0
22
59000
1
21
9600
2
25
9600
3
23
65500
4
24
54400
5
21
9900
6
26
77100
7
24
78956
8
24
83000
9
21
10000
21% of Rows are Defaults
0
22
59000
1
21
9600
2
25
9600
3
23
65500
4
24
54400
5
21
9900
6
26
77100
7
24
78956
8
24
83000
9
21
10000
0
22
59000
1
21
9600
2
25
9600
3
23
65500
4
24
54400
5
21
9900
6
26
77100
7
24
78956
8
24
83000
9
21
10000
0
-0.9044705536367257
-0.11435433131777786
1
-1.0618516828494695
-0.9109406370949584
2
-0.4323271659984943
-0.9109406370949584
3
-0.747089424423982
-0.009540343715517274
4
-0.5897082952112381
-0.1885303840824546
5
-1.0618516828494695
-0.9061030684363925
6
-0.27494603678575047
0.17751231108236318
7
-0.5897082952112381
0.20744073585002404
8
-0.5897082952112381
0.272651161367492
9
-1.0618516828494695
-0.9044905455502039
Fitting 3 folds for each of 18 candidates, totalling 54 fits
0
1
24.296141703923546
1
2
22.439138571421307
2
3
24.97808806101481
3
4
26.287990649541214
4
5
21.228907982508343
5
6
41.65275247891744
6
7
29.42949390411377
7
8
31.247227907180783
8
9
29.10541939735413
9
10
19.784565687179565
True Negative: 4969
False Positive: 86
False Negative: 433
True Positive: 996
precision recall f1-score support
Non-Default 0.92 0.98 0.95 5055
Default 0.92 0.70 0.79 1429
accuracy 0.92 6484
macro avg 0.92 0.84 0.87 6484
weighted avg 0.92 0.92 0.92 6484
Best Estimator
------------------------------------------------------------------------------------------
DeepClassifier(
model=<function create_classifier at 0x7fa9f6713560>
build_fn=None
warm_start=False
random_state=None
optimizer=<class 'keras.optimizer_v2.adam.Adam'>
loss=binary_crossentropy
metrics=None
batch_size=None
validation_batch_size=None
verbose=0
callbacks=<class 'keras.callbacks.EarlyStopping'>
validation_split=0.0
shuffle=True
run_eagerly=False
epochs=100
model__architecture={'Layers': ['Dense', 'Dense', 'Dense'], 'ActivationFunctions': ['relu', 'relu', 'sigmoid'], 'Neurons': [50, 25, 1]}
callbacks__monitor=val_loss
callbacks__min_delta=0.0001
callbacks__patience=20
callbacks__verbose=0
callbacks__restore_best_weights=True
train_ratio=0.8
val_ratio=0.2
batch_size_custom=256
fit__shuffle=True
optimizer__learning_rate=0.001
class_weight=None
)
------------------------------------------------------------------------------------------
/shared-libs/python3.7/py/lib/python3.7/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
from .autonotebook import tqdm as notebook_tqdm
100%|██████████| 50/50 [00:31<00:00, 1.56it/s]