{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "from sklearn.neural_network import MLPClassifier\n#>>> clf.fit(X, y)\nimport pandas as pd\nimport numpy as np"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "X = [[0, 0], [10, 1], [8, 9], [11, 1], [12, 3]]\nX = pd.DataFrame(X)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "y1 = [0, 1, 3, 7, 9]\ny = pd.DataFrame(y)\ny = y.values.ravel()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "clf = MLPClassifier(algorithm='l-bfgs', alpha=1e-5, hidden_layer_sizes=(15, 2), random_state=1)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "clf.fit(X, y) "
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "clf.predict([[2., 2.], [-1., -2.]])"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "classes.classes_"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "test1 = [[2, 2],[4,7],[12,3]]\ntest1 = pd.DataFrame(test1)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "y_pr = clf.predict_proba(test1)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "y_pr[1,:]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "#print(y_pr[0,:])\nprint(y_pr.argsort())\nprint(y_pr.argsort()[::-1])\nprint(y_pr.argsort()[:2])"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "y_pr[1].argsort() #.values[-3:]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "y1 = [0, 1, 3, 7, 9]\ny1 = pd.DataFrame(y1)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "a = y1.values"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "a[y_pr.argsort()[::-1]]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import ml_metrics as metrics"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "def find_top_5(row):\n    return list(row.nlargest(5).index)"
 },
 {
  "cell_type": "markdown",
  "metadata": {},
  "source": "preds = []\nfor index, row in prediction_frame.iterrows():\n    preds.append(find_top_5(row))"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "np.array_str(a[y_pr.argsort()[::-1][:2]])[1:-1]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "most_popular"
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}