{ "cells": [ { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "\n", "# Pandas Tutorial\n", "\n", "\n", "Jeff Reback\n", "\n", "@jreback\n", "\n", "November 11, 2015\n", "\n", "PyData NYC 2015\n", "\n", "http://tiny.cc/pandaspydata\n" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "subslide" } }, "source": [ "Installation documentation\n", "\n", "http://pandas.pydata.org/pandas-docs/stable/install.html" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "fragment" } }, "source": [ "Pandas Main Documentation\n", "\n", "http://pandas.pydata.org/pandas-docs/stable/index.html" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "fragment" } }, "source": [ "Tutorials\n", "\n", "http://pandas.pydata.org/pandas-docs/stable/tutorials.html" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "fragment" } }, "source": [ "Parts of this tutorial taken from\n", "\n", "https://github.com/TomAugspurger/PyDataSeattle" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "subslide" } }, "source": [ "# Installation\n", "\n", "Let's make sure that we have some dependencies installed" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false, "slideshow": { "slide_type": "fragment" } }, "outputs": [ { "data": { "text/plain": [ "'3.4.3 |Continuum Analytics, Inc.| (default, Oct 20 2015, 14:27:51) \\n[GCC 4.2.1 (Apple Inc. build 5577)]'" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import sys\n", "sys.version" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": false, "slideshow": { "slide_type": "subslide" } }, "outputs": [ { "data": { "text/plain": [ "'0.17.0'" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import numpy as np\n", "import pandas as pd\n", "import statsmodels\n", "import sklearn\n", "import seaborn\n", "import xlsxwriter\n", "import sqlalchemy\n", "%matplotlib inline\n", "\n", "pd.options.display.max_rows = 12\n", "pd.options.display.max_columns = 10\n", "pd.__version__" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "fragment" } }, "source": [ "A nice way to install everything\n", "\n", "```\n", "conda install --file requirements.txt\n", "```" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# Overview" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "fragment" } }, "source": [ "1. Data IO\n", "2. Examining Data\n", "3. Groupby\n", "4. Tidy Data\n", "5. Timeseries\n", "6. Compute" ] }, { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "slide" } }, "source": [ "# Thanks" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Contribute to pandas!\n", "\n", "https://github.com/pydata/pandas/issues" ] } ], "metadata": { "celltoolbar": "Slideshow", "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": "3.4.3" } }, "nbformat": 4, "nbformat_minor": 0 }