Weather Analysis

Goals of this Notebook

The goal of this notebook is to summarize the weather data

Which days had the most rain, and how much rain are we talking about?
What are the hottest and coldest days in history?
Which years had the most days of 100+ temperature?

Additional quests

Number of days (per year) with snow
Number of days (per year) below freezing
Number of days (per year) not above freezing
Number of days (per year) with 100+ in the month of May
Same but for June and July in separate lists

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.0      ✔ purrr   1.0.1 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.1      ✔ stringr 1.5.0 
## ✔ readr   2.1.3      ✔ forcats 0.5.2 
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(janitor)

## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test

library(lubridate)

## Loading required package: timechange
## 
## Attaching package: 'lubridate'
## 
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

Importing clean data

weather <- read_rds("data-processed/01-weather.rds")

weather %>% glimpse()

## Rows: 30,914
## Columns: 8
## $ station <chr> "USW00013958", "USW00013958", "USW00013958", "USW00013958", "U…
## $ name    <chr> "AUSTIN CAMP MABRY, TX US", "AUSTIN CAMP MABRY, TX US", "AUSTI…
## $ date    <date> 1938-06-01, 1938-06-02, 1938-06-03, 1938-06-04, 1938-06-05, 1…
## $ prcp    <dbl> 0.00, 0.00, 0.00, 0.40, 0.02, 0.00, 0.00, 0.00, 1.60, 0.01, 0.…
## $ snow    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ snwd    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tmax    <dbl> 91, 94, 94, 90, 94, 92, 95, 92, 87, 90, 92, 91, 91, 91, 89, 89…
## $ tmin    <dbl> 72, 67, 70, 68, 68, 70, 70, 76, 64, 76, 75, 71, 70, 68, 71, 70…

Creating yr column

Creating a column for the year

weather_yr <- weather %>%
  mutate(yr = year(date)) # take the year and rename it yr in its own column

weather_yr %>% glimpse()

## Rows: 30,914
## Columns: 9
## $ station <chr> "USW00013958", "USW00013958", "USW00013958", "USW00013958", "U…
## $ name    <chr> "AUSTIN CAMP MABRY, TX US", "AUSTIN CAMP MABRY, TX US", "AUSTI…
## $ date    <date> 1938-06-01, 1938-06-02, 1938-06-03, 1938-06-04, 1938-06-05, 1…
## $ prcp    <dbl> 0.00, 0.00, 0.00, 0.40, 0.02, 0.00, 0.00, 0.00, 1.60, 0.01, 0.…
## $ snow    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ snwd    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tmax    <dbl> 91, 94, 94, 90, 94, 92, 95, 92, 87, 90, 92, 91, 91, 91, 89, 89…
## $ tmin    <dbl> 72, 67, 70, 68, 68, 70, 70, 76, 64, 76, 75, 71, 70, 68, 71, 70…
## $ yr      <dbl> 1938, 1938, 1938, 1938, 1938, 1938, 1938, 1938, 1938, 1938, 19…

Days with the most rain

Finding which days had the most rain and how much rain they had

weather_yr %>%
  arrange(desc(prcp)) %>% # arranging what days had the most precipitation in descending order
  distinct(date, prcp) %>% # keep only the date and prcp columns
  head(10) # keeping the top 10 rows only

Hottest and coldest days in history

Finding the hottest and coldest days in history

weather_yr %>%
  arrange(desc(tmax)) %>% # arranging what days had the hottest temperature in descending order
  distinct(date, tmax) %>% # keep only the date and tmax columns
  filter(tmax >= 108) # keeping only the rows where the max temp is 108 degrees or hotter

weather_yr %>%
  arrange(tmin) %>% # arranging what days had the coldest temperature in ascending order
  distinct(date, tmin) %>% # keep only the date and tmin columns
  filter(tmin <=12) # keeping only the rows where the min temp is 12 degrees or colder

Years with the most days of 100+ temperature

Finding the years with the most days of tmax 100+

weather_100 <- weather_yr %>%
  filter(tmax >= 100) %>% # filter tmax to 100+
  group_by(yr) %>% # group by year
  summarize(days = n()) %>% # summarize number of days of 100+ temperature
  arrange(desc(days)) %>% # arrange appearances in descending order
  filter(days >= 42) %>% # keeping only the years where the number of days was 42+
  head(5)
  
weather_100

Number of days per year with snow

Finding the number of days that had snow each year

weather_yr %>%
  filter(snow > 0) %>% # filter snow to greater than 0
  group_by(yr) %>% # group by year
  summarize(snow_days = n()) %>% # summarize number of days with snow
  arrange(desc(yr)) # arrange year in descending order

Number of days per year below freezing

Finding the number of days each year where the tmin is below 32

weather_yr %>%
  filter(tmin <= 32) %>% # filter tmin to less than 0
  group_by(yr) %>% # group by year
  summarize(days = n()) %>% # summarize number of days where tmin is less than 32
  arrange(desc(yr)) # arrange year in descending order

Number of days per year not above freezing

Finding the number of days each year where the tmax is below 32

weather_yr %>%
  filter(tmax <= 32) %>% # filter tmax to less than 32
  group_by(yr) %>% # group by year
  summarize(days = n()) %>% # summarize number of days where tmax is less than 32
  arrange(desc(yr)) # arrange year in descending order

Number of days 100+ in May per year

Finding the number of days where the tmax was 100+ in May each year

weather_yr %>%
  filter(
    tmax >= 100, # filter tmax to 100+
    month(date) == 05 # filter month to May
  ) %>%
  group_by(yr) %>% # group by year
  summarize(days = n()) %>% # summarize number of days where tmax is 100+
  arrange(desc(yr)) # arrange year in descending order

Number of days 100+ in June per year

Finding the number of days where the tmax was 100+ in June each year

weather_yr %>%
  filter(
    tmax >= 100, # filter tmax to 100+
    month(date) == 06 # filter month to June
  ) %>%
  group_by(yr) %>% # group by year
  summarize(days = n()) %>% # summarize number of days where tmax is 100+
  arrange(desc(yr)) # arrange year in descending order

Number of days 100+ in July per year

Finding the number of days where the tmax was 100+ in July each year

weather_yr %>%
  filter(
    tmax >= 100, # filter tmax to 100+
    month(date) == 07 # filter month to July
  ) %>%
  group_by(yr) %>% # group by year
  summarize(days = n()) %>% # summarize number of days where tmax is 100+
  arrange(desc(yr)) # arrange year in descending order

Goals of summarizing with math

Required quests

Which years had the most total rainfall and how much? Which had the least?
Which years had the most total snowfall and how much?
What is the average rainfall for each month across time? i.e. what is the average rain for January, then February, etc.

Additional quests

What is the earliest date in each year with 100+ temperature? Which year had the earliest date? (This is where yday proves useful).
What is the earliest day (but after July 1) for a freeze each year? Which year had the earliest date?
What is the latest date (but before July 1) for a freeze each year? Which year had the latest date?

Creating mo and yday columns

Creating a column for the month and yday

weather_mo <- weather_yr %>%
  mutate(mo = month(date, label = TRUE)) %>% # take the date and rename it mo in its own column
  mutate(yday = yday(date)) # convert the day into a number and create a yday column

weather_mo %>% glimpse()

## Rows: 30,914
## Columns: 11
## $ station <chr> "USW00013958", "USW00013958", "USW00013958", "USW00013958", "U…
## $ name    <chr> "AUSTIN CAMP MABRY, TX US", "AUSTIN CAMP MABRY, TX US", "AUSTI…
## $ date    <date> 1938-06-01, 1938-06-02, 1938-06-03, 1938-06-04, 1938-06-05, 1…
## $ prcp    <dbl> 0.00, 0.00, 0.00, 0.40, 0.02, 0.00, 0.00, 0.00, 1.60, 0.01, 0.…
## $ snow    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ snwd    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tmax    <dbl> 91, 94, 94, 90, 94, 92, 95, 92, 87, 90, 92, 91, 91, 91, 89, 89…
## $ tmin    <dbl> 72, 67, 70, 68, 68, 70, 70, 76, 64, 76, 75, 71, 70, 68, 71, 70…
## $ yr      <dbl> 1938, 1938, 1938, 1938, 1938, 1938, 1938, 1938, 1938, 1938, 19…
## $ mo      <ord> Jun, Jun, Jun, Jun, Jun, Jun, Jun, Jun, Jun, Jun, Jun, Jun, Ju…
## $ yday    <dbl> 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 16…

Which years had the most total rainfall and how much? Which had the least?

Finding rainfall amount each year and arranging by greatest amount and least amount

weather_mo %>%
  group_by(yr) %>% # group by year
  summarize(rain_amount = sum(prcp)) %>% # find the sum of all the rain in each year
  arrange(desc(rain_amount)) %>% # arrange sum of rain in each year in descending order
  filter(
    rain_amount > 40,
    yr < 2023,
    yr > 1938,
  )

weather_mo %>%
  group_by(yr) %>%
  summarize(rain_amount = sum(prcp)) %>% # find the sum of all the rain in each year
  arrange(rain_amount) %>% # arrange sum of rain in each year in ascending order
  filter(
    yr < 2023,
    yr > 1938,
    rain_amount < 25
  )

Which years had the most total snowfall and how much?

Finding how much snowfall occurred in each year

weather_mo %>%
  group_by(yr) %>%
  summarize(snowfall_amount = sum(snow)) %>% # find sum of all snow in each year
  arrange(desc(snowfall_amount)) %>% # arrange sum of rain in each year in descending order
  filter(
    yr < 2023,
    yr > 1938,
    snowfall_amount > 1
  )

What is the average rainfall for each month across time?

Finding the average rainfall for each month over all the years

weather_rainfall <- weather_mo %>%
  group_by(mo, yr) %>% # group by both month and year
  summarize(total_rainfall = sum(prcp)) %>% # find the total rainfall in each month of every year
  group_by(mo) %>% # group the answers by month
  summarize(average_rainfall = mean(total_rainfall)) # find the mean of all rainfall for each month over all the years

## `summarise()` has grouped output by 'mo'. You can override using the `.groups`
## argument.

weather_rainfall

What is the earliest date in each year with 100+ temperature? Which year had the earliest date?

Finding the first day each year where tmax was 100+, and which year that happened first

weather_mo %>%
  group_by(yr) %>%
  filter(tmax >= 100) %>%
  slice_min(date) %>% # takes the earliest date value
  select(date, tmax, tmin, yr, mo, yday) %>%
  arrange(yday)

What is the earliest day (but after July 1) for a freeze each year? Which year had the earliest date?

Finding the first day each year after July 1 that was freezing, and which year that happened first

weather_mo %>%
  group_by(yr) %>%
  filter(
    tmin <= 32,
    mo >= "Jul"
  ) %>%
  slice_min(date) %>% # takes the earliest date value
  select(date, tmax, tmin, yr, mo, yday) %>%
  arrange(yday)

What is the latest date (but before July 1) for a freeze each year? Which year had the latest date?

weather_mo %>%
  group_by(yr) %>% 
  filter(
    tmin <= 32,
    mo < "Jul"
  ) %>%
  slice_min(date) %>% # takes the earliest date value
  select(date, tmax, tmin, yr, mo, yday) %>%
  arrange(yday)

Goals of visualizations

Plot the top years with the most 100+ days as a horizontal bar chart
Plot the average rainfall by month as a vertical bar chart
Plot the yearly average low and high temperatures as a line chart

Most 100+ days plot

Plotting the top years with the most 100+ days

ggplot(weather_100, aes(x = yr %>% reorder(days), y = days)) + # sets x and y axes
  geom_col() + # adds the bars
  coord_flip() + # flips the axis
  geom_text(aes(label = days), hjust = 2, color = "white") + # plots read-able votes text values on chart
  labs(
    title = "Top Five Years With the Most 100+ Degree Days in Austin from 1938-2023",
    subtitle = str_wrap("Most 100+ days each year from the National Centers for Environmental Information's Austin Camp Mabry data"),
    caption = "By Shezan Samanani",
    x = "Year",
    y = "Number of Days"
  )

Average rainfall by month plot

Plotting the average rainfall by month

ggplot(weather_rainfall, aes(x = mo, y = average_rainfall)) + # sets x and y axes
  geom_col() + # adds the bars
  labs(
    title = "Average Rainfall by Month in Austin from 1938-2023",
    subtitle = str_wrap("Average rainfall amount in each month from the National Centers for Environmental Information's Austin Camp Mabry data"),
    caption = "By Shezan Samanani",
    x = "Month",
    y = "Average Rainfall Amount (inches)"
  )

Yearly average high and low temperature

Finding the yearly average high and low temperatures and pivoting long

weather_avg <- weather_mo %>%
  group_by(yr) %>%
  summarize(
    avg_high = mean(tmax),
    avg_low = mean(tmin)
  ) %>%
  filter(
    yr > 1938,
    yr < 2023
  )

weather_avg

weather_long <- weather_avg %>%
  pivot_longer(
    cols = avg_high:avg_low,
    names_to = "temp_type",
    values_to = "avg_temp"
  )

weather_long

Yearly average high and low temperatures plot

Plotting the average high and low temperatures for each year

ggplot(weather_long, aes(x = yr, y = avg_temp)) + 
  geom_point(aes(color = temp_type)) +
  geom_line(aes(color = temp_type)) + # The aes selects a color for each temp_type
  labs(
    title = "Average Yearly High and Low Temperatures in Austin from 1939-2022",
    subtitle = str_wrap("Average high and low temperatures for each year from the National Centers for Environmental Information's Austin Camp Mabry data"),
    caption = "By Shezan Samanani",
    x = "Year",
    y = "Average Temperature (fahrenheit)"
  )