Homework 2- Data Hack
Jesu Rosas
2026-04-13
Load data
library(pacman)
p_load(tidyverse, tidylog, janitor)
ff <- read_csv(
"https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2018/2018-09-04/fastfood_calories.csv"
)## New names:
## Rows: 515 Columns: 18
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (3): restaurant, item, salad dbl (15): ...1, calories, cal_fat, total_fat,
## sat_fat, trans_fat, cholestero...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`Question 1
1.a
ff <- ff %>%
clean_names()
Mcdonalds <- ff %>%
filter(restaurant == "Mcdonalds")## filter: removed 458 rows (89%), 57 rows remainingsummary(Mcdonalds)## x1 restaurant item calories
## Min. : 1 Length:57 Length:57 Min. : 140.0
## 1st Qu.:15 Class :character Class :character 1st Qu.: 380.0
## Median :29 Mode :character Mode :character Median : 540.0
## Mean :29 Mean : 640.4
## 3rd Qu.:43 3rd Qu.: 740.0
## Max. :57 Max. :2430.0
## cal_fat total_fat sat_fat trans_fat
## Min. : 50.0 Min. : 5.00 Min. : 0.500 Min. :0.0000
## 1st Qu.: 160.0 1st Qu.: 18.00 1st Qu.: 4.500 1st Qu.:0.0000
## Median : 240.0 Median : 27.00 Median : 7.000 Median :0.0000
## Mean : 285.6 Mean : 31.81 Mean : 8.289 Mean :0.4649
## 3rd Qu.: 320.0 3rd Qu.: 36.00 3rd Qu.:11.000 3rd Qu.:1.0000
## Max. :1270.0 Max. :141.00 Max. :27.000 Max. :3.0000
## cholesterol sodium total_carb fiber
## Min. : 0.0 Min. : 20 Min. : 9.00 Min. :0.000
## 1st Qu.: 70.0 1st Qu.: 870 1st Qu.: 32.00 1st Qu.:2.000
## Median : 95.0 Median :1120 Median : 46.00 Median :3.000
## Mean :109.7 Mean :1438 Mean : 48.79 Mean :3.228
## 3rd Qu.:125.0 3rd Qu.:1780 3rd Qu.: 62.00 3rd Qu.:4.000
## Max. :475.0 Max. :6080 Max. :156.00 Max. :8.000
## sugar protein vit_a vit_c
## Min. : 0.00 Min. : 7.0 Min. : 0.00 Min. : 0.0
## 1st Qu.: 4.00 1st Qu.: 25.0 1st Qu.: 2.00 1st Qu.: 2.0
## Median : 9.00 Median : 33.0 Median : 6.00 Median :15.0
## Mean :11.07 Mean : 40.3 Mean : 33.72 Mean :18.3
## 3rd Qu.:13.00 3rd Qu.: 46.0 3rd Qu.: 20.00 3rd Qu.:25.0
## Max. :87.00 Max. :186.0 Max. :180.00 Max. :70.0
## calcium salad
## Min. : 0.0 Length:57
## 1st Qu.: 6.0 Class :character
## Median : 15.0 Mode :character
## Mean : 20.6
## 3rd Qu.: 20.0
## Max. :290.0Mean calories is. 640.4 in McDonalds Max is 2430 and min is 140 calories per food item 20 piece Buttermilk Crispy Chicken Tenders is the item with max calories
1.b
high_cal <- ff %>%
filter(
calories > 1000
) ## filter: removed 487 rows (95%), 28 rows remaininghigh_cal %>%
count(restaurant, sort= T)## count: now 6 rows and 2 columns, ungrouped## # A tibble: 6 × 2
## restaurant n
## <chr> <int>
## 1 Sonic 8
## 2 Burger King 6
## 3 Mcdonalds 6
## 4 Subway 4
## 5 Dairy Queen 3
## 6 Arbys 11.c
sub_chick_1000 <- ff %>%
filter(
restaurant == "Subway"| restaurant == "Chick Fil-A",
calories < 500
)## filter: removed 440 rows (85%), 75 rows remaining75 items
Question 2
2.a
ff %>%
group_by(restaurant) %>%
summarise(mean(calories))## group_by: one grouping variable (restaurant)
## summarise: now 8 rows and 2 columns, ungrouped## # A tibble: 8 × 2
## restaurant `mean(calories)`
## <chr> <dbl>
## 1 Arbys 533.
## 2 Burger King 609.
## 3 Chick Fil-A 384.
## 4 Dairy Queen 520.
## 5 Mcdonalds 640.
## 6 Sonic 632.
## 7 Subway 503.
## 8 Taco Bell 444.McDonalds
2.b
nutrition_by_restaurant <- ff %>%
group_by(restaurant) %>%
summarize(
number_of_items = n(),
average_calories = mean(calories, na.rm = T),
average_protein = mean(protein, na.rm = T),
average_sodium = mean(sodium, na.rm = T),
average_total_fat = mean(total_fat, na.rm = T),
.groups = "drop"
)## group_by: one grouping variable (restaurant)
## summarize: now 8 rows and 6 columns, ungroupedQuestion 3
3.a
ff <- ff %>%
group_by(restaurant) %>%
mutate(
restaurant_avg_cal = mean(calories, na.rm = T),
cal_vs_avg = calories - restaurant_avg_cal
) %>%
ungroup()## group_by: one grouping variable (restaurant)
## mutate (grouped): new variable 'restaurant_avg_cal' (double) with 8 unique values and 0% NA
## new variable 'cal_vs_avg' (double) with 333 unique values and 0% NA
## ungroup: no grouping variables remain3.b
ff %>%
arrange(desc(cal_vs_avg)) %>%
select(restaurant, item, calories, restaurant_avg_cal, cal_vs_avg) %>%
slice(1:5)## select: dropped 15 variables (x1, cal_fat, total_fat, sat_fat, trans_fat, …)
## slice: removed 510 rows (99%), 5 rows remaining## # A tibble: 5 × 5
## restaurant item calories restaurant_avg_cal cal_vs_avg
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 Mcdonalds 20 piece Buttermilk Crispy… 2430 640. 1790.
## 2 Mcdonalds 40 piece Chicken McNuggets 1770 640. 1130.
## 3 Mcdonalds 10 piece Sweet N' Spicy Ho… 1600 640. 960.
## 4 Burger King American Brewhouse King 1550 609. 941.
## 5 Mcdonalds 12 piece Buttermilk Crispy… 1510 640. 870.Question 4
4.a
ff <- ff %>%
mutate(
estimated_cal = (protein*4 + total_carb*4 + total_fat*9),
cal_discrepancy = calories - estimated_cal
)## mutate: new variable 'estimated_cal' (double) with 395 unique values and <1% NA
## new variable 'cal_discrepancy' (double) with 61 unique values and <1% NA4.b
ff %>%
summarize(
min_discrepancy = min(cal_discrepancy, na.rm = TRUE),
mean_discrepancy = mean(cal_discrepancy, na.rm = TRUE),
median_discrepancy = median(cal_discrepancy, na.rm = TRUE),
max_discrepancy = max(cal_discrepancy, na.rm = TRUE)
)## summarize: now one row and 4 columns, ungrouped## # A tibble: 1 × 4
## min_discrepancy mean_discrepancy median_discrepancy max_discrepancy
## <dbl> <dbl> <dbl> <dbl>
## 1 -892 -2.90 -2 190library(ggplot2)
ggplot(data = ff, aes(x = cal_discrepancy)) +
geom_histogram(binwidth = 25,
fill = "pink",
color = "white") +
labs(
title = "Distribution of Calorie Discrepancy",
x = "Reported Calories − Estimated Calories",
y = "Number of Items"
)## Warning: Removed 1 row containing non-finite outside the scale range
## (`stat_bin()`).
4.c
ff %>%
arrange(desc(abs(cal_discrepancy))) %>%
select(restaurant, item, calories, cal_discrepancy) %>%
slice(1:10)## select: dropped 18 variables (x1, cal_fat, total_fat, sat_fat, trans_fat, …)
## slice: removed 505 rows (98%), 10 rows remaining## # A tibble: 10 × 4
## restaurant item calories cal_discrepancy
## <chr> <chr> <dbl> <dbl>
## 1 Sonic Ultimate Chicken Club 100 -892
## 2 Arbys Smokehouse Beef Short Rib Sandwich 590 -281
## 3 Burger King American Brewhouse King 1550 -204
## 4 Subway Footlong Oven Roasted Chicken 640 190
## 5 Burger King Bacon King 1040 188
## 6 Sonic Garlic Parmesan Dunked Ultimate Chicken… 1350 82
## 7 Sonic Buffalo Dunked Ultimate Chicken Sandwich 1000 79
## 8 Dairy Queen Deluxe Double Cheeseburger 640 58
## 9 Dairy Queen Deluxe Double Hamburger 540 54
## 10 Dairy Queen Original Double Cheeseburger 630 52Question 5
5.a
ggplot(data = ff, aes(x = calories)) +
geom_histogram(binwidth = 50,
fill = "pink",
color = "white") +
labs(
title = "Distribution of Calorie Across all Fast Food Items",
x = "Reported Calories",
y = "Number of Items"
)
5.b
ggplot(ff, aes(x = restaurant, y = calories)) +
geom_boxplot(fill = "turquoise", alpha = 0.6) +
coord_flip() +
labs (
title = "Calorie Distribution by Restaurant",
x = NULL,
y = "Calories"
)
5.c
ggplot(nutrition_by_restaurant,
aes(x = reorder(restaurant, average_sodium), y = average_sodium)) +
geom_col(fill = "turquoise") +
coord_flip() +
labs(
title = "Average Sodium per Item by Restaurant",
x = NULL,
y = "Average Sodium (mg)"
)
5.d
ggplot(ff, aes(x = total_fat, y = calories, color = restaurant)) +
geom_point(alpha = 0.4) +
geom_smooth(method = "lm", se = FALSE, color = "turquoise") +
labs(
title = "Does Fat Drive Calories?",
x = "Total Fat (g)",
y = "Calories",
color = "Restaurant"
)## `geom_smooth()` using formula = 'y ~ x'
## Question 6 #### Is there a relationship between
fiber and calories?
ff %>%
ggplot(aes(x = fiber, y = calories)) +
geom_point(alpha = 0.5) +
geom_smooth(method = "lm", se = FALSE) +
labs(
title = "Relationship between Fiber and Calories",
x = "Fiber (g)",
y = "Calories"
)## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 12 rows containing non-finite outside the scale range
## (`stat_smooth()`).## Warning: Removed 12 rows containing missing values or values outside the scale range
## (`geom_point()`).
model <- lm(calories ~ fiber, data = ff)
summary(model)##
## Call:
## lm(formula = calories ~ fiber, data = ff)
##
## Residuals:
## Min 1Q Median 3Q Max
## -470.82 -177.58 -50.25 135.65 1962.13
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 414.919 20.254 20.486 < 2e-16 ***
## fiber 26.476 3.948 6.707 5.38e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 268.7 on 501 degrees of freedom
## (12 observations deleted due to missingness)
## Multiple R-squared: 0.08239, Adjusted R-squared: 0.08056
## F-statistic: 44.98 on 1 and 501 DF, p-value: 5.382e-11