{"id":582,"date":"2020-11-13T02:10:27","date_gmt":"2020-11-12T18:10:27","guid":{"rendered":"https:\/\/byy3.com\/?p=582"},"modified":"2021-01-09T10:10:07","modified_gmt":"2021-01-09T02:10:07","slug":"python%e5%88%a9%e7%94%a8geopandas%e5%ba%93%e5%92%8cpandas%e5%9c%a8anaconda%e7%9a%84jupter-notebook%e4%b8%8b%e7%94%9f%e6%88%90%e7%96%ab%e6%83%85%e6%bc%94%e5%8f%98%e5%9b%be","status":"publish","type":"post","link":"https:\/\/byy3.com\/?p=582","title":{"rendered":"python\u5229\u7528geopandas\u5e93\u548cpandas\u5728anaconda\u7684jupter notebook\u4e0b\u751f\u6210\u75ab\u60c5\u6f14\u53d8\u56fe"},"content":{"rendered":"

\u6570\u636e\u5f00\u6e90\u6765\u6e90\uff1ahttps:\/\/github.com\/lvwuwei\/covid-france<\/a><\/p>\n

\u6f14\u793a\u56fe https:\/\/www.chinanews.ga\/4930.html<\/a><\/p>\n

\n

\u6cd5\u56fd\u65b0\u51a0\u75c5\u6bd2\u53d1\u5c55\u6f14\u53d8\u56fe \u4ece2020\u5e7403\u670818\u65e5\u81f32020\u5e7411\u67088\u65e5 \u8003\u9a8c\u4f60\u673a\u5668\u6027\u80fd\u7684\u65f6\u5019\u5230\u4e86\uff0c\u56e0\u4e3a\u672c\u56fe\u8d85\u8fc7100m \u8bf7\u8010\u5fc3\u7b49\u5f85\u52a0\u8f7d\u2026\u2026\u2026 &\u2026<\/p>\n<\/div>\n

\"python\u5229\u7528geopandas\u5e93\u548cpandas\u5728anaconda\u7684jupter<\/div>\n

demo-covid.ipynb<\/a> \u5229\u7528\u8fd9\u4e2a\u751f\u6210\u6f14\u53d8\u56fe\uff1a\u76ee\u5f55\u4e0b\u9700\u8981\u65b0\u5efa\u4e00\u4e2aimg\u6587\u4ef6\u5939<\/p>\n

\u9700\u8981\u5bfc\u5165\u7684\u4f9d\u8d56\u5e93<\/p>\n

from<\/span> IPython.display<\/span> i<\/span>mport<\/span> HTML<\/span> \r\nimport<\/span> requests<\/span> \r\nimport<\/span> zipfile<\/span> \r\nimport<\/span> io<\/span> from<\/span> datetime<\/span> \r\nimport<\/span> timedelta<\/span>,<\/span> date<\/span> \r\nimport<\/span> matplotlib<\/span> \r\nimport<\/span> matplotlib.pyplot<\/span> as<\/span> plt<\/span> \r\nfrom<\/span> mpl_toolkits.axes_grid1<\/span> import<\/span> make_axes_locatable<\/span> \r\nimport<\/span> pandas<\/span> as<\/span> pd<\/span> \r\nimport<\/span> geopandas<\/span> as<\/span> gpd<\/span> \r\nimport<\/span> contextily<\/span> as<\/span> ctx<\/span> \r\nfrom<\/span> PIL<\/span> import<\/span> Image\r\n\r\n\u6e90\u4ee3\u7801\uff1a\r\n\r\n<\/span><\/span><\/pre>\n
\n
\n
\n
\n
\n
\n
COVID-19 evolution in French departments<\/h1>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nVisualize evolution of the number of people hospitalized in French departments due to COVID-19 infection<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[1]:<\/div>\n
\n
\n
\n
%<\/span>load_ext<\/span> lab_black<\/span>\r\n%<\/span>matplotlib<\/span> inline<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[2]:<\/div>\n
\n
\n
\n
from<\/span> IPython.display<\/span> import<\/span> HTML<\/span>\r\nimport<\/span> requests<\/span>\r\nimport<\/span> zipfile<\/span>\r\nimport<\/span> io<\/span>\r\nfrom<\/span> datetime<\/span> import<\/span> timedelta<\/span>,<\/span> date<\/span>\r\nimport<\/span> matplotlib<\/span>\r\nimport<\/span> matplotlib.pyplot<\/span> as<\/span> plt<\/span>\r\nfrom<\/span> mpl_toolkits.axes_grid1<\/span> import<\/span> make_axes_locatable<\/span>\r\nimport<\/span> pandas<\/span> as<\/span> pd<\/span>\r\nimport<\/span> geopandas<\/span> as<\/span> gpd<\/span>\r\nimport<\/span> contextily<\/span> as<\/span> ctx<\/span>\r\nfrom<\/span> PIL<\/span> import<\/span> Image<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nCOVID data are open data from the French open data portal data.gouv.fr:\u00a0https:\/\/www.data.gouv.fr\/fr\/datasets\/donnees-relatives-a-lepidemie-du-covid-19\/<\/a><\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[3]:<\/div>\n
\n
\n
\n
url_dep<\/span> =<\/span> \"http:\/\/osm13.openstreetmap.fr\/~cquest\/openfla\/export\/departements-20140306-5m-shp.zip\"<\/span>\r\ncovid_url<\/span> =<\/span> (<\/span>\r\n \"https:\/\/www.data.gouv.fr\/fr\/datasets\/r\/63352e38-d353-4b54-bfd1-f1b3ee1cabd7\"<\/span>\r\n)<\/span>\r\nfilter_dep<\/span> =<\/span> [<\/span>\"971\"<\/span>,<\/span> \"972\"<\/span>,<\/span> \"973\"<\/span>,<\/span> \"974\"<\/span>,<\/span> \"976\"<\/span>]<\/span> # only metropolitan France<\/span>\r\nfigsize<\/span> =<\/span> (<\/span>15<\/span>,<\/span> 15<\/span>)<\/span>\r\ntile_zoom<\/span> =<\/span> 7<\/span>\r\nframe_duration<\/span> =<\/span> 500<\/span> # in ms<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nLoad French departements data into a GeoPandas GeoSeries<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
More information on these geographical open data can be found here:\u00a0https:\/\/www.data.gouv.fr\/fr\/datasets\/contours-des-departements-francais-issus-d-openstreetmap\/<\/a><\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[4]:<\/div>\n
\n
\n
\n
local_path<\/span> =<\/span> \"tmp\/\"<\/span>\r\nr<\/span> =<\/span> requests<\/span>.<\/span>get<\/span>(<\/span>url_dep<\/span>)<\/span>\r\nz<\/span> =<\/span> zipfile<\/span>.<\/span>ZipFile<\/span>(<\/span>io<\/span>.<\/span>BytesIO<\/span>(<\/span>r<\/span>.<\/span>content<\/span>))<\/span>\r\nz<\/span>.<\/span>extractall<\/span>(<\/span>path<\/span>=<\/span>local_path<\/span>)<\/span>\r\nfilenames<\/span> =<\/span> [<\/span>\r\n y<\/span>\r\n for<\/span> y<\/span> in<\/span> sorted<\/span>(<\/span>z<\/span>.<\/span>namelist<\/span>())<\/span>\r\n for<\/span> ending<\/span> in<\/span> [<\/span>\"dbf\"<\/span>,<\/span> \"prj\"<\/span>,<\/span> \"shp\"<\/span>,<\/span> \"shx\"<\/span>]<\/span>\r\n if<\/span> y<\/span>.<\/span>endswith<\/span>(<\/span>ending<\/span>)<\/span>\r\n]<\/span>\r\ndbf<\/span>,<\/span> prj<\/span>,<\/span> shp<\/span>,<\/span> shx<\/span> =<\/span> [<\/span>filename<\/span> for<\/span> filename<\/span> in<\/span> filenames<\/span>]<\/span>\r\nfr<\/span> =<\/span> gpd<\/span>.<\/span>read_file<\/span>(<\/span>local_path<\/span> +<\/span> shp<\/span>)<\/span> # + encoding=\"utf-8\" if needed<\/span>\r\nfr<\/span>.<\/span>crs<\/span> =<\/span> \"epsg:4326\"<\/span> # {'init': 'epsg:4326'}<\/span>\r\nmet<\/span> =<\/span> fr<\/span>.<\/span>query<\/span>(<\/span>\"code_insee not in @filter_dep\"<\/span>)<\/span>\r\nmet<\/span>.<\/span>set_index<\/span>(<\/span>\"code_insee\"<\/span>,<\/span> inplace<\/span>=<\/span>True<\/span>)<\/span>\r\nmet<\/span> =<\/span> met<\/span>[<\/span>\"geometry\"<\/span>]<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nLoad the map tile with contextily<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[5]:<\/div>\n
\n
\n
\n
w<\/span>,<\/span> s<\/span>,<\/span> e<\/span>,<\/span> n<\/span> =<\/span> met<\/span>.<\/span>total_bounds<\/span>\r\nbck<\/span>,<\/span> ext<\/span> =<\/span> ctx<\/span>.<\/span>bounds2img<\/span>(<\/span>w<\/span>,<\/span> s<\/span>,<\/span> e<\/span>,<\/span> n<\/span>,<\/span> zoom<\/span>=<\/span>tile_zoom<\/span>,<\/span> ll<\/span>=<\/span>True<\/span>)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nPlot function to save image at a given date (title)<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[6]:<\/div>\n
\n
\n
\n
def<\/span> save_img<\/span>(<\/span>df<\/span>,<\/span> title<\/span>,<\/span> img_name<\/span>,<\/span> vmin<\/span>,<\/span> vmax<\/span>):<\/span>\r\n gdf<\/span> =<\/span> gpd<\/span>.<\/span>GeoDataFrame<\/span>(<\/span>df<\/span>,<\/span> crs<\/span>=<\/span>{<\/span>\"init\"<\/span>:<\/span> \"epsg:4326\"<\/span>})<\/span>\r\n gdf_3857<\/span> =<\/span> gdf<\/span>.<\/span>to_crs<\/span>(<\/span>epsg<\/span>=<\/span>3857<\/span>)<\/span> # web mercator<\/span>\r\n f<\/span>,<\/span> ax<\/span> =<\/span> plt<\/span>.<\/span>subplots<\/span>(<\/span>figsize<\/span>=<\/span>figsize<\/span>)<\/span>\r\n ax<\/span>.<\/span>imshow<\/span>(<\/span>\r\n bck<\/span>,<\/span> extent<\/span>=<\/span>ext<\/span>,<\/span> interpolation<\/span>=<\/span>\"sinc\"<\/span>,<\/span> aspect<\/span>=<\/span>\"equal\"<\/span>\r\n )<\/span> # load background map<\/span>\r\n divider<\/span> =<\/span> make_axes_locatable<\/span>(<\/span>ax<\/span>)<\/span>\r\n cax<\/span> =<\/span> divider<\/span>.<\/span>append_axes<\/span>(<\/span>\r\n \"right\"<\/span>,<\/span> size<\/span>=<\/span>\"5%\"<\/span>,<\/span> pad<\/span>=<\/span>0.1<\/span>\r\n )<\/span> # GeoPandas trick to adjust the legend bar<\/span>\r\n gdf_3857<\/span>.<\/span>plot<\/span>(<\/span>\r\n column<\/span>=<\/span>\"hosp\"<\/span>,<\/span> # Number of people currently hospitalized<\/span>\r\n ax<\/span>=<\/span>ax<\/span>,<\/span>\r\n cax<\/span>=<\/span>cax<\/span>,<\/span>\r\n alpha<\/span>=<\/span>0.75<\/span>,<\/span>\r\n edgecolor<\/span>=<\/span>\"k\"<\/span>,<\/span>\r\n legend<\/span>=<\/span>True<\/span>,<\/span>\r\n cmap<\/span>=<\/span>matplotlib<\/span>.<\/span>cm<\/span>.<\/span>get_cmap<\/span>(<\/span>\"magma_r\"<\/span>),<\/span>\r\n vmin<\/span>=<\/span>vmin<\/span>,<\/span>\r\n vmax<\/span>=<\/span>vmax<\/span>,<\/span>\r\n )<\/span>\r\n\r\n ax<\/span>.<\/span>set_axis_off<\/span>()<\/span>\r\n ax<\/span>.<\/span>get_xaxis<\/span>()<\/span>.<\/span>set_visible<\/span>(<\/span>False<\/span>)<\/span>\r\n ax<\/span>.<\/span>get_yaxis<\/span>()<\/span>.<\/span>set_visible<\/span>(<\/span>False<\/span>)<\/span>\r\n ax<\/span>.<\/span>set_title<\/span>(<\/span>title<\/span>,<\/span> fontsize<\/span>=<\/span>25<\/span>)<\/span>\r\n plt<\/span>.<\/span>savefig<\/span>(<\/span>img_name<\/span>,<\/span> bbox_inches<\/span>=<\/span>\"tight\"<\/span>)<\/span> # pad_inches=-0.1 to remove border<\/span>\r\n plt<\/span>.<\/span>close<\/span>(<\/span>f<\/span>)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nLoad COVID data into a pandas DataFrame<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[7]:<\/div>\n
\n
\n
\n
cov<\/span> =<\/span> pd<\/span>.<\/span>read_csv<\/span>(<\/span>covid_url<\/span>,<\/span> sep<\/span>=<\/span>\";\"<\/span>,<\/span> index_col<\/span>=<\/span>2<\/span>,<\/span> parse_dates<\/span>=<\/span>True<\/span>,)<\/span>\r\ncov<\/span> =<\/span> cov<\/span>.<\/span>query<\/span>(<\/span>\"sexe == 0\"<\/span>)<\/span> # sum of male\/female<\/span>\r\ncov<\/span> =<\/span> cov<\/span>.<\/span>query<\/span>(<\/span>\"dep not in @filter_dep\"<\/span>)<\/span>\r\ncov<\/span>.<\/span>dropna<\/span>(<\/span>inplace<\/span>=<\/span>True<\/span>)<\/span>\r\ncov<\/span>.<\/span>head<\/span>()<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
Out[7]:<\/div>\n
\n
\n\n\n\n\n\n\n\n\n\n\n
<\/th>\ndep<\/th>\nsexe<\/th>\nhosp<\/th>\nrea<\/th>\nrad<\/th>\ndc<\/th>\n<\/tr>\n
jour<\/th>\n<\/th>\n<\/th>\n<\/th>\n<\/th>\n<\/th>\n<\/th>\n<\/tr>\n<\/thead>\n
2020-03-18<\/td>\n01<\/td>\n0<\/td>\n2<\/td>\n0<\/td>\n1<\/td>\n0<\/td>\n<\/tr>\n
2020-03-18<\/td>\n02<\/td>\n0<\/td>\n41<\/td>\n10<\/td>\n18<\/td>\n11<\/td>\n<\/tr>\n
2020-03-18<\/td>\n03<\/td>\n0<\/td>\n4<\/td>\n0<\/td>\n1<\/td>\n0<\/td>\n<\/tr>\n
2020-03-18<\/td>\n04<\/td>\n0<\/td>\n3<\/td>\n1<\/td>\n2<\/td>\n0<\/td>\n<\/tr>\n
2020-03-18<\/td>\n05<\/td>\n0<\/td>\n8<\/td>\n1<\/td>\n9<\/td>\n0<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nAdd geometry data to COVID DataFrame<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[8]:<\/div>\n
\n
\n
\n
cov<\/span>[<\/span>\"geometry\"<\/span>]<\/span> =<\/span> cov<\/span>[<\/span>\"dep\"<\/span>]<\/span>.<\/span>map<\/span>(<\/span>met<\/span>)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nParse recorded days and save one image for each day<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[9]:<\/div>\n
\n
\n
\n
def<\/span> daterange<\/span>(<\/span>date1<\/span>,<\/span> date2<\/span>):<\/span>\r\n for<\/span> n<\/span> in<\/span> range<\/span>(<\/span>int<\/span>((<\/span>date2<\/span> -<\/span> date1<\/span>)<\/span>.<\/span>days<\/span>)<\/span> +<\/span> 1<\/span>):<\/span>\r\n yield<\/span> date1<\/span> +<\/span> timedelta<\/span>(<\/span>n<\/span>)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
Create the folder img at the root of the notebook<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[10]:<\/div>\n
\n
\n
\n
vmax<\/span> =<\/span> cov<\/span>.<\/span>hosp<\/span>.<\/span>max<\/span>()<\/span>\r\nfor<\/span> i<\/span>,<\/span> dt<\/span> in<\/span> enumerate<\/span>(<\/span>daterange<\/span>(<\/span>cov<\/span>.<\/span>index<\/span>.<\/span>min<\/span>(),<\/span> cov<\/span>.<\/span>index<\/span>.<\/span>max<\/span>())):<\/span>\r\n title<\/span> =<\/span> dt<\/span>.<\/span>strftime<\/span>(<\/span>\"<\/span>%d<\/span>-%b-%Y\"<\/span>)<\/span>\r\n df<\/span> =<\/span> cov<\/span>.<\/span>query<\/span>(<\/span>\"jour == @dt\"<\/span>)<\/span>\r\n df<\/span> =<\/span> df<\/span>.<\/span>drop_duplicates<\/span>(<\/span>subset<\/span>=<\/span>[<\/span>\"dep\"<\/span>],<\/span> keep<\/span>=<\/span>\"first\"<\/span>)<\/span>\r\n img_name<\/span> =<\/span> \"img\/\"<\/span> +<\/span> str<\/span>(<\/span>i<\/span>)<\/span> +<\/span> \".png\"<\/span>\r\n save_img<\/span>(<\/span>df<\/span>,<\/span> title<\/span>,<\/span> img_name<\/span>,<\/span> 0<\/span>,<\/span> vmax<\/span>)<\/span>\r\n<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
<\/div>\n
\n
\n
\nCompile images in animated gif<\/h4>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
In\u00a0[11]:<\/div>\n
\n
\n
\n
frames<\/span> =<\/span> []<\/span>\r\nfor<\/span> i<\/span>,<\/span> dt<\/span> in<\/span> enumerate<\/span>(<\/span>daterange<\/span>(<\/span>cov<\/span>.<\/span>index<\/span>.<\/span>min<\/span>(),<\/span> cov<\/span>.<\/span>index<\/span>.<\/span>max<\/span>())):<\/span>\r\n name<\/span> =<\/span> \"img\/\"<\/span> +<\/span> str<\/span>(<\/span>i<\/span>)<\/span> +<\/span> \".png\"<\/span>\r\n frames<\/span>.<\/span>append<\/span>(<\/span>Image<\/span>.<\/span>open<\/span>(<\/span>name<\/span>))<\/span>\r\n\r\nframes<\/span>[<\/span>0<\/span>]<\/span>.<\/span>save<\/span>(<\/span>\r\n \"covid.gif\"<\/span>,<\/span>\r\n format<\/span>=<\/span>\"GIF\"<\/span>,<\/span>\r\n append_images<\/span>=<\/span>frames<\/span>[<\/span>1<\/span>:],<\/span>\r\n save_all<\/span>=<\/span>True<\/span>,<\/span>\r\n duration<\/span>=<\/span>frame_duration<\/span>,<\/span>\r\n loop<\/span>=<\/span>0<\/span>,<\/span>\r\n)<\/span>\r\n\r\nfrom<\/span> IPython.display<\/span> import<\/span> HTML<\/span>\r\n\r\nHTML<\/span>(<\/span>\"<img src='covid.gif'>\"<\/span>)<\/span><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\r\n\r\n<\/pre>\n","protected":false},"excerpt":{"rendered":"
\u6570\u636e\u5f00\u6e90\u6765\u6e90\uff1ahttps:\/\/github.com\/lvwuwei\/covid-france \u6f14\u793a\u56fe http […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[58,57,33,352],"class_list":["post-582","post","type-post","status-publish","format-standard","hentry","category-python","tag-anaconda","tag-jupter-notebook","tag-python"],"_links":{"self":[{"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/posts\/582","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/byy3.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=582"}],"version-history":[{"count":0,"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/posts\/582\/revisions"}],"wp:attachment":[{"href":"https:\/\/byy3.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=582"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/byy3.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=582"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/byy3.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=582"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}