# Load required libraries
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.1 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.3 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(nycflights13)# --- 1. Creating Sample Data for Mutating Joins ---
x <- tribble(
~key, ~val_x,
1, "x1",
2, "x2",
3, "x3"
)
y <- tribble(
~key, ~val_y,
1, "y1",
2, "y2",
4, "y4"
)
# --- 2. Inner Join ---
# Keeps observations that match in both tables
inner_join(x, y, by = "key")## # A tibble: 2 × 3
## key val_x val_y
## <dbl> <chr> <chr>
## 1 1 x1 y1
## 2 2 x2 y2# --- 3. Outer Joins ---
# Left Join: Keeps all observations in x
left_join(x, y, by = "key")## # A tibble: 3 × 3
## key val_x val_y
## <dbl> <chr> <chr>
## 1 1 x1 y1
## 2 2 x2 y2
## 3 3 x3 <NA># Right Join: Keeps all observations in y
right_join(x, y, by = "key")## # A tibble: 3 × 3
## key val_x val_y
## <dbl> <chr> <chr>
## 1 1 x1 y1
## 2 2 x2 y2
## 3 4 <NA> y4# Full Join: Keeps all observations in both x and y
full_join(x, y, by = "key")## # A tibble: 4 × 3
## key val_x val_y
## <dbl> <chr> <chr>
## 1 1 x1 y1
## 2 2 x2 y2
## 3 3 x3 <NA>
## 4 4 <NA> y4# --- Exploring Flights and Planes Data ---
glimpse(flights)## Rows: 336,776
## Columns: 19
## $ year <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2…
## $ month <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ day <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ dep_time <int> 517, 533, 542, 544, 554, 554, 555, 557, 557, 558, 558, …
## $ sched_dep_time <int> 515, 529, 540, 545, 600, 558, 600, 600, 600, 600, 600, …
## $ dep_delay <dbl> 2, 4, 2, -1, -6, -4, -5, -3, -3, -2, -2, -2, -2, -2, -1…
## $ arr_time <int> 830, 850, 923, 1004, 812, 740, 913, 709, 838, 753, 849,…
## $ sched_arr_time <int> 819, 830, 850, 1022, 837, 728, 854, 723, 846, 745, 851,…
## $ arr_delay <dbl> 11, 20, 33, -18, -25, 12, 19, -14, -8, 8, -2, -3, 7, -1…
## $ carrier <chr> "UA", "UA", "AA", "B6", "DL", "UA", "B6", "EV", "B6", "…
## $ flight <int> 1545, 1714, 1141, 725, 461, 1696, 507, 5708, 79, 301, 4…
## $ tailnum <chr> "N14228", "N24211", "N619AA", "N804JB", "N668DN", "N394…
## $ origin <chr> "EWR", "LGA", "JFK", "JFK", "LGA", "EWR", "EWR", "LGA",…
## $ dest <chr> "IAH", "IAH", "MIA", "BQN", "ATL", "ORD", "FLL", "IAD",…
## $ air_time <dbl> 227, 227, 160, 183, 116, 150, 158, 53, 140, 138, 149, 1…
## $ distance <dbl> 1400, 1416, 1089, 1576, 762, 719, 1065, 229, 944, 733, …
## $ hour <dbl> 5, 5, 5, 5, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6…
## $ minute <dbl> 15, 29, 40, 45, 0, 58, 0, 0, 0, 0, 0, 0, 0, 0, 0, 59, 0…
## $ time_hour <dttm> 2013-01-01 05:00:00, 2013-01-01 05:00:00, 2013-01-01 0…glimpse(planes)## Rows: 3,322
## Columns: 9
## $ tailnum <chr> "N10156", "N102UW", "N103US", "N104UW", "N10575", "N105UW…
## $ year <int> 2004, 1998, 1999, 1999, 2002, 1999, 1999, 1999, 1999, 199…
## $ type <chr> "Fixed wing multi engine", "Fixed wing multi engine", "Fi…
## $ manufacturer <chr> "EMBRAER", "AIRBUS INDUSTRIE", "AIRBUS INDUSTRIE", "AIRBU…
## $ model <chr> "EMB-145XR", "A320-214", "A320-214", "A320-214", "EMB-145…
## $ engines <int> 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, …
## $ seats <int> 55, 182, 182, 182, 55, 182, 182, 182, 182, 182, 55, 55, 5…
## $ speed <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ engine <chr> "Turbo-fan", "Turbo-fan", "Turbo-fan", "Turbo-fan", "Turb…# Joining by a single specified column (tailnum) when multiple matches exist (like year)
flights %>%
left_join(planes, by = "tailnum")## # A tibble: 336,776 × 27
## year.x month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 1 517 515 2 830 819
## 2 2013 1 1 533 529 4 850 830
## 3 2013 1 1 542 540 2 923 850
## 4 2013 1 1 544 545 -1 1004 1022
## 5 2013 1 1 554 600 -6 812 837
## 6 2013 1 1 554 558 -4 740 728
## 7 2013 1 1 555 600 -5 913 854
## 8 2013 1 1 557 600 -3 709 723
## 9 2013 1 1 557 600 -3 838 846
## 10 2013 1 1 558 600 -2 753 745
## # ℹ 336,766 more rows
## # ℹ 19 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## # tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## # hour <dbl>, minute <dbl>, time_hour <dttm>, year.y <int>, type <chr>,
## # manufacturer <chr>, model <chr>, engines <int>, seats <int>, speed <int>,
## # engine <chr># When columns have different names in the two tables (e.g., dest and faa)
flights %>%
left_join(airports, c("dest" = "faa"))## # A tibble: 336,776 × 26
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 1 517 515 2 830 819
## 2 2013 1 1 533 529 4 850 830
## 3 2013 1 1 542 540 2 923 850
## 4 2013 1 1 544 545 -1 1004 1022
## 5 2013 1 1 554 600 -6 812 837
## 6 2013 1 1 554 558 -4 740 728
## 7 2013 1 1 555 600 -5 913 854
## 8 2013 1 1 557 600 -3 709 723
## 9 2013 1 1 557 600 -3 838 846
## 10 2013 1 1 558 600 -2 753 745
## # ℹ 336,766 more rows
## # ℹ 18 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## # tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## # hour <dbl>, minute <dbl>, time_hour <dttm>, name <chr>, lat <dbl>,
## # lon <dbl>, alt <dbl>, tz <dbl>, dst <chr>, tzone <chr># --- Semi Join: Keeps observations in x that have a match in y ---
semi_join(x, y, by = "key")## # A tibble: 2 × 2
## key val_x
## <dbl> <chr>
## 1 1 x1
## 2 2 x2# --- Anti Join: Drops observations in x that have a match in y ---
anti_join(x, y, by = "key")## # A tibble: 1 × 2
## key val_x
## <dbl> <chr>
## 1 3 x3# --- Checking Primary Keys ---
airports %>%
count(faa) %>%
filter(n > 1)## # A tibble: 0 × 2
## # ℹ 2 variables: faa <chr>, n <int># --- Set Operations Example ---
df1 <- tribble(
~x, ~y,
1, 1,
2, 1
)
df2 <- tribble(
~x, ~y,
1, 1,
2, 2
)
# Intersect: Rows in both df1 and df2
intersect(df1, df2)## # A tibble: 1 × 2
## x y
## <dbl> <dbl>
## 1 1 1# Union: Unique rows from both tables
union(df1, df2)## # A tibble: 3 × 2
## x y
## <dbl> <dbl>
## 1 1 1
## 2 2 1
## 3 2 2# Set Difference: Rows in df1 not in df2
setdiff(df1, df2)## # A tibble: 1 × 2
## x y
## <dbl> <dbl>
## 1 2 1```