Python Module Index

d | f | h | m | o | p | q | s | v
 
d
dsge (Linux) The dsge module is just a package which contains all of the modules required to do DSGE modelling, that is solving them and then doing further work with the obtained solutions, such as simulating and generating IRFs.
 
f
favar (Linux) The favar module contains the FAVAR class for estimating and doing further work with Factor-augmented Vector Autoregressions commonly used in applied macroeconometrics. It supports advanced methods such as bootstrapping confidence intervals including Killian's boostrap-after-bootstrap small-sample bias correction. Also CPU-intensive methods such as the bootstrap can be computed using Parallel Python to exploit multi-core CPUs. Pretty plotting methods are also included which depend on matplotlib.
filters (Linux) Wrapper package module for all of the time series filters we make available in extracting the cycle and trend from (mostly) simulated data. But these filters are also imported into the macroeconometric class, like VAR and FAVAR to deal with real data.
 
h
helpers (Linux) A module containing just a small number of useful functions, such as getting the current data and some special linear algebra routines compiled in externally.
 
m
macrolab (Linux) The macrolab module contains the the most important classes for doing work with DSGE models. In particular it supplies the DSGEmodel class containing most of the functionality of DSGE model instances. The module also contains the TSDataBase class which was supposed to be an advanced data carrier class to be passed to the DSGE model instance for estimation purposes, but this is deprecated and will probably be replaced with a pandas data frame in the near future.
 
o
one_off (Linux) A collection of tools required for doing intelligent and dynamic DSGE model instance updating at runtime. The version in this module is for the one-off updater behaviour.
 
p
parsers (Linux) Wrapper module for a number of parsing modules which are crucial for the functioning of PyMacLab. The first parser collects raw data (i.e. lines) from the DSGE model files, while the second parser carefully extracts useful information and then stores this by attaching it to the DSGE model instance.
pymaclab (Linux) The var module contains the VAR class for estimating and doing further work with Vector Autoregressions commonly used in applied macroeconometrics. It supports advanced methods such as bootstrapping confidence intervals including Killian's boostrap-after-bootstrap small-sample bias correction. Also CPU-intensive methods such as the bootstrap can be computed using Parallel Python to exploit multi-core CPUs. Pretty plotting methods are also included which depend on matplotlib.
    pymaclab.dsge
    pymaclab.dsge.helpers
    pymaclab.dsge.macrolab
    pymaclab.dsge.parsers
    pymaclab.dsge.solvers
    pymaclab.dsge.updaters.one_off
    pymaclab.dsge.updaters.queued
    pymaclab.filters
    pymaclab.stats.favar
    pymaclab.stats.var
 
q
queued (Linux) A collection of tools required for doing intelligent and dynamic DSGE model instance updating at runtime. The version in this module is for the queued updater behaviour.
 
s
solvers (Linux) Wrapper package for all kinds of modules necessary for finding solutions to DSGE model instances. Contains modules required for finding steady state solutions as well as such which are needed for solving the models dynamically.
 
v
var (Linux) The var module contains the VAR class for estimating and doing further work with Vector Autoregressions commonly used in applied macroeconometrics. It supports advanced methods such as bootstrapping confidence intervals including Killian's boostrap-after-bootstrap small-sample bias correction. Also CPU-intensive methods such as the bootstrap can be computed using Parallel Python to exploit multi-core CPUs. Pretty plotting methods are also included which depend on matplotlib.