Software for Scientists - October 2015

genetic data.ipynb

python_project_demo.ipynb

weather_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "value = 42\n",
    "print \"\"\"The answer to life and everything is %s\"\"\" %value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "value = [4,2]\n",
    "print \"\"\"The answer to life and everything is composed of {} and {}\"\"\".format(*value)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "input_string = \"\"\"Some text <br /> has some <br /> additional\\\n",
    " &nbsp; weird sequences &nbsp; between &nbsp; spaces <br /> &nbsp;.\"\"\"\n",
    "print input_string.replace('<br /> ', '').replace(' &nbsp;', '')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "replace_awfull_seq = ['<br /> ', ' &nbsp;']\n",
    "input_string = \"\"\"Some text <br /> has some <br /> additional\\\n",
    " &nbsp; weird sequences &nbsp; between &nbsp; spaces <br /> &nbsp;.\"\"\"\n",
    "\n",
    "def replace_all(text, items):\n",
    "    for i in items:\n",
    "        text = text.replace(i, '')\n",
    "    return text\n",
    "replace_all(input_string, replace_awfull_seq)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as pyplot\n",
    "from datetime import datetime\n",
    "import time\n",
    "import os, calendar\n",
    "import urllib"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Download Weather Data and Save it to a file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "weather_info = ['Prague', 'Czech+Republic', '2015', '10', '17']\n",
    "\n",
    "file_name = 'weather_data.csv'\n",
    "clean_file_name = 'clean_weather_data.csv'\n",
    "\n",
    "def download_data(weather_info, weather_file):\n",
    "    weather_url = \"\"\"http://www.wunderground.com/history/airport/LKPR/{2}/{3}/{4}\\\n",
    "                    /DailyHistory.html?req_city={0}\\\n",
    "                    &req_state=&req_statename={1}\\\n",
    "                    &reqdb.zip=00000&reqdb.magic=1&reqdb.wmo=11518&format=1\"\"\".format(*weather_info)\n",
    "    download_file = urllib.URLopener()\n",
    "    download_file.retrieve(weather_url, weather_file)\n",
    "\n",
    "download_data(weather_info, file_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Clean the file to a file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "noisy_data_file = open(file_name, \"r\")\n",
    "cleaned_file = open(clean_file_name, \"w\")\n",
    "\n",
    "cleaned_file.write(noisy_data_file.read().replace(\"<br />\",\"\").replace('\\n','',1))\n",
    "noisy_data_file.close()\n",
    "\n",
    "cleaned_file.close()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Process the data in the file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def date2int(date_str):\n",
    "    date = datetime.strptime(date_str, '%I:%M %p')\n",
    "    date = date.strftime('%H:%M')\n",
    "    return date\n",
    "\n",
    "def read_weather(file_name):\n",
    "    dtypes = np.dtype({ 'names' : ('timestamp', 'temp', 'events'),\n",
    "                        'formats' : ['S100', np.float, 'S100'] })\n",
    "\n",
    "    data = np.loadtxt(file_name, delimiter=',', skiprows=1, \n",
    "            converters = { 0 : date2int },\n",
    "            usecols=(0,1,11), dtype=dtypes)\n",
    "\n",
    "    return data\n",
    "data = read_weather('clean_weather_data.csv')\n",
    "# mean_temps = np.mean(data['temp'])\n",
    "# min_temps = np.min(data['temp'])\n",
    "# max_temps = np.max(data['temp'])\n",
    "hour_list = [int(t[:2]) for t in data['timestamp']]\n",
    "temperature = data['temp']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Display results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "temp_hourly = pyplot.plot(hour_list,temperature)\n",
    "pyplot.title('Temperatures in Prague 17 Oct 2015')\n",
    "pyplot.ylabel('Temperature (C)')\n",
    "pyplot.xlabel('Hours of the day')\n",
    "pyplot.xticks(np.arange(min(hour_list), max(hour_list)+2, 2.0))\n",
    "pyplot.show(temp_hourly)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}