Dams Package Demo

In dams: Dams in the United States from the National Inventory of Dams (NID)

This document provides examples on how to obtain data using the dams package and how to create summary graphics of the extracted data.

Data Attributes

If you have not already done so, load the package along with ggplot and maps (for graphics).

require(dams)
require(ggplot2)
require(maps)
require(mapproj)

Load Data

Load the entire dataset. This might take a few moments.

dim(nid_subset)

head(nid_subset, 3)

Summary Graphics

Data for graphics

gfx_data <- nid_subset[, c("year_completed", "state")]

head(gfx_data)

Counts of number of dams built per decade or other time period of interest

gfx_data$year <- cut(gfx_data$year_completed, 
                     breaks = c(0, 1850, seq(1900, 2000, 10), 2014), 
                     labels = c("<1850", "1850-1900", "1910", "1920", "1930",
                              "1940", "1950", "1960", "1970", "1980", "1990", 
                              "2000", "2014"))
table(gfx_data$year)

year_counts <- as.data.frame(table(gfx_data$year), stringsAsFactors = FALSE)
colnames(year_counts) <- c("Year", "Count")

Histogram of number of dams by time period

gfx_bar <- ggplot(year_counts, aes(x = Year, y = Count))
gfx_bar <- gfx_bar + geom_bar(position = "dodge", stat = "identity")
gfx_bar <- gfx_bar + ylab("Number of Dams") + xlab("Year of Completion")
gfx_bar <- gfx_bar + ggtitle("Number of Dams in the NID Database")

plot(gfx_bar)

Counts of dams per state in the US mainland

gfx_data <- subset(gfx_data, !(state %in% c("AK", "HI", "PR", "GU")))
sort(table(gfx_data$state))

Map of dams per state in the US mainland

state_counts <- as.data.frame(table(gfx_data$state), stringsAsFactors = FALSE)
colnames(state_counts) <- c("state", "Count")

# add long names of states
state_names <- data.frame(state = state.abb, 
                          name = state.name, 
                          stringsAsFactors = FALSE)
gfx_data <- merge(state_counts, state_names, by = "state")
# change state name to lower case to be consistent with ggplot
gfx_data$name <- tolower(gfx_data$name)

# geo reference data on states from ggplot
geo_state <- map_data("state")

# merge data with above for graphics
gfx_data <- merge(geo_state, gfx_data, by.x = "region", by.y = "name")
gfx_data <- gfx_data[order(gfx_data$order), ]

# discretize state counts
color_breaks <- c(0, 100, 500, 1000, 2000, 3000, 4000, 5000, 7500)
color_labels <- c("<100", "100 - 500", "500 - 1000", "1000 - 2000",
                  "2000 - 3000", "3000 - 4000", "4000 - 5000", "5000 - 7500")
gfx_data$dams <- cut(gfx_data$Count, 
                     breaks = color_breaks, 
                     labels = color_labels)

gfx_map <- ggplot(data = gfx_data)
gfx_map <- gfx_map + geom_polygon(aes(x = long, y = lat, group = group,
            fill = dams))
gfx_map <- gfx_map + geom_path(data = geo_state, aes(x = long, y = lat,
            group = group, fill = NA))
gfx_map <- gfx_map + labs(list(title = "Number of Dams in the NID Database",
            x = NULL, y = NULL))
gfx_map <- gfx_map + guides(fill = guide_legend(title = "Number of Dams"))
gfx_map <- gfx_map + scale_fill_brewer(palette = "Accent")
gfx_map <- gfx_map + coord_map()

plot(gfx_map)

Other Analyses: Flood Control Dams

A number of interesting analyses could be performed with the dataset. Of interest to water resources managers and hydrologists is the location of flood control dams. It is interesting to see a few states like Texas have a large number of flood control dams.

flood_dams <- subset(nid_subset, length(grep("C", purposes)) > 0)

table(flood_dams$state)

dams documentation built on July 2, 2020, 2:18 a.m.