Geo_spatial_Analysis_1

library(sf)

## Linking to GEOS 3.13.1, GDAL 3.11.4, PROJ 9.7.0; sf_use_s2() is TRUE

library(ggplot2)
library(leaflet)

# 1. Load the data (make sure the file is in your working directory)
df <- read.csv("C:/Users/Hp/Downloads/Coffee_Shops.csv")

# 2. Convert the data frame into a spatial object (sf)
# We specify the coordinates and the CRS (Coordinate Reference System)
# 4326 is the standard WGS84 system used by GPS
df_sf <- st_as_sf(df, coords = c("Longitude", "Latitude"), crs = 4326)

ggplot(data = df_sf) +
  geom_sf(aes(size = Daily_Sales, color = Daily_Sales)) +
  theme_minimal() +
  labs(title = "Coffee Shop Sales Distribution",
       subtitle = "Point Analysis in NYC")

leaflet(df) %>%
  addTiles() %>%  # Adds the default OpenStreetMap background
  addMarkers(lng = ~Longitude, 
             lat = ~Latitude, 
             popup = ~paste(Store_Name, "<br>Sales: $", Daily_Sales))

# Load necessary libraries
library(sf)
library(ggplot2)
library(leaflet)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

# 1. Create 200 observations of synthetic NYC data
set.seed(123) # Makes the "random" data the same every time you run it
n_points <- 200

nyc_data <- data.frame(
  Store_ID = 1:n_points,
  Store_Type = sample(c("Cafe", "Bakery", "Bookstore", "Gym"), n_points, replace = TRUE),
  Daily_Sales = round(runif(n_points, 500, 3000), 0),
  # Random coordinates within NYC bounds (approx Lat: 40.5-40.9, Long: -74.0 to -73.7)
  Latitude = runif(n_points, 40.57, 40.88),
  Longitude = runif(n_points, -74.05, -73.75)
)

# 2. Save this as an Excel-style CSV on your computer so you have it
write.csv(nyc_data, "nyc_business_data.csv", row.names = FALSE)

print(paste("Generated", nrow(nyc_data), "observations."))

## [1] "Generated 200 observations."

# Convert the data frame into a spatial 'sf' object
# 4326 is the CRS code for GPS coordinates (WGS84)
nyc_sf <- st_as_sf(nyc_data, coords = c("Longitude", "Latitude"), crs = 4326)

leaflet(nyc_data) %>%
  addTiles() %>% # Base Map
  addMarkers(
    lng = ~Longitude, 
    lat = ~Latitude,
    clusterOptions = markerClusterOptions(),
    popup = ~paste0("<b>Type:</b> ", Store_Type, "<br><b>Sales:</b> $", Daily_Sales)
  )

ggplot(nyc_data, aes(x = Longitude, y = Latitude)) +
  stat_density_2d(aes(fill = ..level..), geom = "polygon", alpha = 0.4) +
  scale_fill_gradient(low = "yellow", high = "red") +
  geom_point(aes(color = Store_Type), size = 1) +
  theme_minimal() +
  labs(title = "Business Density Across NYC",
       subtitle = "Heatmap showing concentration of store locations")

## Warning: The dot-dot notation (`..level..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(level)` instead.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

library(sf)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ lubridate 1.9.5     ✔ tibble    3.3.1
## ✔ purrr     1.2.1     ✔ tidyr     1.3.2
## ✔ readr     2.1.6     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(ozmaps)
library(tmap)

# 1. Load Australian LGA boundaries from the ozmaps package
# We filter for a specific state (e.g., New South Wales or Queensland) to keep it focused
aus_map <- ozmap_data("abs_lga") 

# 2. Create "Real-World" Synthetic Data
# Let's simulate 'Unemployment Rate' and 'Population Density' for 100+ LGAs
set.seed(42)
my_data <- data.frame(
  NAME = aus_map$NAME,
  Unemployment_Rate = runif(nrow(aus_map), 2, 12),
  Pop_Density = runif(nrow(aus_map), 10, 500)
)

# 3. Join the spatial map with our data
map_combined <- aus_map %>%
  left_join(my_data, by = "NAME") %>%
  st_transform(3112) # Transform to GDA94 / Australian Albers (for accurate distance math)

library(spdep)

## Loading required package: spData

## To access larger datasets in this package, install the spDataLarge
## package with: `install.packages('spDataLarge',
## repos='https://nowosad.github.io/drat/', type='source')`

# 1. Define 'neighbors' (which LGAs touch each other?)
nb <- poly2nb(map_combined, queen = TRUE)

## Warning in poly2nb(map_combined, queen = TRUE): some observations have no neighbours;
## if this seems unexpected, try increasing the snap argument.

## Warning in poly2nb(map_combined, queen = TRUE): neighbour object has 9 sub-graphs;
## if this sub-graph count seems unexpected, try increasing the snap argument.

lw <- nb2listw(nb, style = "W", zero.policy = TRUE)

# 2. Calculate Local Gi* (Hotspot Analysis)
# This identifies areas where high values are surrounded by high values
map_combined$hotspot <- localG(map_combined$Unemployment_Rate, lw)

# 3. Convert to a readable scale
map_combined <- map_combined %>%
  mutate(hotspot_category = case_when(
    hotspot > 2.58 ~ "99% Hotspot",
    hotspot > 1.96 ~ "95% Hotspot",
    hotspot < -2.58 ~ "99% Coldspot",
    hotspot < -1.96 ~ "95% Coldspot",
    TRUE ~ "Not Significant"
  ))

# Set tmap to interactive mode
tmap_mode("view")

## ℹ tmap modes "plot" - "view"
## ℹ toggle with `tmap::ttm()`

tm_shape(map_combined) +
  tm_polygons("hotspot_category", 
              palette = "-RdBu", 
              title = "Unemployment Hotspots",
              popup.vars = c("NAME", "Unemployment_Rate")) +
  tm_layout(title = "Australia Spatial Analysis")

## 
## ── tmap v3 code detected ───────────────────────────────────────────────────────
## [v3->v4] `tm_tm_polygons()`: migrate the argument(s) related to the scale of
## the visual variable `fill` namely 'palette' (rename to 'values') to fill.scale
## = tm_scale(<HERE>).[v3->v4] `tm_polygons()`: migrate the argument(s) related to the legend of the
## visual variable `fill` namely 'title' to 'fill.legend = tm_legend(<HERE>)'[v3->v4] `tm_layout()`: use `tm_title()` instead of `tm_layout(title = )`Multiple palettes called "rd_bu" found: "brewer.rd_bu", "matplotlib.rd_bu". The first one, "brewer.rd_bu", is returned.
## [cols4all] color palettes: use palettes from the R package cols4all. Run
## `cols4all::c4a_gui()` to explore them. The old palette name "-RdBu" is named
## "rd_bu" (in long format "brewer.rd_bu")

# Quick example of the logic (Requires 'rayshader' package)
library(rayshader)

# 1. Create the ggplot
p <- ggplot(map_combined) +
  geom_sf(aes(fill = Unemployment_Rate)) +
  scale_fill_viridis_c()

# 2. Render in 3D
plot_gg(p, multicore = TRUE, width = 5, height = 5, scale = 250)