daily pastebin goal
59%
SHARE
TWEET

Untitled

a guest May 23rd, 2018 54 Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. {
  2.  "cells": [
  3.   {
  4.    "cell_type": "code",
  5.    "execution_count": 3,
  6.    "metadata": {},
  7.    "outputs": [],
  8.    "source": [
  9.     "#Resize the data\n",
  10.     "\n",
  11.     "from PIL import Image\n",
  12.     "import numpy as np\n",
  13.     "from matplotlib.pyplot import *\n",
  14.     "import matplotlib.pyplot as plt\n",
  15.     "from PIL import Image\n",
  16.     "import os, sys\n",
  17.     "path = \"/Users/vasaini/MLHACK/orig\"\n",
  18.     "dirs = os.listdir( path )\n",
  19.     "def resize():\n",
  20.     "    for item in dirs:\n",
  21.     "        if os.path.isfile(path+item):\n",
  22.     "            im = Image.open(path+item)\n",
  23.     "            f, e = os.path.splitext(path+item)\n",
  24.     "            imResize = im.resize ((128,128),\"/Users/vasaini/MLHACK/resized\")\n",
  25.     "                       \n",
  26.     "resize()"
  27.    ]
  28.   },
  29.   {
  30.    "cell_type": "code",
  31.    "execution_count": 4,
  32.    "metadata": {},
  33.    "outputs": [],
  34.    "source": [
  35.     "#Data as np array\n",
  36.     "\n",
  37.     "import os\n",
  38.     "for file in os.listdir(r\"/Users/vasaini/MLHACK/resized\"):\n",
  39.     "    img = Image.open(os.path.join(r'/Users/vasaini/MLHACK/resized', file))\n",
  40.     "    data = np.array(img)"
  41.    ]
  42.   },
  43.   {
  44.    "cell_type": "code",
  45.    "execution_count": 5,
  46.    "metadata": {},
  47.    "outputs": [
  48.     {
  49.      "name": "stdout",
  50.      "output_type": "stream",
  51.      "text": [
  52.       "['axes', 'boots', 'carabiners', 'crampons', 'gloves', 'hardshell_jackets', 'harnesses', 'helmets', 'insulated_jackets', 'pulleys', 'rope', 'tents']\n"
  53.      ]
  54.     }
  55.    ],
  56.    "source": [
  57.     "#Claases in a list\n",
  58.     "\n",
  59.     "root='/Users/vasaini/MLHACK/orig'\n",
  60.     "dirlist = [ item for item in os.listdir(root) if os.path.isdir(os.path.join(root, item)) ]\n",
  61.     "print (dirlist)"
  62.    ]
  63.   },
  64.   {
  65.    "cell_type": "code",
  66.    "execution_count": 8,
  67.    "metadata": {},
  68.    "outputs": [
  69.     {
  70.      "ename": "NameError",
  71.      "evalue": "name 'train_test_split' is not defined",
  72.      "output_type": "error",
  73.      "traceback": [
  74.       "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
  75.       "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
  76.       "\u001b[1;32m<ipython-input-8-9b2434c22d06>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[1;31m# Split our data\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m train, test, train_labels, test_labels = train_test_split(features,\n\u001b[0m\u001b[0;32m      4\u001b[0m                                                           \u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m                                                           \u001b[0mtest_size\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.33\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
  77.       "\u001b[1;31mNameError\u001b[0m: name 'train_test_split' is not defined"
  78.      ]
  79.     }
  80.    ],
  81.    "source": [
  82.     "\n",
  83.     "# Split our data\n",
  84.     "train, test, train_labels, test_labels = train_test_split(features,\n",
  85.     "                                                          labels,\n",
  86.     "                                                          test_size=0.33,\n",
  87.     "                                                          random_state=42)\n",
  88.     "\n"
  89.    ]
  90.   },
  91.   {
  92.    "cell_type": "markdown",
  93.    "metadata": {},
  94.    "source": [
  95.     "Classification SVM-Multi-class\n",
  96.     "\n"
  97.    ]
  98.   },
  99.   {
  100.    "cell_type": "code",
  101.    "execution_count": null,
  102.    "metadata": {},
  103.    "outputs": [],
  104.    "source": [
  105.     "import numpy \n",
  106.     "from PIL import Image\n",
  107.     "import os\n",
  108.     "from sklearn.svm import SVC\n",
  109.     "from sklearn.model_selection import train_test_split\n",
  110.     "for file in os.listdir('C:/Users/vasaini/MLHACK/resized'):\n",
  111.     "    img = Image.open(os.path.join('Users/vasaini/Desktop/Gear images',file))\n",
  112.     "    data = np.array(img)\n",
  113.     "# fit a SVM model to the data\n",
  114.     "model = SVC()\n",
  115.     "model.fit(dataset.data, dataset.target)\n",
  116.     "print(model)\n",
  117.     "# make predictions\n",
  118.     "predicted = model.predict(dataset.data)\n",
  119.     "# Evaluate accuracy\n",
  120.     "print(accuracy_score(test_labels, predicted))\n",
  121.     "# summarize the fit of the model\n",
  122.     "print(metrics.classification_report(expected, predicted))\n",
  123.     "print(metrics.confusion_matrix(expected, predicted))\n"
  124.    ]
  125.   },
  126.   {
  127.    "cell_type": "code",
  128.    "execution_count": null,
  129.    "metadata": {},
  130.    "outputs": [],
  131.    "source": [
  132.     "# creating a confusion matrix\n",
  133.     "knn_predictions = knn.predict(X_test) \n",
  134.     "cm = confusion_matrix(y_test, knn_predictions)\n"
  135.    ]
  136.   }
  137.  ],
  138.  "metadata": {
  139.   "kernelspec": {
  140.    "display_name": "Python 3",
  141.    "language": "python",
  142.    "name": "python3"
  143.   }
  144.  },
  145.  "nbformat": 4,
  146.  "nbformat_minor": 2
  147. }
RAW Paste Data
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy. OK, I Understand
 
Top