{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "accelerator": "GPU", "colab": { "name": "Course 3 - Week 2 - Lesson 1.ipynb", "provenance": [], "collapsed_sections": [], "toc_visible": true }, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.9" } }, "cells": [ { "cell_type": "code", "metadata": { "id": "zX4Kg8DUTKWO" }, "source": [ "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n", "# you may not use this file except in compliance with the License.\n", "# You may obtain a copy of the License at\n", "#\n", "# https://www.apache.org/licenses/LICENSE-2.0\n", "#\n", "# Unless required by applicable law or agreed to in writing, software\n", "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", "# See the License for the specific language governing permissions and\n", "# limitations under the License." ], "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "metadata": { "id": "view-in-github" }, "source": [ "\"Open" ] }, { "cell_type": "code", "metadata": { "id": "P-AhVYeBWgQ3" }, "source": [ "import tensorflow as tf\n", "print(tf.__version__)\n", "\n", "# !pip install -q tensorflow-datasets" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "_IoM4VFxWpMR" }, "source": [ "import tensorflow_datasets as tfds\n", "imdb, info = tfds.load(\"imdb_reviews\", with_info=True, as_supervised=True)\n" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "wHQ2Ko0zl7M4" }, "source": [ "import numpy as np\n", "\n", "train_data, test_data = imdb['train'], imdb['test']\n", "\n", "training_sentences = []\n", "training_labels = []\n", "\n", "testing_sentences = []\n", "testing_labels = []\n", "\n", "# str(s.tonumpy()) is needed in Python3 instead of just s.numpy()\n", "for s,l in train_data:\n", " training_sentences.append(s.numpy().decode('utf8'))\n", " training_labels.append(l.numpy())\n", " \n", "for s,l in test_data:\n", " testing_sentences.append(s.numpy().decode('utf8'))\n", " testing_labels.append(l.numpy())\n", " \n", "training_labels_final = np.array(training_labels)\n", "testing_labels_final = np.array(testing_labels)\n" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "7n15yyMdmoH1" }, "source": [ "vocab_size = 10000\n", "embedding_dim = 16\n", "max_length = 120\n", "trunc_type='post'\n", "oov_tok = \"\"\n", "\n", "\n", "from tensorflow.keras.preprocessing.text import Tokenizer\n", "from tensorflow.keras.preprocessing.sequence import pad_sequences\n", "\n", "tokenizer = Tokenizer(num_words = vocab_size, oov_token=oov_tok)\n", "tokenizer.fit_on_texts(training_sentences)\n", "word_index = tokenizer.word_index\n", "sequences = tokenizer.texts_to_sequences(training_sentences)\n", "padded = pad_sequences(sequences,maxlen=max_length, truncating=trunc_type)\n", "\n", "testing_sequences = tokenizer.texts_to_sequences(testing_sentences)\n", "testing_padded = pad_sequences(testing_sequences,maxlen=max_length)\n" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "9axf0uIXVMhO" }, "source": [ "reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])\n", "\n", "def decode_review(text):\n", " return ' '.join([reverse_word_index.get(i, '?') for i in text])\n", "\n", "print(decode_review(padded[3]))\n", "print(training_sentences[3])" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "5NEpdhb8AxID" }, "source": [ "model = tf.keras.Sequential([\n", " tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),\n", " tf.keras.layers.Flatten(),\n", " tf.keras.layers.Dense(6, activation='relu'),\n", " tf.keras.layers.Dense(1, activation='sigmoid')\n", "])\n", "model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])\n", "model.summary()\n" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "V5LLrXC-uNX6" }, "source": [ "num_epochs = 10\n", "model.fit(padded, training_labels_final, epochs=num_epochs, validation_data=(testing_padded, testing_labels_final))" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "yAmjJqEyCOF_" }, "source": [ "e = model.layers[0]\n", "weights = e.get_weights()[0]\n", "print(weights.shape) # shape: (vocab_size, embedding_dim)" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "jmB0Uxk0ycP6" }, "source": [ "import io\n", "\n", "out_v = io.open('vecs.tsv', 'w', encoding='utf-8')\n", "out_m = io.open('meta.tsv', 'w', encoding='utf-8')\n", "for word_num in range(1, vocab_size):\n", " word = reverse_word_index[word_num]\n", " embeddings = weights[word_num]\n", " out_m.write(word + \"\\n\")\n", " out_v.write('\\t'.join([str(x) for x in embeddings]) + \"\\n\")\n", "out_v.close()\n", "out_m.close()" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "VDeqpOCVydtq" }, "source": [ "try:\n", " from google.colab import files\n", "except ImportError:\n", " pass\n", "else:\n", " files.download('vecs.tsv')\n", " files.download('meta.tsv')" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "YRxoxc2apscY" }, "source": [ "sentence = \"I really think this is amazing. honest.\"\n", "sequence = tokenizer.texts_to_sequences([sentence])\n", "print(sequence)" ], "execution_count": null, "outputs": [] } ] }