lucktroy’s gists

lucktroy / Federated Forest

Created February 2, 2019 03:57

Code & Data

lucktroy / py.gitignore

Last active October 24, 2017 01:24

py.gitignore

	# data file
	*.h5
	*.pkl

	# log file
	*.log

	# Byte-compiled / optimized / DLL files
	__pycache__/
	*.py[cod]

lucktroy / numpy.i

Created October 19, 2014 12:55

numpy swig

	/* -- C -- (not really, but good for syntax highlighting) */
	/* numpy 1.9 */
	#ifdef SWIGPYTHON

	%{
	#ifndef SWIG_FILE_WITH_INIT
	#define NO_IMPORT_ARRAY
	#endif
	#include "stdio.h"
	#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION

lucktroy / id3.py

Last active August 29, 2015 14:05 — forked from cmdelatorre/id3.py

	"""

	http://en.wikipedia.org/wiki/ID3_algorithm
	http://www.cise.ufl.edu/~ddd/cap6635/Fall-97/Short-papers/2.htm

	"""

	from collections import namedtuple, Counter, defaultdict
	from math import log2

lucktroy / sort_list.py

Created August 11, 2014 07:07

Sort a list by multiple attributes

	"""
	url: http://stackoverflow.com/questions/4233476/sort-a-list-by-multiple-attributes
	"""

	s=[[12, 'tall', 'blue', 1],
	[15, 'tall', 'black', 3],
	[13, 'tall', 'blue', 8],
	[9, 'short', 'blue', 3],
	[1, 'short', 'black', 2],
	[2, 'short', 'red', 9],

lucktroy / chmod.sh

Created August 9, 2014 14:34

chmod dirs and files

	#!/bin/sh

	# files
	find . -type f -exec chmod 644 {} \;
	# dirs
	find . -type d -exec chmod 755 {} \;

lucktroy / autoencoder.py

Created March 22, 2014 12:23 — forked from kiyukuta/autoencoder.py

	#coding: utf8
	"""
	1. Download this gist.
	2. Get the MNIST data.
	wget http://deeplearning.net/data/mnist/mnist.pkl.gz
	3. Run this code.
	python autoencoder.py 100 -e 1 -b 20 -v

	Wait about a minute ... and get a vialization of weights.
	"""

lucktroy / grid_search.py

Created March 13, 2014 03:27 — forked from pprett/grid_search.py

	"""Parallel grid search for sklearn's GradientBoosting.

	This script uses IPython.parallel to run cross-validated
	grid search on an IPython cluster. Each cell on the parameter grid
	will be evaluated ``K`` times - results are stored in MongoDB.

	The procedure tunes the number of trees ``n_estimators`` by averaging
	the staged scores of the GBRT model averaged over all K folds.

	You need an IPython ipcluster to connect to - for local use simply

lucktroy / gist:8345728

Created January 10, 2014 01:59 — forked from dmaniry/gist:5170087

	import numpy as np
	from scipy import linalg
	from sklearn.utils import array2d, as_float_array
	from sklearn.base import TransformerMixin, BaseEstimator


	class ZCA(BaseEstimator, TransformerMixin):

	def __init__(self, regularization=10**-5, copy=False):
	self.regularization = regularization

lucktroy / cuda-convnet-13pct.sh

Last active January 2, 2016 01:58

A simple script for the example in https://code.google.com/p/cuda-convnet/wiki/Methodology Please add two params cfgs 'layer-params-conv-local-13pct-pw1.cfg' and 'layer-params-conv-local-13pct-pw2.cfg' in $CUDA_CONVNET/example-layers/ Just copy layer-params-conv-local-13pct.cfg to layer-params-conv-local-13pct-pw1.cfg and layer-params-conv-local…

	# A simple script for the example in https://code.google.com/p/cuda-convnet/wiki/Methodology
	# Please add two params cfgs 'layer-params-conv-local-13pct-pw1.cfg' and 'layer-params-conv-local-13pct-pw2.cfg' in $CUDA_CONVNET/example-layers/
	# Just copy layer-params-conv-local-13pct.cfg to layer-params-conv-local-13pct-pw1.cfg and layer-params-conv-local-13pct-pw2.cfg,
	# and reduce all learning rates (the epsW parameters) to 0.001 and 0.0001, respectively
	# Result: training error 5.80% and testing error 12.90% (NVIDIA Tesla C2075)
	# Junbo Zhang: zjb2046<at>gmail<dot>com
	# Jan. 3, 2014

	#set the output dir, which is used for `--save-path`
	export OUTPUT=$HOME/RET/cuda-convnet/cifar10_13pct

Junbo Zhang lucktroy