a
This commit is contained in:
lda committed
commit
95b5e546dc
19 files changed
+7516
No files matched your search
@@ -0,0 +1,3 @@
|
||||
*.pdf filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.png filter=lfs diff=lfs merge=lfs -text
|
||||
+10
@@ -0,0 +1,10 @@
|
||||
# Python-generated files
|
||||
__pycache__/
|
||||
*.py[oc]
|
||||
build/
|
||||
dist/
|
||||
wheels/
|
||||
*.egg-info
|
||||
|
||||
# Virtual environments
|
||||
.venv
|
||||
@@ -0,0 +1 @@
|
||||
3.14
|
||||
BIN
Binary file not shown.
Binary file not shown.
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,301 @@
|
||||
timestamp,floor_requested,wait_time_seconds,direction,people_count,peak_hour,load_percent
|
||||
2025-01-01 11:31,5,16.53,Down,5,No,53
|
||||
2025-01-01 10:22,12,18.98,Down,3,Yes,20
|
||||
2025-01-01 16:25,4,19.35,Down,1,No,10
|
||||
2025-01-01 10:37,8,3.22,Up,4,Yes,31
|
||||
2025-01-01 07:31,6,17.32,Up,4,No,50
|
||||
2025-01-01 11:48,1,13.05,Down,5,No,57
|
||||
2025-01-01 12:09,11,11.8,Up,1,No,14
|
||||
2025-01-01 07:53,10,12.45,Up,4,No,49
|
||||
2025-01-01 08:12,11,8.59,Up,4,Yes,46
|
||||
2025-01-01 12:01,8,15.04,Up,1,No,10
|
||||
2025-01-01 19:04,3,13.8,Down,5,Yes,43
|
||||
2025-01-01 08:01,10,11.18,Up,1,Yes,10
|
||||
2025-01-01 16:42,11,12.11,Down,2,No,23
|
||||
2025-01-01 15:27,7,14.63,Down,1,No,10
|
||||
2025-01-01 13:07,8,6.29,Up,9,No,78
|
||||
2025-01-01 19:33,12,24.38,Up,5,Yes,47
|
||||
2025-01-01 18:25,6,16.62,Down,4,Yes,26
|
||||
2025-01-01 18:30,3,11.24,Up,4,Yes,33
|
||||
2025-01-01 19:38,11,15.35,Up,4,Yes,25
|
||||
2025-01-01 15:30,3,7.04,Down,4,No,23
|
||||
2025-01-01 18:56,12,12.59,Up,4,Yes,29
|
||||
2025-01-01 18:12,8,2.77,Up,3,Yes,43
|
||||
2025-01-01 15:58,2,5.13,Up,1,No,10
|
||||
2025-01-01 06:30,10,14.78,Down,1,No,13
|
||||
2025-01-01 06:26,5,8.24,Down,1,No,10
|
||||
2025-01-01 19:40,11,14.62,Up,2,Yes,25
|
||||
2025-01-01 10:39,8,15.97,Up,4,Yes,54
|
||||
2025-01-01 10:41,10,18.57,Up,5,Yes,53
|
||||
2025-01-01 10:08,8,8.34,Down,4,Yes,21
|
||||
2025-01-01 18:51,12,10.28,Down,4,Yes,47
|
||||
2025-01-01 14:17,2,13.44,Up,4,No,44
|
||||
2025-01-01 13:21,10,11.07,Up,4,No,41
|
||||
2025-01-01 07:00,12,8.78,Down,8,No,57
|
||||
2025-01-01 17:27,9,15.93,Up,4,No,30
|
||||
2025-01-01 09:34,5,15.34,Up,2,Yes,46
|
||||
2025-01-01 06:15,10,14.71,Down,8,No,70
|
||||
2025-01-01 10:34,12,4.57,Down,1,Yes,11
|
||||
2025-01-01 13:47,6,7.79,Up,3,No,43
|
||||
2025-01-01 11:49,10,18.68,Down,3,No,31
|
||||
2025-01-01 07:47,1,15.75,Down,5,No,57
|
||||
2025-01-01 12:05,11,10.82,Down,3,No,11
|
||||
2025-01-01 14:16,8,22.84,Up,6,No,58
|
||||
2025-01-01 10:49,5,19.11,Up,6,Yes,63
|
||||
2025-01-01 14:37,8,0.96,Up,1,No,10
|
||||
2025-01-01 07:17,1,15.33,Down,5,No,54
|
||||
2025-01-01 07:54,7,11.21,Down,1,No,10
|
||||
2025-01-01 12:00,12,13.15,Up,4,No,40
|
||||
2025-01-01 12:07,4,13.66,Down,3,No,36
|
||||
2025-01-01 17:01,8,5.28,Down,2,No,12
|
||||
2025-01-01 12:04,2,6.8,Up,1,No,33
|
||||
2025-01-01 12:49,4,8.88,Down,5,No,50
|
||||
2025-01-01 11:29,5,13.7,Up,1,No,10
|
||||
2025-01-01 16:39,5,8.64,Down,3,No,21
|
||||
2025-01-01 06:23,5,15.39,Up,5,No,52
|
||||
2025-01-01 15:02,7,13.46,Up,4,No,44
|
||||
2025-01-01 11:16,7,6.64,Up,1,No,10
|
||||
2025-01-01 09:37,7,16.7,Down,8,Yes,73
|
||||
2025-01-01 11:51,2,7.56,Down,1,No,10
|
||||
2025-01-01 16:43,3,11.66,Down,4,No,42
|
||||
2025-01-01 09:43,4,16.48,Down,2,Yes,16
|
||||
2025-01-01 11:39,2,9.92,Down,4,No,42
|
||||
2025-01-01 19:26,1,8.06,Up,1,Yes,12
|
||||
2025-01-01 19:09,1,2.98,Down,4,Yes,52
|
||||
2025-01-01 16:25,2,12.39,Up,3,No,32
|
||||
2025-01-01 06:37,10,18.04,Up,3,No,36
|
||||
2025-01-01 11:58,5,12.72,Down,5,No,35
|
||||
2025-01-01 06:03,4,13.11,Down,3,No,35
|
||||
2025-01-01 08:37,10,9.06,Up,2,Yes,13
|
||||
2025-01-01 07:50,8,12.68,Down,4,No,37
|
||||
2025-01-01 08:42,5,21.53,Up,5,Yes,61
|
||||
2025-01-01 07:40,2,9.09,Down,6,No,66
|
||||
2025-01-01 12:08,11,16.1,Up,3,No,29
|
||||
2025-01-01 14:46,2,12.7,Down,6,No,53
|
||||
2025-01-01 13:01,9,20.52,Down,4,No,59
|
||||
2025-01-01 14:55,7,16.5,Up,5,No,54
|
||||
2025-01-01 16:48,8,13.07,Down,5,No,71
|
||||
2025-01-01 07:01,11,11.81,Down,4,No,43
|
||||
2025-01-01 14:22,8,7.37,Up,4,No,49
|
||||
2025-01-01 10:38,9,5.18,Up,6,Yes,65
|
||||
2025-01-01 10:35,7,14.62,Down,3,Yes,20
|
||||
2025-01-01 16:04,4,21.42,Down,7,No,61
|
||||
2025-01-01 16:37,12,14.32,Up,4,No,47
|
||||
2025-01-01 08:27,11,10.27,Down,4,Yes,29
|
||||
2025-01-01 11:23,8,11.09,Up,1,No,10
|
||||
2025-01-01 16:53,12,13.53,Up,5,No,45
|
||||
2025-01-01 19:10,12,13.64,Up,3,Yes,21
|
||||
2025-01-01 13:51,3,10.06,Down,4,No,36
|
||||
2025-01-01 17:53,10,16.84,Up,3,No,33
|
||||
2025-01-01 16:55,10,4.93,Down,2,No,46
|
||||
2025-01-01 12:57,4,11.9,Down,5,No,37
|
||||
2025-01-01 09:18,8,18.19,Up,5,Yes,57
|
||||
2025-01-01 11:25,12,12.19,Down,1,No,10
|
||||
2025-01-01 08:26,10,13.01,Up,1,Yes,25
|
||||
2025-01-01 12:43,6,11.42,Down,6,No,47
|
||||
2025-01-01 06:17,3,12.52,Up,6,No,57
|
||||
2025-01-01 15:17,11,15.09,Up,1,No,10
|
||||
2025-01-01 18:50,11,14.29,Up,5,Yes,41
|
||||
2025-01-01 06:52,3,13.27,Down,2,No,10
|
||||
2025-01-01 14:33,7,5.58,Down,1,No,14
|
||||
2025-01-01 17:36,9,13.65,Down,6,No,52
|
||||
2025-01-01 06:56,5,15.4,Down,2,No,34
|
||||
2025-01-01 11:42,7,6.06,Down,4,No,26
|
||||
2025-01-01 15:32,4,18.08,Down,2,No,13
|
||||
2025-01-01 06:57,6,11.86,Down,6,No,49
|
||||
2025-01-01 10:41,9,14.29,Down,3,Yes,32
|
||||
2025-01-01 18:36,7,14.66,Up,6,Yes,63
|
||||
2025-01-01 19:56,3,10.71,Up,9,Yes,100
|
||||
2025-01-01 06:52,3,9.19,Up,5,No,37
|
||||
2025-01-01 18:02,7,19.33,Up,1,Yes,22
|
||||
2025-01-01 08:04,6,4.47,Down,1,Yes,10
|
||||
2025-01-01 10:50,12,18.99,Up,4,Yes,42
|
||||
2025-01-01 18:16,1,16.43,Down,4,Yes,33
|
||||
2025-01-01 19:04,2,6.14,Up,3,Yes,33
|
||||
2025-01-01 09:51,2,12.4,Up,5,Yes,42
|
||||
2025-01-01 18:49,4,20.75,Down,5,Yes,48
|
||||
2025-01-01 19:58,7,11.86,Up,6,Yes,70
|
||||
2025-01-01 19:54,10,11.84,Down,1,Yes,10
|
||||
2025-01-01 17:13,4,14.36,Down,6,No,52
|
||||
2025-01-01 15:35,11,14.17,Down,6,No,75
|
||||
2025-01-01 06:33,4,8.09,Down,2,No,10
|
||||
2025-01-01 17:06,12,8.71,Down,4,No,36
|
||||
2025-01-01 17:02,9,20.67,Down,3,No,25
|
||||
2025-01-01 15:47,1,14.32,Down,3,No,29
|
||||
2025-01-01 14:14,10,10.18,Up,2,No,23
|
||||
2025-01-01 18:52,8,15.15,Up,4,Yes,53
|
||||
2025-01-01 19:42,10,6.08,Up,1,Yes,14
|
||||
2025-01-01 19:39,4,12.72,Up,6,Yes,65
|
||||
2025-01-01 10:38,8,10.66,Down,5,Yes,42
|
||||
2025-01-01 11:43,8,9.67,Up,3,No,34
|
||||
2025-01-01 11:53,1,13.08,Down,2,No,24
|
||||
2025-01-01 09:30,2,10.87,Down,2,Yes,11
|
||||
2025-01-01 09:19,12,13.44,Up,2,Yes,10
|
||||
2025-01-01 11:30,8,11.72,Down,4,No,32
|
||||
2025-01-01 10:35,9,12.67,Up,3,Yes,23
|
||||
2025-01-01 18:53,1,12.09,Down,3,Yes,40
|
||||
2025-01-01 08:01,11,9.95,Down,7,Yes,70
|
||||
2025-01-01 16:58,3,8.65,Down,4,No,42
|
||||
2025-01-01 07:09,3,7.43,Up,3,No,32
|
||||
2025-01-01 19:05,11,6.57,Down,4,Yes,34
|
||||
2025-01-01 13:18,12,3.2,Down,4,No,40
|
||||
2025-01-01 13:47,4,4.6,Up,5,No,35
|
||||
2025-01-01 15:00,5,18.01,Up,2,No,15
|
||||
2025-01-01 06:03,11,14.7,Down,1,No,10
|
||||
2025-01-01 06:38,8,8.74,Up,3,No,24
|
||||
2025-01-01 12:05,6,8.49,Up,4,No,38
|
||||
2025-01-01 07:11,6,6.15,Down,3,No,36
|
||||
2025-01-01 09:59,11,8.45,Down,3,Yes,22
|
||||
2025-01-01 06:23,4,17.46,Down,5,No,61
|
||||
2025-01-01 08:26,10,14.85,Up,6,Yes,56
|
||||
2025-01-01 08:39,9,18.72,Up,1,Yes,10
|
||||
2025-01-01 11:18,7,6.44,Up,2,No,15
|
||||
2025-01-01 12:53,3,11.58,Down,4,No,31
|
||||
2025-01-01 13:31,9,7.35,Up,2,No,28
|
||||
2025-01-01 17:46,8,10.02,Up,5,No,62
|
||||
2025-01-01 08:30,12,6.42,Down,1,Yes,10
|
||||
2025-01-01 10:16,9,15.65,Down,4,Yes,55
|
||||
2025-01-01 07:46,8,14.64,Down,1,No,10
|
||||
2025-01-01 08:45,8,12.66,Up,2,Yes,21
|
||||
2025-01-01 17:52,7,15.63,Up,9,No,84
|
||||
2025-01-01 12:10,6,18.98,Up,4,No,41
|
||||
2025-01-01 18:04,6,19.5,Down,4,Yes,21
|
||||
2025-01-01 17:16,11,28.13,Up,4,No,40
|
||||
2025-01-01 17:27,9,7.1,Down,4,No,30
|
||||
2025-01-01 15:38,8,10.08,Down,4,No,44
|
||||
2025-01-01 15:21,12,11.43,Down,4,No,36
|
||||
2025-01-01 13:38,6,3.07,Down,5,No,46
|
||||
2025-01-01 15:04,7,14.05,Down,5,No,32
|
||||
2025-01-01 06:27,8,5.64,Up,3,No,21
|
||||
2025-01-01 19:31,6,8.08,Up,2,Yes,22
|
||||
2025-01-01 19:18,12,5.36,Down,3,Yes,20
|
||||
2025-01-01 06:57,9,10.63,Down,3,No,31
|
||||
2025-01-01 07:39,11,15.61,Up,5,No,44
|
||||
2025-01-01 13:19,8,11.37,Down,6,No,55
|
||||
2025-01-01 18:48,1,14.68,Down,4,Yes,40
|
||||
2025-01-01 10:40,8,16.47,Down,1,Yes,10
|
||||
2025-01-01 08:09,9,15.73,Up,3,Yes,28
|
||||
2025-01-01 07:35,11,11.77,Down,3,No,45
|
||||
2025-01-01 18:36,2,15.92,Up,8,Yes,87
|
||||
2025-01-01 16:54,8,15.32,Up,5,No,35
|
||||
2025-01-01 12:11,1,12.83,Up,1,No,10
|
||||
2025-01-01 13:09,11,15.41,Up,6,No,57
|
||||
2025-01-01 19:24,6,12.41,Down,2,Yes,18
|
||||
2025-01-01 07:33,3,6.19,Up,1,No,14
|
||||
2025-01-01 13:01,11,7.6,Up,2,No,22
|
||||
2025-01-01 11:26,6,11.39,Down,1,No,11
|
||||
2025-01-01 17:23,7,21.29,Up,1,No,10
|
||||
2025-01-01 11:52,7,13.64,Up,5,No,55
|
||||
2025-01-01 19:01,11,16.93,Up,2,Yes,18
|
||||
2025-01-01 11:42,8,13.58,Down,6,No,66
|
||||
2025-01-01 12:36,10,10.01,Up,4,No,33
|
||||
2025-01-01 06:00,1,11.06,Down,5,No,47
|
||||
2025-01-01 13:59,6,16.71,Down,2,No,10
|
||||
2025-01-01 11:03,3,10.77,Down,5,No,43
|
||||
2025-01-01 16:28,7,9.37,Down,3,No,34
|
||||
2025-01-01 18:47,6,8.98,Down,1,Yes,10
|
||||
2025-01-01 15:10,2,6.3,Up,3,No,33
|
||||
2025-01-01 11:21,3,9.71,Up,6,No,41
|
||||
2025-01-01 06:51,6,21.05,Up,6,No,61
|
||||
2025-01-01 11:49,7,16.17,Down,5,No,48
|
||||
2025-01-01 18:32,9,13.67,Down,1,Yes,30
|
||||
2025-01-01 08:04,4,12.1,Down,5,Yes,34
|
||||
2025-01-01 07:03,11,10.82,Up,7,No,59
|
||||
2025-01-01 16:49,9,15.76,Up,8,No,89
|
||||
2025-01-01 07:25,4,2.38,Down,3,No,43
|
||||
2025-01-01 07:43,12,11.82,Up,6,No,71
|
||||
2025-01-01 19:49,1,15.37,Up,4,Yes,36
|
||||
2025-01-01 14:30,11,16.16,Up,4,No,38
|
||||
2025-01-01 10:28,1,7.35,Up,1,Yes,11
|
||||
2025-01-01 10:58,3,12.48,Up,4,Yes,35
|
||||
2025-01-01 07:52,8,16.85,Down,3,No,16
|
||||
2025-01-01 06:00,10,12.56,Down,6,No,48
|
||||
2025-01-01 08:09,8,14.26,Up,5,Yes,65
|
||||
2025-01-01 10:13,3,7.63,Up,4,Yes,38
|
||||
2025-01-01 09:06,2,11.15,Down,3,Yes,19
|
||||
2025-01-01 08:29,9,12.86,Up,3,Yes,40
|
||||
2025-01-01 07:44,7,2.58,Down,2,No,12
|
||||
2025-01-01 08:53,1,12.68,Up,2,Yes,28
|
||||
2025-01-01 10:59,8,5.2,Down,3,Yes,22
|
||||
2025-01-01 19:25,12,6.43,Up,5,Yes,48
|
||||
2025-01-01 08:07,6,10.73,Up,1,Yes,10
|
||||
2025-01-01 16:45,1,10.39,Down,6,No,59
|
||||
2025-01-01 13:30,8,14.97,Up,2,No,10
|
||||
2025-01-01 06:12,3,13.65,Up,7,No,64
|
||||
2025-01-01 09:37,9,14.65,Down,6,Yes,51
|
||||
2025-01-01 08:31,1,0.16,Up,2,Yes,23
|
||||
2025-01-01 19:35,3,11.43,Down,4,Yes,31
|
||||
2025-01-01 08:13,11,11.85,Down,3,Yes,31
|
||||
2025-01-01 17:24,8,18.63,Up,10,No,100
|
||||
2025-01-01 11:37,2,19.98,Down,3,No,24
|
||||
2025-01-01 08:44,9,12.23,Down,4,Yes,50
|
||||
2025-01-01 16:13,6,4.97,Up,4,No,51
|
||||
2025-01-01 07:51,6,20.32,Down,6,No,54
|
||||
2025-01-01 18:41,11,8.69,Up,5,Yes,45
|
||||
2025-01-01 13:39,2,10.25,Down,8,No,63
|
||||
2025-01-01 18:38,7,19.98,Up,4,Yes,28
|
||||
2025-01-01 18:29,12,11.16,Down,2,Yes,25
|
||||
2025-01-01 20:00,5,13.8,Down,3,No,11
|
||||
2025-01-01 13:00,4,16.64,Up,3,No,36
|
||||
2025-01-01 13:07,2,11.6,Up,4,No,49
|
||||
2025-01-01 08:55,4,19.87,Up,4,Yes,55
|
||||
2025-01-01 07:19,1,12.67,Up,2,No,16
|
||||
2025-01-01 09:41,7,15.21,Up,4,Yes,28
|
||||
2025-01-01 09:01,7,9.04,Down,2,Yes,26
|
||||
2025-01-01 13:47,5,7.71,Up,1,No,20
|
||||
2025-01-01 12:20,9,17.77,Up,5,No,43
|
||||
2025-01-01 09:05,10,11.32,Up,6,Yes,48
|
||||
2025-01-01 09:21,6,9.39,Up,6,Yes,45
|
||||
2025-01-01 16:32,10,17.17,Down,2,No,34
|
||||
2025-01-01 16:56,8,16.98,Down,6,No,67
|
||||
2025-01-01 13:37,3,13.61,Up,4,No,39
|
||||
2025-01-01 09:02,5,9.96,Down,7,Yes,68
|
||||
2025-01-01 08:38,5,10.57,Up,8,Yes,72
|
||||
2025-01-01 10:18,12,2.11,Up,1,Yes,11
|
||||
2025-01-01 19:23,3,11.51,Down,3,Yes,21
|
||||
2025-01-01 13:32,6,11.13,Down,4,No,31
|
||||
2025-01-01 07:25,1,12.5,Down,4,No,49
|
||||
2025-01-01 13:04,6,13.37,Down,2,No,10
|
||||
2025-01-01 12:18,4,17.42,Up,1,No,10
|
||||
2025-01-01 08:50,1,17.38,Up,4,Yes,47
|
||||
2025-01-01 12:03,4,16.04,Down,2,No,10
|
||||
2025-01-01 11:55,8,10.94,Down,2,No,11
|
||||
2025-01-01 11:08,9,17.54,Up,4,No,47
|
||||
2025-01-01 13:22,1,8.45,Up,5,No,67
|
||||
2025-01-01 17:15,9,13.62,Up,4,No,51
|
||||
2025-01-01 06:35,4,14.73,Up,4,No,31
|
||||
2025-01-01 07:10,1,6.0,Up,6,No,57
|
||||
2025-01-01 16:54,7,11.66,Up,3,No,24
|
||||
2025-01-01 19:04,6,11.01,Down,2,Yes,21
|
||||
2025-01-01 19:44,12,11.7,Down,2,Yes,10
|
||||
2025-01-01 17:30,4,13.29,Down,5,No,65
|
||||
2025-01-01 10:33,9,6.57,Up,4,Yes,32
|
||||
2025-01-01 09:14,11,15.82,Up,3,Yes,21
|
||||
2025-01-01 13:32,12,16.46,Down,5,No,59
|
||||
2025-01-01 08:13,12,6.77,Down,2,Yes,29
|
||||
2025-01-01 18:32,1,10.72,Down,1,Yes,14
|
||||
2025-01-01 14:49,4,8.54,Down,1,No,10
|
||||
2025-01-01 10:49,2,10.78,Up,1,Yes,10
|
||||
2025-01-01 08:58,12,17.33,Down,4,Yes,27
|
||||
2025-01-01 06:28,3,13.88,Up,4,No,34
|
||||
2025-01-01 10:41,5,13.23,Down,6,Yes,58
|
||||
2025-01-01 17:25,1,14.26,Down,7,No,65
|
||||
2025-01-01 19:39,9,13.03,Up,3,Yes,26
|
||||
2025-01-01 07:48,5,1.91,Up,5,No,47
|
||||
2025-01-01 09:10,12,12.74,Down,4,Yes,36
|
||||
2025-01-01 16:16,2,13.04,Down,5,No,50
|
||||
2025-01-01 14:45,6,13.38,Up,3,No,38
|
||||
2025-01-01 14:51,7,15.08,Up,2,No,26
|
||||
2025-01-01 06:32,7,11.85,Down,1,No,10
|
||||
2025-01-01 12:50,5,13.29,Down,1,No,10
|
||||
2025-01-01 09:36,7,10.52,Down,3,Yes,13
|
||||
2025-01-01 10:34,3,4.95,Up,5,Yes,50
|
||||
2025-01-01 07:28,1,8.18,Down,6,No,67
|
||||
2025-01-01 08:09,2,7.85,Down,7,Yes,69
|
||||
2025-01-01 13:52,1,6.16,Up,7,No,51
|
||||
2025-01-01 12:52,12,15.16,Up,3,No,43
|
||||
2025-01-01 06:50,11,8.89,Up,4,No,19
|
||||
2025-01-01 11:03,2,19.31,Up,6,No,59
|
||||
2025-01-01 11:00,7,12.59,Down,1,No,10
|
||||
2025-01-01 15:54,4,16.59,Up,6,No,69
|
||||
2025-01-01 14:14,5,4.41,Up,3,No,20
|
||||
|
+1162
File diff suppressed because it is too large.
Load diff
+606
@@ -0,0 +1,606 @@
|
||||
# some funny
|
||||
|
||||
## import
|
||||
|
||||
|
||||
|
||||
```python
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
import seaborn as sns
|
||||
from sklearn.decomposition import PCA
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
```
|
||||
|
||||
## read
|
||||
|
||||
|
||||
|
||||
```python
|
||||
# read
|
||||
apple = pd.read_csv("apple_quality.csv")
|
||||
elevator = pd.read_csv("elevator_traffic_dataset.csv")
|
||||
|
||||
# show basic info
|
||||
print(apple.info())
|
||||
print(elevator.info())
|
||||
|
||||
```
|
||||
|
||||
<class 'pandas.core.frame.DataFrame'>
|
||||
RangeIndex: 4000 entries, 0 to 3999
|
||||
Data columns (total 9 columns):
|
||||
# Column Non-Null Count Dtype
|
||||
--- ------ -------------- -----
|
||||
0 A_id 4000 non-null int64
|
||||
1 Size 4000 non-null float64
|
||||
2 Weight 4000 non-null float64
|
||||
3 Sweetness 4000 non-null float64
|
||||
4 Crunchiness 4000 non-null float64
|
||||
5 Juiciness 4000 non-null float64
|
||||
6 Ripeness 4000 non-null float64
|
||||
7 Acidity 4000 non-null float64
|
||||
8 Quality 4000 non-null object
|
||||
dtypes: float64(7), int64(1), object(1)
|
||||
memory usage: 281.4+ KB
|
||||
None
|
||||
<class 'pandas.core.frame.DataFrame'>
|
||||
RangeIndex: 300 entries, 0 to 299
|
||||
Data columns (total 7 columns):
|
||||
# Column Non-Null Count Dtype
|
||||
--- ------ -------------- -----
|
||||
0 timestamp 300 non-null object
|
||||
1 floor_requested 300 non-null int64
|
||||
2 wait_time_seconds 300 non-null float64
|
||||
3 direction 300 non-null object
|
||||
4 people_count 300 non-null int64
|
||||
5 peak_hour 300 non-null object
|
||||
6 load_percent 300 non-null int64
|
||||
dtypes: float64(1), int64(3), object(3)
|
||||
memory usage: 16.5+ KB
|
||||
None
|
||||
|
||||
|
||||
## Questions 1.2
|
||||
|
||||
- Discrete or continuous
|
||||
- Discrete = fixed values (0/1, categories)
|
||||
- Continuous = real numbers (height, weight)
|
||||
- Quantitative or qualitative
|
||||
- Quantitative = numeric, measurable
|
||||
- Qualitative = descriptive (color, gender)
|
||||
- Numerical or categorical
|
||||
- Numerical = numbers
|
||||
- Categorical = labels (even if encoded as numbers)
|
||||
|
||||
|
||||
### Apple
|
||||
|
||||
| Column | Discrete / Continuous | Quant / Qual | Numerical / Categorical | Notes |
|
||||
| ------------- | --------------------- | ------------ | ----------------------- | ------------------------------------------------- |
|
||||
| `A_id` | Discrete | Qualitative | Categorical | ID → **exclude from PCA** |
|
||||
| `Size` | Continuous | Quantitative | Numerical | Negative = centered / standardized value (normal) |
|
||||
| `Weight` | Continuous | Quantitative | Numerical | Same |
|
||||
| `Sweetness` | Continuous | Quantitative | Numerical | Sensor score |
|
||||
| `Crunchiness` | Continuous | Quantitative | Numerical | Sensor score |
|
||||
| `Juiciness` | Continuous | Quantitative | Numerical | Sensor score |
|
||||
| `Ripeness` | Continuous | Quantitative | Numerical | Sensor score |
|
||||
| `Acidity` | Continuous | Quantitative | Numerical | Sensor score |
|
||||
| `Quality` | Discrete | Qualitative | Categorical | **Label (Good/Bad)** |
|
||||
|
||||
|
||||
### Elevator
|
||||
|
||||
| Column | Discrete / Continuous | Quant / Qual | Numerical / Categorical | Notes |
|
||||
| ------------------- | --------------------- | ------------ | ----------------------- | ----------------------------- |
|
||||
| `timestamp` | Continuous (time) | Quantitative | Numerical | Usually **excluded from PCA** |
|
||||
| `floor_requested` | Discrete | Quantitative | Numerical | Integers, ordered |
|
||||
| `wait_time_seconds` | Continuous | Quantitative | Numerical | Good PCA feature |
|
||||
| `direction` | Discrete | Qualitative | Categorical | Label (Up/Down) |
|
||||
| `people_count` | Discrete | Quantitative | Numerical | Count |
|
||||
| `peak_hour` | Discrete | Qualitative | Categorical | Label (Yes/No) |
|
||||
| `load_percent` | Continuous | Quantitative | Numerical | 0–100 |
|
||||
|
||||
|
||||
## Clean the Data
|
||||
|
||||
We need light preparation
|
||||
|
||||
|
||||
|
||||
### Apple: drop ID & encode quality label
|
||||
|
||||
|
||||
|
||||
```python
|
||||
X_apple = apple.drop(columns=["A_id", "Quality"])
|
||||
y_apple = apple["Quality"]
|
||||
|
||||
X_apple.head()
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
<div>
|
||||
<style scoped>
|
||||
.dataframe tbody tr th:only-of-type {
|
||||
vertical-align: middle;
|
||||
}
|
||||
|
||||
.dataframe tbody tr th {
|
||||
vertical-align: top;
|
||||
}
|
||||
|
||||
.dataframe thead th {
|
||||
text-align: right;
|
||||
}
|
||||
</style>
|
||||
<table border="1" class="dataframe">
|
||||
<thead>
|
||||
<tr style="text-align: right;">
|
||||
<th></th>
|
||||
<th>Size</th>
|
||||
<th>Weight</th>
|
||||
<th>Sweetness</th>
|
||||
<th>Crunchiness</th>
|
||||
<th>Juiciness</th>
|
||||
<th>Ripeness</th>
|
||||
<th>Acidity</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<th>0</th>
|
||||
<td>-3.970049</td>
|
||||
<td>-2.512336</td>
|
||||
<td>5.346330</td>
|
||||
<td>-1.012009</td>
|
||||
<td>1.844900</td>
|
||||
<td>0.329840</td>
|
||||
<td>-0.491590</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th>1</th>
|
||||
<td>-1.195217</td>
|
||||
<td>-2.839257</td>
|
||||
<td>3.664059</td>
|
||||
<td>1.588232</td>
|
||||
<td>0.853286</td>
|
||||
<td>0.867530</td>
|
||||
<td>-0.722809</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th>2</th>
|
||||
<td>-0.292024</td>
|
||||
<td>-1.351282</td>
|
||||
<td>-1.738429</td>
|
||||
<td>-0.342616</td>
|
||||
<td>2.838636</td>
|
||||
<td>-0.038033</td>
|
||||
<td>2.621636</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th>3</th>
|
||||
<td>-0.657196</td>
|
||||
<td>-2.271627</td>
|
||||
<td>1.324874</td>
|
||||
<td>-0.097875</td>
|
||||
<td>3.637970</td>
|
||||
<td>-3.413761</td>
|
||||
<td>0.790723</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th>4</th>
|
||||
<td>1.364217</td>
|
||||
<td>-1.296612</td>
|
||||
<td>-0.384658</td>
|
||||
<td>-0.553006</td>
|
||||
<td>3.030874</td>
|
||||
<td>-1.303849</td>
|
||||
<td>0.501984</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
### Elevator: encode direction & drop timestamp
|
||||
|
||||
|
||||
|
||||
```python
|
||||
elev = elevator.copy()
|
||||
|
||||
# encode categorical
|
||||
elev = pd.get_dummies(elev, columns=["direction"], drop_first=True)
|
||||
|
||||
# drop timestamp
|
||||
X_elev = elev.drop(columns=["timestamp", "peak_hour"])
|
||||
y_elev = elev["peak_hour"]
|
||||
X_elev.head()
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
<div>
|
||||
<style scoped>
|
||||
.dataframe tbody tr th:only-of-type {
|
||||
vertical-align: middle;
|
||||
}
|
||||
|
||||
.dataframe tbody tr th {
|
||||
vertical-align: top;
|
||||
}
|
||||
|
||||
.dataframe thead th {
|
||||
text-align: right;
|
||||
}
|
||||
</style>
|
||||
<table border="1" class="dataframe">
|
||||
<thead>
|
||||
<tr style="text-align: right;">
|
||||
<th></th>
|
||||
<th>floor_requested</th>
|
||||
<th>wait_time_seconds</th>
|
||||
<th>people_count</th>
|
||||
<th>load_percent</th>
|
||||
<th>direction_Up</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<th>0</th>
|
||||
<td>5</td>
|
||||
<td>16.53</td>
|
||||
<td>5</td>
|
||||
<td>53</td>
|
||||
<td>False</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th>1</th>
|
||||
<td>12</td>
|
||||
<td>18.98</td>
|
||||
<td>3</td>
|
||||
<td>20</td>
|
||||
<td>False</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th>2</th>
|
||||
<td>4</td>
|
||||
<td>19.35</td>
|
||||
<td>1</td>
|
||||
<td>10</td>
|
||||
<td>False</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th>3</th>
|
||||
<td>8</td>
|
||||
<td>3.22</td>
|
||||
<td>4</td>
|
||||
<td>31</td>
|
||||
<td>True</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th>4</th>
|
||||
<td>6</td>
|
||||
<td>17.32</td>
|
||||
<td>4</td>
|
||||
<td>50</td>
|
||||
<td>True</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
## Question 1.4
|
||||
|
||||
There are labels!
|
||||
|
||||
for Apple is `Quality`
|
||||
|
||||
for elevator we may have `peak_hour` as weak label
|
||||
|
||||
PCA is unsupervised, so labels are not used in PCA, only for visualization or interpretation.
|
||||
|
||||
|
||||
## Summary Statistics
|
||||
|
||||
- Mean: average of a feature
|
||||
- Variance: how spread out values are
|
||||
- Covariance: how two features move together
|
||||
- Correlation: normalized covariance (range -1 to 1)
|
||||
|
||||
Mean, variance, covariance, and correlation are not defined for categorical features unless encoded. Therefore, PCA is applied only to numerical features.
|
||||
|
||||
|
||||
|
||||
```python
|
||||
print("Apple mean:\n", X_apple.mean())
|
||||
print("\nApple variance:\n", X_apple.var())
|
||||
print("\nApple covariance:\n", X_apple.cov())
|
||||
print("\nApple correlation:\n", X_apple.corr())
|
||||
```
|
||||
|
||||
Apple mean:
|
||||
Size -0.503015
|
||||
Weight -0.989547
|
||||
Sweetness -0.470479
|
||||
Crunchiness 0.985478
|
||||
Juiciness 0.512118
|
||||
Ripeness 0.498277
|
||||
Acidity 0.076877
|
||||
dtype: float64
|
||||
|
||||
Apple variance:
|
||||
Size 3.717410
|
||||
Weight 2.568029
|
||||
Sweetness 3.776962
|
||||
Crunchiness 1.967728
|
||||
Juiciness 3.726003
|
||||
Ripeness 3.513476
|
||||
Acidity 4.453238
|
||||
dtype: float64
|
||||
|
||||
Apple covariance:
|
||||
Size Weight Sweetness Crunchiness Juiciness Ripeness \
|
||||
Size 3.717410 -0.527422 -1.216599 0.459425 -0.070312 -0.487070
|
||||
Weight -0.527422 2.568029 -0.480381 -0.215535 -0.285396 -0.732395
|
||||
Sweetness -1.216599 -0.480381 3.776962 -0.102373 0.359690 -0.997409
|
||||
Crunchiness 0.459425 -0.215535 -0.102373 1.967728 -0.702944 -0.531084
|
||||
Juiciness -0.070312 -0.285396 0.359690 -0.702944 3.726003 -0.351485
|
||||
Ripeness -0.487070 -0.732395 -0.997409 -0.531084 -0.351485 3.513476
|
||||
Acidity 0.798357 0.055508 0.352699 0.207045 1.013117 -0.801667
|
||||
|
||||
Acidity
|
||||
Size 0.798357
|
||||
Weight 0.055508
|
||||
Sweetness 0.352699
|
||||
Crunchiness 0.207045
|
||||
Juiciness 1.013117
|
||||
Ripeness -0.801667
|
||||
Acidity 4.453238
|
||||
|
||||
Apple correlation:
|
||||
Size Weight Sweetness Crunchiness Juiciness Ripeness \
|
||||
Size 1.000000 -0.170702 -0.324680 0.169868 -0.018892 -0.134773
|
||||
Weight -0.170702 1.000000 -0.154246 -0.095882 -0.092263 -0.243824
|
||||
Sweetness -0.324680 -0.154246 1.000000 -0.037552 0.095882 -0.273800
|
||||
Crunchiness 0.169868 -0.095882 -0.037552 1.000000 -0.259607 -0.201982
|
||||
Juiciness -0.018892 -0.092263 0.095882 -0.259607 1.000000 -0.097144
|
||||
Ripeness -0.134773 -0.243824 -0.273800 -0.201982 -0.097144 1.000000
|
||||
Acidity 0.196218 0.016414 0.085999 0.069943 0.248714 -0.202669
|
||||
|
||||
Acidity
|
||||
Size 0.196218
|
||||
Weight 0.016414
|
||||
Sweetness 0.085999
|
||||
Crunchiness 0.069943
|
||||
Juiciness 0.248714
|
||||
Ripeness -0.202669
|
||||
Acidity 1.000000
|
||||
|
||||
|
||||
|
||||
```python
|
||||
print("Elevator mean:\n", X_elev.mean())
|
||||
print("\nElevator variance:\n", X_elev.var())
|
||||
print("\nElevator covariance:\n", X_elev.cov())
|
||||
print("\nElevator correlation:\n", X_elev.corr())
|
||||
```
|
||||
|
||||
Elevator mean:
|
||||
floor_requested 6.683333
|
||||
wait_time_seconds 12.227300
|
||||
people_count 3.713333
|
||||
load_percent 36.250000
|
||||
direction_Up 0.503333
|
||||
dtype: float64
|
||||
|
||||
Elevator variance:
|
||||
floor_requested 11.942865
|
||||
wait_time_seconds 20.445000
|
||||
people_count 3.589788
|
||||
load_percent 378.362040
|
||||
direction_Up 0.250825
|
||||
dtype: float64
|
||||
|
||||
Elevator covariance:
|
||||
floor_requested wait_time_seconds people_count \
|
||||
floor_requested 11.942865 1.237570 -0.539242
|
||||
wait_time_seconds 1.237570 20.445000 1.335444
|
||||
people_count -0.539242 1.335444 3.589788
|
||||
load_percent -6.087793 15.086062 33.001672
|
||||
direction_Up 0.123133 0.099156 0.041093
|
||||
|
||||
load_percent direction_Up
|
||||
floor_requested -6.087793 0.123133
|
||||
wait_time_seconds 15.086062 0.099156
|
||||
people_count 33.001672 0.041093
|
||||
load_percent 378.362040 1.027592
|
||||
direction_Up 1.027592 0.250825
|
||||
|
||||
Elevator correlation:
|
||||
floor_requested wait_time_seconds people_count \
|
||||
floor_requested 1.000000 0.079199 -0.082356
|
||||
wait_time_seconds 0.079199 1.000000 0.155883
|
||||
people_count -0.082356 0.155883 1.000000
|
||||
load_percent -0.090563 0.171525 0.895463
|
||||
direction_Up 0.071143 0.043787 0.043306
|
||||
|
||||
load_percent direction_Up
|
||||
floor_requested -0.090563 0.071143
|
||||
wait_time_seconds 0.171525 0.043787
|
||||
people_count 0.895463 0.043306
|
||||
load_percent 1.000000 0.105483
|
||||
direction_Up 0.105483 1.000000
|
||||
|
||||
|
||||
### Most Correlated Pairs
|
||||
|
||||
|
||||
|
||||
```python
|
||||
sns.heatmap(X_apple.corr(), annot=True)
|
||||
plt.title("Apple Correlation Matrix")
|
||||
plt.show()
|
||||
|
||||
sns.heatmap(X_elev.corr(), annot=True)
|
||||
plt.title("Elevator Correlation Matrix")
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
#### apple
|
||||
|
||||
size vs. sweetness? sweetness vs. ripeness? juiciness vs crunchiness? juiciness vs acidity? idek
|
||||
|
||||
#### elevator
|
||||
|
||||
load percent vs people count.
|
||||
wait time seconds vs people count? wait time seconds vs load percent?
|
||||
|
||||
|
||||
### cov
|
||||
|
||||
|
||||
|
||||
```python
|
||||
sns.heatmap(X_apple.cov(), annot=True)
|
||||
plt.title("Apple covariance")
|
||||
plt.show()
|
||||
|
||||
sns.heatmap(X_elev.cov(), annot=True)
|
||||
plt.title("Elevator covariance")
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Question 1.7
|
||||
|
||||
There are no missing data.
|
||||
|
||||
|
||||
## Standardize
|
||||
|
||||
|
||||
|
||||
```python
|
||||
scaler = StandardScaler()
|
||||
|
||||
X_apple_scaled = scaler.fit_transform(X_apple)
|
||||
X_elev_scaled = scaler.fit_transform(X_elev)
|
||||
|
||||
```
|
||||
|
||||
## PCA Fit & Transform
|
||||
|
||||
|
||||
|
||||
```python
|
||||
pca_apple = PCA()
|
||||
apple_pcs = pca_apple.fit_transform(X_apple_scaled)
|
||||
|
||||
print("Explained variance ratio:", pca_apple.explained_variance_ratio_)
|
||||
|
||||
```
|
||||
|
||||
Explained variance ratio: [0.21614201 0.20861653 0.17947635 0.16370152 0.10115033 0.08706457
|
||||
0.04384867]
|
||||
|
||||
|
||||
|
||||
```python
|
||||
pca_elev = PCA()
|
||||
elev_pcs = pca_elev.fit_transform(X_elev_scaled)
|
||||
|
||||
print("Explained variance ratio:", pca_elev.explained_variance_ratio_)
|
||||
|
||||
```
|
||||
|
||||
Explained variance ratio: [0.39472121 0.22406513 0.19121082 0.16957634 0.0204265 ]
|
||||
|
||||
|
||||
## question 2.1
|
||||
|
||||
What PCA actually does:
|
||||
|
||||
- Takes many correlated features
|
||||
- Rotates the space
|
||||
- Finds new axes (principal components)
|
||||
- PC1 = most variance
|
||||
- PC2 = second most, orthogonal
|
||||
|
||||
### Is there any difference while using principal components with highest and lowest values?
|
||||
|
||||
Using lowest-variance components loses information and mostly captures noise.
|
||||
|
||||
## 2D PCA Plot
|
||||
|
||||
|
||||
|
||||
```python
|
||||
plt.figure()
|
||||
plt.scatter(
|
||||
apple_pcs[:, 0], apple_pcs[:, 1], c=(y_apple == "good").astype(int), cmap="coolwarm"
|
||||
)
|
||||
plt.xlabel("PC1")
|
||||
plt.ylabel("PC2")
|
||||
plt.title("Apple PCA 2D")
|
||||
plt.colorbar(label="Good=1 Bad=0")
|
||||
plt.show()
|
||||
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
```python
|
||||
plt.figure()
|
||||
plt.scatter(
|
||||
elev_pcs[:, 0], elev_pcs[:, 1], c=(y_elev == "Yes").astype(int), cmap="viridis"
|
||||
)
|
||||
plt.xlabel("PC1")
|
||||
plt.ylabel("PC2")
|
||||
plt.title("Elevator PCA 2D")
|
||||
plt.colorbar(label="Peak hour (1=Yes)")
|
||||
plt.show()
|
||||
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
BIN
Binary file not shown.
BIN
Binary file not shown.
BIN
Binary file not shown.
BIN
Binary file not shown.
BIN
Binary file not shown.
BIN
Binary file not shown.
@@ -0,0 +1,6 @@
|
||||
def main():
|
||||
print("Hello from ml2!")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,16 @@
|
||||
[project]
|
||||
name = "ml2"
|
||||
version = "0.1.0"
|
||||
description = "Add your description here"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.14"
|
||||
dependencies = [
|
||||
"ipykernel>=7.1.0",
|
||||
"kaggle>=1.8.3",
|
||||
"matplotlib>=3.10.8",
|
||||
"nbconvert>=7.16.6",
|
||||
"numpy>=2.4.0",
|
||||
"pandas>=2.3.3",
|
||||
"scikit-learn>=1.8.0",
|
||||
"seaborn>=0.13.2",
|
||||
]
|
||||
Reference in new issue
Block a user