{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "%matplotlib inline"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Merge data\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "import pandas as pd\nimport numpy as np"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "**Concat**\n\nCreate a dataFrame\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "dataFrame = pd.DataFrame(np.random.randn(10, 4))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "break in pieces\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "pieces = [dataFrame[:3], dataFrame[3:7], dataFrame[7:]]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "pd.concat(pieces)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "**Join**\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "left = pd.DataFrame({\"key\": [\"foo\", \"foo\"], \"lval\": [1, 2]})\nright = pd.DataFrame({\"key\": [\"foo\", \"foo\"], \"rval\": [4, 5]})"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "pd.merge(left, right, on=\"key\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "**Grouping**\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "dataFrame = pd.DataFrame(\n    {\n        \"A\": [\"foo\", \"bar\", \"foo\", \"bar\", \"foo\", \"bar\", \"foo\", \"foo\"],\n        \"B\": [\"one\", \"one\", \"two\", \"three\", \"two\", \"two\", \"one\", \"three\"],\n        \"C\": np.random.randn(8),\n        \"D\": np.random.randn(8),\n    }\n)\ndataFrame.groupby(\"A\").sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "dataFrame.groupby([\"A\", \"B\"]).sum()"
      ]
    }
  ],
  "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": "3.8.10"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}