code/All Tags.jpeg

This is a binary file and will not be displayed.

code/MC_Tag_df.rda

This is a binary file and will not be displayed.

code/MS_Tag_df.rda

This is a binary file and will not be displayed.

code/MultiSelect.jpeg

This is a binary file and will not be displayed.

+345 -38

code/Survey Question Conversion and Analysis.R

··· 7 7 install.packages("dplyr") 8 8 install.packages("SnowballC") 9 9 install.packages("tibble") 10 10 + install.packages("tidyr") 11 11 + install.packages("patchwork") 12 12 + library(patchwork) 10 13 library(ggplot2) 11 14 library(tidyverse) 12 15 library(tidytext) ··· 15 18 library(dplyr) 16 19 library(SnowballC) 17 20 library(tibble) 21 21 + library(tidyr) 18 22 py2r <- function(df, rows) { 19 23 for (row in rows) { 20 24 # In this case we use reticulate::py_eval to convert a python string ··· 197 201 ams_ms_tagged <- as.data.frame(AMS_multipleselect_tags) 198 202 199 203 AMS_Question_Tags <- data.frame( 200 200 - questions = AMS_questions_list, 201 201 - tags = tagged_AMS_df 204 204 + Questions = AMS_questions_list, 205 205 + Tags = tagged_AMS_df 202 206 ) 203 207 208 208 + colnames(AMS_Question_Tags) <- list("Questions", "Tags") 209 209 + 204 210 AMS_MC_Tags <- data.frame( 205 205 - questions = AMS_MC, 206 206 - tags = ams_mc_tagged 211 211 + Questions = AMS_MC, 212 212 + Tags = ams_mc_tagged 207 213 ) 214 214 + 215 215 + colnames(AMS_MC_Tags) <- list("Questions", "Tags") 208 216 209 217 AMS_MS_Tags <- data.frame( 210 210 - questions = AMS_MS, 211 211 - tags = ams_ms_tagged 218 218 + Questions = AMS_MS, 219 219 + Tags = ams_ms_tagged 212 220 ) 213 221 222 222 + colnames(AMS_MS_Tags) <- list("Questions", "Tags") 223 223 + 214 224 AMS_TI_Tags <- data.frame( 215 215 - questions = AMS_TI, 216 216 - tags = ams_ti_tagged 225 225 + Questions = AMS_TI, 226 226 + Tags = ams_ti_tagged 217 227 ) 218 228 229 229 + colnames(AMS_TI_Tags) <- list("Questions", "Tags") 230 230 + 219 231 AMS_WR_Tags <- data.frame ( 220 220 - questions = AMS_WR, 221 221 - tags = ams_wr_tagged 232 232 + Questions = AMS_WR, 233 233 + Tags = ams_wr_tagged 222 234 ) 223 235 236 236 + colnames(AMS_WR_Tags) <- list("Questions", "Tags") 224 237 225 238 CBMS_all_questions_char <- as.character(CBMS_all_questions) 226 239 ··· 287 300 tags = tagged_CBMS_df 288 301 ) 289 302 303 303 + colnames(CBMS_Question_Tags) <- list("Questions", "Tags") 304 304 + 290 305 CBMS_MC_Tags <- data.frame( 291 291 - questions = CBMSMC_full, 292 292 - tags = CBMS_mc_tagged 306 306 + Questions = CBMSMC_full, 307 307 + Tags = CBMS_mc_tagged 293 308 ) 294 309 all_multiselect_CBMS <- as.data.frame(CBMS_all_multipleselect) 295 310 296 311 class(CBMS_all_multipleselect) 297 312 298 313 CBMS_MS_Tags <- data.frame( 299 299 - questions = CBMS_all_multipleselect, 300 300 - tags = tagged_cbms_ms$CBMS_ms_tagged 314 314 + Questions = CBMS_all_multipleselect, 315 315 + Tags = tagged_cbms_ms$CBMS_ms_tagged 301 316 ) 302 317 303 318 rownames(CBMS_MS_Tags) <- NULL 304 319 305 320 CBMS_TI_Tags <- data.frame( 306 306 - questions = CBMS_all_tableinput, 307 307 - tags = tagged_cbms_ti$CBMS_ti_tagged 321 321 + Questions = CBMS_all_tableinput, 322 322 + Tags = tagged_cbms_ti$CBMS_ti_tagged 308 323 ) 309 324 310 325 rownames(CBMS_TI_Tags) <- NULL 311 326 312 327 CBMS_WR_Tags <- data.frame( 313 313 - questions = CBMS_all_writtenresponse, 314 314 - tags = tagged_cbms_wr$CBMS_wr_tagged 328 328 + Questions = CBMS_all_writtenresponse, 329 329 + Tags = tagged_cbms_wr$CBMS_wr_tagged 315 330 ) 316 331 317 317 - rownames(CBMS_TI_Tags) <- NULL 332 332 + rownames(CBMS_WR_Tags) <- NULL 318 333 319 334 tagged_IPEDS <- sapply(IPEDS_all_questions, function(text) { 320 335 matches <- str_extract_all(text, paste(keywords, collapse = "|"))[[1]] ··· 328 343 tagged_IPEDS_df <- as.data.frame(tagged_IPEDS) 329 344 330 345 346 346 + 331 347 #there were no tagged questions in the IPEDS survey, so I assigned each question type a value of zero. 332 332 - IPEDS_multiplechoice_tagged = 0 333 333 - IPEDS_multipleslect_tagged = 0 334 334 - IPEDS_tableinput_tagged = 0 335 335 - IPEDS_writtenresponse_tagged = 0 348 348 + IPEDS_multiplechoice_tagged <- sapply(IPEDS_MC, function(text) { 349 349 + matches <- str_extract_all(text, paste(keywords, collapse = "|"))[[1]] 350 350 + if (length(matches) > 0) { 351 351 + paste("Tags:", paste(unique(matches), collapse = ", ")) 352 352 + } else { 353 353 + NA 354 354 + } 355 355 + }) 336 356 337 337 - tagged_AMS_count <- tagged_AMS_df[complete.cases(tagged_AMS_df),] |> length() 338 338 - tagged_ams_mc_count <- ams_mc_tagged[complete.cases(ams_mc_tagged),] |> length() 339 339 - tagged_ams_ms_count <- ams_ms_tagged[complete.cases(ams_ms_tagged),] |> length() 340 340 - tagged_ams_ti_count <- ams_ti_tagged[complete.cases(ams_ti_tagged),] |> length() 341 341 - tagged_ams_wr_count <- ams_wr_tagged[complete.cases(ams_wr_tagged),] |> length() 357 357 + tagged_IPEDS_MC <- as.data.frame(IPEDS_multiplechoice_tagged) 358 358 + 359 359 + IPEDS_multipleslect_tagged <- sapply(IPEDS_MS, function(text) { 360 360 + matches <- str_extract_all(text, paste(keywords, collapse = "|"))[[1]] 361 361 + if (length(matches) > 0) { 362 362 + paste("Tags:", paste(unique(matches), collapse = ", ")) 363 363 + } else { 364 364 + NA 365 365 + } 366 366 + }) 367 367 + 368 368 + tagged_IPEDS_MS <- as.data.frame(IPEDS_multipleslect_tagged) 369 369 + rownames(tagged_IPEDS_MS) <- NULL 370 370 + 371 371 + 372 372 + IPEDS_tableinput_tagged <- sapply(IPEDS_TI, function(text) { 373 373 + matches <- str_extract_all(text, paste(keywords, collapse = "|"))[[1]] 374 374 + if (length(matches) > 0) { 375 375 + paste("Tags:", paste(unique(matches), collapse = ", ")) 376 376 + } else { 377 377 + NA 378 378 + } 379 379 + }) 380 380 + 381 381 + tagged_IPEDS_TI <- as.data.frame(IPEDS_tableinput_tagged) 382 382 + 383 383 + IPEDS_writtenresponse_tagged <- sapply(IPEDS_WR, function(text) { 384 384 + matches <- str_extract_all(text, paste(keywords, collapse = "|"))[[1]] 385 385 + if (length(matches) > 0) { 386 386 + paste("Tags:", paste(unique(matches), collapse = ", ")) 387 387 + } else { 388 388 + NA 389 389 + } 390 390 + }) 391 391 + 392 392 + tagged_IPEDS_WR <- as.data.frame(IPEDS_writtenresponse_tagged) 393 393 + 394 394 + IPEDS_Question_Tags <- data.frame( 395 395 + Questions = IPEDS_all_questions, 396 396 + Tags = tagged_IPEDS_df$tagged_IPEDS 397 397 + ) 398 398 + 399 399 + rownames(IPEDS_Question_Tags) <- NULL 400 400 + 401 401 + IPEDS_MC_Tags <- data.frame( 402 402 + Questions = IPEDS_MC, 403 403 + Tags = tagged_IPEDS_MC$IPEDS_multiplechoice_tagged 404 404 + ) 405 405 + 406 406 + rownames(IPEDS_MC_Tags) <- NULL 407 407 + 408 408 + IPEDS_MS_Tags <- data.frame( 409 409 + Questions = IPEDS_MS, 410 410 + Tags = tagged_IPEDS_MS$IPEDS_multipleslect_tagged 411 411 + ) 412 412 + 413 413 + rownames(IPEDS_MS_Tags) <- NULL 414 414 + 415 415 + IPEDS_TI_Tags <- data.frame( 416 416 + Questions = IPEDS_TI, 417 417 + Tags = tagged_IPEDS_TI$IPEDS_tableinput_tagged 418 418 + ) 419 419 + 420 420 + rownames(IPEDS_TI_Tags) <- NULL 421 421 + 422 422 + IPEDS_WR_Tags <- data.frame( 423 423 + Questions = IPEDS_WR, 424 424 + Tags = tagged_IPEDS_WR$IPEDS_writtenresponse_tagged 425 425 + ) 426 426 + 427 427 + rownames(IPEDS_WR_Tags) <- NULL 428 428 + 429 429 + AMS_Question_Tags$Source <- "AMS" 430 430 + CBMS_Question_Tags$Source <- "CBMS" 431 431 + IPEDS_Question_Tags$Source <- "IPEDS" 432 432 + 433 433 + big_question_tag_df <- rbind(AMS_Question_Tags, CBMS_Question_Tags, IPEDS_Question_Tags) 434 434 + 435 435 + #Counting number of each question in big_question_tag_df 436 436 + #Counting AMS 437 437 + AMS_Sources_Counts<- big_question_tag_df|> 438 438 + filter(Source == "AMS", !is.na(Tags))|> 439 439 + nrow() 440 440 + AMS_Sources_Counts 441 441 + 442 442 + #Counting CMS 443 443 + CBMS_Sources_Counts<- big_question_tag_df|> 444 444 + filter(Source == "CBMS", !is.na(Tags)) |> 445 445 + nrow() 446 446 + CBMS_Sources_Counts 447 447 + 448 448 + #Counting IPEDS 449 449 + IPEDS_Sources_Counts<-big_question_tag_df|> 450 450 + filter (Source == "IPEDS", !is.na(Tags)) |> 451 451 + nrow() 452 452 + IPEDS_Sources_Counts 453 453 + 454 454 + Counts_of_Tagged_Sources <- data.frame( 455 455 + AMS = AMS_Sources_Counts, 456 456 + IPEDS = IPEDS_Sources_Counts, 457 457 + CBMS = CBMS_Sources_Counts) 458 458 + 459 459 + Counts_of_Tagged_Sources_long <- pivot_longer( 460 460 + as_tibble(Counts_of_Tagged_Sources), 461 461 + cols = everything(), 462 462 + names_to = "Source", 463 463 + values_to = "Number Tagged" 464 464 + ) 465 465 + 466 466 + All_Tagged_Graph <- ggplot(Counts_of_Tagged_Sources_long, aes(x = Source, y = `Number Tagged`, fill = Source)) + 467 467 + geom_col() + 468 468 + scale_y_continuous(breaks = seq(0, max(Counts_of_Tagged_Sources_long$`Number Tagged`), by = 1)) + 469 469 + labs(y = NULL, 470 470 + x = NULL, 471 471 + title = "ALL") 472 472 + 473 473 + All_Tagged_Graph 474 474 + 475 475 + AMS_MC_Tags$Source = "AMS" 476 476 + CBMS_MC_Tags$Source = "CBMS" 477 477 + IPEDS_MC_Tags$Source = "IPEDS" 342 478 343 343 - tagged_CBMS_count <- tagged_CBMS_df[complete.cases(tagged_CBMS_df),] |> length() 344 344 - tagged_cbms_mc_count <- tagged_cbms_mc[complete.cases(tagged_cbms_mc),] |> length() 345 345 - tagged_cbms_ms_count <- tagged_cbms_ms[complete.cases(tagged_cbms_ms),] |> length() 346 346 - tagged_cbms_wr_count <-tagged_cbms_wr[complete.cases(tagged_cbms_wr),] |> length() 347 347 - tagged_cbms_ti <- tagged_cbms_ti[complete.cases(tagged_cbms_ti),] |> length() 479 479 + MC_Tag_df <- rbind(AMS_MC_Tags, CBMS_MC_Tags, IPEDS_MC_Tags) 348 480 349 481 350 350 - tagged_IPEDS_count <- tagged_IPEDS_df[complete.cases(tagged_IPEDS_df),] |> length() 482 482 + AMS_MC_Sources_Counts<- MC_Tag_df|> 483 483 + filter(Source == "AMS", !is.na(Tags))|> 484 484 + nrow() 485 485 + AMS_MC_Sources_Counts 351 486 352 352 - ggplot 487 487 + #Counting CMS 488 488 + CBMS_MC_Sources_Counts<- MC_Tag_df|> 489 489 + filter(Source == "CBMS", !is.na(Tags)) |> 490 490 + nrow() 491 491 + CBMS_MC_Sources_Counts 353 492 493 493 + #Counting IPEDS 494 494 + IPEDS_MC_Sources_Counts<- MC_Tag_df|> 495 495 + filter (Source == "IPEDS", !is.na(Tags)) |> 496 496 + nrow() 497 497 + IPEDS_MC_Sources_Counts 354 498 499 499 + Counts_of_Tagged_Sources_MC <- data.frame( 500 500 + AMS = AMS_MC_Sources_Counts, 501 501 + IPEDS = IPEDS_MC_Sources_Counts, 502 502 + CBMS = CBMS_MC_Sources_Counts) 355 503 504 504 + Counts_of_Tagged_Sources_MC_long <- pivot_longer( 505 505 + as_tibble(Counts_of_Tagged_Sources_MC), 506 506 + cols = everything(), 507 507 + names_to = "Source", 508 508 + values_to = "Number Tagged" 509 509 + ) 356 510 511 511 + MC_Tagged_Graph <- ggplot(Counts_of_Tagged_Sources_MC_long, aes(x = Source, y = `Number Tagged`, fill = Source)) + 512 512 + geom_col() + 513 513 + scale_y_continuous(breaks = seq(0, max(Counts_of_Tagged_Sources_long$`Number Tagged`), by = 1)) + 514 514 + labs(y = NULL, 515 515 + x = NULL, 516 516 + title = "Multiple Choice") 357 517 358 358 - 359 359 - 518 518 + MC_Tagged_Graph 519 519 + 520 520 + 521 521 + AMS_MS_Tags$Source = "AMS" 522 522 + CBMS_MS_Tags$Source = "CBMS" 523 523 + IPEDS_MS_Tags$Source = "IPEDS" 524 524 + 525 525 + MS_Tag_df <- rbind(AMS_MS_Tags, CBMS_MS_Tags, IPEDS_MS_Tags) 526 526 + 527 527 + 528 528 + AMS_MS_Sources_Counts<- MS_Tag_df|> 529 529 + filter(Source == "AMS", !is.na(Tags))|> 530 530 + nrow() 531 531 + AMS_MS_Sources_Counts 532 532 + 533 533 + #Counting CMS 534 534 + CBMS_MS_Sources_Counts<- MS_Tag_df|> 535 535 + filter(Source == "CBMS", !is.na(Tags)) |> 536 536 + nrow() 537 537 + CBMS_MS_Sources_Counts 538 538 + 539 539 + #Counting IPEDS 540 540 + IPEDS_MS_Sources_Counts<- MS_Tag_df|> 541 541 + filter (Source == "IPEDS", !is.na(Tags)) |> 542 542 + nrow() 543 543 + IPEDS_MS_Sources_Counts 544 544 + 545 545 + Counts_of_Tagged_Sources_MS <- data.frame( 546 546 + AMS = AMS_MS_Sources_Counts, 547 547 + IPEDS = IPEDS_MS_Sources_Counts, 548 548 + CBMS = CBMS_MS_Sources_Counts) 549 549 + 550 550 + Counts_of_Tagged_Sources_MS_long <- pivot_longer( 551 551 + as_tibble(Counts_of_Tagged_Sources_MS), 552 552 + cols = everything(), 553 553 + names_to = "Source", 554 554 + values_to = "Number Tagged" 555 555 + ) 556 556 + 557 557 + MS_Tagged_Graph <- ggplot(Counts_of_Tagged_Sources_MS_long, aes(x = Source, y = `Number Tagged`, fill = Source)) + 558 558 + geom_col() + 559 559 + scale_y_continuous(breaks = seq(0, max(Counts_of_Tagged_Sources_long$`Number Tagged`), by = 1)) + 560 560 + labs(y = NULL, 561 561 + x = NULL, 562 562 + title = "Multiple Select") 563 563 + 564 564 + MS_Tagged_Graph 565 565 + 566 566 + 567 567 + AMS_TI_Tags$Source = "AMS" 568 568 + CBMS_TI_Tags$Source = "CBMS" 569 569 + IPEDS_TI_Tags$Source = "IPEDS" 570 570 + 571 571 + TI_Tag_df <- rbind(AMS_TI_Tags, CBMS_TI_Tags, IPEDS_TI_Tags) 572 572 + 573 573 + 574 574 + AMS_TI_Sources_Counts<- TI_Tag_df|> 575 575 + filter(Source == "AMS", !is.na(Tags))|> 576 576 + nrow() 577 577 + AMS_TI_Sources_Counts 578 578 + 579 579 + #Counting CMS 580 580 + CBMS_TI_Sources_Counts<- TI_Tag_df|> 581 581 + filter(Source == "CBMS", !is.na(Tags)) |> 582 582 + nrow() 583 583 + CBMS_TI_Sources_Counts 584 584 + 585 585 + #Counting IPEDS 586 586 + IPEDS_TI_Sources_Counts<- TI_Tag_df|> 587 587 + filter (Source == "IPEDS", !is.na(Tags)) |> 588 588 + nrow() 589 589 + IPEDS_TI_Sources_Counts 590 590 + 591 591 + Counts_of_Tagged_Sources_TI <- data.frame( 592 592 + AMS = AMS_TI_Sources_Counts, 593 593 + IPEDS = IPEDS_TI_Sources_Counts, 594 594 + CBMS = CBMS_TI_Sources_Counts) 595 595 + 596 596 + Counts_of_Tagged_Sources_TI_long <- pivot_longer( 597 597 + as_tibble(Counts_of_Tagged_Sources_TI), 598 598 + cols = everything(), 599 599 + names_to = "Source", 600 600 + values_to = "Number Tagged" 601 601 + ) 602 602 + 603 603 + TI_Tagged_Graph <- ggplot(Counts_of_Tagged_Sources_TI_long, aes(x = Source, y = `Number Tagged`, fill = Source)) + 604 604 + geom_col() + 605 605 + scale_y_continuous(breaks = seq(0, max(Counts_of_Tagged_Sources_long$`Number Tagged`), by = 1)) + 606 606 + labs(y = NULL, 607 607 + x = NULL, 608 608 + title = "Table Input") 609 609 + 610 610 + TI_Tagged_Graph 611 611 + 612 612 + AMS_WR_Tags$Source = "AMS" 613 613 + CBMS_WR_Tags$Source = "CBMS" 614 614 + IPEDS_WR_Tags$Source = "IPEDS" 615 615 + 616 616 + WR_Tag_df <- rbind(AMS_WR_Tags, CBMS_WR_Tags, IPEDS_WR_Tags) 617 617 + 618 618 + 619 619 + AMS_WR_Sources_Counts<- WR_Tag_df|> 620 620 + filter(Source == "AMS", !is.na(Tags))|> 621 621 + nrow() 622 622 + AMS_WR_Sources_Counts 623 623 + 624 624 + #Counting CMS 625 625 + CBMS_WR_Sources_Counts<- WR_Tag_df|> 626 626 + filter(Source == "CBMS", !is.na(Tags)) |> 627 627 + nrow() 628 628 + CBMS_WR_Sources_Counts 629 629 + 630 630 + #Counting IPEDS 631 631 + IPEDS_WR_Sources_Counts<- WR_Tag_df|> 632 632 + filter (Source == "IPEDS", !is.na(Tags)) |> 633 633 + nrow() 634 634 + IPEDS_WR_Sources_Counts 635 635 + 636 636 + Counts_of_Tagged_Sources_WR <- data.frame( 637 637 + AMS = AMS_WR_Sources_Counts, 638 638 + IPEDS = IPEDS_WR_Sources_Counts, 639 639 + CBMS = CBMS_WR_Sources_Counts) 640 640 + 641 641 + Counts_of_Tagged_Sources_WR_long <- pivot_longer( 642 642 + as_tibble(Counts_of_Tagged_Sources_WR), 643 643 + cols = everything(), 644 644 + names_to = "Source", 645 645 + values_to = "Number Tagged" 646 646 + ) 647 647 + 648 648 + WR_Tagged_Graph <- ggplot(Counts_of_Tagged_Sources_WR_long, aes(x = Source, y = `Number Tagged`, fill = Source)) + 649 649 + geom_col() + 650 650 + scale_y_continuous(breaks = seq(0, max(Counts_of_Tagged_Sources_long$`Number Tagged`), by = 1)) + 651 651 + labs(y = NULL, 652 652 + x = NULL, 653 653 + title = "Written Response") 654 654 + WR_Tagged_Graph 655 655 + 656 656 + Big_Graph <- All_Tagged_Graph + 657 657 + MC_Tagged_Graph + 658 658 + MS_Tagged_Graph + 659 659 + TI_Tagged_Graph + 660 660 + WR_Tagged_Graph + 661 661 + plot_layout(nrow = 1) 360 662 361 361 - 663 663 + Big_Graph 362 664 665 665 + save(big_question_tag_df, file = "big_question_tag_df.rda") 666 666 + save(MC_Tag_df, file = "MC_Tag_df.rda") 667 667 + save(MS_Tag_df, file = "MS_Tag_df.rda") 668 668 + save(TI_Tag_df, file = "TI_Tag_df.rda") 669 669 + save(WR_Tag_df, file = "WR_Tag_df.rda") 363 670 364 671 365 672

code/TI_Tag_df.rda

This is a binary file and will not be displayed.

code/WR_Tag_df.rda

This is a binary file and will not be displayed.

code/big_question_tag_df.rda

This is a binary file and will not be displayed.

code/interactive_wordcloud.R

This is a binary file and will not be displayed.