DatasetVisualization.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import pickle\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def find_modality_bin_behavior(a_path, db_file_name):\n",
    "    \"\"\"\n",
    "    Finds modality, bins, behavior by using `path` and `dataset` file name\n",
    "\n",
    "    :param a_path: Dataset path\n",
    "    :param db_file_name: Dataset file name\n",
    "\n",
    "    :return: modality, bins, behavior\n",
    "    \"\"\"\n",
    "\n",
    "    modality = a_path.split(os.sep)[1].split(\"_\")[0].capitalize()\n",
    "    bins = a_path.split(os.sep)[1].split(\"_\")[1]\n",
    "\n",
    "    if modality == \"Proprioception\":\n",
    "        modality = \"Haptic\"\n",
    "\n",
    "    if (db_file_name.split(\".\")[0].split(\"_\")[0]) == 'low':\n",
    "        behavior = \"Drop\"\n",
    "    else:\n",
    "        behavior = db_file_name.split(\".\")[0].split(\"_\")[0].capitalize()\n",
    "\n",
    "    if behavior == \"Crush\":\n",
    "        behavior = 'Press'\n",
    "\n",
    "    return modality, bins, behavior\n",
    "\n",
    "\n",
    "def read_dataset(a_path, db_file_name):\n",
    "    \"\"\"\n",
    "    Read dataset\n",
    "\n",
    "    :param a_path: Dataset path\n",
    "    :param db_file_name: Dataset file name\n",
    "\n",
    "    :return: interaction_data, category_labels, object_labels\n",
    "    \"\"\"\n",
    "\n",
    "    bin_file = open(a_path + os.sep + db_file_name, \"rb\")\n",
    "    interaction_data = pickle.load(bin_file)\n",
    "    category_labels = pickle.load(bin_file)\n",
    "    object_labels = pickle.load(bin_file)\n",
    "    bin_file.close()\n",
    "\n",
    "    return reshape_full_data(interaction_data), reshape_full_data(category_labels), reshape_full_data(object_labels)\n",
    "\n",
    "\n",
    "def reshape_full_data(data):\n",
    "    \"\"\"\n",
    "    Reshape data into (Categories, Objects, Trials)\n",
    "\n",
    "    :param data: Dataset list\n",
    "\n",
    "    :return: reshaped Dataset list\n",
    "    \"\"\"\n",
    "    return data.reshape(NUM_OF_CATEGORY, OBJECTS_PER_CATEGORY, TRIALS_PER_OBJECT, -1)\n",
    "\n",
    "\n",
    "def print_discretized_data(data, x_values, y_values, modality, behavior, file_path=None):\n",
    "    \"\"\"\n",
    "    prints the data point and save it\n",
    "\n",
    "    :param data: one data point\n",
    "    :param x_values: temporal bins\n",
    "    :param y_values:\n",
    "    :param modality:\n",
    "    :param behavior:\n",
    "    :param file_path:\n",
    "\n",
    "    :return:\n",
    "    \"\"\"\n",
    "    \n",
    "    if x_values and y_values:\n",
    "        data = data.reshape(x_values, y_values)\n",
    "    title_name = behavior+\"-\"+modality+\" Features\"\n",
    "    \n",
    "    #plt.figure(figsize=(5, 10))\n",
    "    plt.title(title_name, fontsize=16)\n",
    "    plt.xlabel(\"Temporal Bins\", fontsize=16)\n",
    "\n",
    "    if modality == 'Haptic':\n",
    "        #plt.imshow(data.T, cmap=plt.cm.gray)\n",
    "        plt.imshow(data.T)\n",
    "        y_label = \"Joints\"\n",
    "    elif modality == 'Audio':\n",
    "        #plt.imshow(np.flipud(data.T), cmap=plt.cm.gray)\n",
    "        plt.imshow(np.flipud(data.T))\n",
    "        y_label = \"Frequency Bins\"\n",
    "    elif modality == 'Vibro':\n",
    "        #plt.imshow(np.flipud(data.T), cmap=plt.cm.gray)\n",
    "        plt.imshow(np.flipud(data.T), interpolation='nearest', aspect='auto')\n",
    "        y_label = \"Frequency Bins\"\n",
    "    elif modality == \"Surf\":\n",
    "        plt.hist(x=interaction_data[1][1][1], bins='auto', color='#0504aa', alpha=0.7, rwidth=0.85)\n",
    "        plt.xlabel(\"Value\", fontsize=16)\n",
    "        y_label = \"Frequency\"\n",
    "    else:\n",
    "        y_label = \"\"\n",
    "    plt.ylabel(y_label, fontsize=16)\n",
    "    \n",
    "    if x_values and y_values:\n",
    "        ax = plt.gca()\n",
    "        ax.set_xticks(np.arange(0, x_values, 1))\n",
    "        ax.set_yticks(np.arange(0, y_values, 1))\n",
    "        #ax.set_yticks([])\n",
    "        ax.set_xticklabels(np.arange(1, x_values + 1, 1))\n",
    "        ax.set_yticklabels(np.arange(1, y_values + 1, 1))\n",
    "\n",
    "        plt.colorbar()\n",
    "\n",
    "    if file_path != None:\n",
    "        plt.savefig(file_path, bbox_inches='tight', dpi=100)\n",
    "\n",
    "    plt.show()\n",
    "    plt.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "CATEGORY_LABELS = {'cup': 8, 'timber': 17, 'bottle': 4, 'tin': 18, 'ball': 1, 'weight': 20, 'eggcoloringcup': 9, 'basket': 2, 'cone': 7, 'cannedfood': 6, 'noodle': 13, 'egg': 10, 'medicine': 11, 'pvc': 15, 'can': 5, 'pasta': 14, 'tupperware': 19, 'bigstuffedanimal': 3, 'smallstuffedanimal': 16, 'metal': 12}\n",
    "OBJECT_LABELS = {'cup_yellow': 40, 'basket_handle': 9, 'pvc_1': 71, 'smallstuffedanimal_moose': 79, 'smallstuffedanimal_headband_bear': 78, 'noodle_2': 62, 'timber_square': 84, 'tupperware_ground_coffee': 92, 'medicine_calcium': 54, 'basket_cylinder': 6, 'egg_cardboard': 46, 'cannedfood_tomato_paste': 30, 'egg_smooth_styrofoam': 49, 'noodle_1': 61, 'basket_funnel': 7, 'can_starbucks': 25, 'weight_3': 98, 'cone_2': 32, 'weight_2': 97, 'bottle_red': 19, 'medicine_aspirin': 52, 'eggcoloringcup_orange': 43, 'bottle_green': 18, 'egg_wood': 50, 'egg_plastic_wrap': 47, 'noodle_3': 63, 'timber_squiggle': 85, 'pasta_pipette': 69, 'noodle_5': 65, 'cannedfood_tomatoes': 29, 'pasta_cremette': 66, 'ball_transparent': 4, 'ball_basket': 2, 'tupperware_coffee_beans': 91, 'metal_thermos': 60, 'bottle_google': 17, 'smallstuffedanimal_otter': 80, 'tin_tea': 90, 'eggcoloringcup_blue': 41, 'tupperware_pasta': 94, 'cup_blue': 36, 'egg_rough_styrofoam': 48, 'bigstuffedanimal_tan_dog': 15, 'timber_semicircle': 83, 'eggcoloringcup_pink': 44, 'cone_5': 35, 'timber_rectangle': 82, 'cannedfood_cowboy_cookout': 27, 'noodle_4': 64, 'tupperware_marbles': 93, 'cone_3': 33, 'pasta_penne': 68, 'pasta_rotini': 70, 'bigstuffedanimal_pink_dog': 14, 'cannedfood_soup': 28, 'tin_snowman': 89, 'metal_flower_cylinder': 56, 'eggcoloringcup_yellow': 45, 'weight_4': 99, 'cup_metal': 38, 'weight_5': 100, 'bigstuffedanimal_frog': 13, 'medicine_ampicillin': 51, 'smallstuffedanimal_bunny': 76, 'cone_4': 34, 'tin_poker': 87, 'can_red_bull_small': 24, 'cannedfood_chili': 26, 'ball_blue': 3, 'smallstuffedanimal_chick': 77, 'ball_base': 1, 'pvc_4': 74, 'medicine_bilberry_extract': 53, 'pvc_2': 72, 'timber_pentagon': 81, 'medicine_flaxseed_oil': 55, 'cup_isu': 37, 'metal_tea_jar': 59, 'ball_yellow_purple': 5, 'cone_1': 31, 'metal_food_can': 57, 'metal_mix_covered_cup': 58, 'tin_pokemon': 86, 'can_arizona': 21, 'bigstuffedanimal_bear': 11, 'can_red_bull_large': 23, 'tupperware_rice': 95, 'bigstuffedanimal_bunny': 12, 'can_coke': 22, 'eggcoloringcup_green': 42, 'pasta_macaroni': 67, 'basket_green': 8, 'pvc_5': 75, 'basket_semicircle': 10, 'tin_snack_depot': 88, 'bottle_sobe': 20, 'weight_1': 96, 'pvc_3': 73, 'cup_paper_green': 39, 'bottle_fuse': 16}\n",
    "\n",
    "NUM_OF_CATEGORY = len(CATEGORY_LABELS)\n",
    "OBJECTS_PER_CATEGORY = 5\n",
    "TRIALS_PER_OBJECT = 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Robot data: \n",
      "Shake Audio 10x10\n",
      "(20, 5, 5, 100)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cat label:  medicine\n",
      "Obj label:  medicine_aspirin\n"
     ]
    }
   ],
   "source": [
    "a_path = \"Datasets\"+os.sep+\"audio_10x10_datasets\"\n",
    "db_file_name = \"shake_audio.bin\"\n",
    "\n",
    "modality, bins, behavior = find_modality_bin_behavior(a_path, db_file_name)\n",
    "print(\"Robot data: \")\n",
    "print(behavior, modality, bins)\n",
    "\n",
    "interaction_data, category_labels, object_labels = read_dataset(a_path, db_file_name)\n",
    "num_of_features = interaction_data.shape[-1]\n",
    "print(interaction_data.shape)\n",
    "\n",
    "cat, obj, tri = 10, 1, 1\n",
    "x_values = int(bins.split('x')[0]) # temporal bins\n",
    "y_values = num_of_features//x_values\n",
    "file_path = None\n",
    "print_discretized_data(interaction_data[cat][obj][tri], x_values, y_values, modality, behavior, file_path=file_path)\n",
    "\n",
    "cat_lab = category_labels[cat][obj][tri]\n",
    "obj_lab = object_labels[cat][obj][tri]\n",
    "print(\"Cat label: \", list(CATEGORY_LABELS.keys())[list(CATEGORY_LABELS.values()).index(cat_lab)])\n",
    "print(\"Obj label: \", list(OBJECT_LABELS.keys())[list(OBJECT_LABELS.values()).index(obj_lab)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Robot data: \n",
      "Shake Haptic 10x10\n",
      "(20, 5, 5, 70)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cat label:  medicine\n",
      "Obj label:  medicine_aspirin\n"
     ]
    }
   ],
   "source": [
    "a_path = \"Datasets\"+os.sep+\"proprioception_10x10_datasets\"\n",
    "db_file_name = \"shake_proprioception_10bin_features.bin\"\n",
    "\n",
    "modality, bins, behavior = find_modality_bin_behavior(a_path, db_file_name)\n",
    "print(\"Robot data: \")\n",
    "print(behavior, modality, bins)\n",
    "\n",
    "interaction_data, category_labels, object_labels = read_dataset(a_path, db_file_name)\n",
    "num_of_features = interaction_data.shape[-1]\n",
    "print(interaction_data.shape)\n",
    "\n",
    "cat, obj, tri = 10, 1, 1\n",
    "x_values = int(bins.split('x')[0]) # temporal bins\n",
    "y_values = num_of_features//x_values\n",
    "file_path = None\n",
    "print_discretized_data(interaction_data[cat][obj][tri], x_values, y_values, modality, behavior, file_path=file_path)\n",
    "\n",
    "cat_lab = category_labels[cat][obj][tri]\n",
    "obj_lab = object_labels[cat][obj][tri]\n",
    "print(\"Cat label: \", list(CATEGORY_LABELS.keys())[list(CATEGORY_LABELS.values()).index(cat_lab)])\n",
    "print(\"Obj label: \", list(OBJECT_LABELS.keys())[list(OBJECT_LABELS.values()).index(obj_lab)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Robot data: \n",
      "Shake Vibro 5x20\n",
      "(20, 5, 5, 100)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cat label:  medicine\n",
      "Obj label:  medicine_aspirin\n"
     ]
    }
   ],
   "source": [
    "a_path = \"Datasets\"+os.sep+\"vibro_5x20_datasets\"\n",
    "db_file_name = \"shake_vibro.bin\"\n",
    "\n",
    "modality, bins, behavior = find_modality_bin_behavior(a_path, db_file_name)\n",
    "print(\"Robot data: \")\n",
    "print(behavior, modality, bins)\n",
    "\n",
    "interaction_data, category_labels, object_labels = read_dataset(a_path, db_file_name)\n",
    "num_of_features = interaction_data.shape[-1]\n",
    "print(interaction_data.shape)\n",
    "\n",
    "cat, obj, tri = 10, 1, 1\n",
    "x_values = int(bins.split('x')[0]) # temporal bins\n",
    "y_values = num_of_features//x_values\n",
    "file_path = None\n",
    "print_discretized_data(interaction_data[cat][obj][tri], x_values, y_values, modality, behavior, file_path=file_path)\n",
    "\n",
    "cat_lab = category_labels[cat][obj][tri]\n",
    "obj_lab = object_labels[cat][obj][tri]\n",
    "print(\"Cat label: \", list(CATEGORY_LABELS.keys())[list(CATEGORY_LABELS.values()).index(cat_lab)])\n",
    "print(\"Obj label: \", list(OBJECT_LABELS.keys())[list(OBJECT_LABELS.values()).index(obj_lab)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Robot data: \n",
      "Shake Surf 128\n",
      "(20, 5, 5, 128)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cat label:  medicine\n",
      "Obj label:  medicine_aspirin\n"
     ]
    }
   ],
   "source": [
    "a_path = \"Datasets\"+os.sep+\"surf_128_datasets\"\n",
    "db_file_name = \"shake_surf.bin\"\n",
    "\n",
    "modality, bins, behavior = find_modality_bin_behavior(a_path, db_file_name)\n",
    "print(\"Robot data: \")\n",
    "print(behavior, modality, bins)\n",
    "\n",
    "interaction_data, category_labels, object_labels = read_dataset(a_path, db_file_name)\n",
    "num_of_features = interaction_data.shape[-1]\n",
    "print(interaction_data.shape)\n",
    "\n",
    "cat, obj, tri = 10, 1, 1\n",
    "x_values = None\n",
    "y_values = None\n",
    "file_path = None\n",
    "print_discretized_data(interaction_data[cat][obj][tri], x_values, y_values, modality, behavior, file_path=file_path)\n",
    "\n",
    "cat_lab = category_labels[cat][obj][tri]\n",
    "obj_lab = object_labels[cat][obj][tri]\n",
    "print(\"Cat label: \", list(CATEGORY_LABELS.keys())[list(CATEGORY_LABELS.values()).index(cat_lab)])\n",
    "print(\"Obj label: \", list(OBJECT_LABELS.keys())[list(OBJECT_LABELS.values()).index(obj_lab)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.5.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}