Upload results/ralph23_pca_variance_report.txt with huggingface_hub
Browse files
results/ralph23_pca_variance_report.txt
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
======================================================================
|
| 2 |
+
Ralph23 Task 1: PFAM PCA Variance Report
|
| 3 |
+
======================================================================
|
| 4 |
+
|
| 5 |
+
Provenance:
|
| 6 |
+
Script: ralph23_t01_pfam_pca_20260211_211025.py
|
| 7 |
+
Input: /media/drn2/External/TARA-Oceans/03_analyses/ALGAGPT-based-analyses/algagpt_gee_pfam_merged_SMART_20260119_100639.tsv
|
| 8 |
+
Date: 2026-02-11 21:12:35
|
| 9 |
+
Integrity Check: PASSED
|
| 10 |
+
|
| 11 |
+
Input matrix: 1810 samples x 20318 PFAM domains
|
| 12 |
+
NaN values replaced with 0: 0
|
| 13 |
+
|
| 14 |
+
--- Cumulative Explained Variance ---
|
| 15 |
+
PCs Individual% Cumulative%
|
| 16 |
+
------ ------------ ------------
|
| 17 |
+
1 60.7130 60.7130
|
| 18 |
+
2 21.2400 81.9530
|
| 19 |
+
3 5.4673 87.4203
|
| 20 |
+
4 1.9192 89.3395
|
| 21 |
+
5 1.9070 91.2465
|
| 22 |
+
6 1.3732 92.6197
|
| 23 |
+
7 1.1492 93.7689
|
| 24 |
+
8 0.8961 94.6650
|
| 25 |
+
9 0.6919 95.3569
|
| 26 |
+
10 0.4671 95.8240
|
| 27 |
+
11 0.3801 96.2041
|
| 28 |
+
12 0.3466 96.5507
|
| 29 |
+
13 0.2170 96.7678
|
| 30 |
+
14 0.1829 96.9507
|
| 31 |
+
15 0.1738 97.1245
|
| 32 |
+
16 0.1558 97.2803
|
| 33 |
+
17 0.1456 97.4259
|
| 34 |
+
18 0.1340 97.5599
|
| 35 |
+
19 0.1202 97.6801
|
| 36 |
+
20 0.1115 97.7916
|
| 37 |
+
21 0.1049 97.8965
|
| 38 |
+
22 0.0886 97.9851
|
| 39 |
+
23 0.0814 98.0665
|
| 40 |
+
24 0.0717 98.1382
|
| 41 |
+
25 0.0670 98.2052
|
| 42 |
+
26 0.0644 98.2696
|
| 43 |
+
27 0.0610 98.3307
|
| 44 |
+
28 0.0558 98.3865
|
| 45 |
+
29 0.0549 98.4414
|
| 46 |
+
30 0.0529 98.4943
|
| 47 |
+
31 0.0461 98.5404
|
| 48 |
+
32 0.0447 98.5851
|
| 49 |
+
33 0.0419 98.6270
|
| 50 |
+
34 0.0392 98.6663
|
| 51 |
+
35 0.0381 98.7044
|
| 52 |
+
36 0.0353 98.7397
|
| 53 |
+
37 0.0343 98.7740
|
| 54 |
+
38 0.0341 98.8081
|
| 55 |
+
39 0.0327 98.8408
|
| 56 |
+
40 0.0318 98.8726
|
| 57 |
+
41 0.0297 98.9023
|
| 58 |
+
42 0.0269 98.9292
|
| 59 |
+
43 0.0262 98.9554
|
| 60 |
+
44 0.0260 98.9814
|
| 61 |
+
45 0.0246 99.0061
|
| 62 |
+
46 0.0228 99.0289
|
| 63 |
+
47 0.0219 99.0508
|
| 64 |
+
48 0.0207 99.0715
|
| 65 |
+
49 0.0189 99.0904
|
| 66 |
+
50 0.0184 99.1088
|
| 67 |
+
51 0.0181 99.1269
|
| 68 |
+
52 0.0172 99.1442
|
| 69 |
+
53 0.0171 99.1613
|
| 70 |
+
54 0.0164 99.1777
|
| 71 |
+
55 0.0160 99.1936
|
| 72 |
+
56 0.0144 99.2081
|
| 73 |
+
57 0.0139 99.2219
|
| 74 |
+
58 0.0135 99.2354
|
| 75 |
+
59 0.0132 99.2486
|
| 76 |
+
60 0.0126 99.2612
|
| 77 |
+
61 0.0121 99.2734
|
| 78 |
+
62 0.0111 99.2844
|
| 79 |
+
63 0.0111 99.2955
|
| 80 |
+
64 0.0106 99.3061
|
| 81 |
+
|
| 82 |
+
--- Key Milestones ---
|
| 83 |
+
10 PCs: 95.82% cumulative variance
|
| 84 |
+
20 PCs: 97.79% cumulative variance
|
| 85 |
+
32 PCs: 98.59% cumulative variance
|
| 86 |
+
50 PCs: 99.11% cumulative variance
|
| 87 |
+
64 PCs: 99.31% cumulative variance
|
| 88 |
+
|
| 89 |
+
--- Output Files ---
|
| 90 |
+
/media/drn2/External/TARA-Oceans/03_analyses/WorldModelApp/data/consolidated_pfam_pca32.npy shape=(1810, 32)
|
| 91 |
+
/media/drn2/External/TARA-Oceans/03_analyses/WorldModelApp/data/consolidated_pfam_pca64.npy shape=(1810, 64)
|
| 92 |
+
/media/drn2/External/TARA-Oceans/03_analyses/WorldModelApp/data/consolidated_pfam_pca32_model.joblib (fitted PCA object)
|
| 93 |
+
/media/drn2/External/TARA-Oceans/03_analyses/WorldModelApp/data/consolidated_pfam_pca64_model.joblib (fitted PCA object)
|
| 94 |
+
/media/drn2/External/TARA-Oceans/03_analyses/WorldModelApp/data/consolidated_pfam_pca32_variance.npy (per-component variance ratios)
|
| 95 |
+
/media/drn2/External/TARA-Oceans/03_analyses/WorldModelApp/data/consolidated_pfam_pca64_variance.npy (per-component variance ratios)
|
| 96 |
+
|
| 97 |
+
Runtime: 10.8 seconds
|