{ "cells": [ { "cell_type": "markdown", "id": "innovative-airplane", "metadata": {}, "source": [ "# In Class Notebook, Week 13" ] }, { "cell_type": "markdown", "id": "27102a29", "metadata": {}, "source": [ "You can always access the notebook URL: https://github.com/UIUC-iSchool-DataViz/is445_bcubcg_fall2023/blob/master/week13/inClass_week13.ipynb \n", "\n", "Or into the nbviewer interface for a plain-text rendering:\n", "\n", "https://kokes.github.io/nbviewer.js/viewer.html" ] }, { "cell_type": "code", "execution_count": 1, "id": "6414d67e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Intel MKL WARNING: Support of Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) enabled only processors has been deprecated. Intel oneAPI Math Kernel Library 2025.0 will require Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.\n", "Intel MKL WARNING: Support of Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) enabled only processors has been deprecated. Intel oneAPI Math Kernel Library 2025.0 will require Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.\n" ] } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "import altair as alt\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 2, "id": "e969f346", "metadata": {}, "outputs": [], "source": [ "corgs = pd.read_csv('https://raw.githubusercontent.com/UIUC-iSchool-DataViz/is445_data/main/corgs_per_country_over_time_columns_2020.csv')" ] }, { "cell_type": "code", "execution_count": 3, "id": "dde6699f", "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", " \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", "
YearsUnited StatesBrazilRussiaJapanVietnamGermanyFranceUnited KingdomItaly...CroatiaNew ZealandIrelandLithuaniaUruguayLatviaSloveniaEstoniaNetherlands AntillesKosovo
01917000000010...0000000000
11918000000000...0000000000
21919000000000...0000000001
31920000000000...0000000000
41921000000000...0000000000
\n", "

5 rows × 41 columns

\n", "
" ], "text/plain": [ " Years United States Brazil Russia Japan Vietnam Germany France \\\n", "0 1917 0 0 0 0 0 0 0 \n", "1 1918 0 0 0 0 0 0 0 \n", "2 1919 0 0 0 0 0 0 0 \n", "3 1920 0 0 0 0 0 0 0 \n", "4 1921 0 0 0 0 0 0 0 \n", "\n", " United Kingdom Italy ... Croatia New Zealand Ireland Lithuania \\\n", "0 1 0 ... 0 0 0 0 \n", "1 0 0 ... 0 0 0 0 \n", "2 0 0 ... 0 0 0 0 \n", "3 0 0 ... 0 0 0 0 \n", "4 0 0 ... 0 0 0 0 \n", "\n", " Uruguay Latvia Slovenia Estonia Netherlands Antilles Kosovo \n", "0 0 0 0 0 0 0 \n", "1 0 0 0 0 0 0 \n", "2 0 0 0 0 0 1 \n", "3 0 0 0 0 0 0 \n", "4 0 0 0 0 0 0 \n", "\n", "[5 rows x 41 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corgs.head()" ] }, { "cell_type": "code", "execution_count": 5, "id": "eb48dbe2", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.Chart(...)" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "linecorg = alt.Chart(corgs).mark_line().encode(\n", " alt.X('Years:Q'),\n", " alt.Y('United States:Q')\n", ")\n", "linecorg" ] }, { "cell_type": "code", "execution_count": 6, "id": "438bd13d", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 1917\n", "1 1918\n", "2 1919\n", "3 1920\n", "4 1921\n", " ... \n", "99 2016\n", "100 2017\n", "101 2018\n", "102 2019\n", "103 2020\n", "Name: Years, Length: 104, dtype: int64" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corgs['Years']" ] }, { "cell_type": "code", "execution_count": 7, "id": "5581d4ce", "metadata": {}, "outputs": [], "source": [ "corgs['Years'] = pd.to_datetime(corgs['Years'].astype('int'), format='%Y')" ] }, { "cell_type": "code", "execution_count": 8, "id": "dd3d9f2b", "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", " \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", "
YearsUnited StatesBrazilRussiaJapanVietnamGermanyFranceUnited KingdomItaly...CroatiaNew ZealandIrelandLithuaniaUruguayLatviaSloveniaEstoniaNetherlands AntillesKosovo
01917-01-01000000010...0000000000
11918-01-01000000000...0000000000
21919-01-01000000000...0000000001
31920-01-01000000000...0000000000
41921-01-01000000000...0000000000
\n", "

5 rows × 41 columns

\n", "
" ], "text/plain": [ " Years United States Brazil Russia Japan Vietnam Germany France \\\n", "0 1917-01-01 0 0 0 0 0 0 0 \n", "1 1918-01-01 0 0 0 0 0 0 0 \n", "2 1919-01-01 0 0 0 0 0 0 0 \n", "3 1920-01-01 0 0 0 0 0 0 0 \n", "4 1921-01-01 0 0 0 0 0 0 0 \n", "\n", " United Kingdom Italy ... Croatia New Zealand Ireland Lithuania \\\n", "0 1 0 ... 0 0 0 0 \n", "1 0 0 ... 0 0 0 0 \n", "2 0 0 ... 0 0 0 0 \n", "3 0 0 ... 0 0 0 0 \n", "4 0 0 ... 0 0 0 0 \n", "\n", " Uruguay Latvia Slovenia Estonia Netherlands Antilles Kosovo \n", "0 0 0 0 0 0 0 \n", "1 0 0 0 0 0 0 \n", "2 0 0 0 0 0 1 \n", "3 0 0 0 0 0 0 \n", "4 0 0 0 0 0 0 \n", "\n", "[5 rows x 41 columns]" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corgs.head()" ] }, { "cell_type": "code", "execution_count": 9, "id": "4322cfaa", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.Chart(...)" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "linecorg = alt.Chart(corgs).mark_line().encode(\n", " alt.X('Years:T'),\n", " alt.Y('United States:Q')\n", ")\n", "linecorg" ] }, { "cell_type": "code", "execution_count": 10, "id": "4b3cd4ee", "metadata": {}, "outputs": [], "source": [ "corgs = corgs.set_index('Years')" ] }, { "cell_type": "code", "execution_count": 11, "id": "c71e4a5a", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
United StatesBrazilRussiaJapanVietnamGermanyFranceUnited KingdomItalySouth Africa...CroatiaNew ZealandIrelandLithuaniaUruguayLatviaSloveniaEstoniaNetherlands AntillesKosovo
Years
1917-01-010000000100...0000000000
1918-01-010000000000...0000000000
1919-01-010000000000...0000000001
1920-01-010000000000...0000000000
1921-01-010000000000...0000000000
\n", "

5 rows × 40 columns

\n", "
" ], "text/plain": [ " United States Brazil Russia Japan Vietnam Germany France \\\n", "Years \n", "1917-01-01 0 0 0 0 0 0 0 \n", "1918-01-01 0 0 0 0 0 0 0 \n", "1919-01-01 0 0 0 0 0 0 0 \n", "1920-01-01 0 0 0 0 0 0 0 \n", "1921-01-01 0 0 0 0 0 0 0 \n", "\n", " United Kingdom Italy South Africa ... Croatia New Zealand \\\n", "Years ... \n", "1917-01-01 1 0 0 ... 0 0 \n", "1918-01-01 0 0 0 ... 0 0 \n", "1919-01-01 0 0 0 ... 0 0 \n", "1920-01-01 0 0 0 ... 0 0 \n", "1921-01-01 0 0 0 ... 0 0 \n", "\n", " Ireland Lithuania Uruguay Latvia Slovenia Estonia \\\n", "Years \n", "1917-01-01 0 0 0 0 0 0 \n", "1918-01-01 0 0 0 0 0 0 \n", "1919-01-01 0 0 0 0 0 0 \n", "1920-01-01 0 0 0 0 0 0 \n", "1921-01-01 0 0 0 0 0 0 \n", "\n", " Netherlands Antilles Kosovo \n", "Years \n", "1917-01-01 0 0 \n", "1918-01-01 0 0 \n", "1919-01-01 0 1 \n", "1920-01-01 0 0 \n", "1921-01-01 0 0 \n", "\n", "[5 rows x 40 columns]" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corgs.head()" ] }, { "cell_type": "code", "execution_count": 12, "id": "c0848291", "metadata": {}, "outputs": [], "source": [ "corg_source = corgs.reset_index().melt('Years', \n", " var_name='Country', \n", " value_name='born')" ] }, { "cell_type": "code", "execution_count": 17, "id": "4c2e8aae", "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", "
YearsCountryborn
01917-01-01United States0
11918-01-01United States0
21919-01-01United States0
31920-01-01United States0
41921-01-01United States0
\n", "
" ], "text/plain": [ " Years Country born\n", "0 1917-01-01 United States 0\n", "1 1918-01-01 United States 0\n", "2 1919-01-01 United States 0\n", "3 1920-01-01 United States 0\n", "4 1921-01-01 United States 0" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_source.head()" ] }, { "cell_type": "code", "execution_count": 18, "id": "ba4d7c28", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.Chart(...)" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "linecorg = alt.Chart(corg_source).mark_line().encode(\n", " alt.X('Years:T'),\n", " alt.Y('born:Q', scale=alt.Scale(type='symlog')),\n", " color='Country:N'\n", ")\n", "linecorg" ] }, { "cell_type": "code", "execution_count": 19, "id": "a820b0be", "metadata": {}, "outputs": [], "source": [ "from vega_datasets import data" ] }, { "cell_type": "code", "execution_count": 21, "id": "30cd5df4", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'https://cdn.jsdelivr.net/npm/vega-datasets@v1.29.0/data/world-110m.json'" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.world_110m.url" ] }, { "cell_type": "code", "execution_count": 28, "id": "6d25878d", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.Chart(...)" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "geo = alt.topo_feature(data.world_110m.url, feature='countries')\n", "\n", "# world background\n", "world = alt.Chart(geo).mark_geoshape(\n", " fill='gray',\n", " stroke='white'\n", ").properties(\n", " width=800,\n", " height=400\n", ").project('equirectangular')\n", "\n", "world" ] }, { "cell_type": "code", "execution_count": 29, "id": "904b2bdb", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
United StatesBrazilRussiaJapanVietnamGermanyFranceUnited KingdomItalySouth Africa...CroatiaNew ZealandIrelandLithuaniaUruguayLatviaSloveniaEstoniaNetherlands AntillesKosovo
Years
1917-01-010000000100...0000000000
1918-01-010000000000...0000000000
1919-01-010000000000...0000000001
1920-01-010000000000...0000000000
1921-01-010000000000...0000000000
\n", "

5 rows × 40 columns

\n", "
" ], "text/plain": [ " United States Brazil Russia Japan Vietnam Germany France \\\n", "Years \n", "1917-01-01 0 0 0 0 0 0 0 \n", "1918-01-01 0 0 0 0 0 0 0 \n", "1919-01-01 0 0 0 0 0 0 0 \n", "1920-01-01 0 0 0 0 0 0 0 \n", "1921-01-01 0 0 0 0 0 0 0 \n", "\n", " United Kingdom Italy South Africa ... Croatia New Zealand \\\n", "Years ... \n", "1917-01-01 1 0 0 ... 0 0 \n", "1918-01-01 0 0 0 ... 0 0 \n", "1919-01-01 0 0 0 ... 0 0 \n", "1920-01-01 0 0 0 ... 0 0 \n", "1921-01-01 0 0 0 ... 0 0 \n", "\n", " Ireland Lithuania Uruguay Latvia Slovenia Estonia \\\n", "Years \n", "1917-01-01 0 0 0 0 0 0 \n", "1918-01-01 0 0 0 0 0 0 \n", "1919-01-01 0 0 0 0 0 0 \n", "1920-01-01 0 0 0 0 0 0 \n", "1921-01-01 0 0 0 0 0 0 \n", "\n", " Netherlands Antilles Kosovo \n", "Years \n", "1917-01-01 0 0 \n", "1918-01-01 0 0 \n", "1919-01-01 0 1 \n", "1920-01-01 0 0 \n", "1921-01-01 0 0 \n", "\n", "[5 rows x 40 columns]" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corgs.head()" ] }, { "cell_type": "code", "execution_count": 31, "id": "67131932", "metadata": {}, "outputs": [], "source": [ "import requests\n", "def get_boundingbox_country(country, output_as='center'):\n", " \"\"\"\n", " get the bounding box of a country in EPSG4326 given a country name\n", "\n", " Parameters\n", " ----------\n", " country : str\n", " name of the country in english and lowercase\n", " output_as : 'str\n", " chose from 'boundingbox' or 'center'. \n", " - 'boundingbox' for [latmin, latmax, lonmin, lonmax]\n", " - 'center' for [latcenter, loncenter]\n", "\n", " Returns\n", " -------\n", " output : list\n", " list with coordinates as str\n", " \"\"\"\n", " # create url\n", " url = '{0}{1}{2}'.format('http://nominatim.openstreetmap.org/search?country=',\n", " country,\n", " '&format=json&polygon=0')\n", " response = requests.get(url).json()[0]\n", "\n", " # parse response to list\n", " if output_as == 'boundingbox':\n", " lst = response[output_as]\n", " output = [float(i) for i in lst]\n", " if output_as == 'center':\n", " lst = [response.get(key) for key in ['lat','lon']]\n", " output = [float(i) for i in lst]\n", " return output" ] }, { "cell_type": "code", "execution_count": 33, "id": "deaedb68", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(39.7837304, -100.445882)" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lat,long = get_boundingbox_country('usa')\n", "lat, long" ] }, { "cell_type": "code", "execution_count": 34, "id": "6fe25e11", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(39.7837304, -100.445882)" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lat, long = get_boundingbox_country('us')\n", "lat,long" ] }, { "cell_type": "code", "execution_count": 35, "id": "537fa3bf", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(39.7837304, -100.445882)" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lat, long = get_boundingbox_country('United States')\n", "lat, long" ] }, { "cell_type": "code", "execution_count": 36, "id": "1734639b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['United States', 'Brazil', 'Russia', 'Japan', 'Vietnam', 'Germany',\n", " 'France', 'United Kingdom', 'Italy', 'South Africa', 'Ukraine', 'Spain',\n", " 'Poland', 'Canada', 'Korea, North', 'Romania', 'Australia', 'Portugal',\n", " 'Belgium', 'Czech Republic', 'Hungary', 'Belarus', 'Sweden', 'Austria',\n", " 'Switzerland', 'Israel', 'Serbia', 'Denmark', 'Finland', 'Norway',\n", " 'Croatia', 'New Zealand', 'Ireland', 'Lithuania', 'Uruguay', 'Latvia',\n", " 'Slovenia', 'Estonia', 'Netherlands Antilles', 'Kosovo'],\n", " dtype='object')" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corgs.columns" ] }, { "cell_type": "code", "execution_count": 37, "id": "235f7860", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "United States 39.7837304 -100.445882\n", "Brazil -10.3333333 -53.2\n", "Russia 64.6863136 97.7453061\n", "Japan 36.5748441 139.2394179\n", "Vietnam 15.9266657 107.9650855\n", "Germany 51.1638175 10.4478313\n", "France 46.603354 1.8883335\n", "United Kingdom 54.7023545 -3.2765753\n", "Italy 42.6384261 12.674297\n", "South Africa -28.8166236 24.991639\n", "Ukraine 49.4871968 31.2718321\n", "Spain 39.3260685 -4.8379791\n", "Poland 52.215933 19.134422\n", "Canada 61.0666922 -107.991707\n", "Korea, North 40.3736611 127.0870417\n", "Romania 45.9852129 24.6859225\n", "Australia -24.7761086 134.755\n", "Portugal 39.6621648 -8.1353519\n", "Belgium 50.6402809 4.6667145\n", "Czech Republic 49.7439047 15.3381061\n", "Hungary 47.1817585 19.5060937\n", "Belarus 53.4250605 27.6971358\n", "Sweden 59.6749712 14.5208584\n", "Austria 47.59397 14.12456\n", "Switzerland 46.7985624 8.2319736\n", "Israel 31.39480005 34.63358319049945\n", "Serbia 44.1534121 20.55144\n", "Denmark 55.670249 10.3333283\n", "Finland 63.2467777 25.9209164\n", "Norway 61.1529386 8.7876653\n", "Croatia 45.3658443 15.6575209\n", "New Zealand -41.5000831 172.8344077\n", "Ireland 52.865196 -7.9794599\n", "Lithuania 55.3500003 23.7499997\n", "Uruguay -32.8755548 -56.0201525\n", "Latvia 56.8406494 24.7537645\n", "Slovenia 46.1199444 14.8153333\n", "Estonia 58.7523778 25.3319078\n" ] }, { "ename": "IndexError", "evalue": "list index out of range", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[37], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m lat, long \u001b[38;5;241m=\u001b[39m [], []\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m c \u001b[38;5;129;01min\u001b[39;00m corgs\u001b[38;5;241m.\u001b[39mcolumns:\n\u001b[0;32m----> 3\u001b[0m la,lo \u001b[38;5;241m=\u001b[39m \u001b[43mget_boundingbox_country\u001b[49m\u001b[43m(\u001b[49m\u001b[43mc\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[38;5;28mprint\u001b[39m(c,la,lo)\n\u001b[1;32m 5\u001b[0m lat\u001b[38;5;241m.\u001b[39mappend(la); long\u001b[38;5;241m.\u001b[39mappend(lo)\n", "Cell \u001b[0;32mIn[31], line 24\u001b[0m, in \u001b[0;36mget_boundingbox_country\u001b[0;34m(country, output_as)\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[38;5;66;03m# create url\u001b[39;00m\n\u001b[1;32m 21\u001b[0m url \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{0}\u001b[39;00m\u001b[38;5;132;01m{1}\u001b[39;00m\u001b[38;5;132;01m{2}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mformat(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttp://nominatim.openstreetmap.org/search?country=\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[1;32m 22\u001b[0m country,\n\u001b[1;32m 23\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m&format=json&polygon=0\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m---> 24\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mrequests\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[43murl\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mjson\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\n\u001b[1;32m 26\u001b[0m \u001b[38;5;66;03m# parse response to list\u001b[39;00m\n\u001b[1;32m 27\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m output_as \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mboundingbox\u001b[39m\u001b[38;5;124m'\u001b[39m:\n", "\u001b[0;31mIndexError\u001b[0m: list index out of range" ] } ], "source": [ "lat, long = [], []\n", "for c in corgs.columns:\n", " la,lo = get_boundingbox_country(c)\n", " print(c,la,lo)\n", " lat.append(la); long.append(lo)" ] }, { "cell_type": "code", "execution_count": 38, "id": "93169802", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Netherlands Antilles'" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "c" ] }, { "cell_type": "code", "execution_count": 39, "id": "1cd7efec", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
United StatesBrazilRussiaJapanVietnamGermanyFranceUnited KingdomItalySouth Africa...CroatiaNew ZealandIrelandLithuaniaUruguayLatviaSloveniaEstoniaNetherlandsKosovo
Years
1917-01-010000000100...0000000000
1918-01-010000000000...0000000000
1919-01-010000000000...0000000001
1920-01-010000000000...0000000000
1921-01-010000000000...0000000000
\n", "

5 rows × 40 columns

\n", "
" ], "text/plain": [ " United States Brazil Russia Japan Vietnam Germany France \\\n", "Years \n", "1917-01-01 0 0 0 0 0 0 0 \n", "1918-01-01 0 0 0 0 0 0 0 \n", "1919-01-01 0 0 0 0 0 0 0 \n", "1920-01-01 0 0 0 0 0 0 0 \n", "1921-01-01 0 0 0 0 0 0 0 \n", "\n", " United Kingdom Italy South Africa ... Croatia New Zealand \\\n", "Years ... \n", "1917-01-01 1 0 0 ... 0 0 \n", "1918-01-01 0 0 0 ... 0 0 \n", "1919-01-01 0 0 0 ... 0 0 \n", "1920-01-01 0 0 0 ... 0 0 \n", "1921-01-01 0 0 0 ... 0 0 \n", "\n", " Ireland Lithuania Uruguay Latvia Slovenia Estonia \\\n", "Years \n", "1917-01-01 0 0 0 0 0 0 \n", "1918-01-01 0 0 0 0 0 0 \n", "1919-01-01 0 0 0 0 0 0 \n", "1920-01-01 0 0 0 0 0 0 \n", "1921-01-01 0 0 0 0 0 0 \n", "\n", " Netherlands Kosovo \n", "Years \n", "1917-01-01 0 0 \n", "1918-01-01 0 0 \n", "1919-01-01 0 1 \n", "1920-01-01 0 0 \n", "1921-01-01 0 0 \n", "\n", "[5 rows x 40 columns]" ] }, "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean = corgs.copy()\n", "\n", "corg_clean = corg_clean.rename(columns={'Netherlands Antilles':'Netherlands'})\n", "corg_clean.head()" ] }, { "cell_type": "code", "execution_count": 40, "id": "5a748803", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "United States 39.7837304 -100.445882\n", "Brazil -10.3333333 -53.2\n", "Russia 64.6863136 97.7453061\n", "Japan 36.5748441 139.2394179\n", "Vietnam 15.9266657 107.9650855\n", "Germany 51.1638175 10.4478313\n", "France 46.603354 1.8883335\n", "United Kingdom 54.7023545 -3.2765753\n", "Italy 42.6384261 12.674297\n", "South Africa -28.8166236 24.991639\n", "Ukraine 49.4871968 31.2718321\n", "Spain 39.3260685 -4.8379791\n", "Poland 52.215933 19.134422\n", "Canada 61.0666922 -107.991707\n", "Korea, North 40.3736611 127.0870417\n", "Romania 45.9852129 24.6859225\n", "Australia -24.7761086 134.755\n", "Portugal 39.6621648 -8.1353519\n", "Belgium 50.6402809 4.6667145\n", "Czech Republic 49.7439047 15.3381061\n", "Hungary 47.1817585 19.5060937\n", "Belarus 53.4250605 27.6971358\n", "Sweden 59.6749712 14.5208584\n", "Austria 47.59397 14.12456\n", "Switzerland 46.7985624 8.2319736\n", "Israel 31.39480005 34.63358319049945\n", "Serbia 44.1534121 20.55144\n", "Denmark 55.670249 10.3333283\n", "Finland 63.2467777 25.9209164\n", "Norway 61.1529386 8.7876653\n", "Croatia 45.3658443 15.6575209\n", "New Zealand -41.5000831 172.8344077\n", "Ireland 52.865196 -7.9794599\n", "Lithuania 55.3500003 23.7499997\n", "Uruguay -32.8755548 -56.0201525\n", "Latvia 56.8406494 24.7537645\n", "Slovenia 46.1199444 14.8153333\n", "Estonia 58.7523778 25.3319078\n", "Netherlands 52.24764975 5.541246849406163\n", "Kosovo 42.5869578 20.9021231\n" ] } ], "source": [ "lat, long = [], []\n", "for c in corg_clean.columns:\n", " la,lo = get_boundingbox_country(c)\n", " print(c,la,lo)\n", " lat.append(la); long.append(lo)" ] }, { "cell_type": "code", "execution_count": 41, "id": "c76eef50", "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", " \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", " \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", " \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", "
United StatesBrazilRussiaJapanVietnamGermanyFranceUnited KingdomItalySouth Africa...CroatiaNew ZealandIrelandLithuaniaUruguayLatviaSloveniaEstoniaNetherlandsKosovo
Years
1917-01-010000000100...0000000000
1918-01-010000000000...0000000000
1919-01-010000000000...0000000001
1920-01-010000000000...0000000000
1921-01-010000000000...0000000000
..................................................................
2016-01-0122902172054552820...8309000271772
2017-01-0121302602128601040...4300200825101
2018-01-011980329034225520...6300000161256
2019-01-011180189003062120...0000000161251
2020-01-0120160000000...00000000017
\n", "

104 rows × 40 columns

\n", "
" ], "text/plain": [ " United States Brazil Russia Japan Vietnam Germany France \\\n", "Years \n", "1917-01-01 0 0 0 0 0 0 0 \n", "1918-01-01 0 0 0 0 0 0 0 \n", "1919-01-01 0 0 0 0 0 0 0 \n", "1920-01-01 0 0 0 0 0 0 0 \n", "1921-01-01 0 0 0 0 0 0 0 \n", "... ... ... ... ... ... ... ... \n", "2016-01-01 229 0 217 2 0 54 55 \n", "2017-01-01 213 0 260 2 1 28 60 \n", "2018-01-01 198 0 329 0 3 42 25 \n", "2019-01-01 118 0 189 0 0 30 62 \n", "2020-01-01 2 0 16 0 0 0 0 \n", "\n", " United Kingdom Italy South Africa ... Croatia New Zealand \\\n", "Years ... \n", "1917-01-01 1 0 0 ... 0 0 \n", "1918-01-01 0 0 0 ... 0 0 \n", "1919-01-01 0 0 0 ... 0 0 \n", "1920-01-01 0 0 0 ... 0 0 \n", "1921-01-01 0 0 0 ... 0 0 \n", "... ... ... ... ... ... ... \n", "2016-01-01 28 2 0 ... 8 3 \n", "2017-01-01 10 4 0 ... 4 3 \n", "2018-01-01 5 2 0 ... 6 3 \n", "2019-01-01 1 2 0 ... 0 0 \n", "2020-01-01 0 0 0 ... 0 0 \n", "\n", " Ireland Lithuania Uruguay Latvia Slovenia Estonia \\\n", "Years \n", "1917-01-01 0 0 0 0 0 0 \n", "1918-01-01 0 0 0 0 0 0 \n", "1919-01-01 0 0 0 0 0 0 \n", "1920-01-01 0 0 0 0 0 0 \n", "1921-01-01 0 0 0 0 0 0 \n", "... ... ... ... ... ... ... \n", "2016-01-01 0 9 0 0 0 27 \n", "2017-01-01 0 0 2 0 0 8 \n", "2018-01-01 0 0 0 0 0 16 \n", "2019-01-01 0 0 0 0 0 16 \n", "2020-01-01 0 0 0 0 0 0 \n", "\n", " Netherlands Kosovo \n", "Years \n", "1917-01-01 0 0 \n", "1918-01-01 0 0 \n", "1919-01-01 0 1 \n", "1920-01-01 0 0 \n", "1921-01-01 0 0 \n", "... ... ... \n", "2016-01-01 17 72 \n", "2017-01-01 25 101 \n", "2018-01-01 12 56 \n", "2019-01-01 12 51 \n", "2020-01-01 0 17 \n", "\n", "[104 rows x 40 columns]" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean" ] }, { "cell_type": "code", "execution_count": 42, "id": "2138162f", "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", " \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", "
Years1917-01-011918-01-011919-01-011920-01-011921-01-011922-01-011923-01-011924-01-011925-01-011926-01-01...2011-01-012012-01-012013-01-012014-01-012015-01-012016-01-012017-01-012018-01-012019-01-012020-01-01
United States0000000000...4084313762803012292131981182
Brazil0000000000...0000000000
Russia0000000000...898211512723721726032918916
Japan0000000000...0000022000
Vietnam0000000000...0000001300
\n", "

5 rows × 104 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 1918-01-01 1919-01-01 1920-01-01 1921-01-01 \\\n", "United States 0 0 0 0 0 \n", "Brazil 0 0 0 0 0 \n", "Russia 0 0 0 0 0 \n", "Japan 0 0 0 0 0 \n", "Vietnam 0 0 0 0 0 \n", "\n", "Years 1922-01-01 1923-01-01 1924-01-01 1925-01-01 1926-01-01 \\\n", "United States 0 0 0 0 0 \n", "Brazil 0 0 0 0 0 \n", "Russia 0 0 0 0 0 \n", "Japan 0 0 0 0 0 \n", "Vietnam 0 0 0 0 0 \n", "\n", "Years ... 2011-01-01 2012-01-01 2013-01-01 2014-01-01 \\\n", "United States ... 408 431 376 280 \n", "Brazil ... 0 0 0 0 \n", "Russia ... 89 82 115 127 \n", "Japan ... 0 0 0 0 \n", "Vietnam ... 0 0 0 0 \n", "\n", "Years 2015-01-01 2016-01-01 2017-01-01 2018-01-01 2019-01-01 \\\n", "United States 301 229 213 198 118 \n", "Brazil 0 0 0 0 0 \n", "Russia 237 217 260 329 189 \n", "Japan 0 2 2 0 0 \n", "Vietnam 0 0 1 3 0 \n", "\n", "Years 2020-01-01 \n", "United States 2 \n", "Brazil 0 \n", "Russia 16 \n", "Japan 0 \n", "Vietnam 0 \n", "\n", "[5 rows x 104 columns]" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean_t = corg_clean.T\n", "corg_clean_t.head()" ] }, { "cell_type": "code", "execution_count": 43, "id": "5e0ad58a", "metadata": {}, "outputs": [], "source": [ "corg_clean_t.index.name" ] }, { "cell_type": "code", "execution_count": 44, "id": "05f61e28", "metadata": {}, "outputs": [], "source": [ "corg_clean_t.index.name ='Country'" ] }, { "cell_type": "code", "execution_count": 45, "id": "17c3247d", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Years'" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean_t.axes[1].name" ] }, { "cell_type": "code", "execution_count": 46, "id": "9b62dcc2", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Years1917-01-011918-01-011919-01-011920-01-011921-01-011922-01-011923-01-011924-01-011925-01-011926-01-01...2011-01-012012-01-012013-01-012014-01-012015-01-012016-01-012017-01-012018-01-012019-01-012020-01-01
Country
United States0000000000...4084313762803012292131981182
Brazil0000000000...0000000000
Russia0000000000...898211512723721726032918916
Japan0000000000...0000022000
Vietnam0000000000...0000001300
\n", "

5 rows × 104 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 1918-01-01 1919-01-01 1920-01-01 1921-01-01 \\\n", "Country \n", "United States 0 0 0 0 0 \n", "Brazil 0 0 0 0 0 \n", "Russia 0 0 0 0 0 \n", "Japan 0 0 0 0 0 \n", "Vietnam 0 0 0 0 0 \n", "\n", "Years 1922-01-01 1923-01-01 1924-01-01 1925-01-01 1926-01-01 \\\n", "Country \n", "United States 0 0 0 0 0 \n", "Brazil 0 0 0 0 0 \n", "Russia 0 0 0 0 0 \n", "Japan 0 0 0 0 0 \n", "Vietnam 0 0 0 0 0 \n", "\n", "Years ... 2011-01-01 2012-01-01 2013-01-01 2014-01-01 \\\n", "Country ... \n", "United States ... 408 431 376 280 \n", "Brazil ... 0 0 0 0 \n", "Russia ... 89 82 115 127 \n", "Japan ... 0 0 0 0 \n", "Vietnam ... 0 0 0 0 \n", "\n", "Years 2015-01-01 2016-01-01 2017-01-01 2018-01-01 2019-01-01 \\\n", "Country \n", "United States 301 229 213 198 118 \n", "Brazil 0 0 0 0 0 \n", "Russia 237 217 260 329 189 \n", "Japan 0 2 2 0 0 \n", "Vietnam 0 0 1 3 0 \n", "\n", "Years 2020-01-01 \n", "Country \n", "United States 2 \n", "Brazil 0 \n", "Russia 16 \n", "Japan 0 \n", "Vietnam 0 \n", "\n", "[5 rows x 104 columns]" ] }, "execution_count": 46, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean_t.head()" ] }, { "cell_type": "code", "execution_count": 47, "id": "c0ea6fce", "metadata": {}, "outputs": [], "source": [ "corg_clean_t['Latitude'] = lat\n", "corg_clean_t['Longitude'] = long" ] }, { "cell_type": "code", "execution_count": 48, "id": "8db8c0f8", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Years1917-01-01 00:00:001918-01-01 00:00:001919-01-01 00:00:001920-01-01 00:00:001921-01-01 00:00:001922-01-01 00:00:001923-01-01 00:00:001924-01-01 00:00:001925-01-01 00:00:001926-01-01 00:00:00...2013-01-01 00:00:002014-01-01 00:00:002015-01-01 00:00:002016-01-01 00:00:002017-01-01 00:00:002018-01-01 00:00:002019-01-01 00:00:002020-01-01 00:00:00LatitudeLongitude
Country
United States0000000000...376280301229213198118239.783730-100.445882
Brazil0000000000...00000000-10.333333-53.200000
Russia0000000000...1151272372172603291891664.68631497.745306
Japan0000000000...0002200036.574844139.239418
Vietnam0000000000...0000130015.926666107.965086
\n", "

5 rows × 106 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 00:00:00 1918-01-01 00:00:00 1919-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1920-01-01 00:00:00 1921-01-01 00:00:00 1922-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1923-01-01 00:00:00 1924-01-01 00:00:00 1925-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1926-01-01 00:00:00 ... 2013-01-01 00:00:00 \\\n", "Country ... \n", "United States 0 ... 376 \n", "Brazil 0 ... 0 \n", "Russia 0 ... 115 \n", "Japan 0 ... 0 \n", "Vietnam 0 ... 0 \n", "\n", "Years 2014-01-01 00:00:00 2015-01-01 00:00:00 2016-01-01 00:00:00 \\\n", "Country \n", "United States 280 301 229 \n", "Brazil 0 0 0 \n", "Russia 127 237 217 \n", "Japan 0 0 2 \n", "Vietnam 0 0 0 \n", "\n", "Years 2017-01-01 00:00:00 2018-01-01 00:00:00 2019-01-01 00:00:00 \\\n", "Country \n", "United States 213 198 118 \n", "Brazil 0 0 0 \n", "Russia 260 329 189 \n", "Japan 2 0 0 \n", "Vietnam 1 3 0 \n", "\n", "Years 2020-01-01 00:00:00 Latitude Longitude \n", "Country \n", "United States 2 39.783730 -100.445882 \n", "Brazil 0 -10.333333 -53.200000 \n", "Russia 16 64.686314 97.745306 \n", "Japan 0 36.574844 139.239418 \n", "Vietnam 0 15.926666 107.965086 \n", "\n", "[5 rows x 106 columns]" ] }, "execution_count": 48, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean_t.head()" ] }, { "cell_type": "code", "execution_count": 51, "id": "d91bd74a", "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", "
YearsCountryLatitudeLongitude
0United States39.783730-100.445882
1Brazil-10.333333-53.200000
2Russia64.68631497.745306
3Japan36.574844139.239418
4Vietnam15.926666107.965086
\n", "
" ], "text/plain": [ "Years Country Latitude Longitude\n", "0 United States 39.783730 -100.445882\n", "1 Brazil -10.333333 -53.200000\n", "2 Russia 64.686314 97.745306\n", "3 Japan 36.574844 139.239418\n", "4 Vietnam 15.926666 107.965086" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_subset = corg_clean_t.reset_index()[['Country', 'Latitude', 'Longitude']]\n", "corg_subset.head()" ] }, { "cell_type": "code", "execution_count": 60, "id": "9c938803", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.LayerChart(...)" ] }, "execution_count": 60, "metadata": {}, "output_type": "execute_result" } ], "source": [ "geo = alt.topo_feature(data.world_110m.url, feature='countries')\n", "\n", "# world background\n", "world = alt.Chart(geo).mark_geoshape(\n", " fill='gray',\n", " stroke='white'\n", ").properties(\n", " width=800,\n", " height=400\n", ").project('equirectangular')\n", "\n", "points = alt.Chart(corg_subset).mark_circle().encode(\n", " longitude = 'Longitude:Q',\n", " latitude = 'Latitude:Q',\n", " size=alt.value(100),\n", " tooltip='Country'\n", ")\n", "\n", "world + points" ] }, { "cell_type": "code", "execution_count": 66, "id": "c455888d", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Years1917-01-011918-01-011919-01-011920-01-011921-01-011922-01-011923-01-011924-01-011925-01-011926-01-01...2011-01-012012-01-012013-01-012014-01-012015-01-012016-01-012017-01-012018-01-012019-01-012020-01-01
Country
United States0000000000...4084313762803012292131981182
Brazil0000000000...0000000000
Russia0000000000...898211512723721726032918916
Japan0000000000...0000022000
Vietnam0000000000...0000001300
\n", "

5 rows × 104 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 1918-01-01 1919-01-01 1920-01-01 1921-01-01 \\\n", "Country \n", "United States 0 0 0 0 0 \n", "Brazil 0 0 0 0 0 \n", "Russia 0 0 0 0 0 \n", "Japan 0 0 0 0 0 \n", "Vietnam 0 0 0 0 0 \n", "\n", "Years 1922-01-01 1923-01-01 1924-01-01 1925-01-01 1926-01-01 \\\n", "Country \n", "United States 0 0 0 0 0 \n", "Brazil 0 0 0 0 0 \n", "Russia 0 0 0 0 0 \n", "Japan 0 0 0 0 0 \n", "Vietnam 0 0 0 0 0 \n", "\n", "Years ... 2011-01-01 2012-01-01 2013-01-01 2014-01-01 \\\n", "Country ... \n", "United States ... 408 431 376 280 \n", "Brazil ... 0 0 0 0 \n", "Russia ... 89 82 115 127 \n", "Japan ... 0 0 0 0 \n", "Vietnam ... 0 0 0 0 \n", "\n", "Years 2015-01-01 2016-01-01 2017-01-01 2018-01-01 2019-01-01 \\\n", "Country \n", "United States 301 229 213 198 118 \n", "Brazil 0 0 0 0 0 \n", "Russia 237 217 260 329 189 \n", "Japan 0 2 2 0 0 \n", "Vietnam 0 0 1 3 0 \n", "\n", "Years 2020-01-01 \n", "Country \n", "United States 2 \n", "Brazil 0 \n", "Russia 16 \n", "Japan 0 \n", "Vietnam 0 \n", "\n", "[5 rows x 104 columns]" ] }, "execution_count": 66, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean_t.loc[:,(corg_clean_t.columns!='Longitude')&(corg_clean_t.columns!='Latitude')].head()" ] }, { "cell_type": "code", "execution_count": 68, "id": "e81e2e7b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Country\n", "United States 16130\n", "Brazil 1\n", "Russia 1834\n", "Japan 7\n", "Vietnam 4\n", "Germany 892\n", "France 597\n", "United Kingdom 2649\n", "Italy 106\n", "South Africa 28\n", "Ukraine 19\n", "Spain 5\n", "Poland 859\n", "Canada 391\n", "Korea, North 5\n", "Romania 7\n", "Australia 891\n", "Portugal 7\n", "Belgium 110\n", "Czech Republic 271\n", "Hungary 8\n", "Belarus 38\n", "Sweden 2008\n", "Austria 29\n", "Switzerland 30\n", "Israel 32\n", "Serbia 2\n", "Denmark 2176\n", "Finland 4051\n", "Norway 1077\n", "Croatia 21\n", "New Zealand 1097\n", "Ireland 29\n", "Lithuania 29\n", "Uruguay 2\n", "Latvia 3\n", "Slovenia 1\n", "Estonia 97\n", "Netherlands 536\n", "Kosovo 649\n", "dtype: int64" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean_t.loc[:,(corg_clean_t.columns!='Longitude')&(corg_clean_t.columns!='Latitude')].sum(axis=1)" ] }, { "cell_type": "code", "execution_count": 69, "id": "891e6fe3", "metadata": {}, "outputs": [], "source": [ "corg_clean_t['Total Corg'] = corg_clean_t.loc[:,(corg_clean_t.columns!='Longitude')&(corg_clean_t.columns!='Latitude')].sum(axis=1)" ] }, { "cell_type": "code", "execution_count": 70, "id": "e582e565", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Years1917-01-01 00:00:001918-01-01 00:00:001919-01-01 00:00:001920-01-01 00:00:001921-01-01 00:00:001922-01-01 00:00:001923-01-01 00:00:001924-01-01 00:00:001925-01-01 00:00:001926-01-01 00:00:00...2014-01-01 00:00:002015-01-01 00:00:002016-01-01 00:00:002017-01-01 00:00:002018-01-01 00:00:002019-01-01 00:00:002020-01-01 00:00:00LatitudeLongitudeTotal Corg
Country
United States0000000000...280301229213198118239.783730-100.44588216130
Brazil0000000000...0000000-10.333333-53.2000001
Russia0000000000...1272372172603291891664.68631497.7453061834
Japan0000000000...002200036.574844139.2394187
Vietnam0000000000...000130015.926666107.9650864
\n", "

5 rows × 107 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 00:00:00 1918-01-01 00:00:00 1919-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1920-01-01 00:00:00 1921-01-01 00:00:00 1922-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1923-01-01 00:00:00 1924-01-01 00:00:00 1925-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1926-01-01 00:00:00 ... 2014-01-01 00:00:00 \\\n", "Country ... \n", "United States 0 ... 280 \n", "Brazil 0 ... 0 \n", "Russia 0 ... 127 \n", "Japan 0 ... 0 \n", "Vietnam 0 ... 0 \n", "\n", "Years 2015-01-01 00:00:00 2016-01-01 00:00:00 2017-01-01 00:00:00 \\\n", "Country \n", "United States 301 229 213 \n", "Brazil 0 0 0 \n", "Russia 237 217 260 \n", "Japan 0 2 2 \n", "Vietnam 0 0 1 \n", "\n", "Years 2018-01-01 00:00:00 2019-01-01 00:00:00 2020-01-01 00:00:00 \\\n", "Country \n", "United States 198 118 2 \n", "Brazil 0 0 0 \n", "Russia 329 189 16 \n", "Japan 0 0 0 \n", "Vietnam 3 0 0 \n", "\n", "Years Latitude Longitude Total Corg \n", "Country \n", "United States 39.783730 -100.445882 16130 \n", "Brazil -10.333333 -53.200000 1 \n", "Russia 64.686314 97.745306 1834 \n", "Japan 36.574844 139.239418 7 \n", "Vietnam 15.926666 107.965086 4 \n", "\n", "[5 rows x 107 columns]" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean_t.head()" ] }, { "cell_type": "code", "execution_count": 71, "id": "494966fa", "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", "
YearsCountryLatitudeLongitudeTotal Corg
0United States39.783730-100.44588216130
1Brazil-10.333333-53.2000001
2Russia64.68631497.7453061834
3Japan36.574844139.2394187
4Vietnam15.926666107.9650864
\n", "
" ], "text/plain": [ "Years Country Latitude Longitude Total Corg\n", "0 United States 39.783730 -100.445882 16130\n", "1 Brazil -10.333333 -53.200000 1\n", "2 Russia 64.686314 97.745306 1834\n", "3 Japan 36.574844 139.239418 7\n", "4 Vietnam 15.926666 107.965086 4" ] }, "execution_count": 71, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_subset2 = corg_clean_t.reset_index()[['Country', 'Latitude', 'Longitude', 'Total Corg']]\n", "corg_subset2.head()" ] }, { "cell_type": "code", "execution_count": 80, "id": "de4f706b", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.LayerChart(...)" ] }, "execution_count": 80, "metadata": {}, "output_type": "execute_result" } ], "source": [ "geo = alt.topo_feature(data.world_110m.url, feature='countries')\n", "\n", "# world background\n", "world = alt.Chart(geo).mark_geoshape(\n", " fill='gray',\n", " stroke='white'\n", ").properties(\n", " width=800,\n", " height=400\n", ").project('equirectangular')\n", "\n", "points = alt.Chart(corg_subset2).mark_circle().encode(\n", " longitude = 'Longitude:Q',\n", " latitude = 'Latitude:Q',\n", " size=alt.Size('Total Corg:Q', scale=alt.Scale(type='log')),\n", " #size=alt.Size('Total Corg:Q', scale=None),\n", " tooltip='Country'\n", ")\n", "\n", "world + points" ] }, { "cell_type": "code", "execution_count": 81, "id": "4139924e", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Years1917-01-01 00:00:001918-01-01 00:00:001919-01-01 00:00:001920-01-01 00:00:001921-01-01 00:00:001922-01-01 00:00:001923-01-01 00:00:001924-01-01 00:00:001925-01-01 00:00:001926-01-01 00:00:00...2014-01-01 00:00:002015-01-01 00:00:002016-01-01 00:00:002017-01-01 00:00:002018-01-01 00:00:002019-01-01 00:00:002020-01-01 00:00:00LatitudeLongitudeTotal Corg
Country
United States0000000000...280301229213198118239.783730-100.44588216130
Brazil0000000000...0000000-10.333333-53.2000001
Russia0000000000...1272372172603291891664.68631497.7453061834
Japan0000000000...002200036.574844139.2394187
Vietnam0000000000...000130015.926666107.9650864
\n", "

5 rows × 107 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 00:00:00 1918-01-01 00:00:00 1919-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1920-01-01 00:00:00 1921-01-01 00:00:00 1922-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1923-01-01 00:00:00 1924-01-01 00:00:00 1925-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1926-01-01 00:00:00 ... 2014-01-01 00:00:00 \\\n", "Country ... \n", "United States 0 ... 280 \n", "Brazil 0 ... 0 \n", "Russia 0 ... 127 \n", "Japan 0 ... 0 \n", "Vietnam 0 ... 0 \n", "\n", "Years 2015-01-01 00:00:00 2016-01-01 00:00:00 2017-01-01 00:00:00 \\\n", "Country \n", "United States 301 229 213 \n", "Brazil 0 0 0 \n", "Russia 237 217 260 \n", "Japan 0 2 2 \n", "Vietnam 0 0 1 \n", "\n", "Years 2018-01-01 00:00:00 2019-01-01 00:00:00 2020-01-01 00:00:00 \\\n", "Country \n", "United States 198 118 2 \n", "Brazil 0 0 0 \n", "Russia 329 189 16 \n", "Japan 0 0 0 \n", "Vietnam 3 0 0 \n", "\n", "Years Latitude Longitude Total Corg \n", "Country \n", "United States 39.783730 -100.445882 16130 \n", "Brazil -10.333333 -53.200000 1 \n", "Russia 64.686314 97.745306 1834 \n", "Japan 36.574844 139.239418 7 \n", "Vietnam 15.926666 107.965086 4 \n", "\n", "[5 rows x 107 columns]" ] }, "execution_count": 81, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean_t.head()" ] }, { "cell_type": "code", "execution_count": 82, "id": "be256daa", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Years1917-01-01 00:00:001918-01-01 00:00:001919-01-01 00:00:001920-01-01 00:00:001921-01-01 00:00:001922-01-01 00:00:001923-01-01 00:00:001924-01-01 00:00:001925-01-01 00:00:001926-01-01 00:00:00...2013-01-01 00:00:002014-01-01 00:00:002015-01-01 00:00:002016-01-01 00:00:002017-01-01 00:00:002018-01-01 00:00:002019-01-01 00:00:002020-01-01 00:00:00LatitudeLongitude
Country
United States0000000000...376280301229213198118239.783730-100.445882
Brazil0000000000...00000000-10.333333-53.200000
Russia0000000000...1151272372172603291891664.68631497.745306
Japan0000000000...0002200036.574844139.239418
Vietnam0000000000...0000130015.926666107.965086
\n", "

5 rows × 106 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 00:00:00 1918-01-01 00:00:00 1919-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1920-01-01 00:00:00 1921-01-01 00:00:00 1922-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1923-01-01 00:00:00 1924-01-01 00:00:00 1925-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1926-01-01 00:00:00 ... 2013-01-01 00:00:00 \\\n", "Country ... \n", "United States 0 ... 376 \n", "Brazil 0 ... 0 \n", "Russia 0 ... 115 \n", "Japan 0 ... 0 \n", "Vietnam 0 ... 0 \n", "\n", "Years 2014-01-01 00:00:00 2015-01-01 00:00:00 2016-01-01 00:00:00 \\\n", "Country \n", "United States 280 301 229 \n", "Brazil 0 0 0 \n", "Russia 127 237 217 \n", "Japan 0 0 2 \n", "Vietnam 0 0 0 \n", "\n", "Years 2017-01-01 00:00:00 2018-01-01 00:00:00 2019-01-01 00:00:00 \\\n", "Country \n", "United States 213 198 118 \n", "Brazil 0 0 0 \n", "Russia 260 329 189 \n", "Japan 2 0 0 \n", "Vietnam 1 3 0 \n", "\n", "Years 2020-01-01 00:00:00 Latitude Longitude \n", "Country \n", "United States 2 39.783730 -100.445882 \n", "Brazil 0 -10.333333 -53.200000 \n", "Russia 16 64.686314 97.745306 \n", "Japan 0 36.574844 139.239418 \n", "Vietnam 0 15.926666 107.965086 \n", "\n", "[5 rows x 106 columns]" ] }, "execution_count": 82, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean2 = corg_clean_t.loc[:,(corg_clean_t.columns!='Total Corg')].copy()\n", "corg_clean2.head()" ] }, { "cell_type": "code", "execution_count": 84, "id": "239ef701", "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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Years1917-01-011918-01-011919-01-011920-01-011921-01-011922-01-011923-01-011924-01-011925-01-011926-01-01...2011-01-012012-01-012013-01-012014-01-012015-01-012016-01-012017-01-012018-01-012019-01-012020-01-01
Country
United States0000000000...13982144131478915069153701559915812160101612816130
Brazil0000000000...1111111111
Russia0000000000...26234445958682310401300162918181834
Japan0000000000...3333357777
Vietnam0000000000...0000001444
Germany0000000000...428508589666738792820862892892
France0000000000...276302338375395450510535597597
United Kingdom111111351931...2509253125572579260526332643264826492649
Italy0000000000...818181949698102104106106
South Africa0000000000...19232428282828282828
Ukraine0000000000...891010121212181919
Spain0000000000...0000000055
Poland0000000000...337379460526617692748825859859
Canada0000000000...329344359364377383386390391391
Korea, North0000000000...0034445555
Romania0000000000...0000000077
Australia0000000000...814827844855861870879887891891
Portugal0000000000...0001233577
Belgium0000000000...6379949698104105107110110
Czech Republic0000000000...139150171188210233255264271271
Hungary0000000000...7778888888
Belarus0000000000...00000512213838
Sweden0000000000...1214134214611525164317911928198820072008
Austria0000000000...21222229292929292929
Switzerland0000000000...28292929303030303030
Israel0000000000...0008131721253232
Serbia0000000000...0000112222
Denmark0000000000...1549165317601856196720452115214821762176
Finland0000000000...2824296731103308350936953961404440484051
Norway0000000000...434503570669770873970105610771077
Croatia0000000000...000031115212121
New Zealand0000000000...1080108010821083108810911094109710971097
Ireland0000000000...29292929292929292929
Lithuania0000000000...552020202929292929
Uruguay0000000000...0000002222
Latvia0000000000...3333333333
Slovenia0000000000...1111111111
Estonia0000000000...11181824305765819797
Netherlands0000000000...323375417448470487512524536536
Kosovo0011111111...185204251288352424525581632649
\n", "

40 rows × 104 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 1918-01-01 1919-01-01 1920-01-01 1921-01-01 \\\n", "Country \n", "United States 0 0 0 0 0 \n", "Brazil 0 0 0 0 0 \n", "Russia 0 0 0 0 0 \n", "Japan 0 0 0 0 0 \n", "Vietnam 0 0 0 0 0 \n", "Germany 0 0 0 0 0 \n", "France 0 0 0 0 0 \n", "United Kingdom 1 1 1 1 1 \n", "Italy 0 0 0 0 0 \n", "South Africa 0 0 0 0 0 \n", "Ukraine 0 0 0 0 0 \n", "Spain 0 0 0 0 0 \n", "Poland 0 0 0 0 0 \n", "Canada 0 0 0 0 0 \n", "Korea, North 0 0 0 0 0 \n", "Romania 0 0 0 0 0 \n", "Australia 0 0 0 0 0 \n", "Portugal 0 0 0 0 0 \n", "Belgium 0 0 0 0 0 \n", "Czech Republic 0 0 0 0 0 \n", "Hungary 0 0 0 0 0 \n", "Belarus 0 0 0 0 0 \n", "Sweden 0 0 0 0 0 \n", "Austria 0 0 0 0 0 \n", "Switzerland 0 0 0 0 0 \n", "Israel 0 0 0 0 0 \n", "Serbia 0 0 0 0 0 \n", "Denmark 0 0 0 0 0 \n", "Finland 0 0 0 0 0 \n", "Norway 0 0 0 0 0 \n", "Croatia 0 0 0 0 0 \n", "New Zealand 0 0 0 0 0 \n", "Ireland 0 0 0 0 0 \n", "Lithuania 0 0 0 0 0 \n", "Uruguay 0 0 0 0 0 \n", "Latvia 0 0 0 0 0 \n", "Slovenia 0 0 0 0 0 \n", "Estonia 0 0 0 0 0 \n", "Netherlands 0 0 0 0 0 \n", "Kosovo 0 0 1 1 1 \n", "\n", "Years 1922-01-01 1923-01-01 1924-01-01 1925-01-01 1926-01-01 \\\n", "Country \n", "United States 0 0 0 0 0 \n", "Brazil 0 0 0 0 0 \n", "Russia 0 0 0 0 0 \n", "Japan 0 0 0 0 0 \n", "Vietnam 0 0 0 0 0 \n", "Germany 0 0 0 0 0 \n", "France 0 0 0 0 0 \n", "United Kingdom 1 3 5 19 31 \n", "Italy 0 0 0 0 0 \n", "South Africa 0 0 0 0 0 \n", "Ukraine 0 0 0 0 0 \n", "Spain 0 0 0 0 0 \n", "Poland 0 0 0 0 0 \n", "Canada 0 0 0 0 0 \n", "Korea, North 0 0 0 0 0 \n", "Romania 0 0 0 0 0 \n", "Australia 0 0 0 0 0 \n", "Portugal 0 0 0 0 0 \n", "Belgium 0 0 0 0 0 \n", "Czech Republic 0 0 0 0 0 \n", "Hungary 0 0 0 0 0 \n", "Belarus 0 0 0 0 0 \n", "Sweden 0 0 0 0 0 \n", "Austria 0 0 0 0 0 \n", "Switzerland 0 0 0 0 0 \n", "Israel 0 0 0 0 0 \n", "Serbia 0 0 0 0 0 \n", "Denmark 0 0 0 0 0 \n", "Finland 0 0 0 0 0 \n", "Norway 0 0 0 0 0 \n", "Croatia 0 0 0 0 0 \n", "New Zealand 0 0 0 0 0 \n", "Ireland 0 0 0 0 0 \n", "Lithuania 0 0 0 0 0 \n", "Uruguay 0 0 0 0 0 \n", "Latvia 0 0 0 0 0 \n", "Slovenia 0 0 0 0 0 \n", "Estonia 0 0 0 0 0 \n", "Netherlands 0 0 0 0 0 \n", "Kosovo 1 1 1 1 1 \n", "\n", "Years ... 2011-01-01 2012-01-01 2013-01-01 2014-01-01 \\\n", "Country ... \n", "United States ... 13982 14413 14789 15069 \n", "Brazil ... 1 1 1 1 \n", "Russia ... 262 344 459 586 \n", "Japan ... 3 3 3 3 \n", "Vietnam ... 0 0 0 0 \n", "Germany ... 428 508 589 666 \n", "France ... 276 302 338 375 \n", "United Kingdom ... 2509 2531 2557 2579 \n", "Italy ... 81 81 81 94 \n", "South Africa ... 19 23 24 28 \n", "Ukraine ... 8 9 10 10 \n", "Spain ... 0 0 0 0 \n", "Poland ... 337 379 460 526 \n", "Canada ... 329 344 359 364 \n", "Korea, North ... 0 0 3 4 \n", "Romania ... 0 0 0 0 \n", "Australia ... 814 827 844 855 \n", "Portugal ... 0 0 0 1 \n", "Belgium ... 63 79 94 96 \n", "Czech Republic ... 139 150 171 188 \n", "Hungary ... 7 7 7 8 \n", "Belarus ... 0 0 0 0 \n", "Sweden ... 1214 1342 1461 1525 \n", "Austria ... 21 22 22 29 \n", "Switzerland ... 28 29 29 29 \n", "Israel ... 0 0 0 8 \n", "Serbia ... 0 0 0 0 \n", "Denmark ... 1549 1653 1760 1856 \n", "Finland ... 2824 2967 3110 3308 \n", "Norway ... 434 503 570 669 \n", "Croatia ... 0 0 0 0 \n", "New Zealand ... 1080 1080 1082 1083 \n", "Ireland ... 29 29 29 29 \n", "Lithuania ... 5 5 20 20 \n", "Uruguay ... 0 0 0 0 \n", "Latvia ... 3 3 3 3 \n", "Slovenia ... 1 1 1 1 \n", "Estonia ... 11 18 18 24 \n", "Netherlands ... 323 375 417 448 \n", "Kosovo ... 185 204 251 288 \n", "\n", "Years 2015-01-01 2016-01-01 2017-01-01 2018-01-01 2019-01-01 \\\n", "Country \n", "United States 15370 15599 15812 16010 16128 \n", "Brazil 1 1 1 1 1 \n", "Russia 823 1040 1300 1629 1818 \n", "Japan 3 5 7 7 7 \n", "Vietnam 0 0 1 4 4 \n", "Germany 738 792 820 862 892 \n", "France 395 450 510 535 597 \n", "United Kingdom 2605 2633 2643 2648 2649 \n", "Italy 96 98 102 104 106 \n", "South Africa 28 28 28 28 28 \n", "Ukraine 12 12 12 18 19 \n", "Spain 0 0 0 0 5 \n", "Poland 617 692 748 825 859 \n", "Canada 377 383 386 390 391 \n", "Korea, North 4 4 5 5 5 \n", "Romania 0 0 0 0 7 \n", "Australia 861 870 879 887 891 \n", "Portugal 2 3 3 5 7 \n", "Belgium 98 104 105 107 110 \n", "Czech Republic 210 233 255 264 271 \n", "Hungary 8 8 8 8 8 \n", "Belarus 0 5 12 21 38 \n", "Sweden 1643 1791 1928 1988 2007 \n", "Austria 29 29 29 29 29 \n", "Switzerland 30 30 30 30 30 \n", "Israel 13 17 21 25 32 \n", "Serbia 1 1 2 2 2 \n", "Denmark 1967 2045 2115 2148 2176 \n", "Finland 3509 3695 3961 4044 4048 \n", "Norway 770 873 970 1056 1077 \n", "Croatia 3 11 15 21 21 \n", "New Zealand 1088 1091 1094 1097 1097 \n", "Ireland 29 29 29 29 29 \n", "Lithuania 20 29 29 29 29 \n", "Uruguay 0 0 2 2 2 \n", "Latvia 3 3 3 3 3 \n", "Slovenia 1 1 1 1 1 \n", "Estonia 30 57 65 81 97 \n", "Netherlands 470 487 512 524 536 \n", "Kosovo 352 424 525 581 632 \n", "\n", "Years 2020-01-01 \n", "Country \n", "United States 16130 \n", "Brazil 1 \n", "Russia 1834 \n", "Japan 7 \n", "Vietnam 4 \n", "Germany 892 \n", "France 597 \n", "United Kingdom 2649 \n", "Italy 106 \n", "South Africa 28 \n", "Ukraine 19 \n", "Spain 5 \n", "Poland 859 \n", "Canada 391 \n", "Korea, North 5 \n", "Romania 7 \n", "Australia 891 \n", "Portugal 7 \n", "Belgium 110 \n", "Czech Republic 271 \n", "Hungary 8 \n", "Belarus 38 \n", "Sweden 2008 \n", "Austria 29 \n", "Switzerland 30 \n", "Israel 32 \n", "Serbia 2 \n", "Denmark 2176 \n", "Finland 4051 \n", "Norway 1077 \n", "Croatia 21 \n", "New Zealand 1097 \n", "Ireland 29 \n", "Lithuania 29 \n", "Uruguay 2 \n", "Latvia 3 \n", "Slovenia 1 \n", "Estonia 97 \n", "Netherlands 536 \n", "Kosovo 649 \n", "\n", "[40 rows x 104 columns]" ] }, "execution_count": 84, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean2.loc[:,(corg_clean2.columns!='Latitude')&(corg_clean2.columns!='Longitude')].cumsum(axis=1)" ] }, { "cell_type": "code", "execution_count": 85, "id": "81cebdf1", "metadata": {}, "outputs": [], "source": [ "corg_clean2.loc[:,(corg_clean2.columns!='Latitude')&(corg_clean2.columns!='Longitude')] = \\\n", " corg_clean2.loc[:,(corg_clean2.columns!='Latitude')&(corg_clean2.columns!='Longitude')].cumsum(axis=1)" ] }, { "cell_type": "code", "execution_count": 86, "id": "997a92a3", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Years1917-01-01 00:00:001918-01-01 00:00:001919-01-01 00:00:001920-01-01 00:00:001921-01-01 00:00:001922-01-01 00:00:001923-01-01 00:00:001924-01-01 00:00:001925-01-01 00:00:001926-01-01 00:00:00...2013-01-01 00:00:002014-01-01 00:00:002015-01-01 00:00:002016-01-01 00:00:002017-01-01 00:00:002018-01-01 00:00:002019-01-01 00:00:002020-01-01 00:00:00LatitudeLongitude
Country
United States0000000000...147891506915370155991581216010161281613039.783730-100.445882
Brazil0000000000...11111111-10.333333-53.200000
Russia0000000000...4595868231040130016291818183464.68631497.745306
Japan0000000000...3335777736.574844139.239418
Vietnam0000000000...0000144415.926666107.965086
\n", "

5 rows × 106 columns

\n", "
" ], "text/plain": [ "Years 1917-01-01 00:00:00 1918-01-01 00:00:00 1919-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1920-01-01 00:00:00 1921-01-01 00:00:00 1922-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1923-01-01 00:00:00 1924-01-01 00:00:00 1925-01-01 00:00:00 \\\n", "Country \n", "United States 0 0 0 \n", "Brazil 0 0 0 \n", "Russia 0 0 0 \n", "Japan 0 0 0 \n", "Vietnam 0 0 0 \n", "\n", "Years 1926-01-01 00:00:00 ... 2013-01-01 00:00:00 \\\n", "Country ... \n", "United States 0 ... 14789 \n", "Brazil 0 ... 1 \n", "Russia 0 ... 459 \n", "Japan 0 ... 3 \n", "Vietnam 0 ... 0 \n", "\n", "Years 2014-01-01 00:00:00 2015-01-01 00:00:00 2016-01-01 00:00:00 \\\n", "Country \n", "United States 15069 15370 15599 \n", "Brazil 1 1 1 \n", "Russia 586 823 1040 \n", "Japan 3 3 5 \n", "Vietnam 0 0 0 \n", "\n", "Years 2017-01-01 00:00:00 2018-01-01 00:00:00 2019-01-01 00:00:00 \\\n", "Country \n", "United States 15812 16010 16128 \n", "Brazil 1 1 1 \n", "Russia 1300 1629 1818 \n", "Japan 7 7 7 \n", "Vietnam 1 4 4 \n", "\n", "Years 2020-01-01 00:00:00 Latitude Longitude \n", "Country \n", "United States 16130 39.783730 -100.445882 \n", "Brazil 1 -10.333333 -53.200000 \n", "Russia 1834 64.686314 97.745306 \n", "Japan 7 36.574844 139.239418 \n", "Vietnam 4 15.926666 107.965086 \n", "\n", "[5 rows x 106 columns]" ] }, "execution_count": 86, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_clean2.head()" ] }, { "cell_type": "code", "execution_count": 88, "id": "9be5c288", "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", "
CountryLongitudeLatitudeYearcumulative_sum
0United States-100.44588239.7837301917-01-010
1Brazil-53.200000-10.3333331917-01-010
2Russia97.74530664.6863141917-01-010
3Japan139.23941836.5748441917-01-010
4Vietnam107.96508615.9266661917-01-010
\n", "
" ], "text/plain": [ " Country Longitude Latitude Year cumulative_sum\n", "0 United States -100.445882 39.783730 1917-01-01 0\n", "1 Brazil -53.200000 -10.333333 1917-01-01 0\n", "2 Russia 97.745306 64.686314 1917-01-01 0\n", "3 Japan 139.239418 36.574844 1917-01-01 0\n", "4 Vietnam 107.965086 15.926666 1917-01-01 0" ] }, "execution_count": 88, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_melt = corg_clean2.reset_index().melt(['Country','Longitude', 'Latitude'], \n", " var_name='Year', value_name = 'cumulative_sum')\n", "corg_melt.head()" ] }, { "cell_type": "code", "execution_count": 89, "id": "95d91d3f", "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", "
CountryLongitudeLatitudeYearcumulative_sumyear_int
0United States-100.44588239.7837301917-01-0101917
1Brazil-53.200000-10.3333331917-01-0101917
2Russia97.74530664.6863141917-01-0101917
3Japan139.23941836.5748441917-01-0101917
4Vietnam107.96508615.9266661917-01-0101917
\n", "
" ], "text/plain": [ " Country Longitude Latitude Year cumulative_sum year_int\n", "0 United States -100.445882 39.783730 1917-01-01 0 1917\n", "1 Brazil -53.200000 -10.333333 1917-01-01 0 1917\n", "2 Russia 97.745306 64.686314 1917-01-01 0 1917\n", "3 Japan 139.239418 36.574844 1917-01-01 0 1917\n", "4 Vietnam 107.965086 15.926666 1917-01-01 0 1917" ] }, "execution_count": 89, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corg_melt['year_int'] = corg_melt['Year'].dt.year.astype('int')\n", "corg_melt.head()" ] }, { "cell_type": "code", "execution_count": 97, "id": "9da200c2", "metadata": {}, "outputs": [], "source": [ "slider = alt.binding_range(min=corg_melt['year_int'].min(), \n", " max = corg_melt['year_int'].max(),\n", " step=1, name='Year:')\n", "selector = alt.selection_point(name='Selection', fields=['year_int'], \n", " bind=slider, value=2000, nearest=True)" ] }, { "cell_type": "code", "execution_count": 99, "id": "8e3b7193", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.LayerChart(...)" ] }, "execution_count": 99, "metadata": {}, "output_type": "execute_result" } ], "source": [ "geo = alt.topo_feature(data.world_110m.url, feature='countries')\n", "\n", "# world background\n", "world = alt.Chart(geo).mark_geoshape(\n", " fill='gray',\n", " stroke='white'\n", ").properties(\n", " width=800,\n", " height=400\n", ").project('equirectangular')\n", "\n", "size = alt.condition(selector, alt.Size('cumulative_sum:Q', scale=None), alt.value(0))\n", "\n", "points = alt.Chart(corg_melt).mark_circle().encode(\n", " longitude = 'Longitude:Q',\n", " latitude = 'Latitude:Q',\n", " size=size,\n", " tooltip=['Country','cumulative_sum']\n", ").add_params(\n", " selector\n", ")\n", "\n", "chart = world + points\n", "chart" ] }, { "cell_type": "code", "execution_count": 100, "id": "aac6c35a", "metadata": {}, "outputs": [], "source": [ "#chart.save ..." ] }, { "cell_type": "code", "execution_count": 101, "id": "c41c4132", "metadata": {}, "outputs": [], "source": [ "world = alt.Chart(geo).mark_geoshape(\n", " fill='gray',\n", " stroke='white'\n", ")" ] }, { "cell_type": "code", "execution_count": 104, "id": "043cb13b", "metadata": {}, "outputs": [], "source": [ "import geopandas\n", "gdf = geopandas.read_file(data.us_10m.url)" ] }, { "cell_type": "code", "execution_count": 105, "id": "f5a1aa45", "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", "
idgeometry
022051GEOMETRYCOLLECTION EMPTY
153000POLYGON ((-122.65544 48.41032, -122.65544 48.4...
253073MULTIPOLYGON (((-120.85361 49.00011, -120.7674...
330105POLYGON ((-106.11238 48.99904, -106.15187 48.8...
430029POLYGON ((-114.06985 48.99904, -114.05908 48.8...
.........
322672037MULTIPOLYGON (((-65.63591 18.28406, -65.63591 ...
322772069POLYGON ((-65.74000 18.17395, -65.79743 18.069...
322872147POLYGON ((-65.53182 18.07995, -65.57849 18.118...
322978010POLYGON ((-64.90011 17.67440, -64.87139 17.770...
323072051POLYGON ((-66.21379 18.46455, -66.25327 18.394...
\n", "

3231 rows × 2 columns

\n", "
" ], "text/plain": [ " id geometry\n", "0 22051 GEOMETRYCOLLECTION EMPTY\n", "1 53000 POLYGON ((-122.65544 48.41032, -122.65544 48.4...\n", "2 53073 MULTIPOLYGON (((-120.85361 49.00011, -120.7674...\n", "3 30105 POLYGON ((-106.11238 48.99904, -106.15187 48.8...\n", "4 30029 POLYGON ((-114.06985 48.99904, -114.05908 48.8...\n", "... ... ...\n", "3226 72037 MULTIPOLYGON (((-65.63591 18.28406, -65.63591 ...\n", "3227 72069 POLYGON ((-65.74000 18.17395, -65.79743 18.069...\n", "3228 72147 POLYGON ((-65.53182 18.07995, -65.57849 18.118...\n", "3229 78010 POLYGON ((-64.90011 17.67440, -64.87139 17.770...\n", "3230 72051 POLYGON ((-66.21379 18.46455, -66.25327 18.394...\n", "\n", "[3231 rows x 2 columns]" ] }, "execution_count": 105, "metadata": {}, "output_type": "execute_result" } ], "source": [ "gdf" ] }, { "cell_type": "code", "execution_count": null, "id": "0345aab6", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.8.12" } }, "nbformat": 4, "nbformat_minor": 5 }