sdaza

# intro to instrumental variables
# author: sebastian daza


# load libraries
library(simsem)
library(data.table)
library(texreg)
library(ivpack)
library(lme4)

sdaza

public void sqlToCSV (ResultSet rs, String filename) {
    try {
        FileWriter fw = new FileWriter(filename + ".csv");
        int cols = rs.getMetaData().getColumnCount();
        for(int i = 1; i <= cols; i ++){
            fw.append(rs.getMetaData().getColumnLabel(i));
            if(i < cols) fw.append(',');
            else fw.append('\n');
        }
        while (rs.next()) {

sdaza

# stratified sampling example and weighted means

set.seed(1)
library(data.table)

dat =  data.table(
  ID = 1:100,
  A = sample(c("AA", "BB", "CC", "DD", "EE"), 100, replace = TRUE),
  B = rnorm(100), C = abs(round(rnorm(100), digits=1)),
  D = sample(c("CA", "NY", "TX"), 100, replace = TRUE),

sdaza

# author: sebastian daza
# web: sdaza.com


# libraries
library(data.table)
library(xtable)


# create descriptive tables

sdaza

import re
from pyspark.sql import Row
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import HashingTF, Tokenizer
from pyspark.sql.types import DoubleType
from operator import add
from lxml import etree
# from pyspark.sql import SQLContext
# sqlContext = SQLContext(sc)

sdaza

# load data
load("ex.Rdata")

###################################
# example only using mice package
###################################

library(mice)

imp <- mice(ex, maxit = 0)

sdaza

# EXAMPLES USING PACKAGE ACSR
# AUTHOR: SEBASTIAN DAZA
# March 23, 2015, 8:19 AM

# INSTALL LAST VERSION OF DATA.TABLE AND ACS PACKAGE (YOU HAVE TO INSTALL DEVTOOLS BEFORE!)
# I ASSUME ACS IS ALREADY INSTALLED!
install.packages("devtools")
devtools::install_github("Rdatatable/data.table", build_vignettes = FALSE)

# INSTALL MY PACKAGE

sdaza

library(acs)
rm(list=ls(all=TRUE))

variables <- c("C17002_002", "C17002_003", "C17002_004", "C17002_005","C17002_006", "C17002_001")
dat <- acs.fetch(geo = geo.make(state = "WI", county = "*", tract = "*"), variable = variables)
p_output <- divide.acs(dat[,1] + dat[,2] + dat[,3] + dat[,4] + dat[,5], dat[,6], method = "proportion")
r_output <- divide.acs(dat[,1] + dat[,2] + dat[,3] + dat[,4] + dat[,5], dat[,6], method = "ratio")

sdaza

###########
# Example
##########

library(igraph)

actors <- data.frame(name=c("Alice", "Bob", "Cecil", "David",
                            "Esmeralda"),
                     age=c(48,33,45,34,21),
                     gender=c("F","M","F","M","F"))

sdaza

# MY R FUNCTIONS
# AUTHOR: SEBASTIAN DAZA
# Jun 02, 2014, 10:35 AM

# LOOKING FOR VARIABLES ####
lookvar  <- function(dat, varnames) {
  n  <- names(dat)
  
  nn  <- list()
    for (i in 1:length(varnames)) {