1. Introduction to R
Sebástian Narváez
2022-07-27
Overview
1. Load dependencies
Install packages if needed. Go to the packages tab and install dplyr
and stats packages (also you can use the install.packages
function to install packages from the console, e.g:
install.packages('dplyr')). Then, load packages if
needed:
# tidyverse load dplyr, tidyr, ggplot and others useful packages.
library(tidyverse) ## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.9
## ✔ tidyr 1.2.0 ✔ stringr 1.4.0
## ✔ readr 2.1.2 ✔ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()# Setting the theme for the plots.
theme_set(theme_bw()) 2. Read data
Use the read.csv function to load
precip_car.csv Each row contains the ID, Name, Elevation and
monthly precipitation (p01…p12) for weather stations:
# Define the file path based on the workspace directory (in this case root.dir)
file_path <- "tareas/1_tarea_intro_r/precip_car.csv"
precipitation <- read.csv(file_path)
summary(precipitation)## Id Nombre Latitud Longitud
## Min. :12010090 Length:242 Min. : 7.748 Min. :-76.72
## 1st Qu.:15052510 Class :character 1st Qu.: 9.287 1st Qu.:-75.39
## Median :25020645 Mode :character Median : 9.972 Median :-74.75
## Mean :21722494 Mean :10.009 Mean :-74.38
## 3rd Qu.:28040240 3rd Qu.:10.718 3rd Qu.:-73.35
## Max. :29065020 Max. :12.345 Max. :-71.27
## Altitud p01 p02 p03
## Min. : 1.00 Min. : 0.1429 Min. : 0.03143 Min. : 0.9756
## 1st Qu.: 23.50 1st Qu.: 8.2610 1st Qu.: 8.03171 1st Qu.: 19.3035
## Median : 67.50 Median : 14.8902 Median : 17.81829 Median : 36.9110
## Mean : 99.71 Mean : 18.7426 Mean : 21.78586 Mean : 41.3556
## 3rd Qu.:120.00 3rd Qu.: 22.4701 3rd Qu.: 28.77378 3rd Qu.: 58.6982
## Max. :900.00 Max. :145.2263 Max. :151.92895 Max. :220.0395
## p04 p05 p06 p07
## Min. : 0.878 Min. : 12.84 Min. : 2.415 Min. : 2.22
## 1st Qu.: 72.887 1st Qu.:124.32 1st Qu.: 92.814 1st Qu.: 83.41
## Median : 99.753 Median :159.95 Median :120.887 Median :114.34
## Mean :100.795 Mean :155.91 Mean :122.514 Mean :117.71
## 3rd Qu.:126.951 3rd Qu.:188.52 3rd Qu.:152.900 3rd Qu.:153.95
## Max. :317.761 Max. :474.00 Max. :411.632 Max. :497.75
## p08 p09 p10 p11
## Min. : 10.12 Min. : 30.76 Min. : 66.67 Min. : 39.04
## 1st Qu.:111.35 1st Qu.:131.12 1st Qu.:142.24 1st Qu.: 94.73
## Median :147.51 Median :161.60 Median :171.33 Median :117.91
## Mean :147.19 Mean :160.12 Mean :182.39 Mean :127.24
## 3rd Qu.:181.84 3rd Qu.:188.14 3rd Qu.:208.37 3rd Qu.:146.72
## Max. :572.68 Max. :508.49 Max. :598.42 Max. :507.58
## p12 Biome Depto
## Min. : 8.117 Length:242 Length:242
## 1st Qu.: 33.123 Class :character Class :character
## Median : 42.861 Mode :character Mode :character
## Mean : 50.057
## 3rd Qu.: 54.410
## Max. :238.295Improve the data frame converting the categorical variables (Depto and Biome) from character to factor:
precipitation$Depto <- factor(precipitation$Depto)
precipitation$Biome <- factor(precipitation$Biome)
summary(precipitation)## Id Nombre Latitud Longitud
## Min. :12010090 Length:242 Min. : 7.748 Min. :-76.72
## 1st Qu.:15052510 Class :character 1st Qu.: 9.287 1st Qu.:-75.39
## Median :25020645 Mode :character Median : 9.972 Median :-74.75
## Mean :21722494 Mean :10.009 Mean :-74.38
## 3rd Qu.:28040240 3rd Qu.:10.718 3rd Qu.:-73.35
## Max. :29065020 Max. :12.345 Max. :-71.27
##
## Altitud p01 p02 p03
## Min. : 1.00 Min. : 0.1429 Min. : 0.03143 Min. : 0.9756
## 1st Qu.: 23.50 1st Qu.: 8.2610 1st Qu.: 8.03171 1st Qu.: 19.3035
## Median : 67.50 Median : 14.8902 Median : 17.81829 Median : 36.9110
## Mean : 99.71 Mean : 18.7426 Mean : 21.78586 Mean : 41.3556
## 3rd Qu.:120.00 3rd Qu.: 22.4701 3rd Qu.: 28.77378 3rd Qu.: 58.6982
## Max. :900.00 Max. :145.2263 Max. :151.92895 Max. :220.0395
##
## p04 p05 p06 p07
## Min. : 0.878 Min. : 12.84 Min. : 2.415 Min. : 2.22
## 1st Qu.: 72.887 1st Qu.:124.32 1st Qu.: 92.814 1st Qu.: 83.41
## Median : 99.753 Median :159.95 Median :120.887 Median :114.34
## Mean :100.795 Mean :155.91 Mean :122.514 Mean :117.71
## 3rd Qu.:126.951 3rd Qu.:188.52 3rd Qu.:152.900 3rd Qu.:153.95
## Max. :317.761 Max. :474.00 Max. :411.632 Max. :497.75
##
## p08 p09 p10 p11
## Min. : 10.12 Min. : 30.76 Min. : 66.67 Min. : 39.04
## 1st Qu.:111.35 1st Qu.:131.12 1st Qu.:142.24 1st Qu.: 94.73
## Median :147.51 Median :161.60 Median :171.33 Median :117.91
## Mean :147.19 Mean :160.12 Mean :182.39 Mean :127.24
## 3rd Qu.:181.84 3rd Qu.:188.14 3rd Qu.:208.37 3rd Qu.:146.72
## Max. :572.68 Max. :508.49 Max. :598.42 Max. :507.58
##
## p12 Biome Depto
## Min. : 8.117 Sub-Humid Tropical Forests: 5 La Guajira:45
## 1st Qu.: 33.123 Tropical deserts : 17 Cordoba :42
## Median : 42.861 Tropical dry forests :212 Magdalena :37
## Mean : 50.057 Tropical rainforests : 8 Cesar :36
## 3rd Qu.: 54.410 Bolivar :34
## Max. :238.295 Sucre :23
## (Other) :253. Calc the mean anual precipitation by station using the function
rowSums:
# the data is sliced to only sum the precipitation columns.
precipitation$p_anual <- rowSums(precipitation[,6:17])
head(precipitation)## Id Nombre Latitud Longitud Altitud
## 1 12045010 ARBOLETES [12045010] 8.846944 -76.43194 4
## 2 12015070 AEROPUERTO LOS CEDROS [12015070] 7.816389 -76.71789 41
## 3 12010110 PRADO MAR [12010110] 7.987417 -76.63853 5
## 4 12015020 UNIBAN [12015020] 7.825917 -76.65133 43
## 5 12010090 TRIGANA [12010090] 7.747667 -76.71189 4
## 6 14010100 PINTADA LA [14010100] 10.955111 -74.99500 200
## p01 p02 p03 p04 p05 p06 p07
## 1 72.6317073 53.2756098 64.448780 133.06585 176.6366 155.76829 162.49268
## 2 145.2263158 151.9289474 220.039474 302.97368 330.0342 288.39474 326.23947
## 3 91.3585366 118.3658537 128.648780 202.77073 247.9512 221.45366 202.57805
## 4 124.4073171 111.1000000 154.853659 234.59512 275.4610 241.79756 254.85366
## 5 135.9243902 141.6634146 183.790244 259.66829 312.9659 314.43415 286.25610
## 6 0.1428571 0.8214286 3.071429 23.00357 109.5107 95.42857 69.48929
## p08 p09 p10 p11 p12 Biome Depto
## 1 194.9610 164.2829 175.6976 157.1049 96.85122 Tropical dry forests Antioquia
## 2 283.7211 291.4526 288.5105 294.8237 238.29474 Tropical rainforests Antioquia
## 3 243.4951 218.1707 202.2098 187.5366 173.50488 Tropical rainforests Antioquia
## 4 249.7488 270.7122 265.2293 259.2293 193.31951 Tropical rainforests Antioquia
## 5 294.0927 273.6341 257.4805 251.8878 238.04878 Tropical rainforests Antioquia
## 6 127.1714 184.9643 189.9821 129.7321 33.50000 Tropical dry forests Atlantico
## p_anual
## 1 1607.2171
## 2 3161.6395
## 3 2238.0439
## 4 2635.3073
## 5 2949.8463
## 6 966.81794. Calculate mean annual precipitation for each
Depto using the aggregate function:
Parameters:
x(first argument by default): The data to be aggregate by groups.by: The classification of all entries inxneeded to be grouped.FUN: Function to apply to grouped data.
mean_anual_prec_depto <- aggregate(
precipitation$p_anual, by = list(precipitation$Depto), FUN = mean
)
colnames(mean_anual_prec_depto) <- c('Depto', 'mean_anual_precipitation')
mean_anual_prec_depto## Depto mean_anual_precipitation
## 1 Antioquia 2518.4108
## 2 Atlantico 996.3746
## 3 Bolivar 1490.1788
## 4 Cesar 1415.9017
## 5 Cordoba 1435.9659
## 6 La Guajira 673.1426
## 7 Magdalena 1295.4668
## 8 Sucre 1251.94095. Calculate mean annual precipitation for each
Biome using the aggregate function:
mean_anual_prec_biome <- aggregate(
precipitation$p_anual, by = list(precipitation$Biome), FUN = mean
)
colnames(mean_anual_prec_biome) <- c('Biome', 'mean_anual_precipitation')
mean_anual_prec_biome## Biome mean_anual_precipitation
## 1 Sub-Humid Tropical Forests 2483.0590
## 2 Tropical deserts 379.0881
## 3 Tropical dry forests 1246.8179
## 4 Tropical rainforests 2287.72446. Create box plot of annual precip by biome using
ggplot packages:
ggplot(data = precipitation) +
geom_boxplot(
mapping = aes(
x = Biome,
y = p_anual,
fill = Biome,
),
show.legend = FALSE
) +
labs(
title = "Mean anual precipitation by biome",
x = "Biomes",
y = "Precipitation [mm]"
)
Questions
1. What are the data frame dimensions (# rows and columns)?
dim(precipitation)## [1] 242 20The dataframe have 242 entries (rows) and 20 variables (columns).
2. Show summary tables (mean precip by departamento and biome)
Overview points 4 and 5.
3. Show boxplot: are the results what you expected?
Yes, in theory, deserts and tropical dry forest experiment less precipitations than sub-humid tropical forest and tropical forest.