{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "assignment3.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "Pka5Mc5ROaj7"
      },
      "source": [
        "'''\n",
        "Trains a simple convnet on the MNIST dataset.\n",
        "Credit: Keras Team\n",
        "'''\n",
        "\n",
        "from __future__ import print_function\n",
        "import keras\n",
        "from keras.datasets import mnist\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, Dropout, Flatten\n",
        "from keras.layers import Conv2D, MaxPooling2D"
      ],
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RBPGZTlvOTRZ"
      },
      "source": [
        "# DEFINING *SOME* HYPERPARAMETERS\n",
        "batch_size = 256\n",
        "num_classes = 10\n",
        "epochs = 2 \n",
        "\n",
        "# DATA CLEAN-UP\n",
        "img_rows, img_cols = 28, 28\n",
        "\n",
        "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
        "\n",
        "x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)\n",
        "x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)\n",
        "input_shape = (img_rows, img_cols, 1)\n",
        "\n",
        "x_train = x_train.astype('float32')\n",
        "x_test = x_test.astype('float32')\n",
        "x_train /= 255\n",
        "x_test /= 255\n",
        "\n",
        "print('x_train shape:', x_train.shape)\n",
        "print(x_train.shape[0], 'train samples')\n",
        "print(x_test.shape[0], 'test samples')\n",
        "\n",
        "y_train = keras.utils.to_categorical(y_train, num_classes)\n",
        "y_test = keras.utils.to_categorical(y_test, num_classes)\n",
        "\n",
        "# MODEL DEFINITION (some hardcodede hyperparameters)\n",
        "model = Sequential()\n",
        "model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape))\n",
        "model.add(Conv2D(64, (3, 3), activation='relu'))\n",
        "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
        "model.add(Dropout(0.9))\n",
        "model.add(Flatten())\n",
        "model.add(Dense(128, activation='relu'))\n",
        "model.add(Dropout(0.9))\n",
        "model.add(Dense(num_classes, activation='softmax'))\n",
        "\n",
        "# MODEL COMPILATION AND TRAINING\n",
        "model.compile(loss=keras.losses.categorical_crossentropy,\n",
        "              optimizer=keras.optimizers.SGD(lr=0.001),\n",
        "              metrics=['accuracy'])\n",
        "\n",
        "model.fit(x_train, y_train,\n",
        "          batch_size=batch_size,\n",
        "          epochs=epochs,\n",
        "          verbose=1,\n",
        "          validation_data=(x_test, y_test))\n",
        "\n",
        "# MODEL EVALUATION\n",
        "score = model.evaluate(x_test, y_test, verbose=0)\n",
        "\n",
        "print('Test loss:', score[0])\n",
        "print('Test accuracy:', score[1])\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eokZIP_eOe5C"
      },
      "source": [
        "# if you are running this notebook on your local machine, install with pip\n",
        "# !pip install pymagnitude\n",
        "\n",
        "# if you are using Colab, install magnitude using the following:\n",
        "! echo \"Installing Magnitude.... (please wait, can take a while)\"\n",
        "! (curl https://raw.githubusercontent.com/plasticityai/magnitude/master/install-colab.sh | /bin/bash 1>/dev/null 2>/dev/null)\n",
        "! echo \"Done installing Magnitude.\""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UQwjlYsIU9bo"
      },
      "source": [
        "!wget http://magnitude.plasticity.ai/word2vec/light/GoogleNews-vectors-negative300.magnitude"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jdAovzVbOrtP"
      },
      "source": [
        "from pymagnitude import *\n",
        "\n",
        "file_path = \"GoogleNews-vectors-negative300.magnitude\"\n",
        "vectors = Magnitude(file_path)\n",
        "print(vectors.distance(\"cat\", \"dog\"))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "1ecai0hDOt78"
      },
      "source": [
        "1. What is the dimensionality of these word embeddings? Provide an integer answer.\n",
        "2.  What are the top-5 most similar words to picnic (not including picnic itself)?\n",
        "3. According to the word embeddings, which of these words is not like the others? `[tissue', 'papyrus', 'manila', 'newsprint', 'parchment', 'gazette’]`\n",
        "4. Solve the following analogy: “leg is to jump as `X` is to throw”.\n",
        "5. Is the word `alumni` in the vocabulary? What about `alumnus`?\n",
        "6. How many words are in the vocabulary?"
      ]
    }
  ]
}