standarderror’s gists

standarderror / smear.sql

Created August 29, 2017 23:55

Smearing start-end date data

	Imagine you have some start-end data:

	create table PRD_CAA_CRE_DDWSP_PI6_DPOL.TBL_DATA_1 as (
	select ACCT_ID
	, START_DATE
	, END_DATE
	, CURR_CRDT_LIM_AMT
	from PRD_ADS_IL_VR.VR_S_ACCT_CRDT_CRD_RAW
	sample 1000)
	with data;

standarderror / SQL to R.txt

Created April 8, 2017 10:26

SQL equivalents in R

	SELECT ... FROM a JOIN b WHERE ... GROUP BY ... HAVING ... ORDER BY ...

	is equivalent to a chain of R commands involving

	a %>%
	select(...) %>%
	filter(...) %>%
	inner_join(b, ...) %>%
	group_by(...) %>%
	summarise(...) %>%

standarderror / 20161112_Neural_Style_TensorFlow.py

Created November 12, 2016 04:26

20161112_Neural_Style_TensorFlow

	import os
	import numpy as np
	import scipy.misc
	import scipy.io
	import math
	import tensorflow as tf
	from sys import stderr
	from functools import reduce
	import time

standarderror / CNN: train CNN for cat dog data.py

Last active March 19, 2018 01:09

	"""
	Based on the tflearn CIFAR-10 example at:
	https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_cifar10.py
	"""

	from __future__ import division, print_function, absolute_import

	from skimage import color, io
	from scipy.misc import imresize
	import numpy as np

standarderror / CNN: visualise conv layer outputs.py

Last active September 30, 2016 05:12

	# choose images & plot the first one
	im = allX[102:103]
	plt.axis('off')
	plt.imshow(im[0].astype('uint8'))
	plt.gcf().set_size_inches(2, 2)

	# run images through 1st conv layer
	m2 = tflearn.DNN(conv_1, session=model.session)
	yhat = m2.predict(im)

standarderror / 20160215_Decision_boundaries.py

Last active February 16, 2016 01:12

20160215 Decision Boundaries

	### Prepeare python
	%pylab inline

	import numpy as np
	import pandas as pd
	import statsmodels.api as sm
	import scipy.stats as stats
	import neurolab as nl
	from sklearn.datasets import make_classification
	from sklearn import neighbors, tree, svm

standarderror / Autoencoder.py

Last active September 26, 2016 03:36

20150715 Autoencoder

	### Autoencoder

	###################################
	## [1] Parameters & hyperparameters
	###################################

	# shape of data
	N = shape(X)[1] # num observation
	D = shape(X)[0] # num features (dimensionality)

standarderror / index.html

Created January 12, 2015 03:41

20150115 Regression Animation in Viewbox

	<!DOCTYPE html>
	<meta charset="utf-8">
	<style>

	#chart {
	/* margin-left:50%; */
	}

	.circle {
	stroke: '#fff';

standarderror / index.html

Last active February 17, 2016 10:04

20150111 Regression Scatterplot Animation

	<!DOCTYPE html>
	<meta charset="utf-8">
	<style>

	#chart {
	}


	.circle {
	stroke: '#fff';

standarderror / d3.min.js

Last active August 29, 2015 14:12

20150107 Movies by genre history

!function(){function n(n,t){return t>n?-1:n>t?1:n>=t?0:0/0}function t(n){return null===n?0/0:+n}function e(n){return!isNaN(n)}function r(n){return{left:function(t,e,r,u){for(arguments.length<3&&(r=0),arguments.length<4&&(u=t.length);u>r;){var i=r+u>>>1;n(t[i],e)<0?r=i+1:u=i}return r},right:function(t,e,r,u){for(arguments.length<3&&(r=0),arguments.length<4&&(u=t.length);u>r;){var i=r+u>>>1;n(t[i],e)>0?u=i:r=i+1}return r}}}function u(n){return n.length}function i(n){for(var t=1;n*t%1;)t*=10;return t}function o(n,t){for(var e in t)Object.defineProperty(n.prototype,e,{value:t[e],enumerable:!1})}function a(){this._=Object.create(null)}function c(n){return(n+="")===da||n[0]===ma?ma+n:n}function l(n){return(n+="")[0]===ma?n.slice(1):n}function s(n){return c(n)in this._}function f(n){return(n=c(n))in this._&&delete this._[n]}function h(){var n=[];for(var t in this._)n.push(l(t));return n}function g(){var n=0;for(var t in this._)++n;return n}function p(){for(var n in this._)return!1;return!0}function v(){this._=Object

Cam standarderror