
adding cleaned datasets into lipids.db
	adding dataset: zhou0817 ... ok
	adding dataset: hine1217 ... ok
	adding dataset: hine0217 ... ok
	adding dataset: hine0119 ... ok
	adding dataset: leap0219 ... ok
	adding dataset: blaz0818 ... ok
	adding dataset: tsug0220_pos ... ok
	adding dataset: tsug0220_neg ... ok
	adding dataset: tsug0220_neg_corr ... ok
	adding dataset: hine0520 ... ok

adding predicted m/z into lipids.db ... ok

training new predictive CCS model (and input scaler) ...
using these datasets for CCS prediction:
	zhou0817 hine1217 hine0217 hine0119 leap0219 blaz0818 tsug0220_pos tsug0220_neg_corr hine0520
X: (4583, 39)
y: (4583,)
splitting data into training and test sets
X_train: (3666, 39)
y_train: (3666,)
X_test: (917, 39)
y_test: (917,)
scaling input data
X_train_s: (3666, 39)
training model
TRAINING SET PERFORMANCE
mean absolute error: 1.38 Å^2
median absolute error: 0.78 Å^2
median relative error: 0.27 %
RMSE: 2.16 Å^2
TEST SET PERFORMANCE
mean absolute error: 1.47 Å^2
median absolute error: 0.88 Å^2
median relative error: 0.31 %
RMSE: 2.21 Å^2
... ok

adding predicted CCS to database ... ok

characterizing CCS prediction performance ... ok

training new predictive RT model (and input scaler) ...
X: (632, 26)
y: (632,)
splitting data into training and test sets
X_train: (505, 26)
y_train: (505,)
X_test: (127, 26)
y_test: (127,)
scaling input data
X_train_s: (505, 26)
training model
TRAINING SET PERFORMANCE
mean absolute error: 0.10 min
median absolute error: 0.07 min
RMSE: 0.14 min
TEST SET PERFORMANCE
mean absolute error: 0.11 min
median absolute error: 0.07 min
RMSE: 0.16 min
... ok

adding predicted RT to database ... ok

characterizing RT prediction performance ... ok

