Goodmoring people. We are trying making a model with hyperparameter tuning with a costum dataset. The problem is that the error is not going down, while it should be doing that. The numbers are also very high. When done with tuning, the output we get is nan. Can someone explain why it is not going down and why we are getting nan as an output. We are using mse.
import tensorflow
import pandas as pd
import tensorflow as tf
# import HPT requirements
from kerastuner import HyperModel
import keras
from tensorflow.keras.layers import (
Dense,
Dropout,
)
# load data
ds = pd.read_csv("datasets/ds_extended.csv").dropna()
# preprocessing data
rows = len(ds.index)
jaartallen = ds.pop("jaartallen")
testdata = ds.sample(n = round(rows/10))
traindata = pd.concat([ds,testdata]).drop_duplicates(keep=False)
y_train = traindata.pop("loonbelasting(mln)")
y_test = testdata.pop("loonbelasting(mln)")
x_train = traindata
x_test = testdata
# ANN model
class ANNHyperModel(HyperModel):
def __init__(self, input_shape, num_classes, layers):
self.input_shape = input_shape
self.num_classes = num_classes
self.layers = layers
def build(self, hp):
model = keras.Sequential()
# add first layer
model.add(Dense(
units=6,
input_shape=self.input_shape,
activation='relu'))
# add middle layers
for i in range(self.layers):
model.add(
Dense(
units=hp.Int(
'units',
min_value=1,
max_value=10,
step=5,
default=30
),
activation=hp.Choice(
'dense_activation',
values=['relu', 'tanh', 'sigmoid'],
default='relu'
)
)
)
model.add(
Dropout(
rate=hp.Float(
'dropout',
min_value=0.0,
max_value=0.5,
default=0.25,
step=0.05
)
)
)
# add output layer
model.add(
Dense(self.num_classes, activation='softmax'))
# compile model
model.compile(
optimizer=keras.optimizers.Adam(
hp.Float(
'learning_rate',
min_value=2E-2,
max_value=4E-2,
sampling='LOG',
default=3E-2)),
loss='mae',
metrics=['mse']
)
return model
NUM_CLASSES = 62000
INPUT_SHAPE = x_train.loc[0].shape
LAYERS = 5
# create hypermodel
hypermodel = ANNHyperModel(num_classes=NUM_CLASSES, input_shape=INPUT_SHAPE, layers=LAYERS)
# perform hyperparameter tuning
from kerastuner.tuners import RandomSearch
MAX_TRIALS = 20
EXECUTION_PER_TRIAL = 10
tuner = RandomSearch(
hypermodel,
objective='mse',
seed=1,
max_trials=MAX_TRIALS,
executions_per_trial=EXECUTION_PER_TRIAL,
directory='random_search',
project_name='inkomstenbelasting'
)
SEARCH_EPOCHS = 1
tuner.search(x_train, y_train, epochs=SEARCH_EPOCHS, validation_split=0.1)
# get the results
results = tuner.results_summary()
best_model = tuner.get_best_models(num_models=1)[0]
loss, accuracy = best_model.evaluate(x_test, y_test)
"""
while accuracy == 0:
best_model.fit(x_train, y_train)"""
This is the output we get:
480/481 [============================>.] - ETA: 0s - loss: 1066199616.0000 - mean_absolute_error: 31202.4492WARNING:tensorflow:Can save best model only with mse available, skipping.
481/481 [==============================] - 26s 55ms/step - loss: 1066175872.0000 - mean_absolute_error: 31202.8555 - val_loss: 2047683840.0000 - val_mean_absolute_error: 45249.4258
And when done tuning this is the rest of the output we get:
1/60 [..............................] - ETA: 0s - loss: nan - mse: nan
5/60 [=>............................] - ETA: 0s - loss: nan - mse: nan
9/60 [===>..........................] - ETA: 0s - loss: nan - mse: nan
13/60 [=====>........................] - ETA: 0s - loss: nan - mse: nan
17/60 [=======>......................] - ETA: 0s - loss: nan - mse: nan
21/60 [=========>....................] - ETA: 0s - loss: nan - mse: nan
25/60 [===========>..................] - ETA: 0s - loss: nan - mse: nan
29/60 [=============>................] - ETA: 0s - loss: nan - mse: nan
33/60 [===============>..............] - ETA: 0s - loss: nan - mse: nan
37/60 [=================>............] - ETA: 0s - loss: nan - mse: nan
41/60 [===================>..........] - ETA: 0s - loss: nan - mse: nan
45/60 [=====================>........] - ETA: 0s - loss: nan - mse: nan
49/60 [=======================>......] - ETA: 0s - loss: nan - mse: nan
53/60 [=========================>....] - ETA: 0s - loss: nan - mse: nan
57/60 [===========================>..] - ETA: 0s - loss: nan - mse: nan
60/60 [==============================] - 1s 13ms/step - loss: nan - mse: nan
This is the head of our dataset:
Name: loonbelasting(mln), Length: 17100, dtype: float64
<bound method NDFrame.head of btw_laag btw_hoog ... bevolking vennootschapsbelasting(mln)
0 6 17.5 ... 1.532312e+07 9459.000
1 6 17.5 ... 1.532329e+07 9462.041
2 6 17.5 ... 1.532346e+07 9465.082
3 6 17.5 ... 1.532363e+07 9468.123
4 6 17.5 ... 1.532381e+07 9471.164
... ... ... ... ... ...
18995 6 21.0 ... 1.682904e+07 14500.680
18996 6 21.0 ... 1.682909e+07 14502.744
18997 6 21.0 ... 1.682914e+07 14504.808
18998 6 21.0 ... 1.682919e+07 14506.872
18999 6 21.0 ... 1.682924e+07 14508.936
