.Rhistory

knitr::opts_chunk$set(echo = TRUE, fig.height = 4.35, fig.width = 4.75)
data(gapminder, package = "gapminder")
head(gapminder)
seq(nrow(gapminder))
head(gapminder)
obs <- nrow(gapminder)
for (i in seq(obs)) {
gapminder[["gdp"]][i] <- gapminder[i, "pop"] * gapminder[i, "gpdPercap"]
}
head(gapminder)
for (i in seq(obs)) {
gapminder[i, "gdp"] <- gapminder[i, "pop"] * gapminder[i, "gpdPercap"]
}
gapminder$gdp <- NA
gapminder$gdp <- NULL
head(gapminder)
gapminder$gdp <- NA
head(gapminder)
obs <- nrow(gapminder)
for (i in seq(obs)) {
gapminder$gdp[i] <- gapminder[i, "pop"] * gapminder[i, "gpdPercap"]
}
for (i in seq(obs)) {
gapminder[i, "gdp"] <- gapminder[i, "pop"] * gapminder[i, "gpdPercap"]
}
seq(obs)
gapminder[1, "gdp"] <- gapminder[1, "pop"] * gapminder[1, "gpdPercap"]
gapminder[1, "pop"] * gapminder[1, "gpdPercap"]
gapminder[1, "pop"]
gapminder[1, "gpdPercap"]
head(gapminder)
gapminder <- gapminder %>% select(-gpd)
library(tidyverse)
gapminder <- gapminder %>% select(-gpd)
gapminder <- gapminder %>% select(-gdp)
obs <- nrow(gapminder)
for (i in seq(obs)) {
gapminder[i, "gdp"] <- gapminder[i, "pop"] * gapminder[i, "gdpPercap"]
}
head(gapminder)
# create a vector of values that you want to repeat the function for
obs <- seq(nrow(gapminder))
obs
obs <- seq_along(nrow(gapminder))
obs
# create a vector of values that you want to repeat the function for
obs <- 1:nrow(gapminder))
# create a vector of values that you want to repeat the function for
obs <- 1:nrow(gapminder)
obs
for (i in obs) { # the function to repeat is enclosed in braces {}
gapminder[i, "log_gdpPercap"] <- log(gapminder[i, "gdpPercap"])
gapminder[i, "log_pop"] <- log(gapminder[i, "pop"])
}
head(gapminder)
le_by_year <- data.frame(year = unique(gapminder$year),
mean_le = NA)
# Create the vector to loop over
years <- unique(gapminder$year)
for (i in years) {
le_by_year[i, "mean_le"] <- mean(gapminder[gapminder$year == i, "lifeExp"],
na.rm = T)
)
}
le_by_year <- data.frame(year = unique(gapminder$year),
mean_le = NA)
# Create the vector to loop over
years <- unique(gapminder$year)
for (i in years) {
le_by_year[i, "mean_le"] <- mean(gapminder[gapminder$year == i, "lifeExp"],
na.rm = T)
}
le_by_year
le_by_year <- data.frame(year = unique(gapminder$year),
mean_le = NA)
# Create the vector to loop over
years <- unique(gapminder$year)
for (i in years) {
le_by_year <- mean(gapminder[gapminder$year == i, "lifeExp"],
na.rm = T)
}
for (i in years) {
le_by_year <- mean(gapminder[gapminder$year == i, "lifeExp"],
na.rm = T)
}
le_by_year
rm(le_by_year)
le_by_year <- c(NULL)
for (i in years) {
le_by_year$i <- mean(gapminder[gapminder$year == i, "lifeExp"],
na.rm = T)
}
years <- unique(gapminder$year)
for (i in years) {
mean_le <- mean(gapminder$lifeExp[gapminder$year == i],
na.rm = T)
paste0(i, ": ", mean_le)
}
for (i in years) {
mean_le <- mean(gapminder$lifeExp[gapminder$year == i],
na.rm = T)
paste0(i, ": ", mean_le)
}
for (i in years) {
mean_le <- mean(gapminder$lifeExp[gapminder$year == i],
na.rm = T)
cat(i, ": ", mean_le)
}
for (i in years) {
mean_le <- mean(gapminder$lifeExp[gapminder$year == i],
na.rm = T)
print(paste0(i, ": ", mean_le))
}
for (i in years) {
mean_le <- mean(gapminder[gapminder$year == i, "lifeExp"],
na.rm = T)
paste0(i, ": ", mean_le)
}
for (i in years) {
mean_le <- mean(gapminder[gapminder$year == i, "lifeExp"],
na.rm = T)
print(paste0(i, ": ", mean_le))
}
mean(gapminder[gapminder$year == 1952, "lifeExp"], na.rm = T)
gapminder[gapminder$year == 1952, "lifeExp"]
knitr::opts_chunk$set(echo = TRUE, fig.height = 4.35, fig.width = 4.75)
data(gapminder, package = "gapminder")
head(gapminder)
class(gapminder)
glimpse(gapminder)
gapminder[gapminder$year == 1952, "lifeExp"]
mean(gapminder[gapminder$year == 1952, "lifeExp"], na.rm = T)
conts <- unique(gapminder$continent)
for (i in conts) {
mean_le <- mean(gapminder[gapminder$continent == i, "lifeExp"],
na.rm = T)
print(paste0(i, ": ", mean_le))
}
gapminder$gdpPercap
log_gdpPercap <- log(gapminder$gdpPercap)
gapminder$vec_log_gdpPercap <- log(gapminder$gdpPercap)
gapminder$vec_log_gdpPercap == gapminder$log_gdpPercap
gapminder$vec_log_gdpPercap
gapminder$log_gdpPercap
log(gapminder$gdpPercap)
gapminder$vec_log_gdpPercap <- log(gapminder$gdpPercap)
gapminder$vec_log_gdpPercap == gapminder$log_gdpPercap
gapminder$vec_log_gdpPercap
gapminder$vec_log_gdpPercap == gapminder$log_gdpPercap
all(gapminder$vec_log_gdpPercap == gapminder$log_gdpPercap)
viz_lm(gapminder, "lifeExp", "gdpPercap", 1977)
viz_lm <-
function(df, dv, iv, year) {
dat <- df[df[["year"]] == year, ]
y <- log(dat[[dv]])
x <- log(dat[[iv]])
fit <- lm(y ~ x)
plot(y ~ x, main = year,
xlab = iv, ylab = dv)
lines(x, predict(fit), col = 'blue')
}
viz_lm(gapminder, "lifeExp", "gdpPercap", 1977)
here::here()
gapminder5 <- read.csv("data/gapminder5.csv", stringsAsFactors=FALSE)
head(gapminder5)
head(gapminder)
for (i in obs) { # the function to repeat is enclosed in braces {}
gapminder[i, "log_gdpPercap"] <- log(gapminder[i, "gdpPercap"])
gapminder[i, "log_pop"] <- log(gapminder[i, "pop"])
}
obs <- 1:nrow(gapminder)
for (i in obs) { # the function to repeat is enclosed in braces {}
gapminder[i, "log_gdpPercap"] <- log(gapminder[i, "gdpPercap"])
gapminder[i, "log_pop"] <- log(gapminder[i, "pop"])
}
head(gapminder)
gapminder$vec_log_gdpPercap == gapminder$log_gdpPercap
year<-2002
if(any(gapminder$year == year)){
print(paste("Record(s) for the year",year,"found."))
} else {
print(paste("No records for year",year))
}
thresholdValue <- 50
for(i in unique(gapminder$continent)) {
tmp <- mean(gapminder$lifeExp[gapminder$continent==i])
if(tmp < thresholdValue) {
print(paste("Average Life Expectancy in", i, "is less than", thresholdValue))
} else {
print(paste("Average Life Expectancy in", i, "is greater than", thresholdValue))
} # end if else condition
}
lowerThreshold <- 50
upperThreshold <- 70
for(iCountry in unique(gapminder$country)){
tmp <- mean(gapminder$lifeExp[gapminder$country==iCountry])
if(tmp < lowerThreshold){
print(paste("Average Life Expectancy in", iCountry, "is less than", lowerThreshold))
}
else if(tmp > lowerThreshold & tmp < upperThreshold){
print(paste("Average Life Expectancy in", iCountry, "is between", lowerThreshold, "and", upperThreshold))
}
else{
print(paste("Average Life Expectancy in", iCountry, "is greater than", upperThreshold))
}
}
threshold <- 60
for (i in unique(gapminder$continent)) {
tmp <- mean(gapminder$lifeExp[gapminder$continent==i])
if (tmp < threshold) {
print(paste("Mean Life Expectancy in", i, "is less than", threshold))
} else {
print(paste("Mean Life Expectancy in", i, "is greater than", threshold))
}
}
threshold <- 70
for (i in unique(gapminder$continent)) {
tmp <- mean(gapminder$lifeExp[gapminder$continent==i])
if (tmp < threshold) {
print(paste("Mean Life Expectancy in", i, "is less than", threshold))
} else {
print(paste("Mean Life Expectancy in", i, "is greater than", threshold))
}
}
lower_threshold <- 50
upper_threshold <- 70
for(i in unique(gapminder$country)){
tmp <- mean(gapminder$lifeExp[gapminder$country==i])
if(tmp < lower_threshold){
print(paste("Average Life Expectancy in", i, "is less than", lower_threshold))
}
else if(tmp > lower_threshold & tmp < upper_threshold){
print(paste("Average Life Expectancy in", i, "is between", lower_threshold, "and", upper_threshold))
}
else{
print(paste("Average Life Expectancy in", i, "is greater than", upper_threshold))
}
}
overall_mean <- mean(gapminder$pop)
for (i in unique(gapminder$country)) {
country_mean <- mean(gapminder$pop[gapminder$country==i])
if (country_mean < overall_mean) {
print(paste("Average Life Expectancy in", i, "is", country_mean))
}
}
overall_mean <- mean(gapminder$pop)
for (i in unique(gapminder$country)) {
country_mean <- mean(gapminder$pop[gapminder$country==i])
if (country_mean < overall_mean) {
mean_le <- mean(gapminder$lifeExp[gapminder$country==i])
print(paste("Average Life Expectancy in", i, "is", mean_le))
}
}
thresholdValue <- 50
for(iContinent in unique(gapminder$continent)) {
tmp <- mean(gapminder$lifeExp[gapminder$continent==iContinent])
if(tmp < thresholdValue) {
print(paste("Average Life Expectancy in", iContinent, "is less than", thresholdValue))
} else {
print(paste("Average Life Expectancy in", iContinent, "is greater than", thresholdValue))
} # end if else condition
}
lower_threshold <- 50
upper_threshold <- 70
for (i in unique(gapminder$continent)){
tmp <- mean(gapminder$lifeExp[gapminder$continent==i])
if (tmp < lower_threshold){
print(paste("Average Life Expectancy in", i, "is less than", lower_threshold))
}
else if (tmp > lower_threshold & tmp < upper_threshold){
print(paste("Average Life Expectancy in", i, "is between", lower_threshold, "and", upper_threshold))
}
else{
print(paste("Average Life Expectancy in", i, "is greater than", upper_threshold))
}
}
getwd()
gapminder <- read.csv("bootcamp-2018/data/gapminder5.csv", stringsAsFactors=FALSE)
gapminder <- read.csv(here::here("data/gapminder5.csv", stringsAsFactors=FALSE)
school <- read.csv(here::here("data/nys_schools.csv"))
census <- read.csv(here::here("data/nys_acs.csv"))
library(tidyverse)
school_dat <- school %>% left_join(nys_acs, by = c("county_name", "year"))
school_dat <- school %>% left_join(census, by = c("county_name", "year"))
school_dat <- school %>% right_join(census, by = c("county_name", "year"))
summary(lm(mean_ela_score ~ county_per_poverty))
summary(lm(mean_ela_score ~ county_per_poverty, data = school_dat))
school_dat %>% group_by(county_name, year) %>% summarize(mean_ela = mean(mean_ela_score, na.rm - T), county_per_poverty = county_per_poverty) summary(lm(mean_ela ~ county_per_poverty, data = school_dat))
school_dat %>% group_by(county_name, year) %>% summarize(mean_ela = mean(mean_ela_score, na.rm - T), county_per_poverty = county_per_poverty) summary(lm(mean_ela ~ county_per_poverty, data = .))
school_dat %>% group_by(county_name, year) %>% summarize(mean_ela = mean(mean_ela_score, na.rm - T), county_per_poverty = county_per_poverty) %>% summary(lm(mean_ela ~ county_per_poverty, data = .))
school_dat %>% group_by(county_name, year) %>% summarize(mean_ela = mean(mean_ela_score, na.rm = T), county_per_poverty = county_per_poverty) %>% summary(lm(mean_ela ~ county_per_poverty, data = .))
school_dat %>% group_by(county_name, year) %>% summarize(mean_ela = mean(mean_ela_score, na.rm = T), county_per_poverty = mean(county_per_poverty, na.rm = T)) %>% summary(lm(mean_ela ~ county_per_poverty, data = .))
school_dat %>% group_by(county_name, year) %>% summarize(mean_ela = mean(mean_ela_score, na.rm = T), county_per_poverty = mean(county_per_poverty, na.rm = T)) %>% lm(mean_ela ~ county_per_poverty, data = .)) %>% summary()
school_dat %>% group_by(county_name, year) %>% summarize(mean_ela = mean(mean_ela_score, na.rm = T), county_per_poverty = mean(county_per_poverty, na.rm = T)) %>% lm(mean_ela ~ county_per_poverty, data = .) %>% summary()
school_dat <- school_dat %>% na_if(-99)
school_dat %>% group_by(county_name, year) %>% summarize(mean_ela = mean(mean_ela_score, na.rm = T), county_per_poverty = mean(county_per_poverty, na.rm = T)) %>% lm(mean_ela ~ county_per_poverty, data = .) %>% summary()
View(school_dat)
View(school)