sentiment_analyser_app_with_lstm_network.py

# -*- coding: utf-8 -*-
"""Sentiment Analyser App with LSTM network.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1xIRgpiUQHwuGWhYHC7103aOJGI7I-mTa
"""

import torch

#Get system variables for using later in GPU and file locations
from os.path import exists
from wheel.pep425tags import get_abbr_impl, get_impl_ver, get_abi_tag
platform='{}{}-{}'.format(get_abbr_impl(), get_impl_ver(), get_abi_tag())
cuda_output = !ldconfig -p|grep cudart.so|sed -e 's/.*\.\([0-9]*\)\.\([0-9]*\)$/cu\1\2/'
accelerator = cuda_output[0] if exists('/dev/nvidia0') else 'cpu'

import torch

import torch
import numpy as np

#check if cuda is available
train_on_GPU=torch.cuda.is_available();

if not train_on_GPU:
    print('Not available')
else:
    print('Available')

#download the required data and place it in appropriate directory
!mkdir -p data
!wget -cq https://github.com/udacity/deep-learning-v2-pytorch/raw/master/sentiment-rnn/data/labels.txt -O data/labels.txt
!wget -cq https://github.com/udacity/deep-learning-v2-pytorch/raw/master/sentiment-rnn/data/reviews.txt -O data/reviews.txt

import numpy as np

#read data//Open the first movie review and recursively search through the whole file

with open('data/reviews.txt','r') as f:
  reviews=f.read()
with open('data/labels.txt','r') as f:
  labels=f.read()

"""#Data Preprocessing:


*   Remove Punctuation
*   Split text into each review using \n as delimiter
*   COmbine all the reviews into one large string
"""

from string import punctuation

print(punctuation) #the characters we are getting rid off

# get rid of punctuation
reviews = reviews.lower() # lowercase, standardize
all_text = ''.join([c for c in reviews if c not in punctuation])

# split by new lines and spaces
reviews_split = all_text.split('\n')
all_text = ' '.join(reviews_split)

# creating a list of words
words = all_text.split() #tokenize the string

"""#Encoding the words

The embedding lookup requires that we pass in integers to our network. The easiest way to do this is to create dictionaries that map the words in the vocabulary to integers. Then we can convert each of our reviews into integers so they can be passed into the network.The fastest way to do this is by using word2vec which converts words into vectors;which helps in the lookup of words.
"""

from collections import Counter

## Build a dictionary that maps words to integers
counts = Counter(words)
vocab = sorted(counts, key=counts.get, reverse=True)
vocab_to_int = {word: ii for ii, word in enumerate(vocab, 1)}

## use the dict to tokenize each review in reviews_split
## store the tokenized reviews in reviews_ints
reviews_ints = []
for review in reviews_split:
    reviews_ints.append([vocab_to_int[word] for word in review.split()])

# stats about vocabulary
print('Unique words: ', len((vocab_to_int)))  # should ~ 74000+
print()

# print tokens in first review
print('Tokenized review: \n', reviews_ints[:1])

"""#Encoding the labels

Our labels are "positive" or "negative". To use these labels in our network, we need to convert them to 0 and 1.
"""

# 1=positive, 0=negative label conversion
labels_split = labels.split('\n')
encoded_labels = np.array([1 if label == 'positive' else 0 for label in labels_split])

"""# Removing Outliers

1. Getting rid of extremely long or short reviews; the outliers
2. Padding/truncating the remaining data so that we have reviews of the same length.
"""

# outlier review stats
review_lens = Counter([len(x) for x in reviews_ints])
print("0-length reviews: {}".format(review_lens[0]))
print("Max rev length: {}".format(max(review_lens)))

print('No. of revs before removing outliers: ', len(reviews_ints))

## remove any reviews/labels with zero length from the reviews_ints list.

# get indices of any reviews with length 0
non_zero_idx = [ii for ii, review in enumerate(reviews_ints) if len(review) != 0]

# remove 0-length reviews and their labels
reviews_ints = [reviews_ints[ii] for ii in non_zero_idx]
encoded_labels = np.array([encoded_labels[ii] for ii in non_zero_idx])

print('No. of revs after removing outliers: ', len(reviews_ints))

"""# Padding sequences

To deal with both short and very long reviews, we'll pad or truncate all our reviews to a specific length. For reviews shorter than some `seq_length`, we'll pad with 0s. For reviews longer than `seq_length`, we can truncate them to the first `seq_length` words. A good `seq_length`, in this case, is 200.
"""

def pad_features(reviews_ints, seq_length):
    ''' Return features of review_ints, where each review is padded with 0's 
        or truncated to the input seq_length.
    '''
    
    # getting the correct rows x cols shape
    features = np.zeros((len(reviews_ints), seq_length), dtype=int)

    # for each review, I grab that review and 
    for i, row in enumerate(reviews_ints):
        features[i, -len(row):] = np.array(row)[:seq_length]
    
    return features

# Testing the implementation!

seq_length = 200

features = pad_features(reviews_ints, seq_length=seq_length)

## test statements
assert len(features)==len(reviews_ints), "Your features should have as many rows as reviews."
assert len(features[0])==seq_length, "Each feature row should contain seq_length values."

# print first 10 values of the first 30 batches 
print(features[:30,:10])

"""#$ Training $$ Validation $ And Test"""

split_frac = 0.8

## split data into training, validation, and test data (features and labels, x and y)

split_idx = int(len(features)*split_frac)
train_x, remaining_x = features[:split_idx], features[split_idx:]
train_y, remaining_y = encoded_labels[:split_idx], encoded_labels[split_idx:]

test_idx = int(len(remaining_x)*0.5)
val_x, test_x = remaining_x[:test_idx], remaining_x[test_idx:]
val_y, test_y = remaining_y[:test_idx], remaining_y[test_idx:]

## print out the shapes of your resultant feature data
print("\t\t\tFeature Shapes:")
print("Train set: \t\t{}".format(train_x.shape), 
      "\nValidation set: \t{}".format(val_x.shape),
      "\nTest set: \t\t{}".format(test_x.shape))

"""---
# ***DataLoaders and Batching***

After creating training, test, and validation data, we can create DataLoaders for this data by following two steps:
1. Create a known format for accessing our data, using TensorDataset which takes in an input set of data and a target set of data with the same first dimension, and creates a dataset.
2. Create DataLoaders and batch our training, validation, and test Tensor datasets.

```
train_data = TensorDataset(torch.from_numpy(train_x), torch.from_numpy(train_y))
train_loader = DataLoader(train_data, batch_size=batch_size)
```

This is an alternative to creating a generator function for batching our data into full batches.
"""

import torch
from torch.utils.data import TensorDataset, DataLoader

# create Tensor datasets
train_data = TensorDataset(torch.from_numpy(train_x), torch.from_numpy(train_y))
valid_data = TensorDataset(torch.from_numpy(val_x), torch.from_numpy(val_y))
test_data = TensorDataset(torch.from_numpy(test_x), torch.from_numpy(test_y))

# dataloaders
batch_size = 50

# make sure to SHUFFLE your data
train_loader = DataLoader(train_data, shuffle=True, batch_size=batch_size)
valid_loader = DataLoader(valid_data, shuffle=True, batch_size=batch_size)
test_loader = DataLoader(test_data, shuffle=True, batch_size=batch_size)

# obtain one batch of training data
dataiter = iter(train_loader)
sample_x, sample_y = dataiter.next()

print('Sample input size: ', sample_x.size()) # batch_size, seq_length
print('Sample input: \n', sample_x)
print()
print('Sample label size: ', sample_y.size()) # batch_size
print('Sample label: \n', sample_y)

"""---
# Sentiment Network with PyTorch


<img src="https://github.com/udacity/deep-learning-v2-pytorch/blob/master/sentiment-rnn/assets/network_diagram.png?raw=1" width=40%>

The layers are as follows:
1. An embedding layer that converts our word tokens (integers) into embeddings of a specific size.
2. An LSTM layer defined by a hidden_state size and number of layers
3. A fully-connected output layer that maps the LSTM layer outputs to a desired output_size
4. A sigmoid activation layer which turns all outputs into a value 0-1; return **only the last sigmoid output** as the output of this network.

## The Embedding Layer

We need to add an [embedding layer](https://pytorch.org/docs/stable/nn.html#embedding) because there are 74000+ words in our vocabulary. It is massively inefficient to one-hot encode that many classes. So, instead of one-hot encoding, we can have an embedding layer and use that layer as a lookup table. You could train an embedding layer using Word2Vec, then load it here. But, it's fine to just make a new layer, using it for only dimensionality reduction, and let the network learn the weights.

## The LSTM Layer(s)

We'll create an LSTM to use in our recurrent network, which takes in an input_size, a hidden_dim, a number of layers, a dropout probability (for dropout between multiple layers), and a batch_first parameter.

Most of the time, you're network will have better performance with more layers; between 2-3. Adding more layers allows the network to learn really complex relationships.
"""

# First checking if GPU is available
train_on_gpu=torch.cuda.is_available()

if(train_on_gpu):
    print('Training on GPU.')
else:
    print('No GPU available, training on CPU.')

import torch.nn as nn

class SentimentRNN(nn.Module):
    """
    The RNN model that will be used to perform Sentiment analysis.
    """

    def __init__(self, vocab_size, output_size, embedding_dim, hidden_dim, n_layers, drop_prob=0.5):
        """
        Initialize the model by setting up the layers.
        """
        super(SentimentRNN, self).__init__()

        self.output_size = output_size
        self.n_layers = n_layers
        self.hidden_dim = hidden_dim
        
        # embedding and LSTM layers
        self.embedding = nn.Embedding(vocab_size, embedding_dim)
        self.lstm = nn.LSTM(embedding_dim, hidden_dim, n_layers, 
                            dropout=drop_prob, batch_first=True)
        
        # dropout layer
        self.dropout = nn.Dropout(0.3)
        
        # linear and sigmoid layers
        self.fc = nn.Linear(hidden_dim, output_size)
        self.sig = nn.Sigmoid()
        

    def forward(self, x, hidden):
        """
        Perform a forward pass of our model on some input and hidden state.
        """
        batch_size = x.size(0)

        # embeddings and lstm_out
        x = x.long()
        embeds = self.embedding(x)
        lstm_out, hidden = self.lstm(embeds, hidden)
    
        # stack up lstm outputs
        lstm_out = lstm_out.contiguous().view(-1, self.hidden_dim)
        
        # dropout and fully-connected layer
        out = self.dropout(lstm_out)
        out = self.fc(out)
        # sigmoid function
        sig_out = self.sig(out)
        
        # reshape to be batch_size first
        sig_out = sig_out.view(batch_size, -1)
        sig_out = sig_out[:, -1] # get last batch of labels
        
        # return last sigmoid output and hidden state
        return sig_out, hidden
    
    
    def init_hidden(self, batch_size):
        ''' Initializes hidden state '''
        # Create two new tensors with sizes n_layers x batch_size x hidden_dim,
        # initialized to zero, for hidden state and cell state of LSTM
        weight = next(self.parameters()).data
        
        if (train_on_gpu):
            hidden = (weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().cuda(),
                  weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().cuda())
        else:
            hidden = (weight.new(self.n_layers, batch_size, self.hidden_dim).zero_(),
                      weight.new(self.n_layers, batch_size, self.hidden_dim).zero_())
        
        return hidden

"""## Instantiate the network

Here, we'll instantiate the network. First up, defining the hyperparameters.

* `vocab_size`: Size of our vocabulary or the range of values for our input, word tokens.
* `output_size`: Size of our desired output; the number of class scores we want to output (pos/neg).
* `embedding_dim`: Number of columns in the embedding lookup table; size of our embeddings.
* `hidden_dim`: Number of units in the hidden layers of our LSTM cells. Usually larger is better performance wise. Common values are 128, 256, 512, etc.
* `n_layers`: Number of LSTM layers in the network. Typically between 1-3
"""

# Instantiate the model w/ hyperparams
vocab_size = len(vocab_to_int)+1 # +1 for the 0 padding + our word tokens
output_size = 1
embedding_dim = 400
hidden_dim = 256
n_layers = 2

net = SentimentRNN(vocab_size, output_size, embedding_dim, hidden_dim, n_layers)

print(net)

"""---
# Training

>We'll use a new kind of cross entropy loss, which is designed to work with a single Sigmoid output. BCELoss or **Binary Cross Entropy Loss**, applies cross entropy loss to a single value between 0 and 1.

We also have some data and training hyparameters:

* `lr`: Learning rate for our optimizer.
* `epochs`: Number of times to iterate through the training dataset.
* `clip`: The maximum gradient value to clip at (to prevent exploding gradients).
"""

# loss and optimization functions
lr=0.001

criterion = nn.BCELoss()
optimizer = torch.optim.Adam(net.parameters(), lr=lr)

# training params

epochs = 4 # 3-4 is approx where I noticed the validation loss stop decreasing

counter = 0
print_every = 100
clip=5 # gradient clipping

# move model to GPU, if available
if(train_on_gpu):
    net.cuda()

net.train()
# train for some number of epochs
for e in range(epochs):
    # initialize hidden state
    h = net.init_hidden(batch_size)

    # batch loop
    for inputs, labels in train_loader:
        counter += 1

        if(train_on_gpu):
            inputs, labels = inputs.cuda(), labels.cuda()

        # Creating new variables for the hidden state, otherwise
        # we'd backprop through the entire training history
        h = tuple([each.data for each in h])

        # zero accumulated gradients
        net.zero_grad()

        # get the output from the model
        output, h = net(inputs, h)

        # calculate the loss and perform backprop
        loss = criterion(output.squeeze(), labels.float())
        loss.backward()
        # `clip_grad_norm` helps prevent the exploding gradient problem in RNNs / LSTMs.
        nn.utils.clip_grad_norm_(net.parameters(), clip)
        optimizer.step()

        # loss stats
        if counter % print_every == 0:
            # Get validation loss
            val_h = net.init_hidden(batch_size)
            val_losses = []
            net.eval()
            for inputs, labels in valid_loader:

                # Creating new variables for the hidden state, otherwise
                # we'd backprop through the entire training history
                val_h = tuple([each.data for each in val_h])

                if(train_on_gpu):
                    inputs, labels = inputs.cuda(), labels.cuda()

                output, val_h = net(inputs, val_h)
                val_loss = criterion(output.squeeze(), labels.float())

                val_losses.append(val_loss.item())

            net.train()
            print("Epoch: {}/{}...".format(e+1, epochs),
                  "Step: {}...".format(counter),
                  "Loss: {:.6f}...".format(loss.item()),
                  "Val Loss: {:.6f}".format(np.mean(val_losses)))

"""---
## Testing

There are a few ways to test your network.

* **Test data performance:** First, we'll see how our trained model performs on all of our defined test_data, above. We'll calculate the average loss and accuracy over the test data.

* **Inference on user-generated data:** Second, we'll see if we can input just one example review at a time (without a label), and see what the trained model predicts. Looking at new, user input data like this, and predicting an output label, is called **inference**.
"""

# Get test data loss and accuracy

test_losses = [] # track loss
num_correct = 0

# init hidden state
h = net.init_hidden(batch_size)

net.eval()
# iterate over test data
for inputs, labels in test_loader:

    # Creating new variables for the hidden state, otherwise
    # we'd backprop through the entire training history
    h = tuple([each.data for each in h])

    if(train_on_gpu):
        inputs, labels = inputs.cuda(), labels.cuda()
    
    # get predicted outputs
    output, h = net(inputs, h)
    
    # calculate loss
    test_loss = criterion(output.squeeze(), labels.float())
    test_losses.append(test_loss.item())
    
    # convert output probabilities to predicted class (0 or 1)
    pred = torch.round(output.squeeze())  # rounds to the nearest integer
    
    # compare predictions to true label
    correct_tensor = pred.eq(labels.float().view_as(pred))
    correct = np.squeeze(correct_tensor.numpy()) if not train_on_gpu else np.squeeze(correct_tensor.cpu().numpy())
    num_correct += np.sum(correct)


# -- stats! -- ##
# avg test loss
print("Test loss: {:.3f}".format(np.mean(test_losses)))

# accuracy over all test data
test_acc = num_correct/len(test_loader.dataset)
print("Test accuracy: {:.3f}".format(test_acc))

"""---


#Example on a review
"""

# positive review
test_review_neg = 'The best movie I have seen; acting was terrific and it was value for money. This movie had the best acting and the dialogue was awesome.'

from string import punctuation

def tokenize_review(test_review):
    test_review = test_review.lower() # lowercase
    # get rid of punctuation
    test_text = ''.join([c for c in test_review if c not in punctuation])

    # splitting by spaces
    test_words = test_text.split()

    # tokens
    test_ints = []
    test_ints.append([vocab_to_int[word] for word in test_words])

    return test_ints

# test code and generate tokenized review
test_ints = tokenize_review(test_review_neg)
print(test_ints)

# test sequence padding
seq_length=200
features = pad_features(test_ints, seq_length)

print(features)

def predict(net, test_review, sequence_length=200):
    
    net.eval()
    
    # tokenize review
    test_ints = tokenize_review(test_review)
    
    # pad tokenized sequence
    seq_length=sequence_length
    features = pad_features(test_ints, seq_length)
    
    # convert to tensor to pass into your model
    feature_tensor = torch.from_numpy(features)
    
    batch_size = feature_tensor.size(0)
    
    # initialize hidden state
    h = net.init_hidden(batch_size)
    
    if(train_on_gpu):
        feature_tensor = feature_tensor.cuda()
    
    # get the output from the model
    output, h = net(feature_tensor, h)
    
    # convert output probabilities to predicted class (0 or 1)
    pred = torch.round(output.squeeze()) 
    # printing output value, before rounding
    print('Pred value, pre-rounding: {:.6f}'.format(output.item()))
    
    # print custom response
    if(pred.item()==1):
        print("Pos rev!")
    else:
        print("Neg rev!")

# call function
# trying negative and positive reviews!
seq_length=200
predict(net, test_review_neg, seq_length)

# neg test review
test_review_pos = 'This movie had the worst acting and the dialogue was so bad. I vomited upon leaving.'

# call function
# try negative and positive reviews!
seq_length=200
predict(net, test_review_pos, seq_length)

torch.save(net.state_dict(), 'sentiment.pth')

!ls

"""# Converted PyTorch Model to ONNX file

![alt text](https://azurecomcdn.azureedge.net/mediahandler/acomblog/media/Default/blog/13189eea-5f0f-4ef9-83d1-92679b3a60f6.png)
"""

from torch.autograd import Variable
import torch.onnx

# Load the trained model from file
net_save = SentimentRNN(vocab_size, output_size, embedding_dim, hidden_dim, n_layers)

trained_model = net_save
trained_model.load_state_dict(torch.load('sentiment.pth'))

# Export the trained model to ONNX
dummy_input = Variable(torch.randn(1, 1, 28, 28)) # one black and white 28 x 28 picture will be the input to the model
torch.onnx.export(trained_model, dummy_input, "sentiment.onnx")

"""## Converted ONNX to Tensorflow then download"""

##git clone git@github.com:onnx/onnx-tensorflow.git && cd onnx-tensorflow
### pip install -e .

import onnx
import warnings
from onnx_tf.backend import prepare

model = onnx.load('sentiment.onnx') # Load the ONNX file
tf_rep = prepare(model) # Import the ONNX model to Tensorflow
tf_rep.export_graph("tb_pb/sentiment.pb")