José María Mateos rinze

## ImagePlusHyp.java
package jclustering;

import ij.ImagePlus;

/**
 * This class extends {@link ImagePlus} in order to add a handy {@link #getTac}
 * method that allows to easily grab time-activity curves.
 *
 * @author <a href="mailto:jmmateos@mce.hggm.es">José María Mateos</a>.
 *

## ruido_madrid.csv

          
            station
            Leq
            L1
            L10
            L50
            L90
            L99
            date

            
              14
              GLORIETA FDEZ. LADREDA
              67.3
              75.3
              69.8
              64.3
              56.7
              50
              1998-09-30

            
              16
              ARTURO SORIA
              59.5
              67.8
              61.6
              56
              45.3
              39.1
              1998-09-30

            
              19
              ALTO DE EXTREMADURA
              63
              72.4
              66.3
              59.3
              51.4
              47
              1998-09-30

            
              27
              GLORIETA CARLOS V
              74.3
              84.4
              79.5
              67.8
              62
              55.5
              1998-10-31

            
              29
              PLAZA DE ESPAÑA
              66.3
              74
              68.8
              64.5
              59.6
              54.8
              1998-10-31

            
              31
              PLAZA DOCTOR MARAÑÓN
              72.5
              80.2
              75.6
              70.2
              63.1
              55.2
              1998-10-31

            
              32
              PLAZA M. DE SALAMANCA
              73.1
              88.4
              69.9
              63.6
              51.8
              42.1
              1998-10-31

            
              36
              RAMÓN Y CAJAL
              70.3
              77.2
              72.9
              68.8
              56.8
              46.3
              1998-10-31

            
              39
              GLORIETA FDEZ. LADREDA
              68
              75.8
              70.2
              64.6
              56.8
              49.8
              1998-10-31

## ingresos.R
# Eustat data analysis
library(ggplot2)

eustat <- read.csv(file = "/tmp/ilc_di01_1_Data.csv", na.string = ":")
eustat$Value <- gsub(" ", "", eustat$Value)
eustat$Value <- as.numeric(eustat$Value)

spain <- eustat[eustat$GEO == "Spain" &
                eustat$CURRENCY == "Purchasing Power Standard" &
                eustat$INDIC_IL == "Top cut-off point",

## mariano.ijm
open("C:\\temp\\barcenas.tif");
run("32-bit");
run("Mean...", "radius=30");
open("C:\\temp\\mariano.tif");
run("32-bit");
run("Duplicate...", "title=mariano-1.tif");
run("Mean...", "radius=20");
imageCalculator("Subtract create 32-bit", "mariano.tif","mariano-1.tif");
imageCalculator("Add create 32-bit", "Result of mariano.tif","barcenas.tif");
selectWindow("barcenas.tif");

## dataframe_matrix_timing.R
# Timing measurement in R. Vectorized operation on matrix / data.frame
# Author: José María Mateos - jmmateos@ieee.org
#
# For certain vectorized operations, it makes sense to convert your data.frame
# into a matrix. Even if you are using apply, the data frame iteration can be
# real slow.
#
# In this example, I will compute the Euclidean distance for a random vector
# and a random matrix / data.frame of thousands of elements. Operations will be
# done in two different ways: using the apply function over the columns and

## header.R
localpath <- "/home/chema/tmp/kaggle/digits/"
if (Sys.info()["sysname"] == "Windows")
    localpath <- "C:/temp/kaggle/digits"

testFile <- file.path(localpath, "test.Rda")
trainFile <- file.path(localpath, "train.Rda")

if(!file.exists(testFile) && !file.exists(trainFile)) {
    testCSV <- file.path(localpath, "test.csv")
    trainCSV <- file.path(localpath, "train.csv")

## keybase.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                rinze
                / keybase.md
            
            
              Created
              February 8, 2015 22:56
            
          
    Keybase proof

I hereby claim:

I am rinze on github.
I am rinzewind (https://keybase.io/rinzewind) on keybase.
I have a public key whose fingerprint is C7F0 E413 1FFF 47C6 A2A7  F76B F4FE 866D 2948 FA19

To claim this, I am signing this object:

  
## gist:a8dfd32b80fac8d9d8e1
### Keybase proof

I hereby claim:

  * I am rinze on github.
  * I am rinzewind (https://keybase.io/rinzewind) on keybase.
  * I have a public key whose fingerprint is 67AF C4B2 E15C 4F4C 67BD  5F58 5ADF 9021 2630 80EC

To claim this, I am signing this object:

## build_dataset.py
#!/usr/bin/env python
# -*- coding: utf-8 -*-

import csv
import codecs
import cStringIO
import os
from collections import namedtuple

def getParties(parties_file):

## loo_cv_comparison.R
library(C50)

# Test data
group <- c(rep('groupA', 10), rep('groupB', 10))
data <- data.frame(group = group, var = c(rep(0, 10), rep(0, 10)))

# Leave-one-out
probs <-  lapply(1:nrow(data), function(i) {
    train <- data[-i, ]
    test <- data[i, ]
	package jclustering;

	import ij.ImagePlus;

	/**
	* This class extends {@link ImagePlus} in order to add a handy {@link #getTac}
	* method that allows to easily grab time-activity curves.
	*
	* @author <a href="mailto:jmmateos@mce.hggm.es">José María Mateos</a>.
	*
	station	Leq	L1	L10	L50	L90	L99	date
14	GLORIETA FDEZ. LADREDA	67.3	75.3	69.8	64.3	56.7	50	1998-09-30
16	ARTURO SORIA	59.5	67.8	61.6	56	45.3	39.1	1998-09-30
19	ALTO DE EXTREMADURA	63	72.4	66.3	59.3	51.4	47	1998-09-30
27	GLORIETA CARLOS V	74.3	84.4	79.5	67.8	62	55.5	1998-10-31
29	PLAZA DE ESPAÑA	66.3	74	68.8	64.5	59.6	54.8	1998-10-31
31	PLAZA DOCTOR MARAÑÓN	72.5	80.2	75.6	70.2	63.1	55.2	1998-10-31
32	PLAZA M. DE SALAMANCA	73.1	88.4	69.9	63.6	51.8	42.1	1998-10-31
36	RAMÓN Y CAJAL	70.3	77.2	72.9	68.8	56.8	46.3	1998-10-31
39	GLORIETA FDEZ. LADREDA	68	75.8	70.2	64.6	56.8	49.8	1998-10-31
	# Eustat data analysis
	library(ggplot2)

	eustat <- read.csv(file = "/tmp/ilc_di01_1_Data.csv", na.string = ":")
	eustat$Value <- gsub(" ", "", eustat$Value)
	eustat$Value <- as.numeric(eustat$Value)

	spain <- eustat[eustat$GEO == "Spain" &
	eustat$CURRENCY == "Purchasing Power Standard" &
	eustat$INDIC_IL == "Top cut-off point",
	open("C:\\temp\\barcenas.tif");
	run("32-bit");
	run("Mean...", "radius=30");
	open("C:\\temp\\mariano.tif");
	run("32-bit");
	run("Duplicate...", "title=mariano-1.tif");
	run("Mean...", "radius=20");
	imageCalculator("Subtract create 32-bit", "mariano.tif","mariano-1.tif");
	imageCalculator("Add create 32-bit", "Result of mariano.tif","barcenas.tif");
	selectWindow("barcenas.tif");
	# Timing measurement in R. Vectorized operation on matrix / data.frame
	# Author: José María Mateos - jmmateos@ieee.org
	#
	# For certain vectorized operations, it makes sense to convert your data.frame
	# into a matrix. Even if you are using apply, the data frame iteration can be
	# real slow.
	#
	# In this example, I will compute the Euclidean distance for a random vector
	# and a random matrix / data.frame of thousands of elements. Operations will be
	# done in two different ways: using the apply function over the columns and
	### Keybase proof

	I hereby claim:

	* I am rinze on github.
	* I am rinzewind (https://keybase.io/rinzewind) on keybase.
	* I have a public key whose fingerprint is 67AF C4B2 E15C 4F4C 67BD 5F58 5ADF 9021 2630 80EC

	To claim this, I am signing this object:
	#!/usr/bin/env python
	# -- coding: utf-8 --

	import csv
	import codecs
	import cStringIO
	import os
	from collections import namedtuple

	def getParties(parties_file):
	library(C50)

	# Test data
	group <- c(rep('groupA', 10), rep('groupB', 10))
	data <- data.frame(group = group, var = c(rep(0, 10), rep(0, 10)))

	# Leave-one-out
	probs <- lapply(1:nrow(data), function(i) {
	train <- data[-i, ]
	test <- data[i, ]