#Lab 2, Question 1
surveys <- read_csv(here::here("data",
"surveys.csv"))Example B-level Portfolio
My Grade: I believe my grade equivalent to course work evidenced below to be an A-.
Learning Objective Evidence: In the code chunks below, provide code from Lab or Challenge assignments where you believe you have demonstrated proficiency with the specified learning target. Be sure to specify where the code came from (e.g., Lab 4 Question 2).
Working with Data
WD-1: I can import data from a variety of formats (e.g., csv, xlsx, txt, etc.).
csv
xlsx
#Practice Activity 4, Question 3
military <- read_xlsx(here::here("data",
"gov_spending_per_capita.xlsx"),
sheet = "Share of Govt. spending",
skip = 7,
n_max = 190,
na = c(". .",
"xxx")
)txt
#Check-in 2.3
ages_mystery <- read_table(here::here("Ages_Data",
"ages_space.txt"))WD-2: I can select necessary columns from a dataset.
#Lab 3, Question 5
teacher_evals_clean <- teacher_evals |>
mutate(teacher_id = as.factor(teacher_id)) |>
rename(sex = gender) |>
filter(no_participants >= 10) |>
select(course_id,
teacher_id,
question_no,
no_participants,
resp_share,
SET_score_avg,
percent_failed_cur,
academic_degree,
seniority,
sex) WD-3: I can filter rows from a dataframe for a variety of data types (e.g., numeric, integer, character, factor, date).
- numeric
#Lab 5, Finding the final suspect
person |>
full_join(drivers_license,
join_by(license_id == id)) |>
full_join(facebook_event_checkin,
join_by(id == person_id)) |>
full_join(income,
join_by(ssn)) |>
filter(height == c(65:67),
hair_color == "red",
car_make == "Tesla",
str_detect(event_name, "SQL Symphony")) |>
pull(name)- character – specifically a string (example must use functions from stringr)
#Lab 5
get_fit_now_member |>
full_join(get_fit_now_check_in,
join_by(id == membership_id)) |>
filter(membership_status == "gold",
str_detect(id, "48Z"),
ymd(check_in_date) == "2018-01-09") |>
pull(person_id)- factor
- date (example must use functions from lubridate)
#Lab 5, Crime Scene Report
crime_scene_report |>
filter(city == "SQL City",
type == "murder",
ymd(date) == "2018-01-15") |>
pull(description)WD-4: I can modify existing variables and create new variables in a dataframe for a variety of data types (e.g., numeric, integer, character, factor, date).
- numeric (using
as.numeric()is not sufficient)
#Challenge 3, creating a new variable based of a numeric value
teacher_evals_compare <- teacher_evals_clean |>
filter(question_no == 903) |>
mutate(SET_level = if_else(SET_score_avg >= 4,
"excellent",
"standard")) |>
mutate(sen_level = if_else(seniority <= 4,
"junior",
"senior")) |>
select(course_id, SET_level, sen_level)- character – specifically a string (example must use functions from stringr)
- factor (example must use functions from forcats)
#Lab 4, Question 3
ca_childcare <- ca_childcare |>
mutate(region = fct_collapse(.f = county_name,
"Superior California" = c("Butte County", "Colusa County", "El Dorado County", "Glenn County", "Lassen County", "Modoc County", "Nevada County", "Placer County", "Plumas County", "Sacramento County", "Shasta County", "Sierra County", "Siskiyou County", "Sutter County", "Tehama County", "Yolo County", "Yuba County"),
"North Coast" = c("Del Norte County", "Humboldt County", "Lake County", "Mendocino County", "Napa County", "Sonoma County", "Trinity County"),
"San Francisco Bay Area" = c("Alameda County", "Contra Costa County", "Marin County", "San Francisco County","San Mateo County", "Santa Clara County", "Solano County"),
"Northern San Joaquin Valley" = c("Alpine County", "Amador County", "Calaveras County", "Madera County", "Mariposa County", "Merced County", "Mono County", "San Joaquin County", "Stanislaus County", "Tuolumne County"),
"Central Coast" = c("Monterey County", "San Benito County", "San Luis Obispo County", "Santa Barbara County", "Santa Cruz County", "Ventura County"),
"Southern San Joaquin Valley" = c("Fresno County", "Inyo County", "Kern County", "Kings County", "Tulare County"),
"Inland Empire" = c("Riverside County", "San Bernardino County"),
"Los Angeles County" = c("Los Angeles County"),
"Orange County" = c("Orange County"),
"San Diego - Imperial" = c("San Diego County", "Imperial County")))- date (example must use functions from lubridate)
WD-5: I can use mutating joins to combine multiple dataframes.
left_join()
#Lab 5, Checking license plate and date
get_fit_now_member |>
left_join(get_fit_now_check_in,
join_by(id == membership_id)) |>
filter(membership_status == "gold",
str_detect(id, "48Z"),
ymd(check_in_date) == "2018-01-09") |>
pull(person_id)right_join()
inner_join()
#Lab 5, Checking gym members license plate
person |>
inner_join(drivers_license,
join_by(license_id == id)) |>
filter(str_detect(plate_number,
"H42W")) |>
pull(id)WD-6: I can use filtering joins to filter rows from a dataframe.
semi_join()
anti_join()
WD-7: I can pivot dataframes from long to wide and visa versa
pivot_longer()
#Lab 4, Question 6
ca_childcare |>
select(study_year,
region,
mc_infant,
mc_toddler,
mc_preschool) |>
pivot_longer(cols = c(mc_infant,
mc_toddler,
mc_preschool),
names_to = "mc_cat",
values_to = "mc_cost") |>
mutate(mc_cat = fct_recode(.f = mc_cat,
"Infant" = "mc_infant",
"Toddler" = "mc_toddler",
"Preschool" = "mc_preschool")) |>
ggplot(mapping = aes(x = study_year,
y = mc_cost,
color = fct_reorder2(.f = region,
.x = study_year,
.y = mc_cost))) +
geom_point() +
geom_smooth() +
scale_x_continuous(breaks = c(2008,
2010,
2012,
2014,
2016,
2018)) +
facet_wrap(~ (mc_cat = fct_relevel(mc_cat,
"Infant",
"Toddler",
"Preschool"))) +
theme_bw() +
theme(axis.text.x = element_text(size = 6.5)) +
labs(y = "",
x = "Study Year",
color = "California Region",
title = "Weekly Median Price for Center-Based Childcare ($)")pivot_wider()
#Lab 4, Question 4
ca_childcare |>
select(region, mhi_2018, study_year) |>
filter(study_year %in% c(2008, 2018)) |>
group_by(region, study_year) |>
summarize(avg_income = mean(mhi_2018)) |>
pivot_wider(names_from = study_year, values_from = avg_income) |>
arrange(desc(`2018`))Reproducibility
R-1: I can create professional looking, reproducible analyses using RStudio projects, Quarto documents, and the here package.
I’ve done this in the following provided assignments: Lab3, Lab 4
R-2: I can write well documented and tidy code.
- Example of ggplot2 plotting
#Lab 2, Question 16
#| label: rotated-boxplot
ggplot(surveys, aes(x = weight,
y = species)) +
geom_jitter(alpha = 0.5,
color = "blue") +
geom_boxplot() +
labs(x = "Weight (grams)",
y = "",
title = "Weight by Species")- Example of dplyr pipeline
#Lab 3, Question 5
teacher_evals_clean <- teacher_evals |>
mutate(teacher_id = as.factor(teacher_id)) |>
rename(sex = gender) |>
filter(no_participants >= 10) |>
select(course_id,
teacher_id,
question_no,
no_participants,
resp_share,
SET_score_avg,
percent_failed_cur,
academic_degree,
seniority,
sex) - Example of function formatting
R-3: I can write robust programs that are resistant to changes in inputs.
- Example – any context
#Lab 3, Question 10
teacher_evals_clean |>
filter(question_no == 901) |>
group_by(teacher_id) |>
summarise(mean_score = mean(SET_score_avg)) |>
filter(mean_score == max(mean_score) | mean_score == min(mean_score)) |>
arrange(desc(mean_score))- Example of function stops
Data Visualization & Summarization
DVS-1: I can create visualizations for a variety of variable types (e.g., numeric, character, factor, date)
- at least two numeric variables
#Lab 2, Question 4
ggplot(data = surveys, mapping = aes(x = weight, y = hindfoot_length)) +
geom_point(color = "darkblue", alpha = 0.5) +
facet_wrap(~species) +
labs(x = "Weight (grams)",
y = "",
subtitle = "Hindfoot Length (millimeters)",
title = "Hindfoot Length vs. Weight Faceted by Species of Animal")- at least one numeric variable and one categorical variable
#Lab 2, Question 16
ggplot(surveys, aes(x = weight, y = species)) +
geom_jitter(alpha = 0.5, color = "blue") +
geom_boxplot() +
labs(x = "Weight (grams)",
y = "",
title = "Weight by Species")- at least two categorical variables
#Challenge 2
surveys |>
ggplot(aes(x = weight, y = species, color = genus)) +
geom_boxplot() +
scale_color_manual(values = cdPalette_grey) +
labs(x = "Weight (g)", y = "", subtitle = "Species", legend = "Genus")- dates (timeseries plot)
DVS-2: I use plot modifications to make my visualization clear to the reader.
- I can ensure people don’t tilt their head
#Lab 4, Question 7 (Using subtitle instead of y label)
ca_childcare |>
ggplot(mapping = aes(x = mhi_2018, y = mc_infant)) +
geom_point() +
geom_smooth(method = "lm") +
labs(x = "Median Household Income ($)",
y = "",
subtitle = "Weekly Center-Based Infant Childcare Cost ($)",
title = "Weekly Center-Based Infant Childcare Cost vs Median Houshold Income")- I can modify the text in my plot to be more readable
#Lab 4, Question 6
ca_childcare |>
select(study_year,
region,
mc_infant,
mc_toddler,
mc_preschool) |>
pivot_longer(cols = c(mc_infant,
mc_toddler,
mc_preschool),
names_to = "mc_cat",
values_to = "mc_cost") |>
mutate(mc_cat = fct_recode(.f = mc_cat,
"Infant" = "mc_infant",
"Toddler" = "mc_toddler",
"Preschool" = "mc_preschool")) |>
ggplot(mapping = aes(x = study_year,
y = mc_cost,
color = fct_reorder2(.f = region,
.x = study_year,
.y = mc_cost))) +
geom_point() +
geom_smooth() +
scale_x_continuous(breaks = c(2008,
2010,
2012,
2014,
2016,
2018)) +
facet_wrap(~ (mc_cat = fct_relevel(mc_cat,
"Infant",
"Toddler",
"Preschool"))) +
theme_bw() +
theme(axis.text.x = element_text(size = 6.5)) +
labs(y = "",
x = "Study Year",
color = "California Region",
title = "Weekly Median Price for Center-Based Childcare ($)")- I can reorder my legend to align with the colors in my plot
#Lab 4, Question 6
ca_childcare |>
select(study_year,
region,
mc_infant,
mc_toddler,
mc_preschool) |>
pivot_longer(cols = c(mc_infant,
mc_toddler,
mc_preschool),
names_to = "mc_cat",
values_to = "mc_cost") |>
mutate(mc_cat = fct_recode(.f = mc_cat,
"Infant" = "mc_infant",
"Toddler" = "mc_toddler",
"Preschool" = "mc_preschool")) |>
ggplot(mapping = aes(x = study_year,
y = mc_cost,
color = fct_reorder2(.f = region,
.x = study_year,
.y = mc_cost))) +
geom_point() +
geom_smooth() +
scale_x_continuous(breaks = c(2008,
2010,
2012,
2014,
2016,
2018)) +
facet_wrap(~ (mc_cat = fct_relevel(mc_cat,
"Infant",
"Toddler",
"Preschool"))) +
theme_bw() +
theme(axis.text.x = element_text(size = 6.5)) +
labs(y = "",
x = "Study Year",
color = "California Region",
title = "Weekly Median Price for Center-Based Childcare ($)")DVS-3: I show creativity in my visualizations
- I can use non-standard colors
- I can use annotations
- I can be creative…
DVS-4: I can calculate numerical summaries of variables.
- Example using
summarize()
#Lab 3, Question 10
teacher_evals_clean |>
filter(seniority == 1) |>
group_by(teacher_id) |>
summarise(avg_fail = mean(percent_failed_cur)) |>
filter(avg_fail == max(avg_fail) | avg_fail == min(avg_fail)) |>
arrange(desc(avg_fail))- Example using
across()
#Lab 3, Question 7 (R recommended I use if_any instead of across)
teacher_evals_clean |>
filter(
if_any(.cols = teacher_id:sex,
.fns = ~ is.na(.x)
)
)DVS-5: I can find summaries of variables across multiple groups.
- Example 1
#Lab 4, Question 4
ca_childcare |>
select(region, mhi_2018, study_year) |>
filter(study_year %in% c(2008, 2018)) |>
group_by(region, study_year) |>
summarize(avg_income = mean(mhi_2018)) |>
pivot_wider(names_from = study_year, values_from = avg_income) |>
arrange(desc(`2018`))- Example 2
#Lab 4, Question 12
teacher_evals_clean |>
filter("female" %in% sex, "dr" %in% academic_degree, "ma" %in% academic_degree) |>
group_by(teacher_id) |>
summarise(avg_resp = mean(resp_share)) |>
filter(avg_resp == max(avg_resp) | avg_resp == min(avg_resp)) |>
arrange(desc(avg_resp))DVS-6: I can create tables which make my summaries clear to the reader.
- Example 1
#Lab 3, Question 11
teacher_evals_clean |>
filter(seniority == 1) |>
group_by(teacher_id) |>
summarise(avg_fail = mean(percent_failed_cur)) |>
filter(avg_fail == max(avg_fail) | avg_fail == min(avg_fail)) |>
arrange(desc(avg_fail))- Example 2
#Lab 3, Question 10
teacher_evals_clean |>
filter(seniority == 1) |>
group_by(teacher_id) |>
summarise(avg_fail = mean(percent_failed_cur)) |>
filter(avg_fail == max(avg_fail) | avg_fail == min(avg_fail)) |>
arrange(desc(avg_fail))DVS-7: I show creativity in my tables.
- Example 1
- Example 2
Program Efficiency
PE-1: I can write concise code which does not repeat itself.
- using a single function call with multiple inputs (rather than multiple function calls)
#Lab 3, Question 5
teacher_evals_clean <- teacher_evals |>
mutate(teacher_id = as.factor(teacher_id)) |>
rename(sex = gender) |>
filter(no_participants >= 10) |>
select(course_id,
teacher_id,
question_no,
no_participants,
resp_share,
SET_score_avg,
percent_failed_cur,
academic_degree,
seniority,
sex) across()
#Lab 3, Question 7 (R recommended I use if_any instead of across)
teacher_evals_clean |>
filter(
if_any(.cols = teacher_id:sex,
.fns = ~ is.na(.x)
)
)map()functions
PE-2: I can write functions to reduce repetition in my code.
- Function that operates on vectors
- Function that operates on data frames
PE-3:I can use iteration to reduce repetition in my code.
across()
map()function with one input (e.g.,map(),map_chr(),map_dbl(), etc.)
map()function with more than one input (e.g.,map_2()orpmap())
PE-4: I can use modern tools when carrying out my analysis.
- I can use functions which are not superseded or deprecated
#Lab 3, Question 9
teacher_evals_clean |>
count(course_id, teacher_id) |>
filter(n == 9)- I can connect a data wrangling pipeline into a
ggplot()
#Lab 4, Question 6
ca_childcare |>
select(study_year,
region,
mc_infant,
mc_toddler,
mc_preschool) |>
pivot_longer(cols = c(mc_infant,
mc_toddler,
mc_preschool),
names_to = "mc_cat",
values_to = "mc_cost") |>
mutate(mc_cat = fct_recode(.f = mc_cat,
"Infant" = "mc_infant",
"Toddler" = "mc_toddler",
"Preschool" = "mc_preschool")) |>
ggplot(mapping = aes(x = study_year,
y = mc_cost,
color = fct_reorder2(.f = region,
.x = study_year,
.y = mc_cost))) +
geom_point() +
geom_smooth() +
scale_x_continuous(breaks = c(2008,
2010,
2012,
2014,
2016,
2018)) +
facet_wrap(~ (mc_cat = fct_relevel(mc_cat,
"Infant",
"Toddler",
"Preschool"))) +
theme_bw() +
theme(axis.text.x = element_text(size = 6.5)) +
labs(y = "",
x = "Study Year",
color = "California Region",
title = "Weekly Median Price for Center-Based Childcare ($)")Data Simulation & Statisical Models
DSSM-1: I can simulate data from a variety of probability models.
- Example 1
- Example 2
DSSM-2: I can conduct common statistical analyses in R.
- Example 1
#Lab 2, Question 17 (ANOVA)
species_mod <- aov(surveys$weight ~ surveys$species)
summary(species_mod)- Example 2
#Lab 4, Question 8 (Linear Regression)
reg_mod1 <- lm(ca_childcare$mc_infant ~ ca_childcare$mhi_2018)
summary(reg_mod1)Revising My Thinking
Throughout the course I have done my best to revise and resubmit every assignment that I have received a growing on. I did not just do this to receive a better grade, I did it to correct small mistakes and try to learn how I could improve on my assignments. While in some cases, my mistakes may have been repeated, I have always believed that practice makes perfect and it will often take multiple trials to get things close to perfect. This being said, I have always seen revisions as a chance to continue practicing my skills in R and increase my attention to detail when it comes to little things that make big differences.
Extending My Thinking
I believe that I mainly demonstrated extended thinking within my challenge assignments. During the challenge assignments I always did my best to attempt the most difficult challenge and at least struggle with the problems a little bit to get better at critical thinking and working around issues in R. During my assignments I believe I extended my thinking by doing my best to find a solution that I was confident in (and understood) and not just surrender to the problem / accept that I was going to get a “growing.”
Peer Support & Collaboration
This was a peer review that I was proud of: “Hey Alison, great job on Lab 4!
First off, I noticed that your code is very tidy for the most part. There were a couple instances where you could have made some returns after commas, but for the most part you did very well. Additionally, I appreciate you sizing down the text size on the x-axis of your graph, I will definitely be adding that to my revisions!
One thing that you might be able to do better is in question 3, instead of using case_when(), you could use fct_collapse() in order to collapse the counties into region groups. This way you don’t have to repetitively type “county_name %in%”. Furthermore, this change would save you some time in writing your code for question 6 (the graph), as your region factors will already be in place.
Again, great job on lab 4!”
I think when it came to working in a pair on practice activities, I never really had any large issues. I was always trying to be conscious of the coder and developer roles and follow the directions as best as possible. I think where I improved was in my advice as the developer to the coder. I became better at explaining my thought processes and explaining how I knew something made sense a certain way. This allowed me and my partner to be much more efficient with our practice activities and gave us more time to learn what was going on in the R code.