{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "ee64eb9c-96df-4a1c-ce4f-336579929471"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import seaborn as sns\n",
        "\n",
        "train_types = {'Agencia_ID':np.uint16, 'Ruta_SAK':np.uint16, 'Cliente_ID':np.uint32, \n",
        "               'Producto_ID':np.uint16, 'Demanda_uni_equil':np.uint32}\n",
        "\n",
        "test_types = {'Agencia_ID':np.uint16, 'Ruta_SAK':np.uint16, 'Cliente_ID':np.uint32, \n",
        "              'Producto_ID':np.uint16, 'id':np.uint32}\n",
        "\n",
        "df_train = pd.read_csv('../input/train.csv', usecols=train_types.keys(), dtype=train_types)\n",
        "df_test = pd.read_csv('../input/test.csv',usecols=test_types.keys(), dtype=test_types)\n",
        "df_client = pd.read_csv('../input/cliente_tabla.csv')\n",
        "df_product = pd.read_csv('../input/producto_tabla.csv')\n",
        "df_town = pd.read_csv('../input/town_state.csv')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "ee39a4bc-feee-7ab0-65ae-4a838d1a102b"
      },
      "outputs": [],
      "source": [
        "print('Train Data\\n', df_train.head(1), '\\n')\n",
        "print('Test Data\\n', df_test.head(1), '\\n')\n",
        "print('Client Data\\n', df_client.head(1), '\\n')\n",
        "print('Product Data\\n', df_product.head(1), '\\n')\n",
        "print('Town Data\\n', df_town.head(1), '\\n')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "f372bc8a-f9a7-4774-03d7-46a92cefbebf"
      },
      "outputs": [],
      "source": [
        "sns.distplot(np.log1p(df_train['Demanda_uni_equil']), kde=False)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "2b8b24b0-7ccb-c044-0d88-7f3771129dfd"
      },
      "outputs": [],
      "source": [
        "agencies_subset = np.zeros(len(df_train))\n",
        "for i in range(4):\n",
        "    this_agency = df_train['Agencia_ID'].unique()[i]\n",
        "    agencies_subset += df_train['Agencia_ID'] == this_agency"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "6c1c9121-8ac4-7e7f-d6e4-276358621577"
      },
      "outputs": [],
      "source": [
        "print(agencies_subset)\n",
        "#sns.distplot(df_train.loc[agencies_subset, 'Demanda_uni_equil'], kde=False)"
      ]
    }
  ],
  "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": "3.5.2"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}