Upload app.py

app.py

@@ -0,0 +1,87 @@
+import tensorflow as tf
+import numpy as np
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import Sequential
+
+import json
+
+
+test_div = 0.75
+
+vocab_size = 10000
+embedding_dim = 16
+max_length = 100
+trunc_type = 'post'
+padding_type = 'post'
+oov_tok = "<OOV>"
+
+sentences = [
+    'Wow this AI is astonishing',
+    'This is the worst AI',
+    'This is the best AI',
+    'I am the best AI',
+    'It is very astonishing that we can train a model on any data we have',
+]
+
+
+headlines = []
+is_sarcastic = []
+article_link = []
+
+with open('Sarcasm_Headlines_Dataset.json', 'r') as f:
+    data = json.load(f)
+
+
+for i in data:
+    headlines.append(i['headline'])
+    is_sarcastic.append(i['is_sarcastic'])
+    article_link.append(i['article_link'])
+
+
+train_data = headlines[:int(len(headlines) * test_div)]
+train_result = is_sarcastic[:int(len(is_sarcastic) * test_div)]
+test_data = headlines[int(len(headlines) * test_div):]
+test_result = is_sarcastic[int(len(is_sarcastic) * test_div):]
+
+
+tokenizer = Tokenizer(num_words=10000, oov_token=oov_tok)
+tokenizer.fit_on_texts(train_data)
+
+word_index = tokenizer.word_index
+
+train_sequences = tokenizer.texts_to_sequences(train_data)
+test_sequences = tokenizer.texts_to_sequences(test_data)
+train_padded = pad_sequences(
+    train_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
+test_padded = pad_sequences(
+    test_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
+
+training_padded = np.array(train_padded)
+training_labels = np.array(train_result)
+testing_padded = np.array(test_padded)
+testing_labels = np.array(test_result)
+
+
+model = Sequential([
+    tf.keras.layers.Embedding(
+        vocab_size, embedding_dim, input_length=max_length),
+    tf.keras.layers.GlobalAveragePooling1D(),
+    tf.keras.layers.Dense(24, activation='relu'),
+    tf.keras.layers.Dense(1, activation='sigmoid')
+])
+model.compile(loss='binary_crossentropy',
+              optimizer='adam', metrics=['accuracy'])
+
+model.summary()
+num_epochs = 30
+history = model.fit(training_padded, training_labels, epochs=num_epochs,
+                    validation_data=(testing_padded, testing_labels), verbose=2)
+
+sentence = ["granny starting to fear spiders in the garden might be real",
+            "game of thrones season finale showing this sunday night",
+            "Central Valley Coalition Suing the EPA Over Clean Air Failures"]
+sequences = tokenizer.texts_to_sequences(sentence)
+padded = pad_sequences(sequences, maxlen=max_length,
+                       padding=padding_type, truncating=trunc_type)
+print(model.predict(padded))