Test number two

solve.py

@@ -8,7 +8,7 @@ import sys
 #for line in sys.stdin
 #if re.search(r'UFO', line) print("P")
 for line in sys.stdin:
-    if re.search(r'(ufo|lol|camera|picture|contact|phenomen|photo|paralysis|haunted|alien|demon|ghost|levitation|paranormal|spirit|telekinesis|flying|fake|sky|dream)', line.lower()):
+    if re.search(r'(video|paranormal|happened|alien|camera|ghost|sleep|dream|moving|sky|contact|sightings|footage|photo|phenomena|phenomenon|spirit|shadow|board|window|creepy|wake|eye|film|circles|lol|extraterrestrial|floating|disclosure|civilization|record|glitch|driving|ufo|flash|sharing)', line.lower()):
         print("P")
     else: 
         print("S")

train/check.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+input="../mostUsedP.txt"
+while IFS= read -r line
+do
+    p=`xzcat in.tsv.xz | paste expected.tsv - |grep "P.* $line" | wc -l`
+    s=`xzcat in.tsv.xz | paste expected.tsv - |grep "S.* $line" | wc -l`
+    diff=$((p-s))
+    if [ $p -ge $s ]
+    then
+        echo "$line, $diff"
+    fi
+done < "$input"

train/moreInP.txt

@@ -0,0 +1,202 @@
+video, 1790
+UFO, 3604
+saw, 958
+light, 1910
+paranormal, 1871
+looks, 459
+happened, 569
+story, 324
+night, 1327
+alien, 1511
+house, 1054
+camera, 1611
+aliens, 794
+experience, 342
+lights, 1214
+looked, 193
+object, 508
+came, 1026
+UFOs, 1097
+room, 273
+seeing, 99
+ghost, 1301
+videos, 645
+nI, 0
+sleep, 503
+weird, 608
+flying, 584
+picture, 718
+dream, 1191
+stories, 385
+moving, 494
+space, 268
+felt, 10
+strange, 436
+objects, 531
+experiences, 519
+technology, 189
+watching, 8
+sky, 769
+fake, 698
+military, 235
+dont, 223
+door, 401
+contact, 333
+planet, 45
+sightings, 620
+phone, 114
+craft, 681
+footage, 612
+advanced, 176
+cool, 83
+dreams, 532
+ghosts, 319
+pictures, 455
+experienced, 300
+eyes, 97
+photo, 1113
+moved, 254
+phenomena, 273
+phenomenon, 220
+air, 298
+image, 174
+happening, 116
+spirit, 470
+travel, 305
+video, 1790
+dark, 384
+bed, 328
+reports, 95
+walking, 138
+beings, 233
+ET, 562
+shadow, 449
+nThe, 0
+Looks, 36
+board, 151
+scared, 322
+night, 1327
+bright, 348
+house, 1054
+spirits, 369
+photos, 511
+Very, 42
+sitting, 42
+lived, 51
+story, 324
+thats, 127
+video, 1790
+speed, 101
+window, 366
+plane, 258
+creepy, 444
+shape, 397
+cameras, 302
+wake, 180
+sighting, 1073
+passed, 24
+eye, 58
+woke, 267
+activity, 64
+dad, 89
+film, 479
+Sounds, 5
+feet, 43
+fake, 698
+standing, 33
+happened, 569
+UFO, 3604
+fly, 648
+ufo, 721
+voice, 95
+night, 1327
+circles, 122
+lol, 310
+seconds, 135
+extraterrestrial, 267
+experience, 342
+paralysis, 332
+aircraft, 247
+room, 273
+brother, 29
+haunted, 335
+youtube, 30
+story, 324
+Ghost, 238
+spot, 79
+paranormal, 1871
+house, 1054
+scary, 136
+distance, 176
+nIf, 0
+witness, 495
+freaked, 236
+witnesses, 224
+music, 34
+weather, 9
+images, 125
+cant, 78
+NASA, 60
+walked, 52
+sky, 769
+floating, 168
+noise, 251
+disclosure, 254
+miles, 78
+civilization, 125
+Ouija, 175
+record, 133
+visit, 217
+audio, 113
+appeared, 103
+incident, 91
+slowly, 24
+stars, 84
+glitch, 602
+corner, 141
+orbs, 254
+lens, 282
+visiting, 83
+town, 36
+camera, 1611
+location, 205
+hoax, 380
+visited, 97
+aliens, 794
+light, 1910
+ship, 144
+recording, 248
+abduction, 239
+experience, 342
+UFOs, 1097
+floor, 32
+driving, 19
+didnt, 119
+UFO, 3604
+project, 19
+communicate, 29
+radar, 77
+visible, 54
+ball, 480
+planes, 75
+street, 30
+flash, 377
+room, 273
+sharing, 271
+balloon, 539
+presence, 26
+entity, 140
+filmed, 193
+sleeping, 70
+witnessed, 138
+Aliens, 95
+reflection, 260
+lucid, 135
+digital, 138
+light, 1910
+entities, 172
+recorded, 74
+fake, 698
+memories, 51
+aliens, 794
+flight, 51