knbknb

# 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())

knbknb

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;

knbknb

# 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)

knbknb

# 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

knbknb

knbknb

# 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)

knbknb

#!/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://$GITHUB_PAT:[email protected]/repos/$user/$repo/issues
echo curl -k -I $url?state=all\\\&per_page=10

knbknb

# 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)


 

knbknb

knbknb

#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){