# Loading dslabs and tidyverse packages
library("dslabs")
library("tidyverse")── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
✔ ggplot2 3.4.0 ✔ purrr 0.3.4
✔ tibble 3.1.8 ✔ dplyr 1.1.0
✔ tidyr 1.2.0 ✔ stringr 1.4.1
✔ readr 2.1.2 ✔ forcats 0.5.2
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()# Looking at help file for gapminder data
help(gapminder)
# Getting an overview of data structure
str(gapminder)'data.frame': 10545 obs. of 9 variables:
$ country : Factor w/ 185 levels "Albania","Algeria",..: 1 2 3 4 5 6 7 8 9 10 ...
$ year : int 1960 1960 1960 1960 1960 1960 1960 1960 1960 1960 ...
$ infant_mortality: num 115.4 148.2 208 NA 59.9 ...
$ life_expectancy : num 62.9 47.5 36 63 65.4 ...
$ fertility : num 6.19 7.65 7.32 4.43 3.11 4.55 4.82 3.45 2.7 5.57 ...
$ population : num 1636054 11124892 5270844 54681 20619075 ...
$ gdp : num NA 1.38e+10 NA NA 1.08e+11 ...
$ continent : Factor w/ 5 levels "Africa","Americas",..: 4 1 1 2 2 3 2 5 4 3 ...
$ region : Factor w/ 22 levels "Australia and New Zealand",..: 19 11 10 2 15 21 2 1 22 21 ...# Getting summary of data from gapminder
summary(gapminder) country year infant_mortality life_expectancy
Albania : 57 Min. :1960 Min. : 1.50 Min. :13.20
Algeria : 57 1st Qu.:1974 1st Qu.: 16.00 1st Qu.:57.50
Angola : 57 Median :1988 Median : 41.50 Median :67.54
Antigua and Barbuda: 57 Mean :1988 Mean : 55.31 Mean :64.81
Argentina : 57 3rd Qu.:2002 3rd Qu.: 85.10 3rd Qu.:73.00
Armenia : 57 Max. :2016 Max. :276.90 Max. :83.90
(Other) :10203 NA's :1453
fertility population gdp continent
Min. :0.840 Min. :3.124e+04 Min. :4.040e+07 Africa :2907
1st Qu.:2.200 1st Qu.:1.333e+06 1st Qu.:1.846e+09 Americas:2052
Median :3.750 Median :5.009e+06 Median :7.794e+09 Asia :2679
Mean :4.084 Mean :2.701e+07 Mean :1.480e+11 Europe :2223
3rd Qu.:6.000 3rd Qu.:1.523e+07 3rd Qu.:5.540e+10 Oceania : 684
Max. :9.220 Max. :1.376e+09 Max. :1.174e+13
NA's :187 NA's :185 NA's :2972
region
Western Asia :1026
Eastern Africa : 912
Western Africa : 912
Caribbean : 741
South America : 684
Southern Europe: 684
(Other) :5586 # Determining the type of gapminder object
class(gapminder)[1] "data.frame"# Creating an object africadata containing only the African countries
africadata <- gapminder %>% filter(continent == "Africa")
# Looking at the structure and summary of object (africadata)
str(africadata)'data.frame': 2907 obs. of 9 variables:
$ country : Factor w/ 185 levels "Albania","Algeria",..: 2 3 18 22 26 27 29 31 32 33 ...
$ year : int 1960 1960 1960 1960 1960 1960 1960 1960 1960 1960 ...
$ infant_mortality: num 148 208 187 116 161 ...
$ life_expectancy : num 47.5 36 38.3 50.3 35.2 ...
$ fertility : num 7.65 7.32 6.28 6.62 6.29 6.95 5.65 6.89 5.84 6.25 ...
$ population : num 11124892 5270844 2431620 524029 4829291 ...
$ gdp : num 1.38e+10 NA 6.22e+08 1.24e+08 5.97e+08 ...
$ continent : Factor w/ 5 levels "Africa","Americas",..: 1 1 1 1 1 1 1 1 1 1 ...
$ region : Factor w/ 22 levels "Australia and New Zealand",..: 11 10 20 17 20 5 10 20 10 10 ...summary(africadata) country year infant_mortality life_expectancy
Algeria : 57 Min. :1960 Min. : 11.40 Min. :13.20
Angola : 57 1st Qu.:1974 1st Qu.: 62.20 1st Qu.:48.23
Benin : 57 Median :1988 Median : 93.40 Median :53.98
Botswana : 57 Mean :1988 Mean : 95.12 Mean :54.38
Burkina Faso: 57 3rd Qu.:2002 3rd Qu.:124.70 3rd Qu.:60.10
Burundi : 57 Max. :2016 Max. :237.40 Max. :77.60
(Other) :2565 NA's :226
fertility population gdp continent
Min. :1.500 Min. : 41538 Min. :4.659e+07 Africa :2907
1st Qu.:5.160 1st Qu.: 1605232 1st Qu.:8.373e+08 Americas: 0
Median :6.160 Median : 5570982 Median :2.448e+09 Asia : 0
Mean :5.851 Mean : 12235961 Mean :9.346e+09 Europe : 0
3rd Qu.:6.860 3rd Qu.: 13888152 3rd Qu.:6.552e+09 Oceania : 0
Max. :8.450 Max. :182201962 Max. :1.935e+11
NA's :51 NA's :51 NA's :637
region
Eastern Africa :912
Western Africa :912
Middle Africa :456
Northern Africa :342
Southern Africa :285
Australia and New Zealand: 0
(Other) : 0 glimpse(africadata)Rows: 2,907
Columns: 9
$ country <fct> "Algeria", "Angola", "Benin", "Botswana", "Burkina Fa…
$ year <int> 1960, 1960, 1960, 1960, 1960, 1960, 1960, 1960, 1960,…
$ infant_mortality <dbl> 148.2, 208.0, 186.9, 115.5, 161.3, 145.1, 166.9, NA, …
$ life_expectancy <dbl> 47.50, 35.98, 38.29, 50.34, 35.21, 40.58, 43.46, 50.1…
$ fertility <dbl> 7.65, 7.32, 6.28, 6.62, 6.29, 6.95, 5.65, 6.89, 5.84,…
$ population <dbl> 11124892, 5270844, 2431620, 524029, 4829291, 2786740,…
$ gdp <dbl> 13828152297, NA, 621797131, 124460933, 596612183, 341…
$ continent <fct> Africa, Africa, Africa, Africa, Africa, Africa, Afric…
$ region <fct> Northern Africa, Middle Africa, Western Africa, South…# Creating an object infantmort_lifeexp containing only infant_mortality and life_expectancy variables
infantmort_lifeexp <- africadata %>%
select(infant_mortality, life_expectancy)
# Looking at the structure and summary of object (infantmort_lifeexp)
str(infantmort_lifeexp)'data.frame': 2907 obs. of 2 variables:
$ infant_mortality: num 148 208 187 116 161 ...
$ life_expectancy : num 47.5 36 38.3 50.3 35.2 ...summary(infantmort_lifeexp) infant_mortality life_expectancy
Min. : 11.40 Min. :13.20
1st Qu.: 62.20 1st Qu.:48.23
Median : 93.40 Median :53.98
Mean : 95.12 Mean :54.38
3rd Qu.:124.70 3rd Qu.:60.10
Max. :237.40 Max. :77.60
NA's :226 glimpse(infantmort_lifeexp)Rows: 2,907
Columns: 2
$ infant_mortality <dbl> 148.2, 208.0, 186.9, 115.5, 161.3, 145.1, 166.9, NA, …
$ life_expectancy <dbl> 47.50, 35.98, 38.29, 50.34, 35.21, 40.58, 43.46, 50.1…# Creating an object pop_lifeexp containing only population and life_expectancy variables
pop_lifeexp <- africadata %>%
select(population, life_expectancy)
# Looking at the structure and summary of object (pop_lifeexp)
str(pop_lifeexp)'data.frame': 2907 obs. of 2 variables:
$ population : num 11124892 5270844 2431620 524029 4829291 ...
$ life_expectancy: num 47.5 36 38.3 50.3 35.2 ...summary(pop_lifeexp) population life_expectancy
Min. : 41538 Min. :13.20
1st Qu.: 1605232 1st Qu.:48.23
Median : 5570982 Median :53.98
Mean : 12235961 Mean :54.38
3rd Qu.: 13888152 3rd Qu.:60.10
Max. :182201962 Max. :77.60
NA's :51 glimpse(pop_lifeexp)Rows: 2,907
Columns: 2
$ population <dbl> 11124892, 5270844, 2431620, 524029, 4829291, 2786740, …
$ life_expectancy <dbl> 47.50, 35.98, 38.29, 50.34, 35.21, 40.58, 43.46, 50.12…# Plotting life expectancy as a function of infant mortality
ggplot(data = infantmort_lifeexp,
(aes(x = infant_mortality, y = life_expectancy))) +
theme_classic() +
geom_point(size = 1.0) +
labs(title = "Life expectancy as a function of infant mortality",
x = "Infant Mortality", y = "Life Expectancy (In Years)") +
theme(axis.text = element_text(face = "bold"), plot.title = element_text(hjust = 0.5, size = 14),
axis.title = element_text(size = 14))Warning: Removed 226 rows containing missing values (`geom_point()`).
# Plotting life expectancy as a function of population size
ggplot(data = pop_lifeexp,
(aes(x = population, y = life_expectancy))) +
theme_classic() +
geom_point(size = 1.0) +
scale_x_continuous(trans = 'log10') +
labs(title = "Life expectancy as a function of population size",
x = "Population (In Logscale)", y = "Life Expectancy (In Years)") +
theme(axis.text = element_text(face = "bold"), plot.title = element_text(hjust = 0.5, size = 14),
axis.title = element_text(size = 14))Warning: Removed 51 rows containing missing values (`geom_point()`).
# Looking at the years having missing data for infant mortality in africadata
infant_mortality_yrs <- africadata %>%
filter(is.na(infant_mortality))
table(infant_mortality_yrs$year)
1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975
10 17 16 16 15 14 13 11 11 7 5 6 6 6 5 5
1976 1977 1978 1979 1980 1981 2016
3 3 2 2 1 1 51 # Creating a new object named africadata_2000 by using only year 2000 data from africadata object
africadata_2000 <- africadata %>%
filter(year == 2000)
# Looking at the structure and summary of object (africadata_2000)
str(africadata_2000)'data.frame': 51 obs. of 9 variables:
$ country : Factor w/ 185 levels "Albania","Algeria",..: 2 3 18 22 26 27 29 31 32 33 ...
$ year : int 2000 2000 2000 2000 2000 2000 2000 2000 2000 2000 ...
$ infant_mortality: num 33.9 128.3 89.3 52.4 96.2 ...
$ life_expectancy : num 73.3 52.3 57.2 47.6 52.6 46.7 54.3 68.4 45.3 51.5 ...
$ fertility : num 2.51 6.84 5.98 3.41 6.59 7.06 5.62 3.7 5.45 7.35 ...
$ population : num 31183658 15058638 6949366 1736579 11607944 ...
$ gdp : num 5.48e+10 9.13e+09 2.25e+09 5.63e+09 2.61e+09 ...
$ continent : Factor w/ 5 levels "Africa","Americas",..: 1 1 1 1 1 1 1 1 1 1 ...
$ region : Factor w/ 22 levels "Australia and New Zealand",..: 11 10 20 17 20 5 10 20 10 10 ...summary(africadata_2000) country year infant_mortality life_expectancy
Algeria : 1 Min. :2000 Min. : 12.30 Min. :37.60
Angola : 1 1st Qu.:2000 1st Qu.: 60.80 1st Qu.:51.75
Benin : 1 Median :2000 Median : 80.30 Median :54.30
Botswana : 1 Mean :2000 Mean : 78.93 Mean :56.36
Burkina Faso: 1 3rd Qu.:2000 3rd Qu.:103.30 3rd Qu.:60.00
Burundi : 1 Max. :2000 Max. :143.30 Max. :75.00
(Other) :45
fertility population gdp continent
Min. :1.990 Min. : 81154 Min. :2.019e+08 Africa :51
1st Qu.:4.150 1st Qu.: 2304687 1st Qu.:1.274e+09 Americas: 0
Median :5.550 Median : 8799165 Median :3.238e+09 Asia : 0
Mean :5.156 Mean : 15659800 Mean :1.155e+10 Europe : 0
3rd Qu.:5.960 3rd Qu.: 17391242 3rd Qu.:8.654e+09 Oceania : 0
Max. :7.730 Max. :122876723 Max. :1.329e+11
region
Eastern Africa :16
Western Africa :16
Middle Africa : 8
Northern Africa : 6
Southern Africa : 5
Australia and New Zealand: 0
(Other) : 0 glimpse(africadata_2000)Rows: 51
Columns: 9
$ country <fct> "Algeria", "Angola", "Benin", "Botswana", "Burkina Fa…
$ year <int> 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,…
$ infant_mortality <dbl> 33.9, 128.3, 89.3, 52.4, 96.2, 93.4, 91.9, 29.1, 113.…
$ life_expectancy <dbl> 73.3, 52.3, 57.2, 47.6, 52.6, 46.7, 54.3, 68.4, 45.3,…
$ fertility <dbl> 2.51, 6.84, 5.98, 3.41, 6.59, 7.06, 5.62, 3.70, 5.45,…
$ population <dbl> 31183658, 15058638, 6949366, 1736579, 11607944, 67670…
$ gdp <dbl> 54790058957, 9129180361, 2254838685, 5632391130, 2610…
$ continent <fct> Africa, Africa, Africa, Africa, Africa, Africa, Afric…
$ region <fct> Northern Africa, Middle Africa, Western Africa, South…# Plotting life expectancy as a function of infant mortality in the year 2000
ggplot(data = africadata_2000,
(aes(x = infant_mortality, y = life_expectancy))) +
theme_classic() +
geom_point(size = 1.0) +
labs(title = "Life expectancy as a function of infant mortality in the year 2000",
x = "Infant Mortality", y = "Life Expectancy (In Years)") +
theme(axis.text = element_text(face = "bold"), plot.title = element_text(hjust = 0.5, size = 14),
axis.title = element_text(size = 14))
# Plotting life expectancy as a function of population size in the year 2000
ggplot(data = africadata_2000,
(aes(x = population, y = life_expectancy))) +
theme_classic() +
geom_point(size = 1.0) +
scale_x_continuous(trans = 'log10') +
labs(title = "Life expectancy as a function of population size in the year 2000",
x = "Population (In Logscale)", y = "Life Expectancy (In Years)") +
theme(axis.text = element_text(face = "bold"), plot.title = element_text(hjust = 0.5, size = 14),
axis.title = element_text(size = 14))
# Using lm function to fit linear regression model using life expectancy as the outcome and infant mortality as the predictor for the year 2000
fit1 <- lm(life_expectancy ~ infant_mortality, data = africadata_2000)
summary(fit1)
Call:
lm(formula = life_expectancy ~ infant_mortality, data = africadata_2000)
Residuals:
Min 1Q Median 3Q Max
-22.6651 -3.7087 0.9914 4.0408 8.6817
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 71.29331 2.42611 29.386 < 2e-16 ***
infant_mortality -0.18916 0.02869 -6.594 2.83e-08 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 6.221 on 49 degrees of freedom
Multiple R-squared: 0.4701, Adjusted R-squared: 0.4593
F-statistic: 43.48 on 1 and 49 DF, p-value: 2.826e-08# Using lm function to fit linear regression model using life expectancy as the outcome and population size as the predictor for the year 2000
fit2 <- lm(life_expectancy ~ population, data = africadata_2000)
summary(fit2)
Call:
lm(formula = life_expectancy ~ population, data = africadata_2000)
Residuals:
Min 1Q Median 3Q Max
-18.429 -4.602 -2.568 3.800 18.802
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 5.593e+01 1.468e+00 38.097 <2e-16 ***
population 2.756e-08 5.459e-08 0.505 0.616
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 8.524 on 49 degrees of freedom
Multiple R-squared: 0.005176, Adjusted R-squared: -0.01513
F-statistic: 0.2549 on 1 and 49 DF, p-value: 0.6159Based on the p-values for each fit, we found statistically significant negative correlation between infant mortality and life expectancy in the year 2000 (p-value: 2.83e-08) while we found no statistically significant correlation between population size and life expectancy in the year 2000 (p-value: 0.616).
—————————————
THIS SECTION ADDED BY NICOLE LUISI
—————————————
#Create some plots
# Install and load new packages
#install.packages(c("plotly", "broom"))
library(plotly)
library(broom)# Create subset for 4 specific regions
africadata_limitregion <- africadata %>%
filter(region %in% c("Northern Africa", "Southern Africa", "Western Africa", "Middle Africa"))
# Set color palette
manualcolors<-c('coral', 'forestgreen', 'darkorange1', 'firebrick4', 'cornflowerblue', 'darkseagreen', 'cyan3',
'brown1', 'blueviolet')
# Generate figure
fig <- plot_ly(data=africadata_limitregion, x = ~year, y = ~life_expectancy, text = ~region, type = 'scatter', mode = 'markers', color = ~region, colors=manualcolors)
fig <- fig %>% layout(title = 'Life Expectancy (years) by Year in 4 Regions of Africa',
yaxis = list(title = "Life Expectancy (yrs)"),
xaxis = list(title = "Year"))
# View figure, hover for data points
fig#library(ggplot2)
# Generate figure
theme_set(
theme_bw() +
theme(legend.position = "top"))
ggplot(africadata, aes(x = gdp, y = infant_mortality)) +
geom_point(aes(color = region, size = fertility), alpha = 0.5) +
scale_color_manual(values = c("#d1495b", "#edae49", "#66a182", "#2e4057", "79b7c5")) +
scale_size(range = c(0.5, 6)) +
xlab("GDP") +
ylab("Infant Mortality (yrs)") +
ggtitle("Infant Mortality by GDP, with Region as Color and Size as Fertility")Warning: Removed 704 rows containing missing values (`geom_point()`).
#Fit a model
# Model for life_expectancy ~ fertility for 4 regions in Africa
newmodel <- lm(life_expectancy ~ fertility, data = africadata_limitregion)
# Summary for new model
summary(newmodel)
Call:
lm(formula = life_expectancy ~ fertility, data = africadata_limitregion)
Residuals:
Min 1Q Median 3Q Max
-21.013 -3.950 1.235 5.186 21.800
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 76.8629 0.7396 103.93 <2e-16 ***
fertility -3.9165 0.1244 -31.47 <2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 7.376 on 1958 degrees of freedom
(35 observations deleted due to missingness)
Multiple R-squared: 0.3359, Adjusted R-squared: 0.3356
F-statistic: 990.5 on 1 and 1958 DF, p-value: < 2.2e-16# Use broom to make table for new model
tidy(newmodel)# A tibble: 2 × 5
term estimate std.error statistic p.value
<chr> <dbl> <dbl> <dbl> <dbl>
1 (Intercept) 76.9 0.740 104. 0
2 fertility -3.92 0.124 -31.5 2.78e-176# Create function to summarize results another way
customoutput <- function (fit) {
require(ggplot2)
ggplot(fit$model, aes_string(x = names(fit$model)[2], y = names(fit$model)[1])) +
geom_point() +
xlab("Fertility") +
ylab("Life Expectancy (yrs)") +
ggtitle("Life Expectancy and Fertility in 4 Regions of Africa") +
stat_smooth(method = "lm", col = "red") +
labs(title = paste("Adj R2 = ",signif(summary(fit)$adj.r.squared, 5),
"Intercept =",signif(fit$coef[[1]],5 ),
" Slope =",signif(fit$coef[[2]], 5),
" P =",signif(summary(fit)$coef[2,4], 5)))
}
customoutput(newmodel)Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
ℹ Please use tidy evaluation ideoms with `aes()``geom_smooth()` using formula = 'y ~ x'