{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Synthetic datasets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This brief presentation shows a few sample images from generated synthetic data focusing on Atomic Pattern Dictionary and sprse encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "import os, sys, glob\n",
    "import pandas\n",
    "import numpy as np\n",
    "from skimage import io\n",
    "import matplotlib.pylab as plt\n",
    "sys.path += [os.path.abspath('.'), os.path.abspath('..')]  # Add path to root\n",
    "import bpdl.data_utils as tl_utils"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['combination.csv', 'datasetBinary_defNoise', 'datasetBinary_deform', 'datasetBinary_noise', 'datasetBinary_raw', 'datasetFuzzy_defNoise', 'datasetFuzzy_deform', 'datasetFuzzy_noise', 'datasetFuzzy_raw', 'datasetFuzzy_raw_gauss-0.001', 'datasetFuzzy_raw_gauss-0.005', 'datasetFuzzy_raw_gauss-0.010', 'datasetFuzzy_raw_gauss-0.025', 'datasetFuzzy_raw_gauss-0.050', 'datasetFuzzy_raw_gauss-0.075', 'datasetFuzzy_raw_gauss-0.100', 'datasetFuzzy_raw_gauss-0.125', 'datasetFuzzy_raw_gauss-0.150', 'datasetFuzzy_raw_gauss-0.200', 'dictionary']\n"
     ]
    }
   ],
   "source": [
    "DEFAULT_PATH = '/mnt/30C0201EC01FE8BC/TEMP'\n",
    "DEFAULT_DATASET = 'atomicPatternDictionary_v0'\n",
    "DEFAULT_IMG_POSIX = '.png'\n",
    "pathDataset = os.path.join(DEFAULT_PATH, DEFAULT_DATASET)\n",
    "print ([os.path.basename(p) for p in glob.glob(os.path.join(pathDataset, '*'))])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def showDatasetImages(pathBase, dataset, imPattern='*', nbSamples=None, perRow=5):\n",
    "    imgs, names = tl_utils.dataset_load_images(os.path.join(pathBase, dataset), imPattern, nbSamples)\n",
    "    nbRows = int(np.ceil(float(len(imgs)) / perRow))\n",
    "    plt.figure(figsize=(10, nbRows * perRow))\n",
    "    for i, img in enumerate(imgs):\n",
    "        plt.subplot(nbRows, perRow, i + 1), plt.imshow(img, cmap=plt.cm.gray), plt.axis('off')\n",
    "    plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAskAAACPCAYAAAAIq0a1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f1ebe72c1d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "showDatasetImages(pathDataset, 'datasetBinary_raw', nbSamples=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAskAAACPCAYAAAAIq0a1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n9OOf6FfKfQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f1ebe14f898>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "showDatasetImages(pathDataset, 'datasetFuzzy_raw', nbSamples=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAskAAACPCAYAAAAIq0a1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f1ebe112f28>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "showDatasetImages(pathDataset, 'datasetBinary_defNoise', nbSamples=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAskAAACPCAYAAAAIq0a1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f1ebe2c5908>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "showDatasetImages(pathDataset, 'datasetFuzzy_defNoise', nbSamples=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAskAAACPCAYAAAAIq0a1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f1ebe128278>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "showDatasetImages(pathDataset, 'dictionary', imPattern='pattern_*', nbSamples=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   combination          name\n0  0;0;0;1;0;0  sample_00000\n1  1;0;0;0;0;1  sample_00001\n2  1;0;0;0;0;0  sample_00002\n3  0;0;0;0;1;0  sample_00003\n4  0;0;0;0;0;1  sample_00004\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.5/dist-packages/IPython/kernel/__main__.py:2: FutureWarning: from_csv is deprecated. Please use read_csv(...) instead. Note that some of the default arguments are different, so please refer to the documentation for from_csv when changing your function calls\n  from IPython.kernel.zmq import kernelapp as app\n"
     ]
    }
   ],
   "source": [
    "pCoding = os.path.join(pathDataset, tl_utils.CSV_NAME_WEIGHTS) # 'combination.csv'\n",
    "df = pandas.read_csv(pCoding, index_col=0)\n",
    "print (df.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    ""
   ]
  }
 ],
 "metadata": {
  "signature": "sha256:e58664f2af3b4f338597769e8146aa67c15e7310a949318a63d8d27edc9ad9ab"
 },
 "nbformat": 4,
 "nbformat_minor": 0
}