clustering on dataset 1
Write about fitness measures
Also make figure which illustrates the fitness measures on different simulation outcomes. The point is to show that the measures are stable.
Cluster par space with Kmeans and calc fit stats for each cluster
Calculate statistics for parameters for each cluster found by k-means (or other clustering algs)
Make new function for scatter plot of labelled data
pickle SVM object for d2
Basic scatter plots for dataset 1
Prepare shizouka for running ga
Make graph for random walk of fundamental and shock of fundamental
Write about slow trader
Use outlier detection on dataset 2
Finish section on genetic algorithm
Collect references for fitness definitions
Make imshow plot for pars and fit
Reduce dimensionality of fitness for dataset 1 and visualize
Figure out how to let figures exceed the text margin a bit
Make loader for pickled generation data that returns dataframe without generations column
Code function for reading data and outputting graph for all graph issues
Write about HFT market maker
Write about HFT chartist
Implement impulse and ramp experiments and create external parameter for controlling the type
Change GA such that invalid genes generated by mutation are mutated until they are valid
d2: Run ga while varying all lat pars and nagents
Prettify graphs for traded prices.
Make general function for making scatter plot with dots coloured by groups
Prints out the attribute names of components in PCA whenever a plot to make PCA is called
Graph showing fitness of best ever individual as a function of generation
Make graph for market model
Refactor all library functions to receive and return pandas dataframes when passing data
Check that averaging over several simulations still works
Make scatter plot PCA-dimreduced pars with kmean-labels as point colors
d4: Run ga with slow sc and fast mm, and vary nagents
Find pars that make slow but stable market
Modify plotting functions so that they take the name of a dataset as input
d5: Run experiment with fast chartists and slow mm, very nagents
Finish list of fixed parameters
Make HFT chartists and market makers have individual latency parameters
Use kernel PCA to visualize parameters
Refactor code for graph styling such that each graph can use different colormaps
Reduce number of data in dataset1 before using affinity propagation.
Write about scaling of genes into pars
Refactor all plotting code to use library function for PCA
Fix bug in function for round_stable fitness
see data in /Users/halfdan/Dropbox/Waseda/Research/MarketSimulation/data/for_testing/unstable
Normalize data before applying PCA
Make it so that each evaluation of the same parameter set is saved in the gene pool data.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.