{
"metadata": {
"name": "basemap"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "raw",
"metadata": {},
"source": [
"Jeffrey S. Whitaker Phone : (303)497-6313\n",
"Meteorologist FAX : (303)497-6449\n",
"NOAA/OAR/CDC R/CDC1 Email :\n",
"Jeffrey.S.Whitaker-32lpuo7BZBA@xxxxxxxxxxxxxxxx\n",
"325 Broadway Office : Skaggs Research Cntr 1D-124\n",
"Boulder, CO, USA 80303-3328 Web : http://tinyurl.com/5telg\n",
"\n",
"http://osdir.com/ml/python.matplotlib.general/2005-10/msg00029.html"
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"vedi anche:\n",
"\n",
"http://www.stanford.edu/class/stats202/unemployment.html"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"the shape files can be downloaded at\n",
"\n",
" http://www.gadm.org/country\n",
"\n",
"for the data see also\n",
"\n",
" http://www.naturalearthdata.com/\n",
"\n",
"take a look at the following example\n",
"\n",
" http://www.geophysique.be/2011/01/27/matplotlib-basemap-tutorial-07-shapefiles-unleached/"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"import pandas\n",
"import pylab\n",
"from mpl_toolkits.basemap import Basemap\n",
"import matplotlib as mpl"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stderr",
"text": [
"/usr/local/lib/python2.7/dist-packages/pytz/__init__.py:35: UserWarning: Module dap was already imported from None, but /usr/lib/python2.7/dist-packages is being added to sys.path\n",
" from pkg_resources import resource_stream\n"
]
}
],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"def chart_info(Series_data, shapefile, extension, shape_key, \n",
" title='', cmap = ['b','purple','r']):\n",
" \"\"\"create a basemap from a shapefile and the information contained in a series coded by region name\n",
" \n",
" Arguments\n",
" ===========\n",
" Series_data: a pandas Series\n",
" This series should contains the data for each region with the same code that can be found under the shapefile\n",
" shapefile: string\n",
" The location of the shapefile that contains the information about the geography\n",
" extension: 4-tuple\n",
" the extension of the projection, in the format north, south, east, west\n",
" shape_key: string\n",
" tha name of the field in the shape file that indicate the region. The values of this field\n",
" should match those on the Series_data\n",
" title: string, optional\n",
" title of the plot\n",
" cmap: pylab colormap or list of colour names, optional\n",
" this gives the colormap that will be used to colorize the plot\n",
" \n",
" Returns\n",
" ===========\n",
" ax: pylab.Axes\n",
" the axes on which the plot has been drawn\n",
" \"\"\"\n",
" ax = pylab.gca()\n",
" # create the colormap if a list of names is given, otherwise\n",
" # use the given colormap\n",
" lscm = matplotlib.colors.LinearSegmentedColormap\n",
" if isinstance(cmap,(list,tuple)):\n",
" cmap = lscm.from_list('mycm',cmap)\n",
" #create a new basemap with the given extension\n",
" #TODO: allow to create more general projections\n",
" north, south, east, west = extension\n",
" m = Basemap(llcrnrlon=west,llcrnrlat=south,urcrnrlon=east,urcrnrlat=north,\n",
" projection='lcc',lat_0=(south+north)/2, lon_0=(east+west)/2)\n",
" #use basemap the read and draw the shapefile\n",
" #it will add two variables to the basemap, m.states and m.states_info\n",
" m.readshapefile(shapefile,'states',drawbounds=True);\n",
" #find minimum and maximum of the dataset to normalize the colors\n",
" max_pop = Series_data.max()*1.0\n",
" min_pop = Series_data.min()*1.0\n",
" # cycle through states, color each one.\n",
" # m.states contains the lines of the borders\n",
" # m.states_info contains the info on the region, like the name\n",
" for state_borders, state_info in zip(m.states, m.states_info):\n",
" statename = state_info[shape_key]\n",
" #skip those that aren't in the dataset without complaints\n",
" if statename not in Series_data:\n",
" continue\n",
" #set the color for each region\n",
" pop = Series_data[statename]\n",
" color = cmap( (pop-min_pop) / (max_pop-min_pop) )\n",
" #extract the x and y of the countours and plot them\n",
" xx,yy = zip(*state_borders)\n",
" patches = ax.fill(xx,yy,facecolor=color,edgecolor=color)\n",
" ax.set_title(title);\n",
" #generate a sintetic colorbar starting from the maximum and minimum of the dataset\n",
" axc, kw = matplotlib.colorbar.make_axes(ax)\n",
" norm = mpl.colors.Normalize(vmin=min_pop, vmax=max_pop)\n",
" cb1 = mpl.colorbar.ColorbarBase(axc, cmap=cmap, norm=norm)\n",
" return ax"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 10
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"try:\n",
" data_USA = pandas.read_csv('./USAinfo/unemployment_2011.csv')\n",
"except:\n",
" data_USA = pandas.read_csv(\"http://stats202.stanford.edu/data/unemployment_2011.csv\",sep='|')\n",
" data_USA.to_csv('./USAinfo/unemployment_2011.csv')"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data_USA[:5]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Unnamed: 0 | \n",
" code | \n",
" state_fips | \n",
" county_fips | \n",
" period | \n",
" civilian | \n",
" employed | \n",
" unemployed | \n",
" rate | \n",
" county | \n",
" state | \n",
" state_code | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 0 | \n",
" CN010010 | \n",
" 1 | \n",
" 1 | \n",
" Jun-11 | \n",
" 26328 | \n",
" 23987 | \n",
" 2341 | \n",
" 8.9 | \n",
" autauga | \n",
" alabama | \n",
" AL | \n",
"
\n",
" \n",
" | 1 | \n",
" 1 | \n",
" PA011000 | \n",
" 1 | \n",
" 3 | \n",
" Jun-11 | \n",
" 88382 | \n",
" 80841 | \n",
" 7541 | \n",
" 8.5 | \n",
" baldwin | \n",
" alabama | \n",
" AL | \n",
"
\n",
" \n",
" | 2 | \n",
" 2 | \n",
" CN010050 | \n",
" 1 | \n",
" 5 | \n",
" Jun-11 | \n",
" 9957 | \n",
" 8774 | \n",
" 1183 | \n",
" 11.9 | \n",
" barbour | \n",
" alabama | \n",
" AL | \n",
"
\n",
" \n",
" | 3 | \n",
" 3 | \n",
" CN010070 | \n",
" 1 | \n",
" 7 | \n",
" Jun-11 | \n",
" 9360 | \n",
" 8307 | \n",
" 1053 | \n",
" 11.3 | \n",
" bibb | \n",
" alabama | \n",
" AL | \n",
"
\n",
" \n",
" | 4 | \n",
" 4 | \n",
" CN010090 | \n",
" 1 | \n",
" 9 | \n",
" Jun-11 | \n",
" 26573 | \n",
" 24168 | \n",
" 2405 | \n",
" 9.1 | \n",
" blount | \n",
" alabama | \n",
" AL | \n",
"
\n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" | \n",
" civilian | \n",
" employed | \n",
" unemployed | \n",
" ratio | \n",
"
\n",
" \n",
" \n",
" \n",
" | Alabama | \n",
" 2150161 | \n",
" 1989181 | \n",
" 160980 | \n",
" 0.074869 | \n",
"
\n",
" \n",
" | Alaska | \n",
" 367279 | \n",
" 341506 | \n",
" 25773 | \n",
" 0.070173 | \n",
"
\n",
" \n",
" | Arizona | \n",
" 3026485 | \n",
" 2778186 | \n",
" 248299 | \n",
" 0.082042 | \n",
"
\n",
" \n",
" | Arkansas | \n",
" 1392559 | \n",
" 1290240 | \n",
" 102319 | \n",
" 0.073476 | \n",
"
\n",
" \n",
" | California | \n",
" 18431866 | \n",
" 16519142 | \n",
" 1912724 | \n",
" 0.103773 | \n",
"
\n",
" \n",
"
\n",
"