I'm getting following error and I'm not able to figure out why:
RuntimeError: Model-building function did not return a valid Keras Model instance, found (<tensorflow.python.keras.engine.functional.Functional object at 0x7f74d8b849d0>, <tensorflow.python.keras.engine.functional.Functional object at 0x7f74d8b80810>)
I have read the answers here and here which seem to telling to import keras from tensorflow instead of stand alone keras which I'm doing but still getting the error. I would very much appreciate your help in figuring this out. Below is my entire code:
from tensorflow.keras.layers import Input, Dense, BatchNormalization, Dropout, Concatenate, Lambda, GaussianNoise, Activation
from tensorflow.keras.models import Model, Sequential
from tensorflow.keras.losses import BinaryCrossentropy
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau
from numba import njit
import tensorflow as tf
import numpy as np
from sklearn.model_selection import KFold
from sklearn.model_selection._split import _BaseKFold, indexable, _num_samples
from sklearn.utils.validation import _deprecate_positional_args
import pandas as pd
import kerastuner as kt
import gc
from tqdm import tqdm
from random import choices
import warnings
warnings.filterwarnings('ignore')
class MyTuner(kt.Tuner):
def run_trial(self, trial, x, y):
cv = PurgedGroupTimeSeriesSplit(n_splits=5, group_gap = 20)
val_losses = []
for train_indices, test_indices in cv.split(x, groups=x[0]):
x_train, y_train = x[train_indices, 1:], y[train_indices]
x_test, y_test = x[test_indices, 1:], y[test_indices]
x_train = apply_transformation(x_train)
x_test = apply_transformation(x_test)
model = self.hypermodel.build(trial.hyperparameters)
model.fit(x_train, y_train, batch_size = hp.Int('batch_size', 500, 5000, step=500, default=4000),
epochs = hp.Int('epochs', 100, 1000, step=200, default=500))
val_losses.append(model.evaluate(x_test, y_test))
self.oracle.update_trial(trial.trial_id, {'val_loss': np.mean(val_losses)})
self.save_model(trial.trial_id, model)
def create_autoencoder(hp, input_dim, output_dim):
i = Input(input_dim)
encoded = BatchNormalization()(i)
encoded = GaussianNoise(hp.Float('gaussian_noise', 1e-2, 1, sampling='log', default=5e-2))(encoded)
encoded = Dense(hp.Int('encoder_dense', 100, 300, step=50, default=64), activation='relu')(encoded)
decoded = Dropout(hp.Float('decoder_dropout_1', 1e-1, 1, sampling='log', default=0.2))(encoded)
decoded = Dense(input_dim,name='decoded')(decoded)
x = Dense(hp.Int('output_x', 32, 100, step=10, default=32),activation='relu')(decoded)
x = BatchNormalization()(x)
x = Dropout(hp.Float('x_dropout_1', 1e-1, 1, sampling='log', default=0.2))(x)
x = Dense(hp.Int('output_x', 32, 100, step=10, default=32),activation='relu')(x)
x = BatchNormalization()(x)
x = Dropout(hp.Float('x_dropout_2', 1e-1, 1, sampling='log', default=0.2))(x)
x = Dense(output_dim,activation='sigmoid',name='label_output')(x)
encoder = Model(inputs=i,outputs=encoded)
autoencoder = Model(inputs=i,outputs=[decoded, x])
# optimizer = hp.Choice('optimizer', ['adam', 'sgd'])
autoencoder.compile(optimizer=Adam(hp.Float('lr', 0.00001, 0.1, default=0.001)),
loss='sparse_binary_crossentropy',
metrics=['accuracy'])
return autoencoder, encoder
build_model = lambda hp: create_autoencoder(hp, X[:, 1:].shape[1], y.shape[1])
tuner = MyTuner(
oracle=kt.oracles.BayesianOptimization(
objective=kt.Objective('val_loss', 'min'),
max_trials=20),
hypermodel=build_model,
directory='./',
project_name='autoencoders')
tuner.search(X, (X,y), callbacks=[EarlyStopping('val_loss',patience=5),
ReduceLROnPlateau('val_loss',patience=3)])
encoder_hp = tuner.get_best_hyperparameters(1)[0]
print("Best Encoder Hyper-parameter:", encoder_hp)
best_autoencoder = tuner.get_best_models(1)[0]
RuntimeError: Model-building function did not return a valid Keras Model instance, found (<tensorflow.python.keras.engine.functional.Functional object at 0x7f74d8b849d0>, <tensorflow.python.keras.engine.functional.Functional object at 0x7f74d8b80810>)
(<tensorflow.python.keras.engine.functional.Functional object at 0x7f74d8b849d0>, <tensorflow.python.keras.engine.functional.Functional object at 0x7f74d8b80810>)
As you can see this a tuple of two Keras Model instance. This is output of create_autoencoder(hp, input_dim, output_dim).
def create_autoencoder(hp, input_dim, output_dim):
# some lines of codes
return autoencoder, encoder
From my understanding, you are not using encoder. Therefore, you can remove it in your function.
That function will be look like this
def create_autoencoder(hp, input_dim, output_dim):
# some lines of codes
return autoencoder
It will only return a Keras Model Instance.
Related
I'm going through some tutorials using the Keras functional API in Tensorflow 2, and I'm having some trouble including BatchNormalization layers when using the functional API.
Using roughly the same code:
This network trains with the sequential API and batch normalization
This network trains with the functional API, but commenting out the batch normalization layers
This network does not train using the functional API and batch normalization layers
Am I missing a step somewhere? Do I set training=true or training=false somewhere in the code?
Working Sequential Code:
#subclassed layers in keras
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.layers import SeparableConv2D
from tensorflow.keras.layers import BatchNormalization
import numpy as np
import logging
tf.get_logger().setLevel(logging.ERROR)
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
import matplotlib.pyplot as plt
%matplotlib inline
cifar_dataset = keras.datasets.cifar10
(train_images, train_labels), (test_images,
test_labels) = cifar_dataset.load_data()
EPOCHS = 128
BATCH_SIZE = 128
#standardize dataset
mean = np.mean(train_images)
stdev = np.std(train_images)
train_images = (train_images - mean)/stdev
test_images = (test_images - mean)/stdev
#change labels to one-hot
train_labels = to_categorical(train_labels, num_classes=10)
test_labels = to_categorical(test_labels, num_classes=10)
# Keras model subclassing: build your own layers
#CNN -> batch norm -> Relu
#create a class for this kind of block
class CNNBlock(layers.Layer):#inherits from layers.Layer - keeps track of what we need for back propagation
def __init__(self, out_channels, kernel_size=3, strides=(1,1)): #needs both __init__ and call functions, initialize layer
super(CNNBlock, self).__init__() #superclass layers.Layer with our new class
self.conv = layers.Conv2D(out_channels, kernel_size, padding='same',
kernel_initializer='he_normal',bias_initializer='zeros')#initialize the conv portion of this class
self.bn = layers.BatchNormalization()#initialize batch normalization in this block
def call(self, input_tensor, training=False): #what happens when this block is encountered, specify training bool for traning/evaluation
#call method (forward method in pytorch)
#take input tensor, run it though our initialized layers in __init__
x = self.conv(input_tensor)#run convolution operation
x = self.bn(x, training=training)#batch norm
x = tf.nn.relu(x)#activation function for this layer
return x
class CNNBlock_init(layers.Layer):#inherits from layers.Layer - keeps track of what we need for back propagation
def __init__(self, out_channels, input_size, kernel_size=3): #needs both __init__ and call functions, initialize layer
super(CNNBlock_init, self).__init__() #superclass layers.Layer with our new class - make sure new class name matches
self.input_size = input_size
self.conv = layers.Conv2D(out_channels, kernel_size,
input_shape=input_size, #first layer needs input shape to build properly
padding='same')#initialize the conv portion of this class
self.bn = layers.BatchNormalization()#initialize batch normalization in this block
def call(self, input_tensor, training=False): #what happens when this block is encountered, specify training bool for traning/evaluation
#call method (forward method in pytorch)
#take input tensor, run it though our initialized layers in __init__
x = self.conv(input_tensor,input_shape=self.input_size)#run convolution operation
x = self.bn(x, training=training)#batch norm
x = tf.nn.relu(x)#activation function for this layer
return x
#build model with this
model = keras.Sequential(
[
CNNBlock(64,kernel_size=4,strides=(2,2)),
Dropout(0.2),
CNNBlock(64,kernel_size=2,strides=(2,2)),
Dropout(0.2),
CNNBlock(32),
Dropout(0.2),
CNNBlock(32),
MaxPooling2D(pool_size=(2,2), strides=2),
Dropout(0.2),
Flatten(),
Dense(64, activation='relu',#dense layers to combine features
kernel_initializer='he_normal',
bias_initializer='zeros'),
Dropout(0.2),
Dense(10, activation='softmax',#softmax for classification
kernel_initializer='glorot_uniform',
bias_initializer='zeros')
])
#compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
#model.build(input_shape=(32,32,3))
#model.summary()
#train model
history = model.fit(
train_images, train_labels,
validation_data=(test_images,test_labels),
epochs=EPOCHS, batch_size=BATCH_SIZE,
verbose=1, shuffle=True) #verbose 1 is cool gives time for each epoch
#evaluate model
import matplotlib.pyplot as plt
%matplotlib inline
def plot_error(history):
history_dict_vals = history.__dict__['history']
history_x = history.epoch
plt.plot(history_x,history_dict_vals['accuracy'],'r-', label='training accuracy')
plt.plot(history_x,history_dict_vals['val_accuracy'],'g-', label='test accuracy')
plt.axis([0,len(history_x),0.0,1])
plt.xlabel('training epochs')
plt.ylabel('accuracy')
plt.legend()
plt.show()
print(f"Final test accuracy = {history_dict_vals['val_accuracy'][-1]}")
plot_error(history)
Working Functional Code:
# same convolutional structure but with the keras functional API
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.layers import SeparableConv2D
from tensorflow.keras.layers import BatchNormalization
from tensorflow.keras.layers import Input
from tensorflow.keras.models import Model
import numpy as np
import logging
tf.get_logger().setLevel(logging.ERROR)
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
import matplotlib.pyplot as plt
%matplotlib inline
cifar_dataset = keras.datasets.cifar10
(train_images, train_labels), (test_images,
test_labels) = cifar_dataset.load_data()
EPOCHS = 128
BATCH_SIZE = 128
#standardize dataset
mean = np.mean(train_images)
stdev = np.std(train_images)
train_images = (train_images - mean)/stdev
test_images = (test_images - mean)/stdev
#change labels to one-hot
train_labels = to_categorical(train_labels, num_classes=10)
test_labels = to_categorical(test_labels, num_classes=10)
# Keras model subclassing: build your own layers
#CNN -> batch norm -> Relu
#create a class for this kind of block
class CNNBlock(layers.Layer):#inherits from layers.Layer - keeps track of what we need for back propagation
def __init__(self, out_channels, kernel_size=3, strides=(1,1)): #needs both __init__ and call functions, initialize layer
super(CNNBlock, self).__init__() #superclass layers.Layer with our new class
self.conv = layers.Conv2D(out_channels, kernel_size, padding='same',
kernel_initializer='he_normal',bias_initializer='zeros')#initialize the conv portion of this class
#self.bn = layers.BatchNormalization()#initialize batch normalization in this block
def call(self, input_tensor, training=False): #what happens when this block is encountered, specify training bool for traning/evaluation
#call method (forward method in pytorch)
#take input tensor, run it though our initialized layers in __init__
x = self.conv(input_tensor)#run convolution operation
#x = self.bn(x, training=training)#batch norm
x = tf.nn.relu(x)#activation function for this layer
return x
class CNNBlock_init(layers.Layer):#inherits from layers.Layer - keeps track of what we need for back propagation
def __init__(self, out_channels, input_size, kernel_size=3): #needs both __init__ and call functions, initialize layer
super(CNNBlock_init, self).__init__() #superclass layers.Layer with our new class - make sure new class name matches
self.input_size = input_size
self.conv = layers.Conv2D(out_channels, kernel_size,
input_shape=input_size, #first layer needs input shape to build properly
padding='same')#initialize the conv portion of this class
#self.bn = layers.BatchNormalization()#initialize batch normalization in this block
def call(self, input_tensor, training=False): #what happens when this block is encountered, specify training bool for traning/evaluation
#call method (forward method in pytorch)
#take input tensor, run it though our initialized layers in __init__
x = self.conv(input_tensor,input_shape=self.input_size)#run convolution operation
#x = self.bn(x, training=training)#batch norm
x = tf.nn.relu(x)#activation function for this layer
return x
#build model with this
#Build the model with the Keras functional API
input_shape = (32,32,3)
chanDim = -1
#define model with first inputs
inputs = Input(shape=input_shape)
#functional API passing layers through
x = CNNBlock(64,kernel_size=4,strides=(2,2))(inputs)
x = Dropout(0.2)(x)
x = CNNBlock(64,kernel_size=2,strides=(2,2))(x)
x = Dropout(0.2)(x)
x = CNNBlock(64)(x)
x = MaxPooling2D(pool_size=(2,2), strides=2)(x)
x = Dropout(0.2)(x)
x = Flatten()(x)
x = Dense(64, activation='relu',#dense layers to combine features
kernel_initializer='he_normal',
bias_initializer='zeros')(x)
x = Dropout(0.2)(x)
y = Dense(10, activation='softmax',#softmax for classification
kernel_initializer='glorot_uniform',
bias_initializer='zeros')(x)
#initialize model with inputs and outputs
model = Model(inputs, y, name='convnet_func')
#compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
#train model
history = model.fit(
train_images, train_labels,
validation_data=(test_images,test_labels),
epochs=EPOCHS, batch_size=BATCH_SIZE,
verbose=1, shuffle=True) #verbose 1 is cool gives time for each epoch
#evaluate model
import matplotlib.pyplot as plt
%matplotlib inline
def plot_error(history):
history_dict_vals = history.__dict__['history']
history_x = history.epoch
plt.plot(history_x,history_dict_vals['accuracy'],'r-', label='training accuracy')
plt.plot(history_x,history_dict_vals['val_accuracy'],'g-', label='test accuracy')
plt.axis([0,len(history_x),0.0,1])
plt.xlabel('training epochs')
plt.ylabel('accuracy')
plt.legend()
plt.show()
print(f"Final test accuracy = {history_dict_vals['val_accuracy'][-1]}")
plot_error(history)
Unfortunately the model does not train when I remove the comments around the batch normalization layers.
import pandas as pd
import matplotlib.pyplot as plt
import re
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM,Dense, Dropout, SpatialDropout1D
from tensorflow.keras.layers import Embedding
from tensorflow.keras.optimizers import Adam
from sklearn.model_selection import train_test_split
data = pd.read_csv("./emails.csv")
print(data.head())
data = data[['text','email_sentiment']]
data['text'] = data['text'].apply(lambda x: x.lower())
data['text'] = data['text'].apply((lambda x: re.sub('[^a-zA-z0-9\s]','',x)))
print(data.head())
max_fatures = 50000
max_seq_length = 250
tokenizer = Tokenizer(num_words=max_fatures,filters='!"#$%&()*+,-./:;<=>?#[\]^_`{|}~', lower=True)
tokenizer.fit_on_texts(data['text'].values)
word_index = tokenizer.word_index
X = tokenizer.texts_to_sequences(data['text'].values)
X = pad_sequences(X,maxlen=max_seq_length)
Y= pd.get_dummies(data['email_sentiment']).values
X_train,Y_train = train_test_split(X,Y, test_size = 0.10, random_state = 42)
embedding_vector_length = 100
lstm_out= 196
model = Sequential()
model.add(Embedding(max_fatures, embedding_vector_length, input_length=X.shape[1]))
model.add(SpatialDropout1D(0.2))
model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(3,activation='softmax'))
model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
print(model.summary())
Error occured:
X_train,Y_train = train_test_split(X,Y, test_size = 0.10, random_state = 42)
ValueError: too many values to unpack (expected 2)
Unable to train X_train with the dataset due to value errors. The X_train value consist of various emails which are categorized to postive negative and neutral sentiment based on LSTM classes 3
When I try to use the TimeSeriesGenerator function, my Keras LSTM NN starts training for a few moments but then gives a ValueError message. What's wrong? I wonder how it can start training and then get an error.
My similar implementation without this function runs smoothly but then the quality of the predictions are awful (and I'm not sure that this function, once successfully implemented, would make a difference).
See the code below:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Nadam
from tensorflow.keras.layers import Input, LSTM, Dense
from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, TerminateOnNaN
from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
data = pd.read_excel('example.xlsx',usecols=['wave','wind','current','X','Y','RZ'])
data = data.apply(lambda x: (x - np.mean(x)) / np.std(x))
n_cutoff = 200
X = np.array(data.loc[n_cutoff:,['wave','wind']])
Y = np.array(data.loc[n_cutoff:,['RZ']])
X = X.reshape(len(X),2)
X = np.append(X, [[0]*np.size(X, axis=1)], axis=0)
Y = Y.reshape(len(Y),1)
Y = np.insert(Y, 0, 0)
n_lag = 3
n_batch = 15
n = int(0.75*len(X))
generator = TimeseriesGenerator(X, Y, length=n_lag, batch_size=n_batch)
inputs = Input(shape=(n_lag,2))
hidden1 = LSTM(units=100,
activation='softmax',
recurrent_activation='linear',
dropout=0.5,
recurrent_dropout=0.5,
return_sequences=True)(inputs)
hidden2 = LSTM(units=30,
activation='softmax',
recurrent_activation='linear',
dropout=0.5,
recurrent_dropout=0.5,
return_sequences=False)(hidden1)
outputs = Dense(units=1,
activation='linear')(hidden2)
model = Model(inputs=inputs, outputs=outputs)
optimizer = Nadam(learning_rate=1e-2, beta_1=0.95, beta_2=0.9, epsilon=1e-7)
model.compile(loss='mean_squared_error', optimizer=optimizer)
history = model.fit(generator,
verbose=1,
steps_per_epoch=int(n/n_batch),
epochs=1,
shuffle=False,
callbacks=[EarlyStopping(monitor='loss', min_delta=0, patience=20, verbose=1, mode='auto'),
ReduceLROnPlateau(monitor='loss', factor=0.5, patience=10, verbose=1, mode='auto', cooldown=1),
TerminateOnNaN()])
Y_hat = model.predict(X[n:])
I'm getting back into python and have been trying out some stuff with tensorflow and keras. I wanted to use the plot_model function and after sorting out some graphviz issues I am now getting this error -
TypeError: add_node() received a non node class object:
I've tried to find an answer myself but have come up short, as the only answer I found with this error didn't seem to be to do with tf. Any suggestions or alternative ideas would be greatly appreciated.
Here's the code and error message - my first question on here so sorry if I missed anything, just let me know.
I'm using miniconda3 with python 3.8
import tensorflow as tf
from tensorflow.keras import Model
from tensorflow.keras.layers import Conv2D, MaxPool2D, Flatten, Dense, Dropout
from tensorflow.keras.datasets import mnist
from tensorflow.keras.utils import plot_model
from tensorflow.keras.callbacks import EarlyStopping
from numpy import argmax
from matplotlib import pyplot
from random import randint
tf.keras.backend.set_floatx("float64")
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
x_train = x_train[..., tf.newaxis]
x_test = x_test[..., tf.newaxis]
class mnist_model(Model):
def __init__(self):
super(mnist_model, self).__init__()
self.conv = Conv2D(32, 3, activation = tf.nn.leaky_relu, kernel_initializer = 'he_uniform', input_shape = (28, 28, 3))
self.pool = MaxPool2D((2,2))
self.flat = Flatten()
self.den1 = Dense(128, activation = tf.nn.relu, kernel_initializer = 'he_normal')
self.drop = Dropout(0.25)
self.den2 = Dense(10, activation = tf.nn.softmax)
def call(self, inputs):
n = self.conv(inputs)
n = self.pool(n)
n = self.flat(n)
n = self.den1(n)
n = self.drop(n)
return self.den2(n)
model = mnist_model()
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
limit = EarlyStopping(monitor = 'val_loss', patience = 5)
history = model.fit(x_train, y_train, batch_size=64, epochs = 1, verbose = 2, validation_split = 0.15, steps_per_epoch = 100, callbacks = [limit])
print("\nTraining finished\n\nTesting 10000 samples")
model.evaluate(x_test, y_test, verbose = 1)
print("Testing finished\n")
plot_model(model, show_shapes = True, rankdir = 'LR')
##################################################################################################################################################################
## Error message: ##
Train on 51000 samples, validate on 9000 samples
Training finished
Testing 10000 samples
10000/10000 [==============================] - 7s 682us/sample - loss: 0.2447 - accuracy: 0.9242
Testing finished
Traceback (most recent call last):
File "C:\Users\Thomas\Desktop\Various Python\Tensorflow\Tensorflow_experimentation\tc_mnist.py", line 60, in <module>
plot_model(model, show_shapes = True, rankdir = 'LR')
File "C:\Users\Thomas\miniconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\utils\vis_utils.py", line 283, in plot_model
dpi=dpi)
File "C:\Users\Thomas\miniconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\utils\vis_utils.py", line 131, in model_to_dot
dot.add_node(node)
File "C:\Users\Thomas\miniconda3\envs\tensorflow\lib\site-packages\pydotplus\graphviz.py", line 1281, in add_node
'class object: {}'.format(str(graph_node))
TypeError: add_node() received a non node class object: <pydotplus.graphviz.Node object at 0x00000221C7E3E888>`
I think root-cause of the issue is with shape inference of Subclassed model where model.summary shows multiple as Output Shape. I added a model call within the subclassed model as shown below.
def model(self):
x = tf.keras.layers.Input(shape=(28, 28, 1))
return Model(inputs=[x], outputs=self.call(x))
With this modification, shape inference is automatic in Functional API. As Functional and Sequential model as static graphs of layers, we can get the shape inference easily. However, subclassed model is a piece of python code (a call method) and there is no graph of layers to infer easily. We cannot know how layers are connected to each other (because that's defined in the body of call, not as an explicit data structure), so we cannot infer input / output shapes.
Please check full code here for your reference.
The problem with this code is that I am giving classifier,
One hot encoded data:
Means:
X-train, X-test, y_train, y_test is one hot encoded.
But the classifier is predicting the output:
y_pred_test, y_pred_train in Numerical form
(which I think is incorrect as well). Can anyone help with this?
This is a dummy example so no concern over low accuracy but just to know why it's predicting the output in not One Hot encoded form.
Thanks !
# -*- coding: utf-8 -*-
import numpy as np
import pandas as pd
x=pd.DataFrame()
x['names']= np.arange(1,10)
x['Age'] = np.arange(1,10)
y=pd.DataFrame()
y['target'] = np.arange(1,10)
from sklearn.preprocessing import OneHotEncoder, Normalizer
ohX= OneHotEncoder()
x_enc = ohX.fit_transform(x).toarray()
ohY = OneHotEncoder()
y_enc = ohY.fit_transform(y).toarray()
print (x_enc)
print("____")
print (y_enc)
import keras
from keras import regularizers
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.models import load_model
from keras.layers.advanced_activations import LeakyReLU
marker="-------"
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split
def create_model(learn_rate=0.001):
model = Sequential()
model.add(Dense(units = 15, input_dim =18,kernel_initializer= 'normal', activation="tanh"))
model.add(Dense(units=9, activation = "softmax"))
model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=['accuracy'])
return model
if __name__=="__main__":
X_train, X_test, y_train, y_test = train_test_split(x_enc, y_enc, test_size=0.33, random_state=42)
print ("\n\n",marker*5," Classification\nX_train shape is: ",X_train.shape,"\tX_test shape is:",X_test.shape)
print ("\ny_train shape is: ",y_train.shape,"\t y_test shape is:",y_test.shape,"\n\n")
norm = Normalizer()
#model
X_train = norm.fit_transform(X_train)
X_test = norm.transform(X_test)
earlyStopping=keras.callbacks.EarlyStopping(monitor='val_loss', patience=0, verbose=0, mode='auto')
model = KerasClassifier(build_fn=create_model, verbose=0)
fit_params={'callbacks': [earlyStopping]}
#grid
# batch_size =[50,100,200, 300,400]
epochs = [2,5]
learn_rate=[0.1,0.001]
param_grid = dict( epochs = epochs, learn_rate = learn_rate)
grid = GridSearchCV(estimator = model, param_grid = param_grid, n_jobs=1)
#Predicting
print (np.shape(X_train), np.shape(y_train))
y_train = np.reshape(y_train, (-1,np.shape(y_train)[1]))
print ("y_train shape after reshaping", np.shape(y_train))
grid_result = grid.fit(X_train, y_train, callbacks=[earlyStopping])
print ("grid score using params: ", grid_result.best_score_, " ",grid_result.best_params_)
#scores
print("SCORES")
print (grid_result.score(X_test,y_test))
# summarize results
#print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
#means = grid_result.cv_results_['mean_test_score']
#stds = grid_result.cv_results_['std_test_score']
#params = grid_result.cv_results_['params']
#for mean, stdev, param in zip(means, stds, params):
# print("%f (%f) with: %r" % (mean, stdev, param))
print("\n\n")
print("y_test is",y_test)
y_hat_test = grid.predict(X_test)
y_hat_train = grid.predict(X_train)
print("y_hat_test is ", y_hat_test)