App Init

app.py

@@ -1,4 +1,108 @@
 import gradio as gr
+from datasets import load_dataset
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+import numpy as np
+import tensorflow as tf
+import random
+import spaces
+
+maxlen = 50
+
+
+
+def get_sequences(tokenizer, tweets):
+  sequences =  tokenizer.texts_to_sequences(tweets)
+  padded = pad_sequences(sequences, truncating='post', padding='post', maxlen=maxlen)
+  return padded
+
+def get_label(idx):
+  if idx == 0: return 'sadness'
+  elif idx == 1: return 'joy'
+  elif idx == 2: return 'love'
+  elif idx == 3: return 'anger'
+  elif idx == 4: return 'fear'
+  else: return 'surprise'
+  
+def get_tweet(data):
+  tweets = [x['text'] for x in data]
+  labels = [get_label(x['label']) for x in data]
+  return tweets, labels
+
+def load_dataset():
+    dataset = load_dataset("dair-ai/emotion")
+    train = dataset['train']
+    val = dataset['validation']
+    test = dataset['test']
+    return train, val, test
+
+
+train, val, test = load_dataset()
+tweets, labels = get_tweet(train)
+tokenizer = Tokenizer(num_words=10000,oov_token='<UNK>')
+tokenizer.fit_on_texts(tweets)
+padded_train_seq = get_sequences(tokenizer, tweets)
+classes = set(labels)
+class_to_index = dict((c,i) for i,c in enumerate(classes))
+index_to_class = dict((v,k) for k,v in class_to_index.items())
+names_to_ids = lambda labels: np.array([class_to_index.get(x) for x in labels])
+train_labels = names_to_ids(labels)
+
+@spaces.GPU
+def load_model():
+   
+
+    model = tf.keras.models.Sequential([
+        tf.keras.layers.Embedding(10000, 16, input_length=maxlen),
+        tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(20, return_sequences=True)),
+        tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(20)),
+        tf.keras.layers.Dense(6, activation='softmax')
+    ])
+
+    model.compile(
+        loss='sparse_categorical_crossentropy',
+        optimizer='adam',
+        metrics=['accuracy']
+    )
+    print(model.summary())
+    val_tweets, val_labels = get_tweet(val)
+    val_seq = get_sequences(tokenizer, val_tweets)
+    val_labels = names_to_ids(val_labels)
+    h = model.fit(
+        padded_train_seq, train_labels, validation_data=(val_seq, val_labels),
+        epochs=20,
+        callbacks=[
+            tf.keras.callbacks.EarlyStopping(monitor='val_accuracy', patience=2)
+        ]
+    )
+    
+    test_tweets, test_labels = get_tweet(test)
+    test_seq = get_sequences(tokenizer, test_tweets)
+    test_labels = names_to_ids(test_labels)
+    
+    _ = model.evaluate(test_seq, test_labels)
+    i = random.randint(0, len(test_labels) - 1)
+    print('Sentence:', test_tweets[i])
+    print('Emotion:', index_to_class[test_labels[i]])
+    p = model.predict(np.expand_dims(test_seq[i],axis=0))[0]
+    pred_class = index_to_class[np.argmax(p).astype('uint8')]
+
+    print('Predicted Emotion:', pred_class)
+    
+    preds = (model.predict(test_seq) > 0.5).astype("int32")
+    print(preds)
+    
+    return model
+    
+model = load_model()
+
+@spaces.GPU
+def predict(tweet):
+    seq = get_sequences(tokenizer, [tweet])
+    p = model.predict(np.expand_dims(seq[0],axis=0))[0]
+    return index_to_class[np.argmax(p).astype('uint8')]
+
+
 
 def greet(name):
     return "Hello " + name + "!!"