The first two PCA axes capture 50.3% of the total variance in the data.
| n_components | 3 |
| method | pca |
| n_rows | 35 |
| n_dropped | 61 |
explained variance
| Axis | Fraction | Cumulative |
| Axis 1 | 0.350574 | 0.350574 |
| Axis 2 | 0.151965 | 0.50254 |
| Axis 3 | 0.109158 | 0.611697 |
ordination scatter
scree
loadings
Warnings
- Excluded identifier-like numeric column(s): PLOT. These look like bookkeeping fields rather than measurements. Select feature columns explicitly if you intended to include them.
Method & Provenance
- Method
- Ordination — PCA
- Engine
- Python · scikit-learn 1.8.0
- Input dataset
-
gallery — catg_example_07_microbial_soil_biology.csv
- Started
- 2026-09-21 02:15:57.280156
- Permanent link
- https://cat-g-omxpert.wishartlab.com/results/by-token/fb6cf1f402b54feeabd9bf3da95b64e6
| Parameter | Value |
| ordination_method | pca |
| method | pca |
| feature_cols | ENV_SOILNH4, ENV_SOILNO3, ENV_SOILP, ENV_SOILOC, ENV_SOILTN, ENV_SOILTC, ENV_PH, ENV_SOILCLAY, ENV_SOILSILT, ENV_SOILSAND, ENV_SOILMOIS, PC_SHOOTMASS, PC_ROOTMASS, PC_LITTERMASS, COVER_TOTAL_JUL, COVER_SHANNON_JUL, SOIL_EC_uS_cm, SOIL_CO2_mg_per_g, BACTERIAL_NECROMASS_C, FUNGAL_NECROMASS_C, MICROBIAL_NECROMASS_C |
| n_components | 3 |
Command history
# python
from sklearn.decomposition import PCA
# python
from sklearn.preprocessing import StandardScaler
# python
X_scaled = StandardScaler().fit_transform(X)
# python
coords = PCA(n_components=3).fit_transform(X_scaled)