Assignment 5.1.pdf

'2.5.0'
<__array_function__ internals>:5: VisibleDeprecationWarning: Creating an ndarray fro
m ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays w
ith different lengths or shapes) is deprecated. If you meant to do this, you must sp
ecify 'dtype=object' when creating the ndarray

C:Userswaleeanaconda3libsite-packageskerasdatasetsimdb.py:155: VisibleDeprec
ationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-t
uple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated.
If you meant to do this, you must specify 'dtype=object' when creating the ndarray

x_train, y_train = np.array(xs[:idx]), np.array(labels[:idx])

C:Userswaleeanaconda3libsite-packageskerasdatasetsimdb.py:156: VisibleDeprec
ationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-t
uple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated.
If you meant to do this, you must specify 'dtype=object' when creating the ndarray

x_test, y_test = np.array(xs[idx:]), np.array(labels[idx:])

[1,

14,

22,

16,

43,

530,

973,

1622,

1385,

65,

458,

4468,

66,

3941,

4,

173,

36,

256,

5,

25,

100,

43,

838,

112,

50,

670,

2,

9,

35,

480,

284,

5,

In [1]: # Import libraries

from tensorflow import keras

from tensorflow.keras.datasets import mnist

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense, Dropout

from tensorflow.keras.optimizers import RMSprop

In [2]: import keras

keras.__version__

Out[2]:
In [3]: # Load the dataset

from keras.datasets import imdb

(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=1000
In [4]: train_data[0]

Out[4]:

150,

4,

172,

112,

167,

2,

336,

385,

39,

4,

172,

4536,

1111,

17,

546,

38,

13,

447,

4,

192,

50,

16,

6,

147,

2025,

19,

14,

22,

4,

1920,

4613,

469,

4,

22,

71,

87,

12,

16,

43,

530,

38,

76,

15,

13,

1247,

4,

22,

17,

515,

17,

12,

16,

626,

18,

2,

5,

62,

386,

12,

8,

316,

8,

106,

5,

4,

2223,

5244,

16,

480,

66,

3785,

33,

4,

130,

12,

16,

38,

619,

5,

25,

124,

51,

36,

135,

48,

25,

1415,

33,

6,

22,

12,

215,

28,

77,

52,

5,

14,

407,

16,

82,

2,

8,

4,

107,

117,

5952,

15,

256,

4,

2,

7,

3766,

5,

723,

36,

71,

43,

530,

476,

26,

400,

317,

46,

7,

4,

2,

1029,

13,

104,

88,

4,

381,

15,

297,

98,

32,

2071,

56,

26,

141,

6,

194,

7486,

18,

4,

226,

22,

21,

134,

476,

26,

480,

5,

144,

30,

5535,

18,

51,

36,

28,

224,

92,

25,

104,

4,

226,

65,

16,

38,

1334,

88,

12,

16,

283,

5,

16,

4472,

113,

103,

32,

15,

16,

5345,

19,

178,

32]
1
9999
In [5]: train_labels[0]

Out[5]:
In [6]: #Due to 10,000 most recent words restriction, no word index will exceed 10,000:

max([max(sequence) for sequence in train_data])
Out[6]:
In [7]: # word_index is a dictionary mapping words to an integer index

word_index = imdb.get_word_index()

# We reverse it, mapping integer indices to words

reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])

# We decode the review; note that our indices were offset by 3

# because 0, 1 and 2 are reserved indices for "padding", "start of sequence", and "u
decoded_review = ' '.join([reverse_word_index.get(i - 3, '?') for i in train_data[0]
decoded_review

"? this film was just brilliant casting location scenery story direction everyone's
really suited the part they played and you could just imagine being there robert ? i
s an amazing actor and now the same being director ? father came from the same scott
ish island as myself so i loved the fact there was a real connection with this film
the witty remarks throughout the film were great it was just brilliant so much that
i bought the film as soon as it was released for ? and would recommend it to everyon
e to watch and the fly fishing was amazing really cried at the end it was so sad and
you know what they say if you cry at a film it must have been good and this definite
ly was also ? to the two little boy's that played the ? of norman and paul they were
just brilliant children are often left out of the ? list i think because the stars t
hat play them all grown up are such a big profile for the whole film but these child
ren are amazing and should be praised for what they have done don't you think the wh
ole story was so lovely because it was true and was someone's life after all that wa
s shared with us all"
array([0., 1., 1., ..., 0., 0., 0.])
C:Userswaleeanaconda3libsite-packagestensorflowpythonkerasoptimizer_v2opti
mizer_v2.py:374: UserWarning: The `lr` argument is deprecated, use `learning_rate` i
nstead.

warnings.warn(

Out[7]:
In [8]: import numpy as np

def vectorize_sequences(sequences, dimension=10000):

results = np.zeros((len(sequences), dimension))

for i, sequence in enumerate(sequences):

results[i, sequence] = 1. # set specific indices of results[i] to 1s

return results

# training data

x_train = vectorize_sequences(train_data)

# test data

x_test = vectorize_sequences(test_data)

In [9]: # sample train data

x_train[0]

Out[9]:
In [10]: # Vectorized labels

y_train = np.asarray(train_labels).astype('float32')

y_test = np.asarray(test_labels).astype('float32')

In [11]: #The Keras implementation

from keras import models

from keras import layers

model = models.Sequential()

model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))

model.add(layers.Dense(16, activation='relu'))

model.add(layers.Dense(1, activation='sigmoid'))

In [12]: model.compile(optimizer='rmsprop',

loss='binary_crossentropy',

metrics=['accuracy'])

In [13]: from keras import optimizers

model.compile(optimizer=optimizers.RMSprop(lr=0.001),



from keras import losses

from keras import metrics

model.compile(optimizer=optimizers.RMSprop(lr=0.001),

loss=losses.binary_crossentropy,

metrics=[metrics.binary_accuracy])

In [14]: x_val = x_train[:10000]

Epoch 1/20

30/30 [==============================] - 63s 419ms/step - loss: 0.6034 - binary_accu
racy: 0.6815 - val_loss: 0.3960 - val_binary_accuracy: 0.8684

Epoch 2/20

30/30 [==============================] - 1s 35ms/step - loss: 0.3324 - binary_accura
cy: 0.9012 - val_loss: 0.3173 - val_binary_accuracy: 0.8795

Epoch 3/20


Epoch 4/20


Epoch 5/20


Epoch 6/20


Epoch 7/20


Epoch 8/20


Epoch 9/20


Epoch 10/20


Epoch 11/20


Epoch 12/20


Epoch 13/20


Epoch 14/20


Epoch 15/20


Epoch 16/20


Epoch 17/20


Epoch 18/20


Epoch 19/20


Epoch 20/20

partial_x_train = x_train[10000:]
y_val = y_train[:10000]

partial_y_train = y_train[10000:]
In [15]: history = model.fit(partial_x_train,

partial_y_train,

epochs=20,

batch_size=512,

validation_data=(x_val, y_val))


{'loss': [0.52616947889328, 0.31405124068260193, 0.23073254525661469, 0.180891424417
49573, 0.15155072510242462, 0.11920173466205597, 0.09928888082504272, 0.080168023705
48248, 0.06698485463857651, 0.05347074940800667, 0.04215071722865105, 0.032081160694
36073, 0.024609368294477463, 0.020660480484366417, 0.012686074711382389, 0.009793567
471206188, 0.008989308960735798, 0.004304599016904831, 0.008949910290539265, 0.00232
2724089026451], 'binary_accuracy': [0.7734000086784363, 0.902733325958252, 0.9275333
285331726, 0.9417999982833862, 0.9536666870117188, 0.9657999873161316, 0.97226667404
1748, 0.9791333079338074, 0.9835333228111267, 0.9874666929244995, 0.991133332252502
4, 0.9941333532333374, 0.9962666630744934, 0.9971333146095276, 0.9986666440963745,
0.9995999932289124, 0.9989333152770996, 0.9998666644096375, 0.9980666637420654, 0.99
99333620071411], 'val_loss': [0.3960328698158264, 0.3172730803489685, 0.280055940151
2146, 0.29149702191352844, 0.27728235721588135, 0.2915444076061249, 0.31624060869216
92, 0.31750768423080444, 0.3556799292564392, 0.3607264757156372, 0.4032689929008484,
0.4143247604370117, 0.47000113129615784, 0.4742533564567566, 0.5077142715454102, 0.5
462456345558167, 0.5740538835525513, 0.6180163621902466, 0.6355932950973511, 0.66371
50645256042], 'val_binary_accuracy': [0.868399977684021, 0.8794999718666077, 0.89190
00029563904, 0.8844000101089478, 0.8912000060081482, 0.888700008392334, 0.8773999810
218811, 0.8851000070571899, 0.8737000226974487, 0.881600022315979, 0.874899983406066
9, 0.880299985408783, 0.8665000200271606, 0.8755999803543091, 0.8741000294685364, 0.
8708999752998352, 0.8708000183105469, 0.8657000064849854, 0.8691999912261963, 0.8687
000274658203]}

In [16]: history_dict = history.history

history_dict.keys()

print(history_dict)

In [17]: import matplotlib.pyplot as plt

acc = history.history['binary_accuracy']

val_acc = history.history['val_binary_accuracy']

#acc = history.history['acc']

#val_acc = history.history['val_acc']

loss = history.history['loss']

val_loss = history.history['val_loss']

epochs = range(1, len(acc) + 1)

# "bo" is for "blue dot"

plt.plot(epochs, loss, 'bo', label='Training loss')

# b is for "solid blue line"

plt.plot(epochs, val_loss, 'b', label='Validation loss')

plt.title('Training and validation loss')

plt.xlabel('Epochs')

plt.ylabel('Loss')

plt.legend()

plt.show()

In [18]: plt.clf() # clear figure

Epoch 1/4

49/49 [==============================] - 4s 22ms/step - loss: 0.5358 - accuracy: 0.7
571

Epoch 2/4

079

Epoch 3/4

321

Epoch 4/4

411

782/782 [==============================] - 8s 2ms/step - loss: 0.3059 - accuracy: 0.
8796

[0.3059064447879791, 0.8795599937438965]
array([[0.22144157],

[0.999939 ],

[0.9658772 ],

...,

#acc_values = history_dict['acc']

#val_acc_values = history_dict['val_acc']

acc = history.history['binary_accuracy']

val_acc = history.history['val_binary_accuracy']

plt.plot(epochs, acc, 'bo', label='Training acc')

plt.plot(epochs, val_acc, 'b', label='Validation acc')

plt.title('Training and validation accuracy')

plt.xlabel('Epochs')

plt.ylabel('Loss')

plt.legend()

plt.show()

In [19]: model = models.Sequential()

model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))

model.add(layers.Dense(16, activation='relu'))

model.add(layers.Dense(1, activation='sigmoid'))

model.compile(optimizer='rmsprop',



model.fit(x_train, y_train, epochs=4, batch_size=512)

results = model.evaluate(x_test, y_test)
In [20]: results

Out[20]:
In [21]: model.predict(x_test)

Out[21]:

[0.16461223],

[0.10813493],

[0.617234 ]], dtype=float32)
In [ ]:

Assignment 5.1.pdf

More Related Content

Similar to Assignment 5.1.pdf (20)

More from dash41 (9)

Recently uploaded (20)

Assignment 5.1.pdf