ORPA-pyOpenRPA/Resources/WPy64-3720/notebooks/docs/pandas_demo_from_jreback.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pandas demo from Jake Reback\n",
    "see https://github.com/jreback/PyDataNYC2015 or http://pandas.pydata.org/pandas-docs/version/0.17.1/style.html#Table-Styles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "pd.options.display.max_rows=12\n",
    "pd.options.display.width=80\n",
    "\n",
    "# read a csv\n",
    "df = pd.read_csv('~/seaborn-data/iris.csv',index_col=False)\n",
    "# adjust column names\n",
    "df.columns = df.columns.str.replace('\\s+','_').str.lower()\n",
    "# in pandas 0.17.1 and more : sample and style ... \n",
    "def color_negative_red(val):\n",
    "    \"\"\"\n",
    "    Takes a scalar and returns a string with\n",
    "    the css property `'color: red'` for negative\n",
    "    strings, black otherwise.\n",
    "    \"\"\"\n",
    "    color = 'red' if   (isinstance(val, (int,   float)) and val < 3) else 'black'\n",
    "    return 'color: %s' % color\n",
    "\n",
    "def highlight_max(s):\n",
    "    '''\n",
    "    highlight the maximum in a Series\n",
    "    '''\n",
    "    is_max = s == s.max()\n",
    "    return ['background-color: yellow' if v else '' for v in is_max]\n",
    "\n",
    "cm = sns.light_palette(\"green\", as_cmap=True)\n",
    "\n",
    "(df\n",
    "   .sample (n=7)\n",
    "   .style\n",
    "   .applymap(color_negative_red, subset=pd.IndexSlice[['sepal_width', 'petal_width']])\n",
    "   .bar(subset=['sepal_length', 'petal_length'], color='#7F7FFF')\n",
    "   .background_gradient(subset=['sepal_width', 'petal_width'], cmap=cm)\n",
    "   .apply(highlight_max)\n",
    "   .highlight_null(null_color='red')\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# assign = define new temporary columns (like 'mutate' in R language)\n",
    "(df\n",
    "   .query('sepal_length > 5')\n",
    "   .assign(sepal_ratio = lambda x: x.sepal_width / x.sepal_length,\n",
    "           petal_ratio = lambda x: x.petal_width / x.petal_length)\n",
    "   .plot\n",
    "   .scatter(x='sepal_ratio', y='petal_ratio', figsize=(8,4))\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# pipe = like '%>%' in R language\n",
    "(df\n",
    "   .query('sepal_length > 5')\n",
    "   .assign(sepal_ratio = lambda x: x.sepal_width / x.sepal_length,\n",
    "           petal_ratio = lambda x: x.petal_width / x.petal_length)\n",
    "   .pipe(sns.pairplot, hue='species', height=1.5)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Pandas interactive\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# create a df with random datas\n",
    "np.random.seed(24)\n",
    "df = pd.DataFrame({'A': np.linspace(1, 10, 10)})\n",
    "df = pd.concat([df, pd.DataFrame(np.random.randn(10, 4), columns=list('BCDE'))],\n",
    "               axis=1)\n",
    "df.iloc[0, 2] = np.nan\n",
    "\n",
    "# interactive\n",
    "#from IPython.html import widgets\n",
    "from ipywidgets import widgets\n",
    "@widgets.interact\n",
    "def f(h_neg=(0, 359, 1), h_pos=(0, 359), s=(0., 99.9), l=(0., 99.9)):\n",
    "    return (df\n",
    "             .style\n",
    "             .background_gradient(\n",
    "                cmap=sns.palettes.diverging_palette(\n",
    "                     h_neg=h_neg, h_pos=h_pos, s=s, l=l, as_cmap=True)\n",
    "             ).highlight_null()\n",
    "           )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from IPython.display import HTML\n",
    "\n",
    "def hover(hover_color=\"#ff0f99\"):\n",
    "    return dict(selector=\"tr:hover\",\n",
    "                props=[(\"background-color\", \"%s\" % hover_color)])\n",
    "\n",
    "styles = [\n",
    "    hover(),\n",
    "    dict(selector=\"th\", props=[(\"font-size\", \"150%\"),\n",
    "                               (\"text-align\", \"center\")]),\n",
    "    dict(selector=\"caption\", props=[(\"caption-side\", \"bottom\")])\n",
    "]\n",
    "html = (df.style.set_table_styles(styles)\n",
    "          .set_caption(\"Hover to highlight.\"))\n",
    "html"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Usefull links\n",
    "\n",
    "### Beginners Training Video: [\"Brandon Rhodes - Pandas From The Ground Up - PyCon 2015 \"](https://www.youtube.com/watch?v=5JnMutdy6Fw)\n",
    "\n",
    "### Pandas [API reference](http://pandas.pydata.org/pandas-docs/stable/api.html)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}