Visualizing Time Series

library(ggplot2)  
library(readr)
library(tidyverse)

The data is available on the following website : https://data.neonscience.org/

data <- read_csv("Met_HARV_Daily_2009_2011.csv")

str(harMetDaily.09.11$date)

##  Date[1:1095], format: "2009-01-01" "2009-01-02" "2009-01-03" "2009-01-04" "2009-01-05" ...

harMetDaily.09.11 %>% 
  select(date, airt) %>% 
  head(10)

## # A tibble: 10 x 2
##    date        airt
##    <date>     <dbl>
##  1 2009-01-01 -15.1
##  2 2009-01-02  -9.1
##  3 2009-01-03  -5.5
##  4 2009-01-04  -6.4
##  5 2009-01-05  -2.4
##  6 2009-01-06  -4.9
##  7 2009-01-07  -2.6
##  8 2009-01-08  -3.2
##  9 2009-01-09  -9.9
## 10 2009-01-10 -11.1

df <- harMetDaily.09.11 %>% 
  select(date, airt)  

ggplot(df, aes(date, airt)) +
  geom_point(color = "purple",
             size = 3,
             pch = 18) +
  labs(x= "Date", 
       y= expression(paste("Temperature ( ", degree ~ C, " )")), 
       title = "Air Temperature (2009-2011)\nNEON Harvard Forest Field Site") +
  scale_x_date(labels = date_format("%b %y")) +
  stat_smooth(colour = "green") +
  theme(plot.title = element_text(color="darkblue", size=14, face="bold.italic"),
        text = element_text(size=14,face="bold"),
        axis.title.x = element_text(size=14, face="bold"),
        axis.title.y = element_text(size=14, face="bold"))

APPLICATION

1. Number of crimes in Toronto

Torontocrimes <- read_csv("Torontocrimes.csv")

str(Torontocrimes$occurrencedate)

## POSIXct[1:166500], format: "2014-06-20 10:55:00" "2014-07-02 00:20:00" "2014-07-02 00:20:00" ...

Torontocrimes %>% 
  filter(occurrenceyear == 2018) %>% 
  select(occurrencedate) %>% 
  mutate(date = as.Date(occurrencedate)) %>% 
  group_by(date) %>% 
  summarise(frequency =  n()) %>% 
  head(10)

## # A tibble: 10 x 2
##    date       frequency
##    <date>         <int>
##  1 2018-01-01       177
##  2 2018-01-02        83
##  3 2018-01-03        67
##  4 2018-01-04        72
##  5 2018-01-05       100
##  6 2018-01-06        89
##  7 2018-01-07        90
##  8 2018-01-08       119
##  9 2018-01-09        87
## 10 2018-01-10        90

nf <- Torontocrimes %>% 
  filter(occurrenceyear == 2018) %>% 
  select(occurrencedate) %>% 
  mutate(date = as.Date(occurrencedate)) %>% 
  group_by(date) %>% 
  summarise(frequency =  n())

ggplot(nf, aes(date, frequency)) + 
  geom_line() +
    theme(plot.title = element_text(color="darkblue", size=14, face="bold.italic"),
        text = element_text(size=14,face="bold"),
        axis.title.x = element_text(size=14, face="bold"),
        axis.title.y = element_text(size=14, face="bold"))

library(ggTimeSeries)

Torontocrimes %>% 
  select(occurrencedate) %>% 
  mutate(date = as.Date(occurrencedate)) %>% 
  group_by(date) %>% 
  summarise(frequency =  n()) %>% 
  ggplot_calendar_heatmap("date", "frequency") +
  xlab(NULL) +
  ylab(NULL) +
  facet_wrap(~Year, ncol = 1) +
  scale_fill_gradient(high="red", low="yellow")+
    theme(plot.title = element_text(color="darkblue", size=14, face="bold.italic"),
        text = element_text(size=14,face="bold"),
        axis.title.x = element_text(size=14, face="bold"),
        axis.title.y = element_text(size=14, face="bold"))

library(gapminder)

gapminder %>% 
  filter(country == "Canada") %>% 
  select(year, lifeExp) %>% 
  ggplot(aes(x=year, y=lifeExp)) +
  geom_line()+
  geom_point(size = 4, color = "blue")+
  labs(x = NULL, y = NULL) + 
  theme(text = element_text(size = 16), 
        panel.border = element_rect(fill = NA, colour = "grey20")) +
  labs(title =  "Life expectancy in Canada",
       x = NULL,
       y = "Life expectancy (Years)") +
  theme_minimal() +
    theme(plot.title = element_text(color="darkblue", size=14, face="bold.italic"),
        text = element_text(size=14,face="bold"),
        axis.title.x = element_text(size=14, face="bold"),
        axis.title.y = element_text(size=14, face="bold"))