|
65 | 65 | "import matplotlib.pyplot as plt\n", |
66 | 66 | "\n", |
67 | 67 | "\n", |
68 | | - "from datetime import datetime\n", |
| 68 | + "from datetime import datetime as dt\n", |
69 | 69 | "import pandas as pd\n", |
70 | 70 | "import numpy as np\n", |
71 | 71 | "from IPython.display import display, HTML\n", |
|
728 | 728 | "source": [ |
729 | 729 | "agg_result = summarize_data.aggregate_points(point_layer=airbnb_layer,\n", |
730 | 730 | " polygon_layer=nyc_tracts_layer,\n", |
731 | | - " output_name='airbnb_counts'+ str(datetime.now().microsecond))" |
| 731 | + " output_name='airbnb_counts'+ str(dt.now().microsecond))" |
732 | 732 | ] |
733 | 733 | }, |
734 | 734 | { |
|
1676 | 1676 | "# Data Enriching operation\n", |
1677 | 1677 | "airbnb_count_by_tract_enriched = enrich_layer(airbnb_count_by_tract,\n", |
1678 | 1678 | " analysis_variables = variable_names,\n", |
1679 | | - " output_name='airbnb_tract_enrich1'+ str(datetime.now().microsecond))" |
| 1679 | + " output_name='airbnb_tract_enrich1'+ str(dt.now().microsecond))" |
1680 | 1680 | ] |
1681 | 1681 | }, |
1682 | 1682 | { |
|
4285 | 4285 | " hotels_lyr,\n", |
4286 | 4286 | " measurement_type='StraightLine',\n", |
4287 | 4287 | " max_count=1,\n", |
4288 | | - " output_name='ny_tract_hotel_dist1' + str(datetime.now().microsecond))" |
| 4288 | + " output_name='ny_tract_hotel_dist1' + str(dt.now().microsecond))" |
4289 | 4289 | ] |
4290 | 4290 | }, |
4291 | 4291 | { |
|
5152 | 5152 | "source": [ |
5153 | 5153 | "# Final hotel Distances in feet — Here in each row column \"hotel_dist\" returns the distance of the nearest hotel from that tract indicated by its geoids.\n", |
5154 | 5154 | "# For example in the first row the tract with ID 36005000100 has a nearest hotel at 5571.75 feet away from it. \n", |
5155 | | - "sdf_tract_hotel_dist_lyr_new = sdf_tract_hotel_dist_lyr[['From_geoid', 'Total_Miles']]\n", |
5156 | | - "sdf_tract_hotel_dist_lyr_new['hotel_dist'] = round(sdf_tract_hotel_dist_lyr_new['Total_Miles'] * 5280, 2)\n", |
| 5155 | + "sdf_tract_hotel_dist_lyr_new = sdf_tract_hotel_dist_lyr[['From_geoid', 'Total_Kilometers']]\n", |
| 5156 | + "sdf_tract_hotel_dist_lyr_new['hotel_dist'] = round(sdf_tract_hotel_dist_lyr_new['Total_Kilometers'] * 3280.84, 2)\n", |
5157 | 5157 | "sdf_tract_hotel_dist_lyr_new.sort_values('From_geoid').head()" |
5158 | 5158 | ] |
5159 | 5159 | }, |
|
5168 | 5168 | " bus_stop_lyr,\n", |
5169 | 5169 | " measurement_type='StraightLine',\n", |
5170 | 5170 | " max_count=1,\n", |
5171 | | - " output_name='ny_tract_bus_stop_dist'+ str(datetime.now().microsecond))\n", |
| 5171 | + " output_name='ny_tract_bus_stop_dist'+ str(dt.now().microsecond))\n", |
5172 | 5172 | "tract_bustop_dist_lyr = tract_bustop_dist.layers[1]\n", |
5173 | | - "sdf_tract_bustop_dist_lyr = pd.DataFrame.spatial.from_layer(tract_bustop_dist_lyr)" |
| 5173 | + "sdf_tract_bustop_dist_lyr =tract_bustop_dist_lyr.query().sdf" |
5174 | 5174 | ] |
5175 | 5175 | }, |
5176 | 5176 | { |
|
5256 | 5256 | "source": [ |
5257 | 5257 | "# Final Bustop Distances in feet — Here in each row column \"busstop_dist\" returns the distance of the nearest bus stop \n", |
5258 | 5258 | "# from that tract indicated by its geoids \n", |
5259 | | - "sdf_tract_bustop_dist_lyr_new = sdf_tract_bustop_dist_lyr[['From_geoid', 'Total_Miles']]\n", |
5260 | | - "sdf_tract_bustop_dist_lyr_new['busstop_dist'] = round(sdf_tract_bustop_dist_lyr_new['Total_Miles'] * 5280)\n", |
| 5259 | + "sdf_tract_bustop_dist_lyr_new = sdf_tract_bustop_dist_lyr[['From_geoid', 'Total_Kilometers']]\n", |
| 5260 | + "sdf_tract_bustop_dist_lyr_new['busstop_dist'] = round(sdf_tract_bustop_dist_lyr_new['Total_Kilometers'] * 3280.84, 2)\n", |
5261 | 5261 | "sdf_tract_bustop_dist_lyr_new.sort_values('From_geoid').head()" |
5262 | 5262 | ] |
5263 | 5263 | }, |
|
5270 | 5270 | "# estimating number of bus stops per tract\n", |
5271 | 5271 | "num_bustops_tracts = summarize_data.aggregate_points(point_layer=bus_stop_lyr,\n", |
5272 | 5272 | " polygon_layer=nyc_tracts_layer,\n", |
5273 | | - " output_name='bustops_by_tracts'+ str(datetime.now().microsecond)) " |
| 5273 | + " output_name='bustops_by_tracts'+ str(dt.now().microsecond)) " |
5274 | 5274 | ] |
5275 | 5275 | }, |
5276 | 5276 | { |
|
5847 | 5847 | " cbd_lyr,\n", |
5848 | 5848 | " measurement_type='StraightLine',\n", |
5849 | 5849 | " max_count=1,\n", |
5850 | | - " output_name='ny_tract_cbd_dist'+ str(datetime.now().microsecond))\n", |
| 5850 | + " output_name='ny_tract_cbd_dist'+ str(dt.now().microsecond))\n", |
5851 | 5851 | "tract_cbd_dist_lyr = tract_cbd_dist.layers[1]\n", |
5852 | | - "sdf_tract_cbd_dist_lyr = pd.DataFrame.spatial.from_layer(tract_cbd_dist_lyr)\n", |
| 5852 | + "sdf_tract_cbd_dist_lyr = tract_cbd_dist_lyr.query().sdf\n", |
5853 | 5853 | "sdf_tract_cbd_dist_lyr.head()" |
5854 | 5854 | ] |
5855 | 5855 | }, |
|
5935 | 5935 | ], |
5936 | 5936 | "source": [ |
5937 | 5937 | "# Final CBD distances in feet — Here in each row the column \"cbd_dst\" returns the distance of the CBD from respective tracts\n", |
5938 | | - "sdf_tract_cbd_dist_lyr_new = sdf_tract_cbd_dist_lyr[['From_geoid', 'Total_Miles']]\n", |
5939 | | - "sdf_tract_cbd_dist_lyr_new['cbd_dist'] = round(sdf_tract_cbd_dist_lyr_new['Total_Miles'] * 5280, 2) \n", |
| 5938 | + "sdf_tract_cbd_dist_lyr_new = sdf_tract_cbd_dist_lyr[['From_geoid', 'Total_Kilometers']]\n", |
| 5939 | + "sdf_tract_cbd_dist_lyr_new['cbd_dist'] = round(sdf_tract_cbd_dist_lyr_new['Total_Kilometers'] * 3280.84, 2) \n", |
5940 | 5940 | "sdf_tract_cbd_dist_lyr_new.sort_values('From_geoid').head()" |
5941 | 5941 | ] |
5942 | 5942 | }, |
|
6200 | 6200 | " subwy_stn_lyr,\n", |
6201 | 6201 | " measurement_type='StraightLine',\n", |
6202 | 6202 | " max_count=1,\n", |
6203 | | - " output_name='ny_tract_subway_station_dist'+ str(datetime.now().microsecond))\n", |
| 6203 | + " output_name='ny_tract_subway_station_dist'+ str(dt.now().microsecond))\n", |
6204 | 6204 | "tract_subwy_stn_dist_lyr = tract_subwy_stn_dist.layers[1]\n", |
6205 | 6205 | "sdf_tract_subwy_stn_dist_lyr = pd.DataFrame.spatial.from_layer(tract_subwy_stn_dist_lyr)\n", |
6206 | 6206 | "sdf_tract_subwy_stn_dist_lyr.head()" |
|
6289 | 6289 | "source": [ |
6290 | 6290 | "# Final Tract to NYC Subway Station distances in feet — Here in each row, column \"subwy_stn_dist\" returns the distance of\n", |
6291 | 6291 | "# the nearest subway station from that tract\n", |
6292 | | - "sdf_tract_subwy_stn_dist_lyr_new = sdf_tract_subwy_stn_dist_lyr[['From_geoid', 'Total_Miles']]\n", |
6293 | | - "sdf_tract_subwy_stn_dist_lyr_new['subwy_stn_dist'] = round(sdf_tract_subwy_stn_dist_lyr_new['Total_Miles'] * 5280, 2) \n", |
| 6292 | + "sdf_tract_subwy_stn_dist_lyr_new = sdf_tract_subwy_stn_dist_lyr[['From_geoid', 'Total_Kilometers']]\n", |
| 6293 | + "sdf_tract_subwy_stn_dist_lyr_new['subwy_stn_dist'] = round(sdf_tract_subwy_stn_dist_lyr_new['Total_Kilometers'] * 3280.84, 2) \n", |
6294 | 6294 | "sdf_tract_subwy_stn_dist_lyr_new.sort_values('From_geoid').head()" |
6295 | 6295 | ] |
6296 | 6296 | }, |
|
6547 | 6547 | " subwy_rt_lyr,\n", |
6548 | 6548 | " measurement_type='StraightLine',\n", |
6549 | 6549 | " max_count=1,\n", |
6550 | | - " output_name='ny_tract_subway_routes_dist'+ str(datetime.now().microsecond))\n", |
| 6550 | + " output_name='ny_tract_subway_routes_dist'+ str(dt.now().microsecond))\n", |
6551 | 6551 | "tract_subwy_rt_dist_lyr = tract_subwy_rt_dist.layers[1]\n", |
6552 | | - "sdf_tract_subwy_rt_dist_lyr = pd.DataFrame.spatial.from_layer(tract_subwy_rt_dist_lyr)\n", |
| 6552 | + "sdf_tract_subwy_rt_dist_lyr = tract_subwy_rt_dist_lyr.query().sdf\n", |
6553 | 6553 | "sdf_tract_subwy_rt_dist_lyr.head()" |
6554 | 6554 | ] |
6555 | 6555 | }, |
|
6636 | 6636 | "source": [ |
6637 | 6637 | "# Final Tract to NYCSubwayRoutes distances in feet — Here in each row, column \"subwy_rt_dist\" returns the distance of\n", |
6638 | 6638 | "# the nearest subway route from that tract\n", |
6639 | | - "sdf_tract_subwy_rt_dist_lyr_new = sdf_tract_subwy_rt_dist_lyr[['From_geoid', 'Total_Miles']]\n", |
6640 | | - "sdf_tract_subwy_rt_dist_lyr_new['subwy_rt_dist'] = round(sdf_tract_subwy_rt_dist_lyr_new['Total_Miles'] * 5280) \n", |
| 6639 | + "sdf_tract_subwy_rt_dist_lyr_new = sdf_tract_subwy_rt_dist_lyr[['From_geoid', 'Total_Kilometers']]\n", |
| 6640 | + "sdf_tract_subwy_rt_dist_lyr_new['subwy_rt_dist'] = round(sdf_tract_subwy_rt_dist_lyr_new['Total_Kilometers'] * 3280.84, 2) \n", |
6641 | 6641 | "sdf_tract_subwy_rt_dist_lyr_new.sort_values('From_geoid').head()" |
6642 | 6642 | ] |
6643 | 6643 | }, |
|
6869 | 6869 | " railroad_lyr,\n", |
6870 | 6870 | " measurement_type='StraightLine',\n", |
6871 | 6871 | " max_count=1,\n", |
6872 | | - " output_name='tract_railroad_dist'+ str(datetime.now().microsecond))\n", |
| 6872 | + " output_name='tract_railroad_dist'+ str(dt.now().microsecond))\n", |
6873 | 6873 | "tract_railroad_dist_lyr = tract_railroad_dist.layers[1]\n", |
6874 | 6874 | "sdf_tract_railroad_dist_lyr = pd.DataFrame.spatial.from_layer(tract_railroad_dist_lyr)\n", |
6875 | 6875 | "sdf_tract_railroad_dist_lyr.head()" |
|
6958 | 6958 | "source": [ |
6959 | 6959 | "# Final Tract to NYCRailroad distances in feet — Here in each row, column \"railroad_dist\" returns the distance of\n", |
6960 | 6960 | "# the nearest rail road route from that tract\n", |
6961 | | - "sdf_tract_railroad_dist_lyr_new = sdf_tract_railroad_dist_lyr[['From_geoid', 'Total_Miles']]\n", |
6962 | | - "sdf_tract_railroad_dist_lyr_new['railroad_dist'] = round(sdf_tract_railroad_dist_lyr_new['Total_Miles'] * 5280, 2) \n", |
| 6961 | + "sdf_tract_railroad_dist_lyr_new = sdf_tract_railroad_dist_lyr[['From_geoid', 'Total_Kilometers']]\n", |
| 6962 | + "sdf_tract_railroad_dist_lyr_new['railroad_dist'] = round(sdf_tract_railroad_dist_lyr_new['Total_Kilometers'] * 3280.84, 2) \n", |
6963 | 6963 | "sdf_tract_railroad_dist_lyr_new.sort_values('From_geoid').head()" |
6964 | 6964 | ] |
6965 | 6965 | }, |
|
7259 | 7259 | " busi_distrs_lyr,\n", |
7260 | 7260 | " measurement_type='StraightLine',\n", |
7261 | 7261 | " max_count=1,\n", |
7262 | | - " output_name='tract_busi_distrs_dist'+ str(datetime.now().microsecond))\n", |
| 7262 | + " output_name='tract_busi_distrs_dist'+ str(dt.now().microsecond))\n", |
7263 | 7263 | "tract_busi_distrs_dist_lyr = tract_busi_distrs_dist.layers[1]\n", |
7264 | 7264 | "sdf_tract_busi_distrs_dist_lyr = pd.DataFrame.spatial.from_layer(tract_busi_distrs_dist_lyr)\n", |
7265 | 7265 | "sdf_tract_busi_distrs_dist_lyr.head()" |
|
7347 | 7347 | ], |
7348 | 7348 | "source": [ |
7349 | 7349 | "# Final Tract to NYC Businesss Districts distances in feet — Here in each row, column \"busi_distr_dist\" returns the distance of the CBD from respective tracts\n", |
7350 | | - "sdf_tract_busi_distrs_dist_lyr_new = sdf_tract_busi_distrs_dist_lyr[['From_geoid', 'Total_Miles']]\n", |
7351 | | - "sdf_tract_busi_distrs_dist_lyr_new['busi_distr_dist'] = round(sdf_tract_busi_distrs_dist_lyr_new['Total_Miles'] * 5280, 2) \n", |
| 7350 | + "sdf_tract_busi_distrs_dist_lyr_new = sdf_tract_busi_distrs_dist_lyr[['From_geoid', 'Total_Kilometers']]\n", |
| 7351 | + "sdf_tract_busi_distrs_dist_lyr_new['busi_distr_dist'] = round(sdf_tract_busi_distrs_dist_lyr_new['Total_Kilometers'] * 3280.84, 2) \n", |
7352 | 7352 | "sdf_tract_busi_distrs_dist_lyr_new.sort_values('From_geoid').head()" |
7353 | 7353 | ] |
7354 | 7354 | }, |
|
8166 | 8166 | " 'ID',\n", |
8167 | 8167 | " 'OBJECTID',\n", |
8168 | 8168 | " 'Point_Count',\n", |
8169 | | - " 'SHAPE',\n", |
8170 | | - " 'Shape__Area',\n", |
8171 | | - " 'Shape__Length',\n", |
| 8169 | + " 'SHAPE', \n", |
8172 | 8170 | " 'aggregationMethod',\n", |
8173 | 8171 | " 'aland',\n", |
8174 | 8172 | " 'apportionmentConfidence',\n", |
|
10439 | 10437 | "# plotting the actual observed vs predicted airbnb properties by tract\n", |
10440 | 10438 | "plt.figure(figsize = [25,12])\n", |
10441 | 10439 | "sns.set(style = 'whitegrid')\n", |
10442 | | - "sns.lineplot(data = y_test_df, markers=True, hue=\"logic\") \n", |
| 10440 | + "sns.lineplot(data = y_test_df, markers=True) \n", |
10443 | 10441 | "\n", |
10444 | 10442 | "#label the plot\n", |
10445 | 10443 | "plt.xlabel('Tract ID', fontsize=15)\n", |
|
10519 | 10517 | "notebookRuntimeVersion": "4.0" |
10520 | 10518 | }, |
10521 | 10519 | "kernelspec": { |
10522 | | - "display_name": "Python 3", |
| 10520 | + "display_name": "pro28_DL18FebA", |
10523 | 10521 | "language": "python", |
10524 | | - "name": "python3" |
| 10522 | + "name": "pro28_dl18feba" |
10525 | 10523 | }, |
10526 | 10524 | "language_info": { |
10527 | 10525 | "codemirror_mode": { |
|
10533 | 10531 | "name": "python", |
10534 | 10532 | "nbconvert_exporter": "python", |
10535 | 10533 | "pygments_lexer": "ipython3", |
10536 | | - "version": "3.6.8" |
| 10534 | + "version": "3.7.9" |
10537 | 10535 | } |
10538 | 10536 | }, |
10539 | 10537 | "nbformat": 4, |
|
0 commit comments