{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "5f008a5c-e726-711e-4710-e9576ecd00b6"
      },
      "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",
        "\n",
        "import numpy as np # linear algebra\n",
        "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
        "\n",
        "# Input data files are available in the \"../input/\" directory.\n",
        "# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n",
        "\n",
        "\n",
        "import pandas as pd\n",
        "\n",
        "\n",
        "from sklearn import linear_model\n",
        "from numpy import genfromtxt, savetxt\n",
        "\n",
        "dataset = pd.read_csv(\"../input/train.csv\")\n",
        "train_Y = dataset.iloc[:,0]\n",
        "train_X = dataset.iloc[:,1:]\n",
        "\n",
        "test_X = pd.read_csv(\"../input/test.csv\")\n",
        "\n",
        "#create and train the random forest\n",
        "model = linear_model.SGDClassifier()\n",
        "\n",
        "model.fit(train_X, train_Y)\n",
        "\n",
        "\n",
        "from subprocess import check_output\n",
        "print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n",
        "\n",
        "# Any results you write to the current directory are saved as output."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "01d3317f-50d8-fea9-8c78-1fe29a067821"
      },
      "outputs": [],
      "source": [
        "train_X.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "fc878511-d4ee-2049-88c7-3cf2fff0b85c"
      },
      "outputs": [],
      "source": [
        "rs = model.predict(test_X)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "0a500c2b-e0e6-881b-6814-61b501e26c13"
      },
      "outputs": [],
      "source": [
        "sm = pd.DataFrame({ 'ImageId': range(1,len(rs)+1), 'Label': rs})\n",
        "    \n",
        "sm.to_csv('mine_submission.csv', index = False)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "1cf46dd1-8660-1044-0da1-60a2da1b0bdd"
      },
      "outputs": [],
      "source": [
        "from subprocess import check_output\n",
        "print(check_output([\"ls\", \".\"]).decode(\"utf8\"))\n"
      ]
    }
  ],
  "metadata": {
    "_change_revision": 0,
    "_is_fork": false,
    "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": "3.6.0"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}