benbovy/Final_Project.ipynb

## Final_Project.ipynb
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'http://berkeleyearth.lbl.gov/auto/Regional/TAVG/Text/afghanistan-TAVG-Trend.txt'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import requests\n",
    "from lxml import html\n",
    "from urllib.request import unquote\n",
    "\n",
    "base_url = \"http://berkeleyearth.lbl.gov/auto/Regional/TAVG/Text/\"\n",
    "\n",
    "page = requests.get(base_url)\n",
    "tree = html.fromstring(page.content)\n",
    "\n",
    "file_links = tree.xpath(\"//a[contains(@href,'.txt')]/@href\")\n",
    "region_names = [unquote(link.split('-')[0]) for link in file_links]\n",
    "\n",
    "regions = {k: base_url + v for k, v in zip(region_names, file_links)}\n",
    "\n",
    "regions['afghanistan']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>anomaly</th>\n",
       "      <th>uncertainty</th>\n",
       "      <th>10-year-anomaly</th>\n",
       "      <th>10-year-uncertainty</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1960-09-01</th>\n",
       "      <td>0.516</td>\n",
       "      <td>0.095</td>\n",
       "      <td>-0.027</td>\n",
       "      <td>0.043</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1855-02-01</th>\n",
       "      <td>-1.233</td>\n",
       "      <td>1.771</td>\n",
       "      <td>-0.463</td>\n",
       "      <td>0.555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1862-04-01</th>\n",
       "      <td>-1.298</td>\n",
       "      <td>1.033</td>\n",
       "      <td>-0.428</td>\n",
       "      <td>0.373</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1778-08-01</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1872-07-01</th>\n",
       "      <td>-0.435</td>\n",
       "      <td>0.994</td>\n",
       "      <td>-0.420</td>\n",
       "      <td>0.240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1927-08-01</th>\n",
       "      <td>-1.366</td>\n",
       "      <td>0.174</td>\n",
       "      <td>0.038</td>\n",
       "      <td>0.081</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1877-08-01</th>\n",
       "      <td>-0.019</td>\n",
       "      <td>0.834</td>\n",
       "      <td>-0.397</td>\n",
       "      <td>0.221</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1793-02-01</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1981-01-01</th>\n",
       "      <td>3.074</td>\n",
       "      <td>0.187</td>\n",
       "      <td>0.123</td>\n",
       "      <td>0.028</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1871-03-01</th>\n",
       "      <td>0.719</td>\n",
       "      <td>1.151</td>\n",
       "      <td>-0.424</td>\n",
       "      <td>0.245</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1983-01-01</th>\n",
       "      <td>1.474</td>\n",
       "      <td>0.198</td>\n",
       "      <td>0.232</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1969-04-01</th>\n",
       "      <td>1.246</td>\n",
       "      <td>0.211</td>\n",
       "      <td>-0.130</td>\n",
       "      <td>0.038</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1964-04-01</th>\n",
       "      <td>-0.211</td>\n",
       "      <td>0.173</td>\n",
       "      <td>-0.076</td>\n",
       "      <td>0.039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1950-07-01</th>\n",
       "      <td>-1.100</td>\n",
       "      <td>0.146</td>\n",
       "      <td>0.092</td>\n",
       "      <td>0.045</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1872-10-01</th>\n",
       "      <td>-0.839</td>\n",
       "      <td>0.608</td>\n",
       "      <td>-0.431</td>\n",
       "      <td>0.246</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1928-04-01</th>\n",
       "      <td>-1.341</td>\n",
       "      <td>0.155</td>\n",
       "      <td>-0.006</td>\n",
       "      <td>0.083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1800-07-01</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1890-02-01</th>\n",
       "      <td>0.090</td>\n",
       "      <td>1.010</td>\n",
       "      <td>-0.482</td>\n",
       "      <td>0.181</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-09-01</th>\n",
       "      <td>0.255</td>\n",
       "      <td>0.113</td>\n",
       "      <td>0.811</td>\n",
       "      <td>0.047</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1962-03-01</th>\n",
       "      <td>-1.195</td>\n",
       "      <td>0.174</td>\n",
       "      <td>0.005</td>\n",
       "      <td>0.035</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            anomaly  uncertainty  10-year-anomaly  10-year-uncertainty\n",
       "date                                                                  \n",
       "1960-09-01    0.516        0.095           -0.027                0.043\n",
       "1855-02-01   -1.233        1.771           -0.463                0.555\n",
       "1862-04-01   -1.298        1.033           -0.428                0.373\n",
       "1778-08-01      NaN          NaN              NaN                  NaN\n",
       "1872-07-01   -0.435        0.994           -0.420                0.240\n",
       "1927-08-01   -1.366        0.174            0.038                0.081\n",
       "1877-08-01   -0.019        0.834           -0.397                0.221\n",
       "1793-02-01      NaN          NaN              NaN                  NaN\n",
       "1981-01-01    3.074        0.187            0.123                0.028\n",
       "1871-03-01    0.719        1.151           -0.424                0.245\n",
       "1983-01-01    1.474        0.198            0.232                0.023\n",
       "1969-04-01    1.246        0.211           -0.130                0.038\n",
       "1964-04-01   -0.211        0.173           -0.076                0.039\n",
       "1950-07-01   -1.100        0.146            0.092                0.045\n",
       "1872-10-01   -0.839        0.608           -0.431                0.246\n",
       "1928-04-01   -1.341        0.155           -0.006                0.083\n",
       "1800-07-01      NaN          NaN              NaN                  NaN\n",
       "1890-02-01    0.090        1.010           -0.482                0.181\n",
       "2000-09-01    0.255        0.113            0.811                0.047\n",
       "1962-03-01   -1.195        0.174            0.005                0.035"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\n",
    "    \"http://berkeleyearth.lbl.gov/auto/Regional/TAVG/Text/united-states-TAVG-Trend.txt\",\n",
    "    delim_whitespace=True,\n",
    "    comment='%',\n",
    "    header=None,\n",
    "    parse_dates=[[0,1]],\n",
    "    index_col=(0),\n",
    "    usecols=(0, 1, 2, 3, 8, 9),\n",
    "    names=(\"year\", \"month\", \"anomaly\", \"uncertainty\", \"10-year-anomaly\", \"10-year-uncertainty\")\n",
    ")\n",
    "df.index.name = \"date\"\n",
    "df.sample(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEKCAYAAAAIO8L1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njUajKYtWEBqNRqMpy/8HliGDfrPpnywAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1134af0b8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[\"anomaly\"].plot(alpha=0.1, linewidth=2)\n",
    "df[\"10-year-anomaly\"].plot(linewidth=2)\n",
    "\n",
    "upper = df[\"10-year-anomaly\"] + df[\"10-year-uncertainty\"]\n",
    "mask = ~np.isnan(upper)\n",
    "lower = df[\"10-year-anomaly\"] - df[\"10-year-uncertainty\"]\n",
    "mask = mask & (~np.isnan(lower))\n",
    "\n",
    "lower.head()\n",
    "\n",
    "plt.fill_between(lower.index[mask], lower[mask], upper[mask], alpha=0.3)\n",
    "\n",
    "plt.ylabel(\"temp anomaly relative 1951-1980 [$^\\circ C$]\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEKCAYAAAAcgp5RAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1173c4908>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEKCAYAAAAcgp5RAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1173c4898>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[\"anomaly\"].hist(bins=20);\n",
    "plt.xlabel(\"anomaly\")\n",
    "plt.figure()\n",
    "df[\"anomaly\"].loc[\"1850\":\"1900\"].hist(bins=20, alpha=0.3)\n",
    "df[\"anomaly\"].loc[\"1950\":\"2000\"].hist(bins=20, alpha=0.3)\n",
    "plt.legend([\"1850-1900\", \"1950-2000\"])\n",
    "plt.xlabel(\"anomaly\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}