{"cells":[{"metadata":{},"cell_type":"markdown","source":"## This code is from NLP Zero to Hero from tensorflow with some modifications\nCode explanation in this videos:\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.text import Tokenizer\nfrom tensorflow.keras.preprocessing.sequence import pad_sequences\n\nprint(tf.__version__)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Natural Language Processing - Tokenization (NLP Zero to Hero - Part 1 / 2)"},{"metadata":{"trusted":true},"cell_type":"code","source":"sentences = {\n 'I love my dog',\n 'I love my car',\n 'You love my dog',\n 'You love my cat'\n}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenizer = Tokenizer(num_words = 100, oov_token='')\ntokenizer.fit_on_texts(sentences)\nword_index = tokenizer.word_index\nsequences = tokenizer.texts_to_sequences(sentences)\npadded = pad_sequences(sequences, padding='post', truncating='post', maxlen=5)\n\nprint(word_index)\nprint(sequences)\nprint(padded)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data = [\n 'i really love my dog',\n 'my dog loves my manatee'\n]\n\ntest_seq = tokenizer.texts_to_sequences(test_data)\nprint(test_seq)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"markdown","source":"## Modeling a Sarcasm Prediction"},{"metadata":{},"cell_type":"markdown","source":"### Training a model to recognize sentiment in text (NLP Zero to Hero - Part 3)"},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\n\ndatastore = pd.read_json('../input/news-headlines-dataset-for-sarcasm-detection/Sarcasm_Headlines_Dataset.json', lines = True)\n\nsentences = datastore['headline'].tolist()\nlabels = datastore['is_sarcastic'].tolist()\nurls = datastore['article_link'].tolist()\n\nvocab_size = 10000\nembedding_dim = 16\nmax_length = 100\ntrunc_type='post'\npadding_type='post'\noov_tok = \"\"\ntraining_size = 20000","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"training_sentences = sentences[0:training_size]\ntesting_sentences = sentences[training_size:]\ntraining_labels = labels[0:training_size]\ntesting_labels = labels[training_size:]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenizer = Tokenizer(num_words=vocab_size, oov_token=oov_tok)\ntokenizer.fit_on_texts(training_sentences)\nword_index = tokenizer.word_index\n\ntraining_sequences = tokenizer.texts_to_sequences(training_sentences)\ntraining_padded = pad_sequences(training_sequences,maxlen=max_length, padding=padding_type, truncating=trunc_type)\n\ntesting_sequences = tokenizer.texts_to_sequences(testing_sentences)\ntesting_padded = pad_sequences(testing_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Need this block to get it to work with TensorFlow 2.x\nimport numpy as np\n\ntraining_padded = np.array(training_padded)\ntraining_labels = np.array(training_labels)\ntesting_padded = np.array(testing_padded)\ntesting_labels = np.array(testing_labels)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.Sequential([\n tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length = max_length),\n tf.keras.layers.GlobalAveragePooling1D(),\n tf.keras.layers.Dense(24, activation='relu'),\n tf.keras.layers.Dense(1, activation='sigmoid')\n])\n\nmodel.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"num_epochs = 30\nhistory = model.fit(training_padded, training_labels, epochs=num_epochs, validation_data=(testing_padded, testing_labels), verbose=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_graphs(history, string):\n plt.plot(history.history[string])\n plt.plot(history.history['val_'+string])\n plt.xlabel(\"Epochs\")\n plt.ylabel(string)\n plt.legend([string, 'val_'+string])\n plt.show()\n \nplot_graphs(history, \"accuracy\")\nplot_graphs(history, \"loss\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sentence = [\"granny starting to fear spiders in the garden might be real\", \"game of thrones season finale showing this sunday night\"]\nsequences = tokenizer.texts_to_sequences(sentence)\npadded = pad_sequences(sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)\nprint(model.predict(padded))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"##### If help you, please upvote! Thak you 😃"},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}