oper655_fa2019/tf5.Rmd at master · AFIT-R/oper655_fa2019 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
---
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```


## diving into the code

```{python}
imdb, info = tfds.load("imdb_reviews/subwords8k",
                       with_info = True,
                       as_supervised = True,
                       data_dir = "data")
```


```{python}
train_data, test_data = imdb['train'], imdb['test']
```

Learn more <a target=" " href='https://www.tensorflow.org/datasets/api_docs/python/tfds/features/text/SubwordTextEncoder'>HERE</a>

```{python}
tokenizer = info.features['text'].encoder
```

```{python}
print(tokenizer.subwords)
```

How the tokenizer encodes strings as numerical values using the vocabulary and then decodes them as well

```{python}
sample_string = "Tensorflow, from basics to mastery"

tokenized_string = tokenizer.encode(sample_string)

print("Tokenized string is {}".format(tokenized_string))

original_string = tokenizer.decode(tokenized_string)
print("The original string: {}".format(original_string))
```

```{python}
for ts in tokenized_string:
  print("{} -----> {}".format(ts,tokenizer.decode([ts])))
```


```{python}
embedding_dim = 64

model3 = tf.keras.Sequential([
  tf.keras.layers.Embedding(tokenizer.vocab_size,
                            embedding_dim),
  tf.keras.layers.GlobalAveragePooling1D(),
  tf.keras.layers.Dense(6,activation = "relu"),
  tf.keras.layers.Dense(1,activation = "sigmoid")
])

model3.summary()
```


```{python}
num_epochs = 10

model3.compile(loss = "binary_crossentropy",
               optimizer = "adam",
               metrics = ['accuracy'])

history = model3.fit(train_data,
                     epochs = num_epochs,
                     validation_data = test_data)
```

```{python}
import matplotlib.pyplot as plt

def plot_graphs(history,string):
  plt.plot(history.history[string])
  plt.plot(history.history["val_"+string])
  plt.xlabel("Epochs")
  plt.ylabel(string)
  plt.legend([string, "val_"+string])
  plt.show()

plot_graphs(history, "acc")
plot_graphs(history, "loss")
```