Paul-Antoine pachevalier

## gmm_vs_lm.R
library("gmm")
set.seed(1234567)
N  <- 1000
dd  <- data.frame(id = 1:N)
dd$u  <- rnorm(N)
dd$x  <- 1 + rnorm(N)
dd$y  <- 1 + dd$x + dd$u
m1  <- lm(y ~ x, data = dd)
m2  <- gmm(y ~ x, x = ~ x,  wmatrix = "ident", data = dd)
coefficients(m1)

## chow_test.R
mc  <- lm(formula = SBR ~ Age, data = ch)
m1  <-  lm(formula = SBR ~ Age, data = subset(ch, Sex == "M"))
m2  <-  lm(formula = SBR ~ Age, data = subset(ch, Sex == "F"))
sc  <- sum(mc$residuals^2)
s1  <- sum(m1$residuals^2)
s2  <- sum(m2$residuals^2)
k  <- 2
# Test statistic
fstat  <- (sc - (s1 + s2)) / k / (s1 + s2) * (length(mc$residuals) - 2*k)
fstat

## piecewise_linear_reg.R
library("strucchange")
library("lubridate")

set.seed(1234567)
N <- 60
df  <- data.frame(id  =  1:N)
df$date  <- seq(as.Date("2013-07-01"), by = "day", along = df$id)
df$date2  <-  difftime(df$date, ymd("2013-07-01"), units = "day")
df$date3  <-  difftime(df$date, ymd("2013-08-01"), units = "day")
difftime(ymd("2013-08-01"), ymd("2013-07-01"), units = "day")

## segmented.R
library("lubridate")
library("strucchange")
library("segmented")

set.seed(1234567)
N <- 60
df  <- data.frame(id  =  1:N)
df$date  <- seq(as.Date("2013-07-01"), by = "day", along = df$id)
df$date2  <-  difftime(df$date, ymd("2013-07-01"), units = "day")
df$date3  <-  ifelse(df$date > as.Date("2013-08-01"), difftime(df$date, ymd("2013-08-01"), units = "day"), 0)

## fake_line_plot.R
N  <- 100
fk  <- data.frame(id = 1:N)
fk$x  <- 1 + rnorm(N)
fk$y1  <- 1 + fk$x + rnorm(N)
fk$y2  <- 2 + fk$x + rnorm(N)

ggplot(data = fk, aes(x = x, y = y1)) +
  geom_line(color = "#339966", size = 2) +
  geom_line(aes(y = y2), color = "#990000", size = 2) +
  theme_tufte()

## function_categorie.R
categorie  <- function(x, breaks) {
  c  <- length(breaks)
  temp  <- 0
  temp[x <= breaks[1]]  <- 1
  for (k in 1:c-1) {
    temp[x > breaks[k] & x <= breaks[k+1]]  <- k+1
  }
  temp[x > breaks[c]]  <- c + 1
  return(temp)
}

## codeiso.csv

          
            ISO
            country

            
              ABW
              Aruba

            
              AFG
              Afghanistan

            
              AGO
              Angola

            
              AIA
              Anguilla

            
              ALA
              Åland Islands

            
              ALB
              Albania

            
              AND
              Andorra

            
              ARE
              United Arab Emirates

            
              ARG
              Argentina

## code_ioc.csv

          
            code
            country

            
              AFG
              Afghanistan

            
              RSA
              South Africa

            
              ALB
              Albania

            
              ALG
              Algeria

            
              GER
              Germany

            
              AND
              Andorra

            
              ANG
              Angola

            
              ANT
              Antigua and Barbuda

            
              AHO
              Netherlands Antilles

## arrange.R
library("dplyr")
set.seed(123)
N <- 100
df <- data.frame(id = 1:N, x = rnorm(N))
df$x[runif(N) < .1]  <- NA
table(is.na(tdf$x))
tdf  <- tbl_df(df)
out  <- arrange(tdf, desc(x))
out2  <- tdf[order(tdf$x, decreasing = TRUE),]

## sample.R
library("ggplot2")
set.seed(1234)
N  <- 100
df  <- data.frame(i = 1:N, x = rnorm(N))
df$y  <- 1 + df$x + rnorm(N)
df$z  <- (runif(N) < .3)

pdf("output/test.pdf")
ggplot(data = df, aes(x = x, y = y, shape = z)) +
  geom_point(size = 3) +
	library("gmm")
	set.seed(1234567)
	N <- 1000
	dd <- data.frame(id = 1:N)
	dd$u <- rnorm(N)
	dd$x <- 1 + rnorm(N)
	dd$y <- 1 + dd$x + dd$u
	m1 <- lm(y ~ x, data = dd)
	m2 <- gmm(y ~ x, x = ~ x, wmatrix = "ident", data = dd)
	coefficients(m1)
	mc <- lm(formula = SBR ~ Age, data = ch)
	m1 <- lm(formula = SBR ~ Age, data = subset(ch, Sex == "M"))
	m2 <- lm(formula = SBR ~ Age, data = subset(ch, Sex == "F"))
	sc <- sum(mc$residuals^2)
	s1 <- sum(m1$residuals^2)
	s2 <- sum(m2$residuals^2)
	k <- 2
	# Test statistic
	fstat <- (sc - (s1 + s2)) / k / (s1 + s2) * (length(mc$residuals) - 2*k)
	fstat
	library("strucchange")
	library("lubridate")

	set.seed(1234567)
	N <- 60
	df <- data.frame(id = 1:N)
	df$date <- seq(as.Date("2013-07-01"), by = "day", along = df$id)
	df$date2 <- difftime(df$date, ymd("2013-07-01"), units = "day")
	df$date3 <- difftime(df$date, ymd("2013-08-01"), units = "day")
	difftime(ymd("2013-08-01"), ymd("2013-07-01"), units = "day")
	library("lubridate")
	library("strucchange")
	library("segmented")

	set.seed(1234567)
	N <- 60
	df <- data.frame(id = 1:N)
	df$date <- seq(as.Date("2013-07-01"), by = "day", along = df$id)
	df$date2 <- difftime(df$date, ymd("2013-07-01"), units = "day")
	df$date3 <- ifelse(df$date > as.Date("2013-08-01"), difftime(df$date, ymd("2013-08-01"), units = "day"), 0)
	N <- 100
	fk <- data.frame(id = 1:N)
	fk$x <- 1 + rnorm(N)
	fk$y1 <- 1 + fk$x + rnorm(N)
	fk$y2 <- 2 + fk$x + rnorm(N)

	ggplot(data = fk, aes(x = x, y = y1)) +
	geom_line(color = "#339966", size = 2) +
	geom_line(aes(y = y2), color = "#990000", size = 2) +
	theme_tufte()
	categorie <- function(x, breaks) {
	c <- length(breaks)
	temp <- 0
	temp[x <= breaks[1]] <- 1
	for (k in 1:c-1) {
	temp[x > breaks[k] & x <= breaks[k+1]] <- k+1
	}
	temp[x > breaks[c]] <- c + 1
	return(temp)
	}
	ISO	country
	ABW	Aruba
	AFG	Afghanistan
	AGO	Angola
	AIA	Anguilla
	ALA	Åland Islands
	ALB	Albania
	AND	Andorra
	ARE	United Arab Emirates
	ARG	Argentina
	code	country
	AFG	Afghanistan
	RSA	South Africa
	ALB	Albania
	ALG	Algeria
	GER	Germany
	AND	Andorra
	ANG	Angola
	ANT	Antigua and Barbuda
	AHO	Netherlands Antilles
	library("dplyr")
	set.seed(123)
	N <- 100
	df <- data.frame(id = 1:N, x = rnorm(N))
	df$x[runif(N) < .1] <- NA
	table(is.na(tdf$x))
	tdf <- tbl_df(df)
	out <- arrange(tdf, desc(x))
	out2 <- tdf[order(tdf$x, decreasing = TRUE),]
	library("ggplot2")
	set.seed(1234)
	N <- 100
	df <- data.frame(i = 1:N, x = rnorm(N))
	df$y <- 1 + df$x + rnorm(N)
	df$z <- (runif(N) < .3)

	pdf("output/test.pdf")
	ggplot(data = df, aes(x = x, y = y, shape = z)) +
	geom_point(size = 3) +