Data-Analysis-Jupyter/random_forest_explained/data/.Rhistory

library(gganimate)
library(ggthemes)
df <- read_csv('data_vis_challenge.csv')
library(tidyverse)
library(gganimate)
library(ggthemes)
df <- read_csv('data_vis_challenge.csv')
df <- gather(df, key = 'species', value = 'rate', -`Light Intensity`, -Temperature)
df <- dplyr::rename(df, intensity = `Light Intensity`, temp = Temperature)
ggplot(data = df, aes(x = temp, y = intensity, color = species, size = intensity)) + geom_point() +
xlab('Temperature') + ylab('Rate')
ggplot(df, aes(x = intensity, y = rate, color = species, frame = temp)) +
geom_point() + theme_classic(12)
library(tidyverse)
library(gganimate)
library(ggthemes)
df <- read_csv('data_vis_challenge.csv')
setwd("C:/Users/Will Koehrsen/Desktop")
load("C:/Users/Will Koehrsen/Desktop/.RData")
ggplot(data = df, aes(x = intensity, y = rate, color = species, frame = temp)) +
geom_point() + theme_classic(12)
table(df$intensity)
table(df$temp)
ggplot(data = df, aes(x = species, y = rate)) + geom_bar(fill = 'navy') +
facet_grid(temp, intensity) + coord_flip()
ggplot(data = df, aes(x = species, y = rate)) + geom_bar(fill = 'navy') +
facet_grid(temp ~ intensity) + coord_flip()
ggplot(data = df, aes(x = species, y = rate)) + geom_bar(stat = 'identity', fill = 'navy') +
facet_grid(temp ~ intensity) + coord_flip()
ggplot(data = df, aes(x = species, y = rate)) + geom_bar(stat = 'identity', fill = 'navy') +
facet_grid(intensity ~ temp) + coord_flip() + theme_hc(12)
ggplot(data = df, aes(x = species, y = rate)) + geom_bar(stat = 'identity', fill = 'navy') +
facet_grid(intensity ~ temp) + coord_flip() + theme_stata(12)
ggplot(data = df, aes(x = species, y = rate)) + geom_bar(stat = 'identity', fill = 'navy') +
facet_grid(intensity ~ temp) + coord_flip() + theme_economist(12)
ggplot(data = df, aes(x = species, y = rate)) + geom_bar(stat = 'identity', fill = 'navy') +
facet_grid(intensity ~ temp) + coord_flip() + theme_hc(12)
ggplot(data = df, aes(x = species, y = rate)) + geom_bar(stat = 'identity', fill = 'navy') +
facet_grid(intensity ~ temp) + coord_flip() + theme_classic(12)
setwd("~/Data-Analysis/random_forest_explained")
library(tidyverse)
library(lubridate)
setwd("~/Data-Analysis/random_forest_explained")
df <- read_csv('1169857.csv')
df <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT WA US')
df <- read_csv('1169857.csv')
table(df$NAME)
df <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- mutate(temps, month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE))
temps$temp_1 <- c(45, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(45, 44, temps$TMAX[1:{nrow(temps) - 2}])
View(temps)
averages <- read_csv('averages.csv')
View(averages)
df <- read_csv('raw_temps.csv')
temps <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- mutate(temps, month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE))
temps$temp_1 <- c(45, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(45, 44, temps$TMAX[1:{nrow(temps) - 2}])
averages <- read_csv('averages.csv')
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')], by = c('month', 'day'),
all.x = TRUE)
View(temps)
df <- read_csv('raw_temps.csv')
temps <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- mutate(temps, month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE))
temps$temp_1 <- c(45, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(45, 44, temps$TMAX[1:{nrow(temps) - 2}])
averages <- read_csv('averages.csv')
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')], by = c('month', 'day'),
all.x = TRUE)
temps <- arrange(temps, DATE)
library(tidyverse)
library(lubridate)
df <- read_csv('raw_temps.csv')
setwd("~/Data-Analysis/random_forest_explained/data")
df <- read_csv('raw_temps.csv')
temps <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- mutate(temps, month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE))
temps$temp_1 <- c(temps$TMAX[1:{nrow(temps) - 1}])
# Read in the data as a dataframe
df <- read_csv('raw_temps.csv')
# Make sure all readings are from same station
temps <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
# Create month, day, and week columns
temps <- mutate(temps, month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE))
# Create the past max temperature columns
temps$temp_1 <- c(NA, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(NA, NA, temps$TMAX[1:{nrow(temps) - 2}])
# Read in the averages as a dataframe
averages <- read_csv('hist_averages.csv')
# Create columns for the month and day
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
# Join the averages to the temperature measurements
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')],
by = c('month', 'day'), all.x = TRUE)
View(temps)
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')],
by = c('month', 'day'), all.x = TRUE) %>% arrange(DATE)
# Read in the data as a dataframe
df <- read_csv('raw_temps.csv')
# Make sure all readings are from same station
temps <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
# Create month, day, and week columns
temps <- mutate(temps, month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE))
# Create the past max temperature columns
temps$temp_1 <- c(NA, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(NA, NA, temps$TMAX[1:{nrow(temps) - 2}])
# Read in the averages as a dataframe
averages <- read_csv('hist_averages.csv')
# Create columns for the month and day
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
# Join the averages to the temperature measurements
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')],
by = c('month', 'day'), all.x = TRUE) %>% arrange(DATE)
df <- read_csv('raw_temps.csv')
temps <- dplyr::filter(df, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- mutate(temps, month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE)) %>%
arrange(DATE)
temps$temp_1 <- c(NA, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(NA, NA, temps$TMAX[1:{nrow(temps) - 2}])
averages <- read_csv('hist_averages.csv')
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')],
by = c('month', 'day'), all.x = TRUE) %>% arrange(DATE)
temps <- dplyr::select(temps, month, day, AWND, PRCP, TMAX, week, temp_1, temp_2, DLY-TMAX-NORMAL)
temps <- dplyr::select(temps, month, day, AWND, PRCP, TMAX, week, temp_1, temp_2, `DLY-TMAX-NORMAL`)
df <- read_csv('raw_temps.csv')
temps <- read_csv('raw_temps.csv')
temps <- dplyr::filter(temps, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- mutate(temps, month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE)) %>%
arrange(DATE)
temps$temp_1 <- c(NA, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(NA, NA, temps$TMAX[1:{nrow(temps) - 2}])
averages <- read_csv('hist_averages.csv')
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')],
by = c('month', 'day'), all.x = TRUE) %>% arrange(DATE)
library(tidyverse)
library(lubridate)
temps <- read_csv('raw_temps.csv')
temps <- dplyr::filter(temps, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- mutate(temps, year = lubridate::year(DATE), month = lubridate::month(DATE),
day = lubridate::day(DATE), week = lubridate::wday(DATE, label = TRUE)) %>%
arrange(DATE)
temps$temp_1 <- c(NA, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(NA, NA, temps$TMAX[1:{nrow(temps) - 2}])
averages <- read_csv('hist_averages.csv')
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')],
by = c('month', 'day'), all.x = TRUE) %>% arrange(DATE) %>% mutate(year = )
temps <- dplyr::select(temps, year, month, day, week, AWND, PRCP, TMAX, temp_1, temp_2, `DLY-TMAX-NORMAL`, TMAX)
temps <- dplyr::select(temps, year, month, day, week, AWND, PRCP, temp_1, temp_2, `DLY-TMAX-NORMAL`, TMAX)
temps <- dplyr::select(temps, year, month, day, week, AWND, PRCP, temp_2, temp_1, `DLY-TMAX-NORMAL`, TMAX)
names(temps) <- c('year', 'month', 'day', 'weekday', 'ws', 'prcp', 'temp_2',
'temp_1', 'average', 'actual')
sapply(temps$average, function(x) (runif(1, min = x - 20, max = x + 20)))
sapply(temps$average, function(x) round(runif(1, min = x - 20, max = x + 20)))
temps$friend <- sapply(temps$average, function(x) round(runif(1, min = x - 20, max = x + 20)))
View(temps)
temps <- temps[-c(1,2), ]
ggplot(temps, aes(x = seq(1, nrow(temps)), y = ws)) + geom_point()
for (column in c('ws', 'prcp', 'temp_2', 'temp_1', 'average', 'actual', 'friend')) {
ggplot(temps, aes(x = seq(1, nrow(temps)), y = column)) + geom_point()
}
print(ggplot(temps, aes(x = seq(1, nrow(temps)), y = column)) + geom_point())
for (column in c('ws', 'prcp', 'temp_2', 'temp_1', 'average', 'actual', 'friend')) {
print(ggplot(temps, aes(x = seq(1, nrow(temps)), y = temps[[column]])) + geom_point())
}
temps <- temps[complete.cases(temps), ]
summary(temps)
write_csv(temps, 'temps_extended.csv')
table(temps$year)
library(tidyverse)
library(lubridate)
temps <- read_csv('raw_temps.csv')
temps <- dplyr::filter(temps, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
temps <- mutate(temps, year = lubridate::year(DATE),
month = lubridate::month(DATE),
day = lubridate::day(DATE),
week = lubridate::wday(DATE, label = TRUE)) %>%
arrange(DATE)
temps$temp_1 <- c(NA, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(NA, NA, temps$TMAX[1:{nrow(temps) - 2}])
library(tidyverse)
library(lubridate)
# Read in the data as a dataframe
temps <- read_csv('raw_temps.csv')
# Make sure all readings are from same station
temps <- dplyr::filter(temps, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
# Create month, day, and week columns
temps <- mutate(temps, year = lubridate::year(DATE),
month = lubridate::month(DATE),
day = lubridate::day(DATE),
week = lubridate::wday(DATE, label = TRUE)) %>%
arrange(DATE)
# Create the past max temperature columns
temps$temp_1 <- c(NA, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(NA, NA, temps$TMAX[1:{nrow(temps) - 2}])
# Shift the average wind speed, precipitation, and snow depth
temps$AWND <- c(NA, temps$AWND[1:{nrow(temps) - 1}])
temps$PRCP <- c(NA, temps$PRCP[1:{nrow(temps) - 1}])
temps$SNWD <- c(NA, temps$SNWD[1:{nrow(temps) - 1}])
averages <- read_csv('hist_averages.csv')
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')],
by = c('month', 'day'), all.x = TRUE) %>% arrange(DATE)
temps <- dplyr::select(temps, year, month, day, week, AWND, PRCP, SNWD,
temp_2, temp_1, `DLY-TMAX-NORMAL`, TMAX)
names(temps) <- c('year', 'month', 'day', 'weekday', 'ws', 'prcp', 'snwd',
'temp_2', 'temp_1', 'average', 'actual')
temps$friend <- sapply(temps$average, function(x)
round(runif(1, min = x - 20, max = x + 20)))
temps <- temps[-c(1,2), ]
temps <- temps[complete.cases(temps), ]
summary(temps)
View(temps)
# RF temperature modeling
#
# Read in data
library(tidyverse)
library(lubridate)
# Read in the data as a dataframe
temps <- read_csv('raw_temps.csv')
# Make sure all readings are from same station
temps <- dplyr::filter(temps, NAME == 'SEATTLE TACOMA INTERNATIONAL AIRPORT, WA US')
# Create month, day, and week columns
temps <- mutate(temps, year = lubridate::year(DATE),
month = lubridate::month(DATE),
day = lubridate::day(DATE),
week = lubridate::wday(DATE, label = TRUE)) %>%
arrange(DATE)
# Create the past max temperature columns
temps$temp_1 <- c(NA, temps$TMAX[1:{nrow(temps) - 1}])
temps$temp_2 <- c(NA, NA, temps$TMAX[1:{nrow(temps) - 2}])
# Shift the average wind speed, precipitation, and snow depth
temps$AWND <- c(NA, temps$AWND[1:{nrow(temps) - 1}])
temps$PRCP <- c(NA, temps$PRCP[1:{nrow(temps) - 1}])
temps$SNWD <- c(NA, temps$SNWD[1:{nrow(temps) - 1}])
# Read in the averages as a dataframe
averages <- read_csv('hist_averages.csv')
# Create columns for the month and day
averages$month <- as.numeric(substr(averages$DATE, 5, 6))
averages$day <- as.numeric(substr(averages$DATE, 7, 8))
# Join the averages to the temperature measurements
temps <- merge(temps, averages[, c('month', 'day', 'DLY-TMAX-NORMAL')],
by = c('month', 'day'), all.x = TRUE) %>% arrange(DATE)
# Select and order relevant columns
temps <- dplyr::select(temps, year, month, day, week, AWND, PRCP, SNWD,
temp_2, temp_1, `DLY-TMAX-NORMAL`, TMAX)
# Rename columns
names(temps) <- c('year', 'month', 'day', 'weekday', 'ws_1', 'prcp_1', 'snwd_1',
'temp_2', 'temp_1', 'average', 'actual')
# Friend predictions
temps$friend <- sapply(temps$average, function(x)
round(runif(1, min = x - 20, max = x + 20)))
# Remove first two rows
temps <- temps[-c(1,2), ]
# Remove na
temps <- temps[complete.cases(temps), ]
# Summary of data
summary(temps)
# Write to csv file
write_csv(temps, 'temps_extended.csv')