core2 %>%
# filter(year==4) %>%
group_by(year) %>%
summarize(mean_score=mean(post_test), mean_score2=mean(pre_test))
core2 %>%
filter(year==4) %>%
summarize(mean_score=mean(post_test), mean_score2=mean(pre_test))
# Scatter plot comparing pop and lifeExp, with color representing continent
ggplot(gapminder_1952, aes(x = pop, y = lifeExp, color = continent)) +
geom_point() +
scale_x_log10()
library(gapminder)
library(dplyr)
library(ggplot2)
gapminder_1952 <- gapminder %>%
filter(year == 1952)
# Scatter plot comparing pop and gdpPercap, with both axes on a log scale
ggplot(gapminder_1952, aes(x = pop, y = gdpPercap)) +
geom_point() +
scale_x_log10() +
scale_y_log10()
#this is a popular data editing package
library(tidyverse)
#this includes datasets
library(gapminder)
#this one includes summarize()
library(FSA)
#The dataset gapminder comes from gapminder package
#lifeExp by subgroup continent
result_mean1<-Summarize(lifeExp ~ continent, data=gapminder)
#lifeExp by subgroup continent and year
result_mean2<-Summarize(lifeExp ~ continent + year, data=gapminder)
#results are in result_mean1 and result_mean2
gapminder %>%
mutate(lifeExp = lifeExp * 12)
library(gapminder)
library(dplyr)
# Filter, mutate, and arrange the gapminder dataset
gapminder %>%
filter(year == 2007) %>%
mutate(lifeExpMonths = 12 * lifeExp) %>%
arrange(desc(lifeExpMonths))
ggplot(abc1,aes(x=GrowthMindset, y=SelfEfficacy))+
geom_point()
#create scales
#problem is that this creates a scale even when there are missing values
wholedata<-transmute(wholedata,flag,dataID,commonID,treat,
GrowthMindset=rowMeans(cbind(q0008_0001, q0008_0002, q0008_0003, q0008_0004, q0008_0005, q0008_0006, q0008_0007, q0008_0008),na.rm=TRUE),
SelfEfficacy=rowMeans(cbind(q0009_0001, q0009_0002, q0009_0003, q0009_0004, q0009_0005),na.rm=TRUE),
MSelfEfficacy=rowMeans(cbind(q0010_0001, q0010_0002, q0010_0003, q0010_0004, q0010_0005, q0010_0006, q0010_0007),na.rm=TRUE),
MathAnxiety=rowMeans(cbind(q0011_0001, q0011_0002, q0011_0003, q0011_0004, q0011_0005, q0011_0006),na.rm=TRUE),
TeacherUse=rowMeans(cbind(q0012_0001, q0012_0002, q0012_0003, q0012_0004, q0013_0001, q0013_0002, q0013_0003, q0013_0004),na.rm=TRUE)
)