Code Club week 7 code resources

folium_base.py

from IPython.display import HTML
import folium

def inline_map(map):
    """
    Embeds the HTML source of the map directly into the IPython notebook.
    
    This method will not work if the map depends on any files (json data). Also this uses
    the HTML5 srcdoc attribute, which may not be supported in all browsers.
    """
    map._build_map()
    return HTML('<iframe srcdoc="{srcdoc}" style="width: 100%; height: 510px; border: none"></iframe>'.format(srcdoc=map.HTML.replace('"', '&quot;')))

def embed_map(map, path="map.html"):
    """
    Embeds a linked iframe to the map into the IPython notebook.
    
    Note: this method will not capture the source of the map into the notebook.
    This method should work for all maps (as long as they use relative urls).
    """
    map.create_map(path=path)
    return HTML('<iframe src="files/{path}" style="width: 100%; height: 510px; border: none"></iframe>'.format(path=path))

food_api.py

import json
import requests

def getFoodRatingData(name,address):
    params={'name':name,'address':address}
    r=requests.get('http://api.ratings.food.gov.uk/Establishments',
                   headers={"x-api-version":2},
                   params=params)
    return r

def parseFoodRatingData(jdata):
    df=pd.DataFrame()
    for establishment in jdata['establishments']:
        info={}
        for item in ['BusinessName','FHRSID','PostCode','RatingValue','RatingDate']:
            info[item]= establishment[item] 
        for item in establishment['geocode']:
            info[item]= establishment['geocode'][item] 
        for item in establishment['scores']:
            info[item]= establishment['scores'][item] 
        df=df.append(info,ignore_index=True)
    return df

def getAndParseFoodRatingData(name,address):
    r=getFoodRatingData(name,address)
    jdata=json.loads(r.content)
    df=parseFoodRatingData(jdata)
    return df

week7_mapping.ipynb

week_7_regexp_and_time.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:09c43f8363f52e1a5113ab06a87e0f67fc683c75835697259a2590319c07be41"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Code Club Week 7"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Regular Expressions"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import re\n",
      "?re"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "txt= 'The cat sat on the mat 11 times.'\n",
      "pattern=re.compile(r'^The (\\w*)')\n",
      "pattern.findall(txt)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "txt= 'The cat sat on the mat 11 times.'\n",
      "pattern=re.compile(r'\\s(.at)')\n",
      "pattern.findall(txt)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern2=re.compile(r'^The (\\w*) sat (.*) (\\d*) times\\.$')\n",
      "grouper=pattern2.match(txt)\n",
      "grouper.groups()"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "grouper.group(2)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern2.match(txt).group(1)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "whatwhere=re.compile(r'^The (?P<what>\\w*) sat (?P<where>.*) (\\d*) times\\.$')\n",
      "whatwhere.match(txt).group('where')"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "whatwhere.match(txt).group(0)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "whatwhere.match(txt).group(3)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "whatwhere.match(txt).groups()"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "re.sub(r'The (\\w*) (.*) ([^\\s]*) ([\\d]{1,}.*)\\.',r'The \\3 \\2 \\1? Was it really \\4?',txt)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Time"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from datetime import datetime\n",
      "\n",
      "#Time and datetimes can be represented as special datetime objects\n",
      "now=datetime.now()\n",
      "now"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#We can index in using .microsecond, .second, .minute, .hour, .day, .month, .year\n",
      "now.microsecond"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#We can format a date in a variety of ways..\n",
      "\n",
      "#Reference: https://docs.python.org/2/library/datetime.html#strftime-and-strptime-behavior\n",
      "\n",
      "now.strftime(\"%d/%m/%Y\")"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "now_sentence=now.strftime(\"%A, %B %d, %Y (week %W)\")\n",
      "now_sentence"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#Shortcuts\n",
      "now_str=now.strftime(\"%F\")\n",
      "now_str"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#Parse the date back\n",
      "datetime.strptime(now_str,\"%Y-%m-%d\")"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "datetime.strptime(now_sentence,\"%A, %B %d, %Y (week %W)\")"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from dateutil.parser import parse\n",
      "?parse\n",
      "\n",
      "parse('11/2/13',dayfirst=True)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "parse('11-10-09',dayfirst=None,yearfirst=None)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "parse('January 22nd, 1983')"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "parse('January 22nd, 1983, 10:23am')"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Code Club Eats"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "To grab a Google Spreadsheet file as a CSV file, use the URL pattern (SHEETNUMBER starts at 0):"
     ]
    },
    {
     "cell_type": "raw",
     "metadata": {},
     "source": [
      "https://docs.google.com/spreadsheets/d/<KEY>/export?gid=SHEETNUMBER&format=csv"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "url='https://docs.google.com/a/okfn.org/spreadsheets/d/1M14S4hqG4F5P8H78VdOMMeoITOPBpVZEGoiCvXEFBQg/export?gid=0&format=csv'\n",
      "cceats=pd.read_csv(url)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "cceats"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Food Standards Agency - www.food.gov.uk\n",
      "\n"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import requests\n",
      "import json"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#http://api.ratings.food.gov.uk/help\n",
      "#http://docs.python-requests.org/en/latest/user/quickstart/\n",
      "\n",
      "params={'name':\"McDonald's\",'address':'SW12 9AU'}\n",
      "r=requests.get('http://api.ratings.food.gov.uk/Establishments',\n",
      "               headers={\"x-api-version\":2},\n",
      "               params=params)\n",
      "j=json.loads(r.content)\n",
      "j"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def getFoodRatingData(name,address):\n",
      "    params={'name':name,'address':address}\n",
      "    r=requests.get('http://api.ratings.food.gov.uk/Establishments',\n",
      "                   headers={\"x-api-version\":2},\n",
      "                   params=params)\n",
      "    return r\n",
      "\n",
      "def parseFoodRatingData(jdata):\n",
      "    df=pd.DataFrame()\n",
      "    for establishment in jdata['establishments']:\n",
      "        info={}\n",
      "        for item in ['BusinessName','FHRSID','PostCode','RatingValue','RatingDate']:\n",
      "            info[item]= establishment[item] \n",
      "        for item in establishment['geocode']:\n",
      "            info[item]= establishment['geocode'][item] \n",
      "        for item in establishment['scores']:\n",
      "            info[item]= establishment['scores'][item] \n",
      "        df=df.append(info,ignore_index=True)\n",
      "    return df\n",
      "\n",
      "def getAndParseFoodRatingData(name,address):\n",
      "    r=getFoodRatingData(name,address)\n",
      "    jdata=json.loads(r.content)\n",
      "    df=parseFoodRatingData(jdata)\n",
      "    return df"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "parseFoodRatingData(j)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "getAndParseFoodRatingData('Sacro Cuore','NW10 3NB')"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "adf=pd.DataFrame()\n",
      "for place in cceats.iterrows():\n",
      "    adf=adf.append(getAndParseFoodRatingData(place[1]['Name'],place[1]['Postcode']))\n",
      "adf[['FHRSID','BusinessName','PostCode','RatingDate','RatingValue','latitude','longitude',\n",
      "               'Structural','Hygiene','ConfidenceInManagement']]"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Mapping"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#!pip install folium\n",
      "import folium"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from IPython.display import HTML\n",
      "import folium\n",
      "\n",
      "def inline_map(map):\n",
      "    \"\"\"\n",
      "    Embeds the HTML source of the map directly into the IPython notebook.\n",
      "    \n",
      "    This method will not work if the map depends on any files (json data). Also this uses\n",
      "    the HTML5 srcdoc attribute, which may not be supported in all browsers.\n",
      "    \"\"\"\n",
      "    map._build_map()\n",
      "    return HTML('<iframe srcdoc=\"{srcdoc}\" style=\"width: 100%; height: 510px; border: none\"></iframe>'.format(srcdoc=map.HTML.replace('\"', '&quot;')))\n",
      "\n",
      "def embed_map(map, path=\"map.html\"):\n",
      "    \"\"\"\n",
      "    Embeds a linked iframe to the map into the IPython notebook.\n",
      "    \n",
      "    Note: this method will not capture the source of the map into the notebook.\n",
      "    This method should work for all maps (as long as they use relative urls).\n",
      "    \"\"\"\n",
      "    map.create_map(path=path)\n",
      "    return HTML('<iframe src=\"files/{path}\" style=\"width: 100%; height: 510px; border: none\"></iframe>'.format(path=path))"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ccd=pd.read_csv('/Users/ajh59/Downloads/Code-Club-s-Fave-Restaurants-Sheet1-csv.csv')\n",
      "ccd"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fmap=folium.Map(location=[51.5, 0], zoom_start=9)\n",
      "\n",
      "for row in ccd.iterrows():\n",
      "    latlon = [ row[1]['latitude'], row[1]['longitude'] ]\n",
      "    fmap.simple_marker( latlon )\n",
      "inline_map(fmap)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "fmap=folium.Map(location=[51.5, 0], zoom_start=9)\n",
      "\n",
      "for row in adf.iterrows():\n",
      "    latlon = [ row[1]['latitude'], row[1]['longitude'] ]\n",
      "    fmap.simple_marker( latlon, clustered_marker=True,\n",
      "                       popup='Name: {name}<br/>Score: {score}'.format(name=row[1]['BusinessName'],\n",
      "                                                                      score=row[1]['RatingValue']) )\n",
      "inline_map(fmap)"
     ],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {
      "activity": false
     },
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}