Deduping the 35,117 Applesoft BASIC files using an MD5 hash, we get down to 25,464 files. What are the most frequent tokens in those files? How many files does each token appear in? And on how many disks?
| $D0 | = | 2,197,259 | 22,607 | 3,831 |
| $BA | 1,314,907 | 24,153 | 4,420 | |
| $AD | IF | 622,207 | 19,653 | 3,566 |
| $C8 | + | 610,700 | 18,782 | 3,478 |
| $C4 | THEN | 607,814 | 19,466 | 3,548 |
| $B0 | GOSUB | 520,918 | 15,774 | 3,197 |
| $C9 | - | 383,512 | 18,891 | 3,555 |
| $AB | GOTO | 363,893 | 18,901 | 3,497 |
| $C1 | TO | 345,009 | 18,570 | 3,446 |
| $B9 | POKE | 276,589 | 17,264 | 3,623 |
| $A2 | VTAB | 276,473 | 16,241 | 3,475 |
| $96 | HTAB | 255,410 | 13,748 | 3,223 |
| $CF | > | 238,829 | 16,884 | 3,386 |
| $D1 | < | 222,194 | 16,695 | 3,353 |
| $81 | FOR | 217,858 | 18,307 | 3,428 |
| $82 | NEXT | 216,301 | 18,277 | 3,427 |
| $B2 | REM | 215,507 | 16,902 | 3,269 |
| $B1 | RETURN | 213,613 | 15,681 | 3,216 |
| $CA | * | 202,012 | 15,002 | 3,104 |
| $AF | & | 156,113 | 3,722 | 858 |
| $E7 | CHR$ | 153,112 | 19,220 | 3,976 |
| $E2 | PEEK | 114,999 | 14,087 | 3,266 |
| $CD | AND | 108,474 | 10,551 | 2,797 |
| $97 | HOME | 102,797 | 18,499 | 3,944 |
| $8C | CALL | 93,682 | 13,592 | 3,322 |
| $C5 | AT | 91,420 | 4,766 | 1,473 |
| $CE | OR | 84,752 | 11,823 | 2,974 |
| $CB | / | 82,732 | 11,732 | 2,839 |
| $93 | HPLOT | 79,392 | 6,200 | 1,742 |
| $83 | DATA | 78,533 | 7,738 | 2,400 |
| $84 | INPUT | 66,551 | 10,848 | 2,596 |
| $D3 | INT | 64,068 | 10,728 | 2,711 |
| $E3 | LEN | 56,610 | 9,478 | 2,635 |
| $9D | NORMAL | 53,647 | 9,928 | 2,709 |
| $92 | HCOLOR= | 50,342 | 6,593 | 1,817 |
| $9E | INVERSE | 42,604 | 8,321 | 2,406 |
| $BE | GET | 40,441 | 11,063 | 2,783 |
| $E5 | VAL | 37,492 | 7,497 | 2,375 |
| $B4 | ON | 36,918 | 7,665 | 2,344 |
| $C2 | FN | 36,639 | 2,298 | 896 |
| $EA | MID$ | 36,355 | 7,017 | 2,327 |
| $DB | RND | 32,469 | 6,148 | 1,875 |
| $E8 | LEFT$ | 31,767 | 7,165 | 2,292 |
| $C0 | TAB | 31,736 | 3,602 | 1,327 |
| $89 | TEXT | 31,231 | 13,080 | 3,315 |
| $94 | DRAW | 29,697 | 2,590 | 925 |
| $E4 | STR$ | 28,866 | 5,116 | 1,789 |
| $C6 | NOT | 23,846 | 3,911 | 1,364 |
| $E6 | ASC | 23,423 | 6,643 | 2,244 |
| $C3 | SPC( | 22,877 | 3,389 | 1,285 |
| $A0 | COLOR= | 22,533 | 1,629 | 788 |
| $8E | HLIN | 22,290 | 985 | 472 |
| $8D | PLOT | 22,084 | 1,357 | 618 |
| $C7 | STEP | 21,190 | 6,770 | 2,235 |
| $87 | READ | 20,495 | 7,743 | 2,418 |
| $80 | END | 18,312 | 11,834 | 2,987 |
| $8F | VLIN | 17,164 | 983 | 474 |
| $86 | DIM | 15,332 | 8,864 | 2,576 |
| $A5 | ONERR | 15,068 | 7,817 | 2,336 |
| $95 | XDRAW | 13,736 | 1,616 | 675 |
| $E9 | RIGHT$ | 12,026 | 3,721 | 1,535 |
| $D4 | ABS | 10,314 | 2,582 | 1,147 |
| $A9 | SPEED= | 10,001 | 3,137 | 1,195 |
| $9F | FLASH | 9,300 | 3,510 | 1,470 |
| $98 | ROT= | 8,567 | 3,026 | 1,144 |
| $91 | HGR | 7,975 | 4,565 | 1,608 |
| $CC | ; | 7,674 | 1,947 | 821 |
| $AA | LET | 7,424 | 852 | 382 |
| $A1 | POP | 6,703 | 2,608 | 1,103 |
| $99 | SCALE= | 6,440 | 2,996 | 1,125 |
| $A3 | HIMEM: | 4,887 | 4,136 | 1,448 |
| $B8 | DEF FN | 4,675 | 2,170 | 876 |
| $90 | HGR2 | 4,429 | 2,171 | 918 |
| $D6 | FRE | 3,830 | 2,256 | 1,137 |
| $D5 | USR | 3,787 | 647 | 300 |
| $AC | RUN | 3,617 | 2,250 | 989 |
| $DF | SIN | 3,597 | 1,148 | 527 |
| $B5 | WAIT | 3,445 | 1,675 | 678 |
| $AE | RESTORE | 3,371 | 2,431 | 1,173 |
| $8A | PR # | 3,304 | 1,710 | 856 |
| $BD | CLEAR | 3,024 | 2,110 | 914 |
| $DE | COS | 2,987 | 979 | 460 |
| $DA | SQR | 2,606 | 1,003 | 465 |
| $88 | GR | 2,605 | 1,374 | 631 |
| $A6 | RESUME | 2,482 | 1,958 | 747 |
| $D2 | SGN | 2,414 | 795 | 470 |
| $A4 | LOMEM: | 2,392 | 2,247 | 866 |
| $D8 | PDL | 2,128 | 687 | 377 |
| $D7 | SCRN ( | 2,072 | 370 | 262 |
| $B3 | STOP | 2,006 | 1,400 | 677 |
| $DC | LOG | 1,446 | 390 | 208 |
| $D9 | POS | 1,116 | 361 | 212 |
| $BF | NEW | 958 | 790 | 490 |
| $85 | DEL | 897 | 394 | 260 |
| $BC | LIST | 868 | 428 | 224 |
| $E1 | ATN | 823 | 434 | 210 |
| $B6 | LOAD | 746 | 187 | 93 |
| $A8 | STORE | 669 | 291 | 209 |
| $DD | EXP | 637 | 283 | 157 |
| $8B | IN # | 589 | 360 | 222 |
| $B7 | SAVE | 526 | 181 | 112 |
| $E0 | TAN | 337 | 181 | 118 |
| $A7 | RECALL | 296 | 121 | 92 |
| $9C | NOTRACE | 232 | 196 | 147 |
| $9B | TRACE | 165 | 67 | 42 |
| $9A | SHLOAD | 134 | 119 | 69 |
| $BB | CONT | 97 | 56 | 40 |
.png)

