{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\ntrain = pd.read_csv( '../input/train.csv' )\nprint( train.head() )"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "test = pd.read_csv( '../input/test.csv' )\nprint( test.head() )"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "X_train = train[['x', 'y', 'time']].values[:100000]\ny_train = train['place_id'].values[:100000]\nweights_train = train['accuracy'].values[:100000]\n\nX_test = test[['x', 'y', 'time']].values\nweights_test = test['accuracy'].values\n"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "from sklearn.cross_validation import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.datasets import make_moons, make_circles, make_classification\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.svm import SVC\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\nfrom sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis\n\nnames = [\"Nearest Neighbors\"] \nclassifiers = [\n    KNeighborsClassifier(3, n_jobs = -1 )\n#    SVC(kernel=\"linear\", C=0.025),\n#    SVC(gamma=2, C=1),\n#    DecisionTreeClassifier(max_depth=5),\n#    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),\n#    AdaBoostClassifier(),\n#    GaussianNB(),\n#    LinearDiscriminantAnalysis(),\n#    QuadraticDiscriminantAnalysis()\n    ]\n\n#figure = plt.figure(figsize=(27, 9))\n\n# iterate over classifiers\nfor name, clf in zip(names, classifiers):\n#    clf.fit(X_train, y_train, weights_train )\n    clf.fit(X_train, y_train )\n    score = clf.score(X_train, y_train)\n\n    print '\\n\\n===== ' + name + ' ======'\n    print 'score: ', score\n    \n    pred_prob = clf.predict_proba(X_train)\n    predicts = [ np.argsort( row )[::-1][:3] for row in pred_prob ]\n\n  \n"
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}