SKFlow Chess Example.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "What is SKFlow\n",
    "\n",
    "\n",
    "Explain Tensorflow models\n",
    "Explain parameters, how they work"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import tensorflow.contrib.learn as skflow\n",
    "from sklearn import datasets, metrics\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First, we read in the CSV file into a Pandas dataframe using the read_csv() method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>kwc</th>\n",
       "      <th>kwr</th>\n",
       "      <th>rwc</th>\n",
       "      <th>rwr</th>\n",
       "      <th>kbc</th>\n",
       "      <th>kbr</th>\n",
       "      <th>result</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a</td>\n",
       "      <td>1</td>\n",
       "      <td>b</td>\n",
       "      <td>3</td>\n",
       "      <td>c</td>\n",
       "      <td>2</td>\n",
       "      <td>draw</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a</td>\n",
       "      <td>1</td>\n",
       "      <td>c</td>\n",
       "      <td>1</td>\n",
       "      <td>c</td>\n",
       "      <td>2</td>\n",
       "      <td>draw</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a</td>\n",
       "      <td>1</td>\n",
       "      <td>c</td>\n",
       "      <td>1</td>\n",
       "      <td>d</td>\n",
       "      <td>1</td>\n",
       "      <td>draw</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a</td>\n",
       "      <td>1</td>\n",
       "      <td>c</td>\n",
       "      <td>1</td>\n",
       "      <td>d</td>\n",
       "      <td>2</td>\n",
       "      <td>draw</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>a</td>\n",
       "      <td>1</td>\n",
       "      <td>c</td>\n",
       "      <td>2</td>\n",
       "      <td>c</td>\n",
       "      <td>1</td>\n",
       "      <td>draw</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  kwc  kwr rwc  rwr kbc  kbr result\n",
       "0   a    1   b    3   c    2   draw\n",
       "1   a    1   c    1   c    2   draw\n",
       "2   a    1   c    1   d    1   draw\n",
       "3   a    1   c    1   d    2   draw\n",
       "4   a    1   c    2   c    1   draw"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"data/krkopt.data.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# http://pandas.pydata.org/pandas-docs/stable/generated/pandas.get_dummies.html\n",
    "feature_keys = ['kwc', 'kwr', 'rwc', 'rwr', 'kbc', 'kbr']\n",
    "\n",
    "features = list()\n",
    "for key in feature_keys:\n",
    "    features.append(pd.get_dummies(df[key], prefix=key))\n",
    "\n",
    "features_df = pd.concat(features, axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>kwc_a</th>\n",
       "      <th>kwc_b</th>\n",
       "      <th>kwc_c</th>\n",
       "      <th>kwc_d</th>\n",
       "      <th>kwr_1</th>\n",
       "      <th>kwr_2</th>\n",
       "      <th>kwr_3</th>\n",
       "      <th>kwr_4</th>\n",
       "      <th>rwc_a</th>\n",
       "      <th>rwc_b</th>\n",
       "      <th>...</th>\n",
       "      <th>kbc_g</th>\n",
       "      <th>kbc_h</th>\n",
       "      <th>kbr_1</th>\n",
       "      <th>kbr_2</th>\n",
       "      <th>kbr_3</th>\n",
       "      <th>kbr_4</th>\n",
       "      <th>kbr_5</th>\n",
       "      <th>kbr_6</th>\n",
       "      <th>kbr_7</th>\n",
       "      <th>kbr_8</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   kwc_a  kwc_b  kwc_c  kwc_d  kwr_1  kwr_2  kwr_3  kwr_4  rwc_a  rwc_b  \\\n",
       "0      1      0      0      0      1      0      0      0      0      1   \n",
       "1      1      0      0      0      1      0      0      0      0      0   \n",
       "2      1      0      0      0      1      0      0      0      0      0   \n",
       "3      1      0      0      0      1      0      0      0      0      0   \n",
       "4      1      0      0      0      1      0      0      0      0      0   \n",
       "\n",
       "   ...    kbc_g  kbc_h  kbr_1  kbr_2  kbr_3  kbr_4  kbr_5  kbr_6  kbr_7  kbr_8  \n",
       "0  ...        0      0      0      1      0      0      0      0      0      0  \n",
       "1  ...        0      0      0      1      0      0      0      0      0      0  \n",
       "2  ...        0      0      1      0      0      0      0      0      0      0  \n",
       "3  ...        0      0      0      1      0      0      0      0      0      0  \n",
       "4  ...        0      0      1      0      0      0      0      0      0      0  \n",
       "\n",
       "[5 rows x 40 columns]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "features_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, let's convert the results column into the same one-hot encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from sklearn import preprocessing\n",
    "le = preprocessing.LabelEncoder()\n",
    "le.fit(df['result'])\n",
    "y = le.transform(df['result'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.cross_validation import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(features_df, y, test_size=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Step #1, avg. loss: 3.53110\n",
      "Step #21, avg. loss: 3.09234\n",
      "Step #41, avg. loss: 2.77886\n",
      "Step #61, avg. loss: 2.74618\n",
      "Step #81, avg. loss: 2.56921\n",
      "Step #101, avg. loss: 2.52313\n",
      "Step #121, avg. loss: 2.37906\n",
      "Step #141, avg. loss: 2.40063\n",
      "Step #161, avg. loss: 2.34971\n",
      "Step #181, avg. loss: 2.29397\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "TensorFlowLinearClassifier(batch_size=32, class_weight=None,\n",
       "              continue_training=False, early_stopping_rounds=None,\n",
       "              keep_checkpoint_every_n_hours=10000, learning_rate=0.1,\n",
       "              max_to_keep=5, n_classes=18, num_cores=4, optimizer='SGD',\n",
       "              steps=200, tf_master='', tf_random_seed=42, verbose=1)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "myClassifier = skflow.TensorFlowLinearClassifier(18)\n",
    "myClassifier.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.231882\n"
     ]
    }
   ],
   "source": [
    "score = metrics.accuracy_score(myClassifier.predict(X_test), y_test)\n",
    "print(\"Accuracy: %f\" % score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import skflow\n",
    "from sklearn import datasets, metrics\n",
    "\n",
    "iris = datasets.load_iris()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}