##READING FILES
chem1_f18 = read.csv("~/Teaching/Grades_and_SRT/Fall2018/chem1331_f18.csv",header = TRUE)
chem1_f19 = read.csv("~/Teaching/Grades_and_SRT/Fall2019/chem1331_f19_grades_canvas.csv",header = TRUE)
chem1_f20 = read.csv("~/Teaching/Grades_and_SRT/Fall2020/chem1331_f20_grades_canvas.csv",header = TRUE)
chem1_f21 = read.csv("~/Teaching/Grades_and_SRT/Fall2021/chem1331_f21_grades_canvas.csv",header = TRUE)
chem1_f22 = read.csv("~/Teaching/Grades_and_SRT/Fall2022/chem1331_f22_grades_canvas.csv",header = TRUE)
chem1_f23 = read.csv("~/Teaching/Grades_and_SRT/Fall2023/chem1331_f23_grades_canvas.csv",header = TRUE)
chem2_s19 = read.csv("~/Teaching/Grades_and_SRT/Spring2019/chem1333_s19.csv", header = TRUE)
chem2_s20 = read.csv("~/Teaching/Grades_and_SRT/Spring2020/chem1333_s20_grades_canvas.csv", header = TRUE)
chem2_s21 = read.csv("~/Teaching/Grades_and_SRT/Spring2021/chem1333_s21_grades_canvas.csv", header = TRUE)
chem2_s22 = read.csv("~/Teaching/Grades_and_SRT/Spring2022/chem1333_s22_grades_canvas.csv", header = TRUE)
chem2_s23 = read.csv("~/Teaching/Grades_and_SRT/Spring2023/chem1333_s23_grades_canvas.csv", header = TRUE)
chem3_f19 = read.csv("~/Teaching/Grades_and_SRT/Fall2019/chem2231_f19_grades_canvas.csv",header = TRUE)
chem3_f20 = read.csv("~/Teaching/Grades_and_SRT/Fall2020/chem2131_f20_grades_canvas.csv",header = TRUE)
chem3_f21 = read.csv("~/Teaching/Grades_and_SRT/Fall2021/chem2131_f21_grades_canvas.csv",header = TRUE)
chem3_f22 = read.csv("~/Teaching/Grades_and_SRT/Fall2022/chem2131_f22_grades_canvas.csv",header = TRUE)
chem3_f23 = read.csv("~/Teaching/Grades_and_SRT/Fall2023/chem2131_f23_grades_canvas.csv",header = TRUE)
chem4_s20 = read.csv("~/Teaching/Grades_and_SRT/Spring2020/chem2333_s20_grades_canvas.csv", header = TRUE)
chem4_s21 = read.csv("~/Teaching/Grades_and_SRT/Spring2021/chem2335_s21_grades_canvas.csv", header = TRUE)
chem4_s22 = read.csv("~/Teaching/Grades_and_SRT/Spring2022/chem2335_s22_grades_canvas.csv", header = TRUE)
chem4_s23 = read.csv("~/Teaching/Grades_and_SRT/Spring2023/chem2335_s23_grades_canvas.csv", header = TRUE)
chem4_s24 = read.csv("~/Teaching/Grades_and_SRT/Spring2024/chem2335_s24_grades_canvas.csv", header = TRUE)
dfs = list(
chem1_f18 = chem1_f18,
chem2_s19 = chem2_s19,
chem3_f19 = chem3_f19,
chem4_s20 = chem4_s20,
chem1_f19 = chem1_f19,
chem2_s20 = chem2_s20,
chem3_f20 = chem3_f20,
chem4_s21 = chem4_s21,
chem1_f20 = chem1_f20,
chem2_s21 = chem2_s21,
chem3_f21 = chem3_f21,
chem4_s22 = chem4_s22,
chem1_f21 = chem1_f21,
chem2_s22 = chem2_s22,
chem3_f22 = chem3_f22,
chem4_s23 = chem4_s23,
chem1_f22 = chem1_f22,
chem2_s23 = chem2_s23,
chem3_f23 = chem3_f23,
chem4_s24 = chem4_s24,
chem1_f23 = chem1_f23
)
getFinalScore = function(dfs){
#For some reason, some Final.Score is lower than Current.Score. Using the highest
for (i in seq_along(dfs)) {
df <- dfs[[i]]
didItChange=FALSE
times=0
for (j in 1:nrow(df)) {
if (df[j, "Current.Score"] > df[j, "Final.Score"]) {
df[j, "Final.Score"] <- df[j, "Current.Score"]
didItChange=TRUE
times=times+1
}
}
#if (didItChange){ print(paste("The dataframe",names(dfs)[i]," Current and Final score are not the same in",times,"students"))}
dfs[[i]] <- df
}
return(dfs)
}
dfs = getFinalScore(dfs)
We started teaching the new curriculum in Fall 2018. The first cohort (f18) finished in Spring 2020
Let’s consider how students flew through the curriculum and how they did. Some students postpone taking Chem3 or Chem4, we are taking their grade into account even if they didn’t take the course during their sophomore year.
###PREPARING FILES
library(purrr)
combined_df <- dfs %>%
map(~ select(.x, SIS.Login.ID, Final.Score)) %>%
reduce(full_join, by = "SIS.Login.ID")
# Rename the Final.Score columns with the names of the original dataframes
names(combined_df)[-1] <- names(dfs)
# Rename the SIS.Login.ID column to student
names(combined_df)[1] <- "student"
f18cohort <- combined_df %>%
filter(!is.na(chem1_f18))
f19cohort <- combined_df %>%
filter(!is.na(chem1_f19))
f20cohort <- combined_df %>%
filter(!is.na(chem1_f20))
f21cohort <- combined_df %>%
filter(!is.na(chem1_f21))
f22cohort <- combined_df %>%
filter(!is.na(chem1_f22))
merge_columns <- function(df, prefix) {
columns <- grep(paste0("^", prefix), names(df), value = TRUE)
merged_column <- ifelse(rowSums(!is.na(df[columns])) == 0, NA,
do.call(pmax, c(df[columns], na.rm = TRUE)))
return(merged_column)
}
returnMergedColumns = function(df){
# Apply the function to merge chem1, chem2, chem3, and chem4 columns
df <- df %>%
mutate(
chem1 = merge_columns(., "chem1"),
chem2 = merge_columns(., "chem2"),
chem3 = merge_columns(., "chem3"),
chem4 = merge_columns(., "chem4")
) %>%
select(student, chem1, chem2, chem3, chem4)
return(df)
}
prepareAlluvial = function(df){
new_df <- df %>%
mutate_at(vars(chem1:chem4), ~case_when(
is.na(.) ~ "OUT",
. > 90 ~ "A",
. >= 80 & . <= 90 ~ "B",
. >= 70 & . < 80 ~ "C",
. >= 60 & . < 70 ~ "D",
TRUE ~ "F"
))
long_df <- pivot_longer(new_df, cols = starts_with("chem"), names_to = "course", values_to = "letterGrade")
# Rename columns
colnames(long_df) <- c("student", "course", "letterGrade")
return(long_df)
}
f18cohort = returnMergedColumns(f18cohort)
f18letter = prepareAlluvial(f18cohort)
f19cohort = returnMergedColumns(f19cohort)
f19letter = prepareAlluvial(f19cohort)
f20cohort = returnMergedColumns(f20cohort)
f20letter = prepareAlluvial(f20cohort)
f21cohort = returnMergedColumns(f21cohort)
f21letter = prepareAlluvial(f21cohort)
f22cohort = returnMergedColumns(f22cohort)
f22letter = prepareAlluvial(f22cohort)
#f18cohort %>% select(-1) %>% arrange(chem2) %>% write.csv("f18cohort.csv", row.names = FALSE)
#f19cohort %>% select(-1) %>% arrange(chem2) %>% write.csv("f19cohort.csv", row.names = FALSE)
#f20cohort %>% select(-1) %>% arrange(chem2) %>% write.csv("f20cohort.csv", row.names = FALSE)
#f21cohort %>% select(-1) %>% arrange(chem2) %>% write.csv("f21cohort.csv", row.names = FALSE)
#write.csv(f22cohort[order(f22cohort$chem2_s23),],"f22cohort.csv")
## REPRESENT
makeAlluvial_Cohort = function(df,thisTitle){
ggplot(df,
aes(x = course, stratum = letterGrade, alluvium = student, fill = letterGrade)) +
scale_x_discrete(expand = c(.1, .1)) +
geom_flow() +
geom_stratum(alpha = .5) +
theme_minimal() +
geom_text(stat = "stratum",
aes(label = percent(after_stat(prop), accuracy = .1)))+
labs(title = thisTitle, x = "", y = "Number of students")
}
makeAlluvial_Cohort2 = function(df,thisTitle){
ggplot(df,
aes(x = course, stratum = letterGrade, alluvium = student, fill = letterGrade)) +
scale_x_discrete(expand = c(.1, .1)) +
geom_flow() +
geom_stratum(alpha = .5) +
theme_minimal() +
geom_text(stat = "stratum",
aes(label = after_stat(count) ))+
labs(title = thisTitle, x = "", y = "Number of students")
}
create_summary_table <- function(df) {
summary_table <- df %>%
group_by(course, letterGrade, .drop = TRUE) %>%
summarize(count = n(), .groups = 'drop') %>%
ungroup() %>%
complete(course, letterGrade, fill = list(count = 0))
# Pivot the data to have courses as columns
summary_table <- summary_table %>%
pivot_wider(names_from = course, values_from = count)
df_sum <- summary_table %>%
bind_rows(
data.frame(
letterGrade = "Total",
chem1 = sum(.$chem1),
chem2 = sum(.$chem2),
chem3 = sum(.$chem3),
chem4 = sum(.$chem4)
)
)
# Calculate percentages and add "%" character
df_percent <- df_sum %>%
mutate(across(starts_with("chem"), ~ scales::percent(./sum(.)*2 , accuracy = 0.1), .names = "{col}%"))
return(df_percent)
}
allCohorts = rbind(f18letter,f19letter)
allCohorts = rbind(allCohorts,f20letter)
allCohorts = rbind(allCohorts,f21letter)
allCohorts = rbind(allCohorts,f22letter)
allCohorts = allCohorts[!duplicated(allCohorts, fromLast = TRUE),]
makeAlluvial_Cohort(allCohorts,"All cohorts")
summary_table <- create_summary_table(allCohorts)
kable(summary_table,caption = "All cohort numbers")
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 318 | 234 | 122 | 112 | 32.8% | 24.1% | 12.6% | 11.5% |
B | 417 | 284 | 158 | 166 | 43.0% | 29.3% | 16.3% | 17.1% |
C | 164 | 163 | 104 | 57 | 16.9% | 16.8% | 10.7% | 5.9% |
D | 45 | 27 | 30 | 14 | 4.6% | 2.8% | 3.1% | 1.4% |
F | 26 | 6 | 6 | 5 | 2.7% | 0.6% | 0.6% | 0.5% |
OUT | 0 | 256 | 550 | 616 | 0.0% | 26.4% | 56.7% | 63.5% |
Total | 970 | 970 | 970 | 970 | 100.0% | 100.0% | 100.0% | 100.0% |
calculate_percentage <- function(df) {
df %>%
mutate(not_out = ifelse(letterGrade != "OUT", 1, 0)) %>%
group_by(course) %>%
summarise(percentage = mean(not_out) * 100)
}
# Apply the function to each dataframe
f18_percentage <- calculate_percentage(f18letter)
f19_percentage <- calculate_percentage(f19letter)
f20_percentage <- calculate_percentage(f20letter)
f21_percentage <- calculate_percentage(f21letter)
f22_percentage <- calculate_percentage(f22letter)
allPercentage <- bind_rows(f18_percentage,
f19_percentage,
f20_percentage,
f21_percentage,
f22_percentage,
.id = "df_id"
)%>%
mutate(df_id = case_when(
df_id == "1" ~ "Fall18",
df_id == "2" ~ "Fall19",
df_id == "3" ~ "Fall20",
df_id == "4" ~ "Fall21",
df_id == "5" ~ "Fall22",
TRUE ~ df_id # Keep other values unchanged
))
ggplot(allPercentage, aes(x = course, y = percentage, group = df_id, color = df_id)) +
geom_line() +
geom_point() +
labs(x = "Course", y = "% students",
title = "Retention across the Chemistry Curriculum") +
scale_color_discrete(name = "Cohort first semester") +
theme_minimal()
spread_df <- spread(allPercentage, df_id, percentage)
library(knitr)
# Print the resulting table
kable(spread_df, format = "markdown",digits = 1, caption = "Percentage of the initial cohort taking the course ")
course | Fall18 | Fall19 | Fall20 | Fall21 | Fall22 |
---|---|---|---|---|---|
chem1 | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 |
chem2 | 71.3 | 73.6 | 72.6 | 74.4 | 73.1 |
chem3 | 43.1 | 50.0 | 41.7 | 38.5 | 41.8 |
chem4 | 36.5 | 44.0 | 32.7 | 31.8 | 36.1 |
Took: * CHEM1 in F18 * CHEM2 in S19 * CHEM3 in F19 or later * CHEM4 in S20 or later
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 90 | 38 | 18 | 16 | 49.7% | 21.0% | 9.9% | 8.8% |
B | 71 | 50 | 36 | 34 | 39.2% | 27.6% | 19.9% | 18.8% |
C | 13 | 34 | 19 | 14 | 7.2% | 18.8% | 10.5% | 7.7% |
D | 2 | 5 | 4 | 2 | 1.1% | 2.8% | 2.2% | 1.1% |
F | 5 | 2 | 1 | 0 | 2.8% | 1.1% | 0.6% | 0.0% |
OUT | 0 | 52 | 103 | 115 | 0.0% | 28.7% | 56.9% | 63.5% |
Total | 181 | 181 | 181 | 181 | 100.0% | 100.0% | 100.0% | 100.0% |
Took: * CHEM1 in F19 * CHEM2 in S20 * CHEM3 in F20 or later * CHEM4 in S21 or later
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 52 | 29 | 23 | 13 | 28.6% | 15.9% | 12.6% | 7.1% |
B | 95 | 59 | 31 | 46 | 52.2% | 32.4% | 17.0% | 25.3% |
C | 25 | 39 | 25 | 19 | 13.7% | 21.4% | 13.7% | 10.4% |
D | 7 | 6 | 10 | 2 | 3.8% | 3.3% | 5.5% | 1.1% |
F | 3 | 1 | 2 | 0 | 1.6% | 0.5% | 1.1% | 0.0% |
OUT | 0 | 48 | 91 | 102 | 0.0% | 26.4% | 50.0% | 56.0% |
Total | 182 | 182 | 182 | 182 | 100.0% | 100.0% | 100.0% | 100.0% |
Took: * CHEM1 in F20 * CHEM2 in S21 * CHEM3 in F21 or later * CHEM4 in S22 or later
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 48 | 59 | 30 | 27 | 21.5% | 26.5% | 13.5% | 12.1% |
B | 80 | 62 | 34 | 30 | 35.9% | 27.8% | 15.2% | 13.5% |
C | 65 | 35 | 23 | 12 | 29.1% | 15.7% | 10.3% | 5.4% |
D | 22 | 5 | 6 | 3 | 9.9% | 2.2% | 2.7% | 1.3% |
F | 8 | 1 | 0 | 1 | 3.6% | 0.4% | 0.0% | 0.4% |
OUT | 0 | 61 | 130 | 150 | 0.0% | 27.4% | 58.3% | 67.3% |
Total | 223 | 223 | 223 | 223 | 100.0% | 100.0% | 100.0% | 100.0% |
Took:
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 71 | 57 | 30 | 30 | 36.4% | 29.2% | 15.4% | 15.4% |
B | 76 | 52 | 22 | 24 | 39.0% | 26.7% | 11.3% | 12.3% |
C | 28 | 29 | 19 | 4 | 14.4% | 14.9% | 9.7% | 2.1% |
D | 14 | 5 | 2 | 2 | 7.2% | 2.6% | 1.0% | 1.0% |
F | 6 | 2 | 2 | 2 | 3.1% | 1.0% | 1.0% | 1.0% |
OUT | 0 | 50 | 120 | 133 | 0.0% | 25.6% | 61.5% | 68.2% |
Total | 195 | 195 | 195 | 195 | 100.0% | 100.0% | 100.0% | 100.0% |
Took:
At the moment of this analysis some students dropped or have not taken ochem2 or chem4, so they may take it in the next year and the results may change
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 60 | 52 | 22 | 26 | 28.8% | 25.0% | 10.6% | 12.5% |
B | 102 | 64 | 37 | 34 | 49.0% | 30.8% | 17.8% | 16.3% |
C | 37 | 29 | 19 | 8 | 17.8% | 13.9% | 9.1% | 3.8% |
D | 4 | 6 | 8 | 5 | 1.9% | 2.9% | 3.8% | 2.4% |
F | 5 | 1 | 1 | 2 | 2.4% | 0.5% | 0.5% | 1.0% |
OUT | 0 | 56 | 121 | 133 | 0.0% | 26.9% | 58.2% | 63.9% |
Total | 208 | 208 | 208 | 208 | 100.0% | 100.0% | 100.0% | 100.0% |
If a student gets less than 74%, what advise should we give them?
Cstud_s23 = chem2_s23[which(chem2_s23$Unposted.Final.Score < 74),]
Cstud_s23 = Cstud_s23
summary_table <- f18cohort %>%
filter(chem2 < 74) %>%
summarize(
students_below_74 = n(),
avg_chem3_score = mean(chem3, na.rm = TRUE),
avg_chem4_score = mean(chem4, na.rm = TRUE)
)
# Print summary table
print(summary_table)
## students_below_74 avg_chem3_score avg_chem4_score
## 1 18 75.0475 74.6
Now let’s just consider only the students who took the four semesters.
There are some students who transferred in GenChem2, so there are some premed-like students that continued to Biochemistry even if they look to be “OUT” of the curriculum.
TODO: Check Biochem lists.
## PREPARE FILES
select_and_add_name <- function(df, name) {
if (any(is.na(df$Final.Score))) {
print(paste("Data frame", name, "contains NA values in the 'grade' column"))
}
selected_df <- df %>%
#select(ID, Final.Score) %>%
select(SIS.Login.ID, Final.Score) %>%
mutate(Final.Score = as.numeric(Final.Score)) # Convert "grade" to numeric type
selected_df$name <- name
return(selected_df)
}
# Apply the function to each dataframe in the list
dfs_with_name <- Map(select_and_add_name, dfs, names(dfs))
# Merge all data frames into one
merged_df <- bind_rows(dfs_with_name)
names(merged_df)[names(merged_df)=="SIS.Login.ID"] = "student"
allCohort <- separate(merged_df, name, into = c("course", "semester"), sep = "_")
allCohort$letterGrade = ifelse(allCohort$Final.Score > 90, "A",
ifelse(allCohort$Final.Score >= 80, "B",
ifelse(allCohort$Final.Score >= 70, "C",
ifelse(allCohort$Final.Score >= 60, "D", "F"))))
# filter just in case they took it twice, just take the highest score
allCohort <- allCohort %>%
group_by(student, course) %>%
filter(Final.Score == max(Final.Score))
# What students took the whole sequence
fullFour <- allCohort %>%
group_by(student) %>%
filter(all(c("chem1", "chem2", "chem3", "chem4") %in% course))
# filter just in case they took it twice, just take the highest score
fullFour <- fullFour %>%
group_by(student, course) %>%
filter(Final.Score == max(Final.Score))
#Writing just in case
## REPRESENTING
selectSemester = function(df,thisSem){
selected_students <- df %>%
filter(course == "chem1" & semester == thisSem) %>%
pull(student) %>%
unique()
# Filter the dataframe to include all rows for selected students
thisSem_df <- df %>%
filter(student %in% selected_students)
return(thisSem_df)
}
plotAlluvialCohort = function(df,thisSem,thisTitle){
thisSem_df = selectSemester(df,thisSem)
ggplot(thisSem_df,
aes(x = course, stratum = letterGrade, alluvium = student, fill = letterGrade)) +
scale_x_discrete(expand = c(.1, .1)) +
geom_flow() +
geom_stratum(alpha = .5) +
theme_minimal() +
geom_text(stat = "stratum",
aes(label = percent(after_stat(prop), accuracy = .1)))+
labs(title = thisTitle, x = "", y = "Number of students")
}
makeAlluvial_Cohort(fullFour,"All cohorts. Students who took the four semesters")
summary_table <- create_summary_table(fullFour)
kable(summary_table,caption = "All cohort numbers. Students who took the four semesters")
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 167 | 148 | 106 | 108 | 49.1% | 43.5% | 31.2% | 31.8% |
B | 153 | 150 | 139 | 161 | 45.0% | 44.1% | 40.9% | 47.4% |
C | 18 | 39 | 79 | 55 | 5.3% | 11.5% | 23.2% | 16.2% |
D | 2 | 3 | 16 | 11 | 0.6% | 0.9% | 4.7% | 3.2% |
F | 0 | 0 | 0 | 5 | 0.0% | 0.0% | 0.0% | 1.5% |
Total | 340 | 340 | 340 | 340 | 100.0% | 100.0% | 100.0% | 100.0% |
summary_table <- create_summary_table(selectSemester(fullFour,"f18"))
kable(summary_table,caption = "All4 F18 cohort numbers")
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 46 | 23 | 16 | 15 | 71.9% | 35.9% | 25.0% | 23.4% |
B | 18 | 32 | 32 | 33 | 28.1% | 50.0% | 50.0% | 51.6% |
C | 0 | 8 | 14 | 14 | 0.0% | 12.5% | 21.9% | 21.9% |
D | 0 | 1 | 2 | 2 | 0.0% | 1.6% | 3.1% | 3.1% |
Total | 64 | 64 | 64 | 64 | 100.0% | 100.0% | 100.0% | 100.0% |
summary_table <- create_summary_table(selectSemester(fullFour,"f19"))
kable(summary_table,caption = "All4 F18 cohort numbers")
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 30 | 21 | 23 | 12 | 38.5% | 26.9% | 29.5% | 15.4% |
B | 45 | 40 | 29 | 46 | 57.7% | 51.3% | 37.2% | 59.0% |
C | 3 | 16 | 20 | 18 | 3.8% | 20.5% | 25.6% | 23.1% |
D | 0 | 1 | 6 | 2 | 0.0% | 1.3% | 7.7% | 2.6% |
Total | 78 | 78 | 78 | 78 | 100.0% | 100.0% | 100.0% | 100.0% |
summary_table <- create_summary_table(selectSemester(fullFour,"f20"))
kable(summary_table,caption = "All4 F20 cohort numbers")
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 27 | 40 | 24 | 27 | 37.5% | 55.6% | 33.3% | 37.5% |
B | 34 | 25 | 28 | 29 | 47.2% | 34.7% | 38.9% | 40.3% |
C | 10 | 7 | 17 | 12 | 13.9% | 9.7% | 23.6% | 16.7% |
D | 1 | 0 | 3 | 3 | 1.4% | 0.0% | 4.2% | 4.2% |
F | 0 | 0 | 0 | 1 | 0.0% | 0.0% | 0.0% | 1.4% |
Total | 72 | 72 | 72 | 72 | 100.0% | 100.0% | 100.0% | 100.0% |
summary_table <- create_summary_table(selectSemester(fullFour,"f21"))
kable(summary_table,caption = "All4 F21 cohort numbers")
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 32 | 28 | 23 | 28 | 58.2% | 50.9% | 41.8% | 50.9% |
B | 19 | 22 | 17 | 20 | 34.5% | 40.0% | 30.9% | 36.4% |
C | 3 | 5 | 13 | 4 | 5.5% | 9.1% | 23.6% | 7.3% |
D | 1 | 0 | 2 | 1 | 1.8% | 0.0% | 3.6% | 1.8% |
F | 0 | 0 | 0 | 2 | 0.0% | 0.0% | 0.0% | 3.6% |
Total | 55 | 55 | 55 | 55 | 100.0% | 100.0% | 100.0% | 100.0% |
summary_table <- create_summary_table(selectSemester(fullFour,"f22"))
kable(summary_table,caption = "All4 F22 cohort numbers")
letterGrade | chem1 | chem2 | chem3 | chem4 | chem1% | chem2% | chem3% | chem4% |
---|---|---|---|---|---|---|---|---|
A | 32 | 36 | 20 | 26 | 45.1% | 50.7% | 28.2% | 36.6% |
B | 37 | 31 | 33 | 33 | 52.1% | 43.7% | 46.5% | 46.5% |
C | 2 | 3 | 15 | 7 | 2.8% | 4.2% | 21.1% | 9.9% |
D | 0 | 1 | 3 | 3 | 0.0% | 1.4% | 4.2% | 4.2% |
F | 0 | 0 | 0 | 2 | 0.0% | 0.0% | 0.0% | 2.8% |
Total | 71 | 71 | 71 | 71 | 100.0% | 100.0% | 100.0% | 100.0% |
chem5_f21 = read.csv("~/Teaching/Grades_and_SRT/BIOC3321\ Grade\ Spreadsheet\ F21\ F22\ F23/Grades-BIOC_3321_(001)_Fall_2021.csv")
chem5_f22 = read.csv("~/Teaching/Grades_and_SRT/BIOC3321\ Grade\ Spreadsheet\ F21\ F22\ F23/Grades-BIOC_3321_(001)_Fall_2022.csv")
chem5_f23 = read.csv("~/Teaching/Grades_and_SRT/BIOC3321\ Grade\ Spreadsheet\ F21\ F22\ F23/Grades-BIOC_3321_(001)_Fall_2023.csv")
chem5_f21 = head(tail(chem5_f21, -1), -1)
chem5_f22 = head(tail(chem5_f22, -1), -1)
chem5_f23 = tail(chem5_f23, -1)
dfs_bio = list(
chem5_f21 = chem5_f21,
chem5_f22 = chem5_f22,
chem5_f23 = chem5_f23
)
dfs_bio = getFinalScore(dfs_bio)
#merged_df = merge(f19cohort,chem5_f21, by.x = "student", by.y = "SIS.Login.ID", all.x = TRUE)
#f19cohort$chem5 = merged_df$Final.Score
addBiochemStudents = function(df1,df2,df3,df4){
#df1 is the original cohort, df2,3, and 4 are the biochem
df1 <- df1 %>%
left_join(select(df2, SIS.Login.ID, Final.Score), by = c("student" = "SIS.Login.ID")) %>%
rename(chem5_f21 = Final.Score)
df1 <- df1 %>%
left_join(select(df3, SIS.Login.ID, Final.Score), by = c("student" = "SIS.Login.ID")) %>%
rename(chem5_f22 = Final.Score)
df1 <- df1 %>%
left_join(select(df4, SIS.Login.ID, Final.Score), by = c("student" = "SIS.Login.ID")) %>%
rename(chem5_f23 = Final.Score)
df1 <- df1 %>%
mutate(chem5 = coalesce(chem5_f21, chem5_f22, chem5_f23)) %>%
select(-chem5_f21, -chem5_f22, -chem5_f23) # Remove intermediate columns
return(df1)
}
addFinalExamBiochemStudents = function(df1,df2,df3,df4){
#df1 is the original cohort, df2,3, and 4 are the biochem
df1 <- df1 %>%
left_join(select(df2, SIS.Login.ID, Final.Exam.Final.Score), by = c("student" = "SIS.Login.ID")) %>%
rename(chem5_f21_final = Final.Exam.Final.Score)
df1 <- df1 %>%
left_join(select(df3, SIS.Login.ID, Final.Exam.Final.Score), by = c("student" = "SIS.Login.ID")) %>%
rename(chem5_f22_final = Final.Exam.Final.Score)
df1 <- df1 %>%
left_join(select(df4, SIS.Login.ID, Final.Exam.Final.Score), by = c("student" = "SIS.Login.ID")) %>%
rename(chem5_f23_final = Final.Exam.Final.Score)
df1 <- df1 %>%
mutate(chem5_final = coalesce(chem5_f21_final, chem5_f22_final, chem5_f23_final)) %>%
select(-chem5_f21_final, -chem5_f22_final, -chem5_f23_final) # Remove intermediate columns
return(df1)
}
f19cohort = addBiochemStudents(f19cohort,chem5_f21,chem5_f22,chem5_f23)
f20cohort = addBiochemStudents(f20cohort,chem5_f21,chem5_f22,chem5_f23)
f21cohort = addBiochemStudents(f21cohort,chem5_f21,chem5_f22,chem5_f23)
f19cohort = addFinalExamBiochemStudents(f19cohort,chem5_f21,chem5_f22,chem5_f23)
f20cohort = addFinalExamBiochemStudents(f20cohort,chem5_f21,chem5_f22,chem5_f23)
f21cohort = addFinalExamBiochemStudents(f21cohort,chem5_f21,chem5_f22,chem5_f23)