-
Notifications
You must be signed in to change notification settings - Fork 18
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
b0b3495
commit 698725c
Showing
1 changed file
with
75 additions
and
120 deletions.
There are no files selected for viewing
195 changes: 75 additions & 120 deletions
195
code/python_foundation/solutions/13_creating_spatial_data_solution.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,126 +1,81 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 2, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| "cells": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "['../data/geonames/US.txt', '../data/geonames/MX.txt', '../data/geonames/CA.txt']\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "import os\n", | ||
| "import pandas as pd\n", | ||
| "import geopandas as gpd\n", | ||
| "\n", | ||
| "data_pkg_path = '../data/geonames/'\n", | ||
| "files = os.listdir(data_pkg_path)\n", | ||
| "\n", | ||
| "filepaths = []\n", | ||
| "for file in files:\n", | ||
| " filepaths.append(os.path.join(data_pkg_path, file))\n", | ||
| "print(filepaths)\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 8, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": { | ||
| "id": "VpQxobY7eNvl" | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "import os\n", | ||
| "import pandas as pd\n", | ||
| "import geopandas as gpd\n", | ||
| "\n", | ||
| "data_pkg_path = 'data/geonames/'" | ||
| ] | ||
| }, | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "(225328, 20)\n", | ||
| "(67134, 20)\n", | ||
| "(57266, 20)\n" | ||
| ] | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": { | ||
| "id": "_Gg6n7SfeNvo" | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "column_names = [\n", | ||
| " 'geonameid', 'name', 'asciiname', 'alternatenames',\n", | ||
| " 'latitude', 'longitude', 'feature class', 'feature code',\n", | ||
| " 'country code', 'cc2', 'admin1 code', 'admin2 code',\n", | ||
| " 'admin3 code', 'admin4 code', 'population', 'elevation',\n", | ||
| " 'dem', 'timezone', 'modification date'\n", | ||
| "]\n", | ||
| "\n", | ||
| "dataframes = []\n", | ||
| "\n", | ||
| "files = os.listdir(data_pkg_path)\n", | ||
| "\n", | ||
| "for file in files:\n", | ||
| " path = os.path.join(data_pkg_path, file)\n", | ||
| " df = pd.read_csv(path, sep='\\t', names=column_names)\n", | ||
| " mountains = df[df['feature class']=='T']\n", | ||
| " dataframes.append(mountains)\n", | ||
| "\n", | ||
| "merged = pd.concat(dataframes)\n", | ||
| "geometry = gpd.points_from_xy(merged.longitude, merged.latitude)\n", | ||
| "gdf = gpd.GeoDataFrame(merged, crs='EPSG:4326', geometry=geometry)\n", | ||
| "\n", | ||
| "output_dir = 'output'\n", | ||
| "output_filename = 'merged.gpkg'\n", | ||
| "output_path = os.path.join(output_dir, output_filename)\n", | ||
| "\n", | ||
| "gdf.to_file(driver='GPKG', filename=output_path, encoding='utf-8')\n", | ||
| "print('Successfully written output file at {}'.format(output_path))" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "column_names = [\n", | ||
| " 'geonameid', 'name', 'asciiname', 'alternatenames', \n", | ||
| " 'latitude', 'longitude', 'feature class', 'feature code',\n", | ||
| " 'country code', 'cc2', 'admin1 code', 'admin2 code',\n", | ||
| " 'admin3 code', 'admin4 code', 'population', 'elevation',\n", | ||
| " 'dem', 'timezone', 'modification date'\n", | ||
| "]\n", | ||
| "\n", | ||
| "dataframes = []\n", | ||
| "for filepath in filepaths:\n", | ||
| " df = pd.read_csv(filepath, sep='\\t', names=column_names)\n", | ||
| " mountains = df[df['feature class'] == 'T']\n", | ||
| " geometry = gpd.points_from_xy(mountains.longitude, mountains.latitude)\n", | ||
| " gdf = gpd.GeoDataFrame(mountains, crs='EPSG:4326', geometry=geometry)\n", | ||
| " print(gdf.shape)\n", | ||
| " dataframes.append(gdf)" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 9, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "(349728, 20)\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "merged = pd.concat(dataframes)\n", | ||
| "print(merged.shape)" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 7, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "Successfully written output file at ../output/merged.gpkg\n" | ||
| ] | ||
| ], | ||
| "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": "3.7.7" | ||
| }, | ||
| "colab": { | ||
| "provenance": [] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "output_dir = '../output'\n", | ||
| "output_filename = 'merged.gpkg'\n", | ||
| "output_path = os.path.join(output_dir, output_filename)\n", | ||
| "\n", | ||
| "merged.to_file(driver='GPKG', filename=output_path, encoding='utf-8')\n", | ||
| "print('Successfully written output file at {}'.format(output_path))" | ||
| ] | ||
| } | ||
| ], | ||
| "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": "3.7.7" | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 4 | ||
| } | ||
| "nbformat": 4, | ||
| "nbformat_minor": 0 | ||
| } |