Knut Behrends knbknb

## query-pubmed-3-terms.R
# Tidyverse-R-code from 2020
# (this code is also artificially slowed down, with purrr::slowly(),
# to avoid HTTP 429 errors (too many requests)

library(tidyverse)
library(httr)
library(xml2)
library(lubridate)
theme_set(theme_bw())

## WekaAPIDemo.java
package demo;

// see http://stackoverflow.com/questions/38464468/weka-linear-regression-doesnt-load/

import weka.classifiers.functions.LinearRegression;
import weka.core.Attribute;
import weka.core.DenseInstance;
import weka.core.FastVector;
import weka.core.Instance;
import weka.core.Instances;

## perceptron-simple.R
# https://gist.github.com/knbknb/1d17caecd9b800d5148a30d537013668
# Thu Aug 16 11:24:05 2018 ------------------------------

# Rosenblatt's perceptron
# this is from 2013, based on a forum post by a chinese user (don't remember his name)
# "learning from data" course, Prof Yaser Abu-Mostafa
# http://work.caltech.edu/telecourse.html

# create a xy-plot and an animated gif visualizing the training process
data(iris)

## twitter_stream_download.py
# To run this code, first edit config.py with your configuration (Auth data), then install necessary modules, then:
#
# Call
#
# mkdir data
# python twitter_stream_download.py -q apple -d data
#
#
# It will produce the list of tweets for the query "apple"
# in the file data/stream_apple.json

## amzn.csv

          
            date
            close

            
              2014-02-07
              361.08

            
              2014-02-06
              354.59

            
              2014-02-05
              346.45

            
              2014-02-04
              347.95

            
              2014-02-03
              346.15

            
              2014-01-31
              358.69

            
              2014-01-30
              403.01

            
              2014-01-29
              384.2

            
              2014-01-28
              394.43

## unnest_united_nations_data_frame.R
# from the datacamp course
# 'Exploratory Data Analysis in R: Case Study'
# by David Robinson
#
# this gist demonstrates an idiom  that I tend to forget the details of
#  group_by / nest / model /unnest
#
# Load purrr, tidyr, and broom
library(purrr)
library(tidyr)

## github_issues.sh
#!/bin/sh
# https://stackoverflow.com/questions/48659631/github-issues-api-and-jq-filter-and-grep
# get github issues
GITHUB_PAT=5b01b116....
#user=Leaflet
#repo=Leaflet
user=stedolan
repo=jq
url=https://$GITHUB_PAT:x-oauth-basic@api.github.com/repos/$user/$repo/issues
echo curl -k -I $url?state=all\\\&per_page=10

## csv2xts--and-more.R
# see also:
# https://s3.amazonaws.com/assets.datacamp.com/blog_assets/xts_Cheat_Sheet_R.pdf


# Open csv file using read.zoo
my_tsdata <- read.zoo("my_tsdata.csv", sep = ",", FUN = as.Date, header = TRUE, index.column = 1)
my_tsdata <- as.xts(my_tsdata)


## CalendarioLiga2013-14.csv

          
            home.team
            score
            away.team
            round
            score_home
            score_visiting
            home.wins
            away.wins

            
              Athletic
              4-2
              Valladolid
              20
              4
              2
              3
              0

            
              Atletico
              1-1
              Sevilla
              20
              1
              1
              1
              1

            
              Betis
              0-5
              R. Madrid
              20
              0
              5
              0
              3

            
              Espanyol
              1-0
              Celta
              20
              1
              0
              3
              0

            
              Villarreal
              2-0
              Almeria
              20
              2
              0
              3
              0

            
              Malaga
              0-0
              Valencia
              20
              0
              0
              1
              1

            
              Elche
              2-0
              Rayo
              20
              2
              0
              3
              0

            
              Getafe
              2-2
              R. Sociedad
              20
              2
              2
              1
              1

            
              Levante
              1-1
              Barcelona
              20
              1
              1
              1
              1

## coreNLP_test.R
#Sys.setenv(JAVA_OPTIONS = "-Xmx8g -Xms1G -XX:+UseConcMarkSweepGC -XX:-UseGCOverheadLimit")
library(tidyverse)
library(coreNLP)
# from: https://stackoverflow.com/questions/48455079/extract-city-names-from-large-text-with-r
# using COreNLP to extract tokens
# knb 20180422

outputloc <- "/opt/smallapps/corenlp/"
nlpver <- 2018
if(nlpver != 2018){
	# Tidyverse-R-code from 2020
	# (this code is also artificially slowed down, with purrr::slowly(),
	# to avoid HTTP 429 errors (too many requests)

	library(tidyverse)
	library(httr)
	library(xml2)
	library(lubridate)
	theme_set(theme_bw())
	package demo;

	// see http://stackoverflow.com/questions/38464468/weka-linear-regression-doesnt-load/

	import weka.classifiers.functions.LinearRegression;
	import weka.core.Attribute;
	import weka.core.DenseInstance;
	import weka.core.FastVector;
	import weka.core.Instance;
	import weka.core.Instances;
	# https://gist.github.com/knbknb/1d17caecd9b800d5148a30d537013668
	# Thu Aug 16 11:24:05 2018 ------------------------------

	# Rosenblatt's perceptron
	# this is from 2013, based on a forum post by a chinese user (don't remember his name)
	# "learning from data" course, Prof Yaser Abu-Mostafa
	# http://work.caltech.edu/telecourse.html

	# create a xy-plot and an animated gif visualizing the training process
	data(iris)
	# To run this code, first edit config.py with your configuration (Auth data), then install necessary modules, then:
	#
	# Call
	#
	# mkdir data
	# python twitter_stream_download.py -q apple -d data
	#
	#
	# It will produce the list of tweets for the query "apple"
	# in the file data/stream_apple.json
	date	close
	2014-02-07	361.08
	2014-02-06	354.59
	2014-02-05	346.45
	2014-02-04	347.95
	2014-02-03	346.15
	2014-01-31	358.69
	2014-01-30	403.01
	2014-01-29	384.2
	2014-01-28	394.43
	# from the datacamp course
	# 'Exploratory Data Analysis in R: Case Study'
	# by David Robinson
	#
	# this gist demonstrates an idiom that I tend to forget the details of
	# group_by / nest / model /unnest
	#
	# Load purrr, tidyr, and broom
	library(purrr)
	library(tidyr)
	#!/bin/sh
	# https://stackoverflow.com/questions/48659631/github-issues-api-and-jq-filter-and-grep
	# get github issues
	GITHUB_PAT=5b01b116....
	#user=Leaflet
	#repo=Leaflet
	user=stedolan
	repo=jq
	url=https://$GITHUB_PAT:x-oauth-basic@api.github.com/repos/$user/$repo/issues
	echo curl -k -I $url?state=all\\\&per_page=10
	# see also:
	# https://s3.amazonaws.com/assets.datacamp.com/blog_assets/xts_Cheat_Sheet_R.pdf


	# Open csv file using read.zoo
	my_tsdata <- read.zoo("my_tsdata.csv", sep = ",", FUN = as.Date, header = TRUE, index.column = 1)
	my_tsdata <- as.xts(my_tsdata)
home.team	score	away.team	round	score_home	score_visiting	home.wins	away.wins
Athletic	4-2	Valladolid	20	4	2	3	0
Atletico	1-1	Sevilla	20	1	1	1	1
Betis	0-5	R. Madrid	20	0	5	0	3
Espanyol	1-0	Celta	20	1	0	3	0
Villarreal	2-0	Almeria	20	2	0	3	0
Malaga	0-0	Valencia	20	0	0	1	1
Elche	2-0	Rayo	20	2	0	3	0
Getafe	2-2	R. Sociedad	20	2	2	1	1
Levante	1-1	Barcelona	20	1	1	1	1
	#Sys.setenv(JAVA_OPTIONS = "-Xmx8g -Xms1G -XX:+UseConcMarkSweepGC -XX:-UseGCOverheadLimit")
	library(tidyverse)
	library(coreNLP)
	# from: https://stackoverflow.com/questions/48455079/extract-city-names-from-large-text-with-r
	# using COreNLP to extract tokens
	# knb 20180422

	outputloc <- "/opt/smallapps/corenlp/"
	nlpver <- 2018
	if(nlpver != 2018){