Universal Code Hub Upgrade

R Code Hub

tidyverse · ggplot2 · sf · terra · lme4 · survey — research-grade scripts

Generate R CodeR (tidyverse / sf / terra) · AI · Premium

🔒 Preview only — sign in and upgrade to generate code. Sign in

⚙ The site owner has not connected an AI provider yet — generation will be available soon.

Study Objective *

Study Area Dataset / Variables Output Type

R Code Library — Ready-to-Run Recipes

4 ready-to-run snippet(s) · curated with sample data, dataset sources & use cases

Visualization🎓 Beginner

ggplot2 — Trend with Confidence BandLoess-smoothed line with 95% CI ribbon across a time series.

#ggplot2#tidyverse

VisualizationBeginner

ggplot2 — Trend with Confidence Band

Loess-smoothed line with 95% CI ribbon across a time series.

🎯 Use Case

Visualizing yearly indicators (temperature, prices, indicators).

👥 Audience

R beginners, social science researchers.

Data to use with this code

trend.csv · csv

year,value
2015,32.1
2016,33.0
2017,33.5
2018,33.9
2019,34.4
2020,34.0
2021,34.8
2022,35.2
2023,35.7
2024,36.0

r-ggplot-trend.R

library(tidyverse)
df <- read_csv('trend.csv')
ggplot(df, aes(year, value)) +
  geom_point(size = 2, colour = '#2563eb') +
  geom_smooth(method = 'loess', se = TRUE, colour = '#dc2626', fill = '#fecaca') +
  labs(title = 'Annual Trend', x = NULL, y = 'Value') +
  theme_minimal(base_size = 13)

📤 Expected Outputs

Trend chart with CI ribbon

#ggplot2#tidyverse

Geospatial🎓 Intermediate

sf — Buffer + Spatial JoinBuffer point features by 500 m and count overlapping facilities per buffer.

#sf#buffer#spatial-join

GeospatialIntermediate

sf — Buffer + Spatial Join

Buffer point features by 500 m and count overlapping facilities per buffer.

🎯 Use Case

Accessibility analysis around schools, clinics, transit stops.

👥 Audience

GIS analysts who prefer R over QGIS scripting.

r-sf-buffer.R

library(sf); library(dplyr)
pts <- st_read('points.geojson')
fac <- st_read('facilities.geojson')
buf <- st_buffer(st_transform(pts, 3857), 500) |> st_transform(4326)
joined <- st_join(buf, fac, join = st_intersects)
result <- joined |> group_by(id) |> summarise(n_facilities = n())
st_write(result, 'buffer_counts.geojson', delete_dsn = TRUE)

📤 Expected Outputs

buffer_counts.geojson with facility counts

#sf#buffer#spatial-join

Remote Sensing🎓 Intermediate

terra — NDVI & Zonal StatsCompute NDVI from a Landsat stack and extract mean NDVI per admin polygon.

#terra#ndvi#zonal

Remote SensingIntermediate

terra — NDVI & Zonal Stats

Compute NDVI from a Landsat stack and extract mean NDVI per admin polygon.

🎯 Use Case

Per-district vegetation monitoring; agro-meteorological reports.

👥 Audience

Researchers who prefer terra over rgdal/raster.

r-terra-ndvi.R

library(terra)
img <- rast('landsat.tif')   # bands: B1..B7
ndvi <- (img[['B5']] - img[['B4']]) / (img[['B5']] + img[['B4']])
adm  <- vect('districts.geojson')
zonal_mean <- extract(ndvi, adm, fun = mean, na.rm = TRUE)
write.csv(zonal_mean, 'ndvi_by_district.csv', row.names = FALSE)
plot(ndvi); plot(adm, add = TRUE, border = 'white')

📤 Expected Outputs

NDVI raster plot
ndvi_by_district.csv

#terra#ndvi#zonal

Public Health🎓 Advanced

survey + svyglm — Logistic Regression on DHSSurvey-weighted logistic regression with stratification & cluster sampling.

#survey#svyglm#dhs

Public HealthAdvanced

survey + svyglm — Logistic Regression on DHS

Survey-weighted logistic regression with stratification & cluster sampling.

🎯 Use Case

Modeling odds of stunting / contraceptive use / vaccination from DHS microdata.

👥 Audience

Epidemiologists, demographic researchers.

Data to use with this code

DHS Program datasets ↗

r-survey-glm.R

library(haven); library(survey)
d <- read_dta('BDIR81FL.DTA')
d$wt <- d$v005 / 1e6
des <- svydesign(ids = ~v021, strata = ~v023, weights = ~wt, data = d, nest = TRUE)
fit <- svyglm(I(v201 > 3) ~ v012 + factor(v025) + v106, family = quasibinomial, design = des)
summary(fit)

📤 Expected Outputs

Weighted logistic regression coefficients

#survey#svyglm#dhs