MainJupyter.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Image Size: 40\nProcessed: 0 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 100 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 200 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 300 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 400 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 500 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 600 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 700 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 0 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 100 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 200 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 300 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 400 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 500 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 600 of 734\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 700 of 734\nTraining Data: (1174400, 52)\nLabel Data: (1174400,)\nTrain Shape: (1174400, 52)\n"
     ]
    }
   ],
   "source": [
    "import PIL\n",
    "from datetime import datetime\n",
    "from PIL import Image\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import scale\n",
    "\n",
    "import FlatPreProcessing\n",
    "\n",
    "from scipy.misc import imread\n",
    "import matplotlib.pyplot as plt\n",
    "from pathlib import Path\n",
    "\n",
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "start1 = datetime.now()\n",
    "BASE_DIR = Path('.')\n",
    "(train_data, label_data) = FlatPreProcessing.main()\n",
    "\n",
    "label_data = label_data.ravel()\n",
    "print(\"Train Shape:\", train_data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting Random Forest...\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Completed fit.\nTime: 0:05:19.892127\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "rf = RandomForestClassifier(n_estimators=20)\n",
    "print(\"Fitting Random Forest...\")\n",
    "start = datetime.now()\n",
    "rf.fit(train_data, label_data)\n",
    "print(\"Completed fit.\")\n",
    "finish = datetime.now()\n",
    "print(\"Time: {}\".format(finish-start))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting Adaboost...\nCompleted fit.\nTime: 0:00:00.000501\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "\n",
    "clf = AdaBoostClassifier(n_estimators=20)\n",
    "print(\"Fitting Adaboost...\")\n",
    "start1 = datetime.now()\n",
    "# randIndexes = np.random.choice(len(label_data), len(label_data) // 10000)\n",
    "# print(\"Number of Sample: {}\".format(len(randIndexes)))\n",
    "# td = [train_data[x] for x in randIndexes]\n",
    "# ld = [label_data[x] for x in randIndexes]\n",
    "td = train_data\n",
    "ld = label_data\n",
    "clf.fit(td, ld)\n",
    "print(\"Completed fit.\")\n",
    "finish1 = datetime.now()\n",
    "print(\"Time: {}\".format(finish1-start1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 0 of 44\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processed: 0 of 44\n"
     ]
    }
   ],
   "source": [
    "# Import the data matrix of the testing data\n",
    "# Skip if cross validating!\n",
    "\n",
    "from LoadTestImages import main\n",
    "test_data = main()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicting Data..\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "finished Predicting!\n525600\n"
     ]
    }
   ],
   "source": [
    "# Standard Prediction Block. Adjust accordingly!\n",
    "\n",
    "print(\"Predicting Data..\")\n",
    "predictions = rf.predict(train_data)\n",
    "print(\"finished Predicting!\")\n",
    "predictions = np.asarray(predictions).ravel()\n",
    "print(predictions.size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross Validating...\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-3-e2e87bf38ae8>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Cross Validating...\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mstart1\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdatetime\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mscores\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcross_val_score\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtrain_data\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabel_data\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcv\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m3\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscoring\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'f1'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      6\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Scores: {}\"\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mscores\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0mfinish1\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdatetime\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_validation.py\u001b[0m in \u001b[0;36mcross_val_score\u001b[0;34m(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch)\u001b[0m\n\u001b[1;32m    138\u001b[0m                                               \u001b[0mtrain\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtest\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverbose\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    139\u001b[0m                                               fit_params)\n\u001b[0;32m--> 140\u001b[0;31m                       for train, test in cv_iter)\n\u001b[0m\u001b[1;32m    141\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mscores\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    142\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m    756\u001b[0m             \u001b[1;31m# was dispatched. In particular this covers the edge\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    757\u001b[0m             \u001b[1;31m# case of Parallel used with an exhausted iterator.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 758\u001b[0;31m             \u001b[1;32mwhile\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdispatch_one_batch\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    759\u001b[0m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_iterating\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    760\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36mdispatch_one_batch\u001b[0;34m(self, iterator)\u001b[0m\n\u001b[1;32m    606\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[1;32mFalse\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    607\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 608\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_dispatch\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtasks\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    609\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    610\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36m_dispatch\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    569\u001b[0m         \u001b[0mdispatch_timestamp\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    570\u001b[0m         \u001b[0mcb\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mBatchCompletionCallBack\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdispatch_timestamp\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 571\u001b[0;31m         \u001b[0mjob\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_async\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcallback\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcb\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    572\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_jobs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    573\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\_parallel_backends.py\u001b[0m in \u001b[0;36mapply_async\u001b[0;34m(self, func, callback)\u001b[0m\n\u001b[1;32m    107\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mapply_async\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcallback\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    108\u001b[0m         \u001b[1;34m\"\"\"Schedule a func to be run\"\"\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 109\u001b[0;31m         \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mImmediateResult\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    110\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mcallback\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    111\u001b[0m             \u001b[0mcallback\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\_parallel_backends.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    324\u001b[0m         \u001b[1;31m# Don't delay the application, to avoid keeping the input\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    325\u001b[0m         \u001b[1;31m# arguments in memory\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 326\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresults\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mbatch\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    327\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    328\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    129\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    130\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 131\u001b[0;31m         \u001b[1;32mreturn\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    132\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__len__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m    129\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    130\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 131\u001b[0;31m         \u001b[1;32mreturn\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    132\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__len__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_validation.py\u001b[0m in \u001b[0;36m_fit_and_score\u001b[0;34m(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)\u001b[0m\n\u001b[1;32m    236\u001b[0m             \u001b[0mestimator\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mfit_params\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    237\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 238\u001b[0;31m             \u001b[0mestimator\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mfit_params\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    239\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    240\u001b[0m     \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\ensemble\\forest.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m    324\u001b[0m                     \u001b[0mt\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtrees\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    325\u001b[0m                     verbose=self.verbose, class_weight=self.class_weight)\n\u001b[0;32m--> 326\u001b[0;31m                 for i, t in enumerate(trees))\n\u001b[0m\u001b[1;32m    327\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    328\u001b[0m             \u001b[1;31m# Collect newly grown trees\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m    756\u001b[0m             \u001b[1;31m# was dispatched. In particular this covers the edge\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    757\u001b[0m             \u001b[1;31m# case of Parallel used with an exhausted iterator.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 758\u001b[0;31m             \u001b[1;32mwhile\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdispatch_one_batch\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    759\u001b[0m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_iterating\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    760\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36mdispatch_one_batch\u001b[0;34m(self, iterator)\u001b[0m\n\u001b[1;32m    606\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[1;32mFalse\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    607\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 608\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_dispatch\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtasks\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    609\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    610\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36m_dispatch\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    569\u001b[0m         \u001b[0mdispatch_timestamp\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    570\u001b[0m         \u001b[0mcb\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mBatchCompletionCallBack\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdispatch_timestamp\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 571\u001b[0;31m         \u001b[0mjob\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_async\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcallback\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcb\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    572\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_jobs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    573\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\_parallel_backends.py\u001b[0m in \u001b[0;36mapply_async\u001b[0;34m(self, func, callback)\u001b[0m\n\u001b[1;32m    107\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mapply_async\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcallback\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    108\u001b[0m         \u001b[1;34m\"\"\"Schedule a func to be run\"\"\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 109\u001b[0;31m         \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mImmediateResult\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    110\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mcallback\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    111\u001b[0m             \u001b[0mcallback\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\_parallel_backends.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    324\u001b[0m         \u001b[1;31m# Don't delay the application, to avoid keeping the input\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    325\u001b[0m         \u001b[1;31m# arguments in memory\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 326\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresults\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mbatch\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    327\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    328\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    129\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    130\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 131\u001b[0;31m         \u001b[1;32mreturn\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    132\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__len__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\externals\\joblib\\parallel.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m    129\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    130\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 131\u001b[0;31m         \u001b[1;32mreturn\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    132\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__len__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\ensemble\\forest.py\u001b[0m in \u001b[0;36m_parallel_build_trees\u001b[0;34m(tree, forest, X, y, sample_weight, tree_idx, n_trees, verbose, class_weight)\u001b[0m\n\u001b[1;32m    118\u001b[0m             \u001b[0mcurr_sample_weight\u001b[0m \u001b[1;33m*=\u001b[0m \u001b[0mcompute_sample_weight\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'balanced'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindices\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    119\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 120\u001b[0;31m         \u001b[0mtree\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcurr_sample_weight\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcheck_input\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    121\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    122\u001b[0m         \u001b[0mtree\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcheck_input\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\tree\\tree.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight, check_input, X_idx_sorted)\u001b[0m\n\u001b[1;32m    737\u001b[0m             \u001b[0msample_weight\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    738\u001b[0m             \u001b[0mcheck_input\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcheck_input\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 739\u001b[0;31m             X_idx_sorted=X_idx_sorted)\n\u001b[0m\u001b[1;32m    740\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    741\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mC:\\Users\\yosep\\Anaconda3\\lib\\site-packages\\sklearn\\tree\\tree.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight, check_input, X_idx_sorted)\u001b[0m\n\u001b[1;32m    348\u001b[0m                                            self.min_impurity_split)\n\u001b[1;32m    349\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 350\u001b[0;31m         \u001b[0mbuilder\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbuild\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtree_\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mX_idx_sorted\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    351\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m    352\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mn_outputs_\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ],
     "output_type": "error"
    }
   ],
   "source": [
    "# Cross Validation Block. Should be used in adjusting algorithm\n",
    "from sklearn.model_selection import cross_val_score\n",
    "print(\"Cross Validating...\")\n",
    "start1 = datetime.now()\n",
    "scores = cross_val_score(rf, train_data, label_data, cv=3, scoring='f1')\n",
    "print(\"Scores: {}\".format(scores))\n",
    "finish1 = datetime.now()\n",
    "print(\"Time: {}\".format(finish1-start1))\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores.mean(), scores.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "60\n(525600,)\nMode Filtered.\n"
     ]
    }
   ],
   "source": [
    "# K Neighbors\n",
    "import LoadTestImages\n",
    "from PIL import ImageFilter\n",
    "prediction_list = np.asarray(predictions)\n",
    "s_n = LoadTestImages.SIZE\n",
    "num_im = 146\n",
    "print(s_n)\n",
    "print(prediction_list.shape)\n",
    "image_list = prediction_list.reshape(num_im, s_n, s_n)\n",
    "filt_image_list = np.ndarray((num_im, s_n, s_n))\n",
    "for i in range(num_im):\n",
    "    im = Image.fromarray(image_list[i])\n",
    "    im_mode = im.filter(ImageFilter.ModeFilter(3))\n",
    "    filt_image_list[i] = im_mode\n",
    "# test_coords = test_data[:, 3:]\n",
    "# print(test_coords.shape)\n",
    "# \n",
    "# print(\"KNN Beginning\")\n",
    "# neigh = KNeighborsClassifier(n_neighbors=15)\n",
    "# neigh.fit(test_coords, predictions.ravel())\n",
    "# \n",
    "# \n",
    "# kpredictions = neigh.predict(test_coords)\n",
    "# \n",
    "# print(\"Pred Shape\", predictions.shape)\n",
    "# \n",
    "# predictions = neigh.predict(test_data.ravel())\n",
    "print(\"Mode Filtered.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "True Positives... 190688.0\nFalse Positives... 10653.0\nFalse Negatives... 18356.0\nPrecision... 0.9470897631381586\nRecall... 0.9121907349648878\nDice Coefficient: 0.9293127185447811\n"
     ]
    }
   ],
   "source": [
    "# Calculate Dice Similarity Coefficient\n",
    "dice_p = filt_image_list.ravel()\n",
    "# dice_p = prediction_list.ravel()\n",
    "truepos = np.sum(np.multiply(dice_p, label_data))\n",
    "print(\"True Positives... {}\".format(truepos))\n",
    "falsepos = np.sum(dice_p) - truepos\n",
    "print(\"False Positives... {}\".format(falsepos))\n",
    "\n",
    "falseneg = np.sum(label_data) - truepos\n",
    "print(\"False Negatives... {}\".format(falseneg))\n",
    "precision = truepos / (truepos+falsepos)\n",
    "print(\"Precision... {}\".format(precision))\n",
    "recall = truepos / (truepos+falseneg)\n",
    "print(\"Recall... {}\".format(recall))\n",
    "dice = 2 * precision * recall / (precision + recall)\n",
    "\n",
    "print(\"Dice Coefficient: {}\".format(dice))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(525600,)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(146, 60, 60)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import LoadTestImages\n",
    "pred_image = np.asarray(predictions)\n",
    "print(pred_image.shape)\n",
    "t_n = LoadTestImages.SIZE\n",
    "pred_image = pred_image.reshape(num_im, t_n, t_n)\n",
    "pred_image.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(525600,)\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWEAAAFhCAYAAACh/xvXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x23ccd78a550>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from scipy.misc import imread\n",
    "import matplotlib.pyplot as plt\n",
    "lb = np.asarray(label_data)\n",
    "print(lb.shape)\n",
    "lb = lb.reshape(146, t_n, t_n)\n",
    "plt.imshow(lb[3])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWEAAAFhCAYAAACh/xvXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nJOj/A3vjsn2gEkSPAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x23ccd6a5ba8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "im = filt_image_list[3]\n",
    "im = Image.fromarray(im).convert('L')\n",
    "# im = Image.open('labelled/31.png')\n",
    "im1 = im.load()\n",
    "plt.imshow(im)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(384, 512)\n1\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAARwAAAFkCAYAAADyhYRMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nWTtSjSAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x18ee6c1e128>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "im = Image.open('../CatDogDataSet/labelled_1345/06.png')\n",
    "print(im.size)\n",
    "im1 = im.load()\n",
    "print(im1[200,150])\n",
    "plt.imshow(im)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(384, 512)\n1\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAARwAAAFkCAYAAADyhYRMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nJGVj4EjKxsCRlI2BIykbA0dSNv8fIacD3gTQo50AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x18eae34e080>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "im = Image.open('labelled/06.png')\n",
    "print(im.size)\n",
    "im1 = im.load()\n",
    "print(im1[200,150])\n",
    "plt.imshow(im)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saved Files\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "from pathlib import Path\n",
    "TRI_DIR = Path('../CatDogDataSet/test_images')\n",
    "BASE_DIR = Path('.')\n",
    "base_out = Path(BASE_DIR, 'labelled')\n",
    "test_dir_out = Path(base_out, 'train')\n",
    "os.makedirs(str(test_dir_out), exist_ok=True)\n",
    "\n",
    "test_path = [x for x in TRI_DIR.iterdir() if TRI_DIR.is_dir() and '.jpg' in str(x).lower()]\n",
    "test_sizes = []\n",
    "for p in test_path:\n",
    "    img = Image.open(p)\n",
    "    test_sizes.append(img.size)\n",
    "    \n",
    "# print(test_sizes)\n",
    "test_names = [os.path.basename(str(x)).split('.')[0] for x in test_path]\n",
    "test_names = ['0{}'.format(x) if (len(x)==1) else x for x in test_names]\n",
    "# print(test_names)\n",
    "count = len(test_names)\n",
    "for i in range(count):\n",
    "    (n_x, n_y) = test_sizes[i]\n",
    "    im = filt_image_list[i]\n",
    "    im = Image.fromarray(im).convert('L')\n",
    "    im = im.resize((n_x,n_y), resample=Image.ANTIALIAS)\n",
    "    basename = '{}.png'.format(test_names[i])\n",
    "    # print(basename)\n",
    "    path_out = os.path.join(str(base_out), basename)\n",
    "    # print(\"Path out:\", str(path_out))\n",
    "    im.save(path_out)\n",
    "# test_mat = np.ndarray(count, 32, 32)\n",
    "\n",
    "print(\"Saved Files\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    ""
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2.0
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}