Add files via upload

pzaldonis · web-flow · commit e09a7bbc5464 · 2024-12-10T15:16:30.000-05:00
diff --git a/december_demo/Find_Common_Columns.R b/december_demo/Find_Common_Columns.R
@@ -0,0 +1,26 @@
+library(arrow)
+library(purrr)
+
+# List of all parquet files
+files_to_check <- list.files(path = getwd(), pattern = ".parquet$", full.names = TRUE)
+
+# Function to get column names from a parquet file
+get_column_names <- function(file) {
+  # Read the schema (column names) of the parquet file
+  schema <- read_parquet(file, as_data_frame = FALSE)$schema
+  schema$names
+}
+
+# Get column names for each file
+column_names_list <- map(files_to_check, get_column_names)
+
+# Find the intersection of column names across all files
+same_columns <- reduce(column_names_list, intersect)
+
+# Print common columns
+cat("Common columns across all parquet files:\n")
+print(same_columns)
+
+# View columns in each file for comparison
+names(column_names_list) <- basename(files_to_check)
+column_names_list
diff --git a/december_demo/MissingColumn.R b/december_demo/MissingColumn.R
@@ -0,0 +1,27 @@
+library(arrow)
+
+# List all files
+files <- list.files(path = getwd(), recursive = TRUE, full.names = TRUE, pattern = ".parquet")
+
+# Function for missing column
+missing_column <- lapply(files, function(file) {
+  data <- read_parquet(file)
+  
+  # Check if 'town' is missing
+  if (!"town" %in% colnames(data)) {
+    return(basename(file))  # Return file name if "town" is missing
+  } else {
+    return(NULL)  # Return NULL if 'town' is present
+  }
+})
+
+# Filter out NULL values to get the list of files without 'town'
+missing_files <- Filter(Negate(is.null), missing_column)
+
+# Print the result
+if (length(missing_files) > 0) {
+  cat("Files missing 'town' column:\n")
+  print(missing_files)
+} else {
+  cat("All files contain the expected column.\n")
+}
diff --git a/december_demo/Parquetize.R b/december_demo/Parquetize.R
@@ -0,0 +1,18 @@
+library(parquetize)
+library(arrow)
+
+
+filesloc<-getwd()
+
+files<-list.files(filesloc,
+                  full.names = TRUE,
+                  pattern=".csv",
+                  recursive=TRUE)
+
+for (i in seq_along(files)){
+  csv<- files[i]
+  parquet<- gsub(".csv",".parquet",csv)
+  csv_to_parquet(csv,path_to_parquet = parquet)
+}
+
+
diff --git a/december_demo/Simple_Map.R b/december_demo/Simple_Map.R
@@ -0,0 +1,43 @@
+# #Easy map 
+library(leaflet)
+
+# Create a simple map using the quakes dataset
+leaflet(data = quakes) %>%
+  addProviderTiles(providers$Stadia.AlidadeSmooth) %>%
+  addCircleMarkers(
+    radius = 1,
+    color = "red",
+    fillOpacity = 1,
+    clusterOptions = markerClusterOptions() # Cluster for performance
+  )
+
+
+library(leaflet)
+library(maps)
+library(sf)
+
+#US states dataset
+#Convert to sf for polygons
+states <- st_as_sf(maps::map("state", plot = FALSE, fill = TRUE))
+
+# Sample points dataset
+points_data <- data.frame(
+  longitude = c(-72.673370, -73.759262, -75.165222),
+  latitude = c(41.765804, 42.652580, 39.952583),
+  label = c("Hartford", "Albany", "Philadelphia")
+)
+
+# Create a map with polygons and points
+leaflet() %>%
+  addProviderTiles(providers$Esri.WorldImagery) %>%
+  addPolygons(data = states, color = "blue", weight = 1, fillOpacity = 0.3) %>%
+  addCircleMarkers(
+    data = points_data,
+    lng = ~longitude,
+    lat = ~latitude,
+    radius = 5,
+    color = "orange",
+    fillOpacity = 1,
+    label = ~label
+  )
+
