{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "above-transformation", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Creating example bls maps\n", "from bls_geo import *\n", "\n", "# can check out https://www.bls.gov/oes/current/oes_stru.htm\n", "bio = '172031'\n", "bio_stats = oes_geo(bio)\n", "areas = get_areas() # this takes a few minutes\n", "state = state_albers()\n", "geo_bio = merge_occgeo(bio_stats,areas)\n", "\n", "ax = geo_bio.plot(column='Employment',cmap='inferno',legend=True,zorder=2)\n", "state.boundary.plot(ax=ax,color='grey',linewidth=0.5,zorder=1)\n", "ax.set_ylim(0.1*1e6,3.3*1e6)\n", "ax.set_xlim(-0.3*1e7,0.3*1e7) # lower 48 focus (for Albers proj)\n", "ax.set_axis_off()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 2, "id": "selective-mainstream", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
Make this Notebook Trusted to load map: File -> Trust Notebook
" ], "text/plain": [ "" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Can export to excel (csv parsing is tough, maybe use tsv instead)\n", "bio_stats.to_excel('biojobs.xlsx')\n", "\n", "att = ['areaName','Employment','Location Quotient','Employment per 1,000 jobs','Annual mean wage']\n", "form = ['',',.0f','.2f','.2f',',.0f']\n", "\n", "map_bio = fol_map(geo_bio,'Employment',['lat', 'lon'],att,form)\n", "#map_bio.save('biomap.html')\n", "map_bio" ] }, { "cell_type": "code", "execution_count": 3, "id": "aquatic-video", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
areaNameEmploymentAnnual mean wageAnnual 75th percentile wage
69New York-Newark-Jersey City, NY-NJ-PA4730129250.0158950.0
92San Francisco-Oakland-Hayward, CA3170148680.0175410.0
105Washington-Arlington-Alexandria, DC-VA-MD-WV2410108060.0132720.0
24Chicago-Naperville-Elgin, IL-IN-WI2410101180.0126170.0
95Seattle-Tacoma-Bellevue, WA2330121090.0149700.0
93San Jose-Sunnyvale-Santa Clara, CA2190146400.0178300.0
30Dallas-Fort Worth-Arlington, TX2160103860.0124100.0
8Atlanta-Sandy Springs-Roswell, GA181092240.0118250.0
60Los Angeles-Long Beach-Anaheim, CA1640117550.0145070.0
78Phoenix-Mesa-Scottsdale, AZ1350109000.0130500.0
\n", "
" ], "text/plain": [ " areaName Employment \\\n", "69 New York-Newark-Jersey City, NY-NJ-PA 4730 \n", "92 San Francisco-Oakland-Hayward, CA 3170 \n", "105 Washington-Arlington-Alexandria, DC-VA-MD-WV 2410 \n", "24 Chicago-Naperville-Elgin, IL-IN-WI 2410 \n", "95 Seattle-Tacoma-Bellevue, WA 2330 \n", "93 San Jose-Sunnyvale-Santa Clara, CA 2190 \n", "30 Dallas-Fort Worth-Arlington, TX 2160 \n", "8 Atlanta-Sandy Springs-Roswell, GA 1810 \n", "60 Los Angeles-Long Beach-Anaheim, CA 1640 \n", "78 Phoenix-Mesa-Scottsdale, AZ 1350 \n", "\n", " Annual mean wage Annual 75th percentile wage \n", "69 129250.0 158950.0 \n", "92 148680.0 175410.0 \n", "105 108060.0 132720.0 \n", "24 101180.0 126170.0 \n", "95 121090.0 149700.0 \n", "93 146400.0 178300.0 \n", "30 103860.0 124100.0 \n", "8 92240.0 118250.0 \n", "60 117550.0 145070.0 \n", "78 109000.0 130500.0 " ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Data science jobs\n", "ds = '152098'\n", "ds_stats = oes_geo(ds)\n", "geo_ds = merge_occgeo(ds_stats,areas)\n", "geo_ds.sort_values(by='Employment',inplace=True,ascending=False)\n", "lim_fields = ['areaName','Employment','Annual mean wage','Annual 75th percentile wage']\n", "geo_ds[lim_fields].head(10)" ] }, { "cell_type": "code", "execution_count": 4, "id": "computational-wright", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
Make this Notebook Trusted to load map: File -> Trust Notebook
" ], "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\n", "map_ds = fol_map(geo_ds,'Annual 75th percentile wage',['lat', 'lon'],att,form)\n", "map_ds" ] }, { "cell_type": "code", "execution_count": null, "id": "regular-terrace", "metadata": {}, "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": "3.7.10" } }, "nbformat": 4, "nbformat_minor": 5 }