{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Corona Virus analysis using 'Novel Corona Virus 2019-20 Dataset'" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "As Github does not support folium map and some rendering techniques, so if you want to see fully rendered notebook, click on below link\n", "\n", "https://nbviewer.jupyter.org/github/Mr-Piyush-Kumar/Data_Science_Projects/blob/master/Corona_virus_analysis/CoronaVirusAnalysis.ipynb" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 1. Introduction" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 1.1 Background\n", "\n", "From World Health Organization - On 31 December 2019, WHO was alerted to several cases of pneumonia in Wuhan City, Hubei Province of China. The virus did not match any other known virus. This raised concern because when a virus is new, we do not know how it affects people.\n", "\n", "So daily level information on the affected people can give some interesting insights when it is made available to the broader data science community." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 2. Data acquisition and cleaning" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "All dataset will be download from below Kaggle webpages. \n", " \n", "Corona Virus dataset from here \n", "World Coordinates dataset from here \n", "World geoJson file from here \n", "China geoJson file from here" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: wget in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (3.2)\n", "file name = 2019_nCoV_data.csv\n" ] } ], "source": [ "# Downlodaing Corona Virus Dataset\n", "\n", "!pip install wget\n", "\n", "import wget\n", "url = 'https://storage.googleapis.com/kagglesdsdata/datasets/494724/966440/2019_nCoV_data.csv?GoogleAccessId=web-data@kaggle-161607.iam.gserviceaccount.com&Expires=1582868558&Signature=JXjN269XVMhWbNH3BAyQozqwNFBePHHrrxpRMk%2BpD3ANojzrkvE5Qer9z1fk1uprgM0njfohll0yPHB8mZs4eN0Ucke7I4JtTTRyISKFWSO%2FCcDZanS9pWX%2FdnEBUV6QindIhmE%2FZeeeRAeKx%2Fd8h3RGlHpCeBm6%2BN7L6XnZj8N%2FsxlmIz%2FXwbxc%2BW2VRi4pG1P0AmJI5PjIc5OVcQISdy0RCGDaJuhAGm4TTarYuZt9j36rFlheXNXitn2EeutI4OI%2B%2BBqTV7fIR5mdBXCa1%2FKiutt3Lu%2BffT7N62dlMXLR4Z0aga4OvzzzwdVuf7TbLWBpqcx6LTQGGD03Fj5kEw%3D%3D&response-content-disposition=attachment%3B+filename%3D2019_nCoV_data.csv'\n", "file = wget.download(url)\n", "print('file name = ',file)\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "file name = world_coordinates.csv\n" ] } ], "source": [ "# Downloading word-coordinates data for visulization on world map\n", "\n", "url1 = 'https://storage.googleapis.com/kagglesdsdata/datasets/500356/927175/world_coordinates.csv?GoogleAccessId=web-data@kaggle-161607.iam.gserviceaccount.com&Expires=1582868625&Signature=soCAku6MmJLB%2FL48Oxs%2FSxaPP11EASBJG%2BPMCRfhPcavNJBDhviiE12SKcfAje07vuDsWsuRiUxRu61KgBObNNe2brA9JHiEL4I4D1dgYk%2F6SKLJz6RFWCwYnr5b%2FAiHfQW2dLxNtRF35MEfR4ncnOW0FHLzgSTd8wq12QrV6y9%2B8XAOyjwcFdkCnLk0eTws0ERhUMC0CSeqFXqkS7leuBxSAUW2jUblrLvir3938JSZ2aqqbywj4eIT5jy0XvmpxepDsYOu1kJpkkyKq4lzyWTwNmr5ljZGWSoJrOVMAIU17z%2FnI3Is2s2YyysoUI6I0XoXRPqyN%2B8pZy0%2F0GPw1Q%3D%3D&response-content-disposition=attachment%3B+filename%3Dworld_coordinates.csv'\n", "file1 = wget.download(url1)\n", "print('file name = ',file1)\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "file name = world-countries.json\n" ] } ], "source": [ "# downloading world geoJson file to draw choropleth map of world\n", "\n", "url2 = 'https://storage.googleapis.com/kagglesdsdata/datasets/7923/11172/world-countries.json?GoogleAccessId=web-data@kaggle-161607.iam.gserviceaccount.com&Expires=1582868666&Signature=ca8CoGxJ1mYdOR%2BKnaYdfO5mW15iNPvFWNOElOCDMUMRAU4wfO9G2W5980D6zYDFO94SrgiFm07enAWeuF3SmUF5XuU70bn%2FDID%2F%2F2%2FU4JHE00szhJWsIyLHm66R%2FInBNR4Wqg1OYgA0qlqw6Ewy9%2F0jAl4P%2Bv62voX7oO1rI%2BEGPwS0DBaHsUHCGwL4GNdxjJJ%2Ba05c6jpksTvP4V%2FWk%2FvLeyGOMa%2BE5FzExHInBlbiCCPX5bsUo%2BjG87kpIokoSIt2eoP7fiVzPnhB6Z83Td3zwr5ld0gJA%2FyxXagrDbB70JwmdgVO%2B3k2%2BySZqgev%2F6rLk7Lm%2FJFy%2B6ZMgPIVcw%3D%3D&response-content-disposition=attachment%3B+filename%3Dworld-countries.json'\n", "file2 = wget.download(url2)\n", "print('file name = ',file2)\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "file name = china.json\n" ] } ], "source": [ "# downloading china geoJson file to draw choropleth map of China\n", "\n", "url3 = 'https://storage.googleapis.com/kagglesdsdata/datasets/496669/922532/china.json?GoogleAccessId=web-data@kaggle-161607.iam.gserviceaccount.com&Expires=1582868706&Signature=L4Xo4fynYwWPvUio3j1NWc4sQBFeAje1N3kZ4%2BzrLJdFZsQiyMJB3lisf%2FVS%2BD7Kq0Pe0aCgxhS1tpmaTbQFF87255Fy%2B7In%2BJOJZnmytgc8NGc6m9ZaOlzuLkgoAT3tgfLYWmRcWLvvBl1cdAArfhl%2BibxSl7%2BbjNvGo3Q0XolnhfdjKZCZ5egh%2FmSV8HUfrf0OBm0%2BXbUEcmV4wkJm8RM8UFSvE1t5HFrhvzO29WmZm9rcwiHKuLPxjl3KGtXpp4ysTJPpScM50UyAgWcrZH1LYeARmGhbnGRarblLGfeHoj2sbO9Nh%2FQAd5XmiNEMtdxTnR99p65Dd07v76979Q%3D%3D&response-content-disposition=attachment%3B+filename%3Dchina.json'\n", "file3 = wget.download(url3)\n", "print('file name = ',file3)\n" ] }, { "cell_type": "code", "execution_count": 5, "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", "
SnoDateProvince/StateCountryLast UpdateConfirmedDeathsRecovered
0101/22/2020 12:00:00AnhuiChina01/22/2020 12:00:001.00.00.0
1201/22/2020 12:00:00BeijingChina01/22/2020 12:00:0014.00.00.0
2301/22/2020 12:00:00ChongqingChina01/22/2020 12:00:006.00.00.0
3401/22/2020 12:00:00FujianChina01/22/2020 12:00:001.00.00.0
4501/22/2020 12:00:00GansuChina01/22/2020 12:00:000.00.00.0
\n", "
" ], "text/plain": [ " Sno Date Province/State Country Last Update \\\n", "0 1 01/22/2020 12:00:00 Anhui China 01/22/2020 12:00:00 \n", "1 2 01/22/2020 12:00:00 Beijing China 01/22/2020 12:00:00 \n", "2 3 01/22/2020 12:00:00 Chongqing China 01/22/2020 12:00:00 \n", "3 4 01/22/2020 12:00:00 Fujian China 01/22/2020 12:00:00 \n", "4 5 01/22/2020 12:00:00 Gansu China 01/22/2020 12:00:00 \n", "\n", " Confirmed Deaths Recovered \n", "0 1.0 0.0 0.0 \n", "1 14.0 0.0 0.0 \n", "2 6.0 0.0 0.0 \n", "3 1.0 0.0 0.0 \n", "4 0.0 0.0 0.0 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# loading corona virus dataset as Pandas Dataframe\n", "import pandas as pd\n", "\n", "corona_df = pd.read_csv('2019_nCoV_data.csv')\n", "corona_df.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Corona Dataset columns decription:-**\n", "\n", "- Sno:- Serial Number. \n", "- Date:- In which date and time, a particular record wrote in the dataset. \n", "- Province/State:- Province/State name of belonging country. \n", "- Country:- Country Name. \n", "- Last Update:- At what time, last case was observed in a particular day. \n", "- Confirmed:- No. of confirmed infected people till now in a particular location (Representing Cumulative Sum). \n", "- Deaths:- No. of deaths till now due to Corona virus in a particular location (Representing Cumulative Sum). \n", "- Recovered:- No. of recovered people till now who was infected in a particular location (Representing Cumulative Sum). " ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "# loading both geoJson files\n", "\n", "world_geoJson = 'world-countries.json' # Path to file\n", "china_geoJson = 'china.json' # Path to file" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**About geoJson file**\n", "\n", "GeoJSON is an open standard geospatial data interchange format that represents simple geographic features and their nonspatial attributes. Based on JavaScript Object Notation (JSON), GeoJSON is a format for encoding a variety of geographic data structures. It uses a geographic coordinate reference system, World Geodetic System 1984, and units of decimal degrees.\n", "\n", "Read more about geoJson file from here.\n", "\n", "I will use these two files to show choropleth map of world as well as of china to representing corona virus outbreak location wise.\n", "\n", "Read about choropleth map from here." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Data Cleaning" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "dropping Sno. from Dataset as it's not required for analysis." ] }, { "cell_type": "code", "execution_count": 7, "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", "
DateProvince/StateCountryLast UpdateConfirmedDeathsRecovered
001/22/2020 12:00:00AnhuiChina01/22/2020 12:00:001.00.00.0
101/22/2020 12:00:00BeijingChina01/22/2020 12:00:0014.00.00.0
201/22/2020 12:00:00ChongqingChina01/22/2020 12:00:006.00.00.0
301/22/2020 12:00:00FujianChina01/22/2020 12:00:001.00.00.0
401/22/2020 12:00:00GansuChina01/22/2020 12:00:000.00.00.0
\n", "
" ], "text/plain": [ " Date Province/State Country Last Update Confirmed \\\n", "0 01/22/2020 12:00:00 Anhui China 01/22/2020 12:00:00 1.0 \n", "1 01/22/2020 12:00:00 Beijing China 01/22/2020 12:00:00 14.0 \n", "2 01/22/2020 12:00:00 Chongqing China 01/22/2020 12:00:00 6.0 \n", "3 01/22/2020 12:00:00 Fujian China 01/22/2020 12:00:00 1.0 \n", "4 01/22/2020 12:00:00 Gansu China 01/22/2020 12:00:00 0.0 \n", "\n", " Deaths Recovered \n", "0 0.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 0.0 0.0 " ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corona_df.drop('Sno',axis=1,inplace=True)\n", "corona_df.head()" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['China', 'US', 'Japan', 'Thailand', 'South Korea',\n", " 'Mainland China', 'Hong Kong', 'Macau', 'Taiwan', 'Singapore',\n", " 'Philippines', 'Malaysia', 'Vietnam', 'Australia', 'Mexico',\n", " 'Brazil', 'France', 'Nepal', 'Canada', 'Cambodia', 'Sri Lanka',\n", " 'Ivory Coast', 'Germany', 'Finland', 'United Arab Emirates',\n", " 'India', 'Italy', 'Sweden', 'Russia', 'Spain', 'UK', 'Belgium',\n", " 'Others', 'Egypt'], dtype=object)" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corona_df.Country.unique()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "China and Mainland China are representing as two different countries in dataset. Lets replace Mainland china with China." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['China', 'US', 'Japan', 'Thailand', 'South Korea', 'Hong Kong',\n", " 'Macau', 'Taiwan', 'Singapore', 'Philippines', 'Malaysia',\n", " 'Vietnam', 'Australia', 'Mexico', 'Brazil', 'France', 'Nepal',\n", " 'Canada', 'Cambodia', 'Sri Lanka', 'Ivory Coast', 'Germany',\n", " 'Finland', 'United Arab Emirates', 'India', 'Italy', 'Sweden',\n", " 'Russia', 'Spain', 'UK', 'Belgium', 'Others', 'Egypt'],\n", " dtype=object)" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corona_df.replace('Mainland China','China',inplace=True)\n", "corona_df.Country.unique()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In Country column, there is one value 'Others'. As I have no information about how many countries are grouped as Others so I am going to drop those rows from dataset having country value Others." ] }, { "cell_type": "code", "execution_count": 10, "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", "
DateProvince/StateCountryLast UpdateConfirmedDeathsRecovered
001/22/2020 12:00:00AnhuiChina01/22/2020 12:00:001.00.00.0
101/22/2020 12:00:00BeijingChina01/22/2020 12:00:0014.00.00.0
201/22/2020 12:00:00ChongqingChina01/22/2020 12:00:006.00.00.0
301/22/2020 12:00:00FujianChina01/22/2020 12:00:001.00.00.0
401/22/2020 12:00:00GansuChina01/22/2020 12:00:000.00.00.0
........................
170302/17/2020 22:00:00Madison, WIUS2020-02-05T21:53:021.00.00.0
170402/17/2020 22:00:00Orange, CAUS2020-02-01T19:53:031.00.00.0
170502/17/2020 22:00:00San Antonio, TXUS2020-02-13T18:53:021.00.00.0
170602/17/2020 22:00:00Seattle, WAUS2020-02-09T07:03:041.00.01.0
170702/17/2020 22:00:00Tempe, AZUS2020-02-01T19:43:031.00.00.0
\n", "

1708 rows × 7 columns

\n", "
" ], "text/plain": [ " Date Province/State Country Last Update \\\n", "0 01/22/2020 12:00:00 Anhui China 01/22/2020 12:00:00 \n", "1 01/22/2020 12:00:00 Beijing China 01/22/2020 12:00:00 \n", "2 01/22/2020 12:00:00 Chongqing China 01/22/2020 12:00:00 \n", "3 01/22/2020 12:00:00 Fujian China 01/22/2020 12:00:00 \n", "4 01/22/2020 12:00:00 Gansu China 01/22/2020 12:00:00 \n", "... ... ... ... ... \n", "1703 02/17/2020 22:00:00 Madison, WI US 2020-02-05T21:53:02 \n", "1704 02/17/2020 22:00:00 Orange, CA US 2020-02-01T19:53:03 \n", "1705 02/17/2020 22:00:00 San Antonio, TX US 2020-02-13T18:53:02 \n", "1706 02/17/2020 22:00:00 Seattle, WA US 2020-02-09T07:03:04 \n", "1707 02/17/2020 22:00:00 Tempe, AZ US 2020-02-01T19:43:03 \n", "\n", " Confirmed Deaths Recovered \n", "0 1.0 0.0 0.0 \n", "1 14.0 0.0 0.0 \n", "2 6.0 0.0 0.0 \n", "3 1.0 0.0 0.0 \n", "4 0.0 0.0 0.0 \n", "... ... ... ... \n", "1703 1.0 0.0 0.0 \n", "1704 1.0 0.0 0.0 \n", "1705 1.0 0.0 0.0 \n", "1706 1.0 0.0 1.0 \n", "1707 1.0 0.0 0.0 \n", "\n", "[1708 rows x 7 columns]" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corona_df = corona_df[corona_df['Country']!='Others'].reset_index(drop=True)\n", "corona_df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 3. Data Analysis" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Handling NaN values**" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1708, 7)" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# shape of our dataset\n", "corona_df.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "total no of 1719 records are there in corona dataset." ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Date 0\n", "Province/State 462\n", "Country 0\n", "Last Update 0\n", "Confirmed 0\n", "Deaths 0\n", "Recovered 0\n", "dtype: int64" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# looking for null values present in corona datset\n", "\n", "corona_df.isna().sum()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In Province/State columns total 462 records have null value." ] }, { "cell_type": "code", "execution_count": 13, "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", "
DateProvince/StateCountryLast UpdateConfirmedDeathsRecovered
3501/22/2020 12:00:00NaNJapan01/22/2020 12:00:002.00.00.0
3601/22/2020 12:00:00NaNThailand01/22/2020 12:00:002.00.00.0
3701/22/2020 12:00:00NaNSouth Korea01/22/2020 12:00:001.00.00.0
7301/23/2020 12:00:00NaNJapan01/23/2020 12:00:001.00.00.0
7401/23/2020 12:00:00NaNThailand01/23/2020 12:00:003.00.00.0
........................
169502/17/2020 22:00:00NaNEgypt2020-02-14T23:53:021.00.00.0
169602/17/2020 22:00:00NaNFinland2020-02-12T00:03:121.00.01.0
169802/17/2020 22:00:00NaNNepal2020-02-12T14:43:031.00.01.0
169902/17/2020 22:00:00NaNSri Lanka2020-02-08T03:43:031.00.01.0
170002/17/2020 22:00:00NaNSweden2020-02-01T02:13:261.00.00.0
\n", "

462 rows × 7 columns

\n", "
" ], "text/plain": [ " Date Province/State Country Last Update \\\n", "35 01/22/2020 12:00:00 NaN Japan 01/22/2020 12:00:00 \n", "36 01/22/2020 12:00:00 NaN Thailand 01/22/2020 12:00:00 \n", "37 01/22/2020 12:00:00 NaN South Korea 01/22/2020 12:00:00 \n", "73 01/23/2020 12:00:00 NaN Japan 01/23/2020 12:00:00 \n", "74 01/23/2020 12:00:00 NaN Thailand 01/23/2020 12:00:00 \n", "... ... ... ... ... \n", "1695 02/17/2020 22:00:00 NaN Egypt 2020-02-14T23:53:02 \n", "1696 02/17/2020 22:00:00 NaN Finland 2020-02-12T00:03:12 \n", "1698 02/17/2020 22:00:00 NaN Nepal 2020-02-12T14:43:03 \n", "1699 02/17/2020 22:00:00 NaN Sri Lanka 2020-02-08T03:43:03 \n", "1700 02/17/2020 22:00:00 NaN Sweden 2020-02-01T02:13:26 \n", "\n", " Confirmed Deaths Recovered \n", "35 2.0 0.0 0.0 \n", "36 2.0 0.0 0.0 \n", "37 1.0 0.0 0.0 \n", "73 1.0 0.0 0.0 \n", "74 3.0 0.0 0.0 \n", "... ... ... ... \n", "1695 1.0 0.0 0.0 \n", "1696 1.0 0.0 1.0 \n", "1698 1.0 0.0 1.0 \n", "1699 1.0 0.0 1.0 \n", "1700 1.0 0.0 0.0 \n", "\n", "[462 rows x 7 columns]" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import numpy as np\n", "\n", "corona_province_nan = corona_df[corona_df['Province/State'].isna()]\n", "corona_province_nan" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([ 2., 1., 3., 0., 5., 7., 4., 8., 14., 11., 10., 6., 17.,\n", " 19., 16., 20., 18., 15., 12., 25., 24., 22., 28., 45., 23., 30.,\n", " 13., 40., 32., 43., 27., 26., 47., 33., 50., 9., 58., 67., 29.,\n", " 72., 75., 59., 34., 77., 66., 35.])" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corona_province_nan.Confirmed.unique()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "So the conclusion is that if a country has low no. of cases then dataset creators didn't divide country data into Province/State." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Replacing Nan Values with respective country name." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "pd.options.mode.chained_assignment = None # avoiding setting with copy warning\n", "corona_df['Province/State'][corona_df['Province/State'].isna()] = corona_df['Country']" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Total 32 countries have been affected by corona virus till now.\n" ] } ], "source": [ "print('Total',len(corona_df.Country.unique()),'countries have been affected by corona virus till now.')" ] }, { "cell_type": "code", "execution_count": 17, "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", "
CountryConfirmedDeathsRecovered
0Australia19.00.010.0
1Belgium1.00.01.0
2Brazil0.00.00.0
3Cambodia1.00.01.0
4Canada11.00.01.0
5China72366.01864.012455.0
6Egypt1.00.00.0
7Finland1.00.01.0
8France12.01.04.0
9Germany23.00.01.0
10Hong Kong60.01.02.0
11India3.00.03.0
12Italy3.00.00.0
13Ivory Coast0.00.00.0
14Japan66.01.012.0
15Macau10.00.05.0
16Malaysia22.00.07.0
17Mexico0.00.00.0
18Nepal1.00.01.0
19Philippines3.01.01.0
20Russia2.00.02.0
21Singapore77.00.024.0
22South Korea30.00.010.0
23Spain2.00.02.0
24Sri Lanka1.00.01.0
25Sweden1.00.00.0
26Taiwan22.01.02.0
27Thailand35.00.015.0
28UK9.00.08.0
29US23.00.03.0
30United Arab Emirates9.00.04.0
31Vietnam16.00.07.0
\n", "
" ], "text/plain": [ " Country Confirmed Deaths Recovered\n", "0 Australia 19.0 0.0 10.0\n", "1 Belgium 1.0 0.0 1.0\n", "2 Brazil 0.0 0.0 0.0\n", "3 Cambodia 1.0 0.0 1.0\n", "4 Canada 11.0 0.0 1.0\n", "5 China 72366.0 1864.0 12455.0\n", "6 Egypt 1.0 0.0 0.0\n", "7 Finland 1.0 0.0 1.0\n", "8 France 12.0 1.0 4.0\n", "9 Germany 23.0 0.0 1.0\n", "10 Hong Kong 60.0 1.0 2.0\n", "11 India 3.0 0.0 3.0\n", "12 Italy 3.0 0.0 0.0\n", "13 Ivory Coast 0.0 0.0 0.0\n", "14 Japan 66.0 1.0 12.0\n", "15 Macau 10.0 0.0 5.0\n", "16 Malaysia 22.0 0.0 7.0\n", "17 Mexico 0.0 0.0 0.0\n", "18 Nepal 1.0 0.0 1.0\n", "19 Philippines 3.0 1.0 1.0\n", "20 Russia 2.0 0.0 2.0\n", "21 Singapore 77.0 0.0 24.0\n", "22 South Korea 30.0 0.0 10.0\n", "23 Spain 2.0 0.0 2.0\n", "24 Sri Lanka 1.0 0.0 1.0\n", "25 Sweden 1.0 0.0 0.0\n", "26 Taiwan 22.0 1.0 2.0\n", "27 Thailand 35.0 0.0 15.0\n", "28 UK 9.0 0.0 8.0\n", "29 US 23.0 0.0 3.0\n", "30 United Arab Emirates 9.0 0.0 4.0\n", "31 Vietnam 16.0 0.0 7.0" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# total cases till now country wise\n", "\n", "countrywise_df = corona_df.groupby(['Country','Province/State']).max()\n", "countrywise_df.reset_index(inplace = True)\n", "countrywise_df = countrywise_df.groupby('Country').sum()\n", "countrywise_df.reset_index(inplace = True)\n", "countrywise_df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "China is most affected by Corona virus." ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "import seaborn as sns\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### **Visualizing spreading of corona virus from beginning to till now. day by day** \n", "\n", "as we have per day data of each country so there is no problem in it." ] }, { "cell_type": "code", "execution_count": 19, "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", "
DateConfirmedDeathsRecovered
001/22/2020 12:00:00555.00.00.0
101/23/2020 12:00:00653.018.030.0
201/24/2020 12:00:00941.026.036.0
301/25/2020 22:00:002019.056.049.0
401/26/2020 23:00:002794.080.054.0
501/27/2020 20:30:004473.0107.063.0
601/28/2020 23:00:006057.0132.0110.0
701/29/2020 21:00:007783.0170.0133.0
801/30/2020 21:30:009776.0213.0187.0
901/31/2020 19:00:0011374.0259.0252.0
1002/01/2020 23:00:0014549.0305.0340.0
1102/02/2020 21:00:0017295.0362.0487.0
1202/03/2020 21:40:0020588.0426.0644.0
1302/04/2020 22:00:0024503.0492.0899.0
1402/05/2020 12:20:0024630.0494.01029.0
1502/06/2020 20:05:0030806.0634.01487.0
1602/07/2020 20:24:0031471.0638.01763.0
1702/08/2020 23:04:0037488.0813.02701.0
1802/09/2020 23:20:0040472.0910.03312.0
1902/10/2020 19:30:0042632.01013.03950.0
2002/11/2020 20:44:0044982.01115.04781.0
2102/12/2020 22:00:0060153.01368.05986.0
2202/13/2020 21:15:0064204.01491.07064.0
2302/14/2020 22:00:0066669.01523.08058.0
2402/15/2020 22:00:0068747.01666.09395.0
2502/16/2020 22:00:0070871.01770.010865.0
2602/17/2020 22:00:0072806.01868.012583.0
\n", "
" ], "text/plain": [ " Date Confirmed Deaths Recovered\n", "0 01/22/2020 12:00:00 555.0 0.0 0.0\n", "1 01/23/2020 12:00:00 653.0 18.0 30.0\n", "2 01/24/2020 12:00:00 941.0 26.0 36.0\n", "3 01/25/2020 22:00:00 2019.0 56.0 49.0\n", "4 01/26/2020 23:00:00 2794.0 80.0 54.0\n", "5 01/27/2020 20:30:00 4473.0 107.0 63.0\n", "6 01/28/2020 23:00:00 6057.0 132.0 110.0\n", "7 01/29/2020 21:00:00 7783.0 170.0 133.0\n", "8 01/30/2020 21:30:00 9776.0 213.0 187.0\n", "9 01/31/2020 19:00:00 11374.0 259.0 252.0\n", "10 02/01/2020 23:00:00 14549.0 305.0 340.0\n", "11 02/02/2020 21:00:00 17295.0 362.0 487.0\n", "12 02/03/2020 21:40:00 20588.0 426.0 644.0\n", "13 02/04/2020 22:00:00 24503.0 492.0 899.0\n", "14 02/05/2020 12:20:00 24630.0 494.0 1029.0\n", "15 02/06/2020 20:05:00 30806.0 634.0 1487.0\n", "16 02/07/2020 20:24:00 31471.0 638.0 1763.0\n", "17 02/08/2020 23:04:00 37488.0 813.0 2701.0\n", "18 02/09/2020 23:20:00 40472.0 910.0 3312.0\n", "19 02/10/2020 19:30:00 42632.0 1013.0 3950.0\n", "20 02/11/2020 20:44:00 44982.0 1115.0 4781.0\n", "21 02/12/2020 22:00:00 60153.0 1368.0 5986.0\n", "22 02/13/2020 21:15:00 64204.0 1491.0 7064.0\n", "23 02/14/2020 22:00:00 66669.0 1523.0 8058.0\n", "24 02/15/2020 22:00:00 68747.0 1666.0 9395.0\n", "25 02/16/2020 22:00:00 70871.0 1770.0 10865.0\n", "26 02/17/2020 22:00:00 72806.0 1868.0 12583.0" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "Day_wise_world_data = corona_df.groupby('Date').sum().reset_index()\n", "Day_wise_world_data" ] }, { "cell_type": "code", "execution_count": 20, "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", "
DateConfirmedDeathsRecovered
001/22/2020 12:00:00549.00.00.0
101/23/2020 12:00:00639.018.030.0
201/24/2020 12:00:00916.026.036.0
301/25/2020 22:00:001979.056.049.0
401/26/2020 23:00:002737.080.051.0
501/27/2020 20:30:004409.0107.060.0
601/28/2020 23:00:005970.0132.0104.0
701/29/2020 21:00:007678.0170.0127.0
801/30/2020 21:30:009658.0213.0179.0
901/31/2020 19:00:0011221.0259.0242.0
1002/01/2020 23:00:0014375.0304.0331.0
1102/02/2020 21:00:0017114.0361.0478.0
1202/03/2020 21:40:0020400.0425.0635.0
1302/04/2020 22:00:0024290.0490.0890.0
1402/05/2020 12:20:0024405.0492.01020.0
1502/06/2020 20:05:0030541.0632.01476.0
1602/07/2020 20:24:0031215.0636.01750.0
1702/08/2020 23:04:0037198.0811.02678.0
1802/09/2020 23:20:0040160.0908.03286.0
1902/10/2020 19:30:0042310.01011.03921.0
2002/11/2020 20:44:0044641.01113.04730.0
2102/12/2020 22:00:0059805.01366.05915.0
2202/13/2020 21:15:0063841.01488.06982.0
2302/14/2020 22:00:0066292.01520.07973.0
2402/15/2020 22:00:0068347.01662.09294.0
2502/16/2020 22:00:0070446.01765.010748.0
2602/17/2020 22:00:0072364.01863.012455.0
\n", "
" ], "text/plain": [ " Date Confirmed Deaths Recovered\n", "0 01/22/2020 12:00:00 549.0 0.0 0.0\n", "1 01/23/2020 12:00:00 639.0 18.0 30.0\n", "2 01/24/2020 12:00:00 916.0 26.0 36.0\n", "3 01/25/2020 22:00:00 1979.0 56.0 49.0\n", "4 01/26/2020 23:00:00 2737.0 80.0 51.0\n", "5 01/27/2020 20:30:00 4409.0 107.0 60.0\n", "6 01/28/2020 23:00:00 5970.0 132.0 104.0\n", "7 01/29/2020 21:00:00 7678.0 170.0 127.0\n", "8 01/30/2020 21:30:00 9658.0 213.0 179.0\n", "9 01/31/2020 19:00:00 11221.0 259.0 242.0\n", "10 02/01/2020 23:00:00 14375.0 304.0 331.0\n", "11 02/02/2020 21:00:00 17114.0 361.0 478.0\n", "12 02/03/2020 21:40:00 20400.0 425.0 635.0\n", "13 02/04/2020 22:00:00 24290.0 490.0 890.0\n", "14 02/05/2020 12:20:00 24405.0 492.0 1020.0\n", "15 02/06/2020 20:05:00 30541.0 632.0 1476.0\n", "16 02/07/2020 20:24:00 31215.0 636.0 1750.0\n", "17 02/08/2020 23:04:00 37198.0 811.0 2678.0\n", "18 02/09/2020 23:20:00 40160.0 908.0 3286.0\n", "19 02/10/2020 19:30:00 42310.0 1011.0 3921.0\n", "20 02/11/2020 20:44:00 44641.0 1113.0 4730.0\n", "21 02/12/2020 22:00:00 59805.0 1366.0 5915.0\n", "22 02/13/2020 21:15:00 63841.0 1488.0 6982.0\n", "23 02/14/2020 22:00:00 66292.0 1520.0 7973.0\n", "24 02/15/2020 22:00:00 68347.0 1662.0 9294.0\n", "25 02/16/2020 22:00:00 70446.0 1765.0 10748.0\n", "26 02/17/2020 22:00:00 72364.0 1863.0 12455.0" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "Day_wise_china_data = corona_df[corona_df['Country']=='China'].groupby('Date').sum().reset_index()\n", "Day_wise_china_data" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# World\n", "plt.figure(figsize=(20,10))\n", "plt.subplot(1,2,1)\n", "plt.plot(Day_wise_world_data.Date,Day_wise_world_data.Confirmed,label='Confirmed',color='r',marker='o')\n", "plt.plot(Day_wise_world_data.Date,Day_wise_world_data.Recovered,label='Recovered',color='g',marker='o')\n", "plt.plot(Day_wise_world_data.Date,Day_wise_world_data.Deaths,label='Deaths',color='b',marker='o')\n", "plt.title('World',size=14)\n", "plt.legend()\n", "plt.xticks(rotation=90)\n", "plt.xlabel('Date',size=14)\n", "plt.ylabel('No. of cases',size=14)\n", "\n", "# China\n", "plt.subplot(1,2,2)\n", "plt.plot(Day_wise_china_data.Date,Day_wise_china_data.Confirmed,label='Confirmed',color='r',marker='o')\n", "plt.plot(Day_wise_china_data.Date,Day_wise_china_data.Recovered,label='Recovered',color='g',marker='o')\n", "plt.plot(Day_wise_china_data.Date,Day_wise_china_data.Deaths,label='Deaths',color='b',marker='o')\n", "plt.title('China',size=14)\n", "plt.legend()\n", "plt.xticks(rotation=90)\n", "plt.xlabel('Date',size=14)\n", "plt.ylabel('No. of cases',size=14)\n", "plt.suptitle('No. of cases of Corona virus day by day',size=15)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The pattern of spreading of corona virus is same for both whole world and China, it's because mostly Chinese people are affected by corona virus and whole world data is totally depend on what is happening in China.\n", "\n", "So we can find hidden pattern in Corona virus dataset using only Chinese Data." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "No. of confirmed cases are increasing exponentially but recovery is not fast as it should be." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### **Analyzing China Data State wise**" ] }, { "cell_type": "code", "execution_count": 22, "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", "
DateProvince/StateCountryLast UpdateConfirmedDeathsRecovered
001/22/2020 12:00:00AnhuiChina01/22/2020 12:00:001.00.00.0
101/22/2020 12:00:00BeijingChina01/22/2020 12:00:0014.00.00.0
201/22/2020 12:00:00ChongqingChina01/22/2020 12:00:006.00.00.0
301/22/2020 12:00:00FujianChina01/22/2020 12:00:001.00.00.0
401/22/2020 12:00:00GansuChina01/22/2020 12:00:000.00.00.0
\n", "
" ], "text/plain": [ " Date Province/State Country Last Update Confirmed \\\n", "0 01/22/2020 12:00:00 Anhui China 01/22/2020 12:00:00 1.0 \n", "1 01/22/2020 12:00:00 Beijing China 01/22/2020 12:00:00 14.0 \n", "2 01/22/2020 12:00:00 Chongqing China 01/22/2020 12:00:00 6.0 \n", "3 01/22/2020 12:00:00 Fujian China 01/22/2020 12:00:00 1.0 \n", "4 01/22/2020 12:00:00 Gansu China 01/22/2020 12:00:00 0.0 \n", "\n", " Deaths Recovered \n", "0 0.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 0.0 0.0 " ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "China_data = corona_df[corona_df['Country']=='China']\n", "China_data.head()" ] }, { "cell_type": "code", "execution_count": 23, "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", "
Province/StateDateCountryLast UpdateConfirmedDeathsRecovered
0Anhui02/17/2020 22:00:00China2020-09-02 01:23:00973.06.0280.0
1Beijing02/17/2020 22:00:00China2020-09-02 03:43:00381.04.0114.0
2Chongqing02/17/2020 22:00:00China2020-09-02 00:43:00553.05.0225.0
3Fujian02/17/2020 22:00:00China2020-09-02 03:43:00290.01.090.0
4Gansu02/17/2020 22:00:00China2020-08-02 15:13:0091.02.058.0
\n", "
" ], "text/plain": [ " Province/State Date Country Last Update Confirmed \\\n", "0 Anhui 02/17/2020 22:00:00 China 2020-09-02 01:23:00 973.0 \n", "1 Beijing 02/17/2020 22:00:00 China 2020-09-02 03:43:00 381.0 \n", "2 Chongqing 02/17/2020 22:00:00 China 2020-09-02 00:43:00 553.0 \n", "3 Fujian 02/17/2020 22:00:00 China 2020-09-02 03:43:00 290.0 \n", "4 Gansu 02/17/2020 22:00:00 China 2020-08-02 15:13:00 91.0 \n", "\n", " Deaths Recovered \n", "0 6.0 280.0 \n", "1 4.0 114.0 \n", "2 5.0 225.0 \n", "3 1.0 90.0 \n", "4 2.0 58.0 " ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "China_data_state_wise = China_data.groupby('Province/State').max().reset_index()\n", "China_data_state_wise.head()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.figure(figsize=(15,12))\n", "ax = sns.barplot(x='Confirmed',y='Province/State',data=China_data_state_wise,errwidth=0)\n", "plt.title('No. of Cases in China till now (State wise)',size=15)\n", "plt.xlabel('No. of Confirmed cases',size=14)\n", "plt.ylabel('Province/State',size=14)\n", "\n", "y=0\n", "for p in ax.patches :\n", " ax.annotate(str(int(p.get_width())),(p.get_width()+100,y+0.1),color='b')\n", " y+=1" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Hubei province is most affected by Corona virus in China, as corona virus started from Wuhan city which is in Hubei province." ] }, { "cell_type": "code", "execution_count": 25, "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", "
CountryConfirmedDeathsRecovered
0Australia19.00.010.0
1Belgium1.00.01.0
2Brazil0.00.00.0
3Cambodia1.00.01.0
4Canada11.00.01.0
\n", "
" ], "text/plain": [ " Country Confirmed Deaths Recovered\n", "0 Australia 19.0 0.0 10.0\n", "1 Belgium 1.0 0.0 1.0\n", "2 Brazil 0.0 0.0 0.0\n", "3 Cambodia 1.0 0.0 1.0\n", "4 Canada 11.0 0.0 1.0" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "Country_wise_except_china = countrywise_df[countrywise_df['Country']!='China']\n", "Country_wise_except_china.head()" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.figure(figsize=(15,12))\n", "sns.set_color_codes('pastel')\n", "sns.barplot(x='Confirmed',y='Country',data=Country_wise_except_china,errwidth=0,color='r',label='Confirmed')\n", "sns.barplot(x='Recovered',y='Country',data=Country_wise_except_china,errwidth=0,color='g',label='Recovered')\n", "sns.barplot(x='Deaths',y='Country',data=Country_wise_except_china,errwidth=0,color='b',label='Deaths')\n", "plt.title('No. of ceases till now country wise except China',size=14)\n", "plt.xlabel('No. of cases',size=13)\n", "plt.ylabel('Country',size=13)\n", "plt.legend()\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### **Geographical Visualization**" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For Geographical Visualization I am using Folium library" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Collecting folium==0.10\n", "\u001b[?25l Downloading https://files.pythonhosted.org/packages/72/ff/004bfe344150a064e558cb2aedeaa02ecbf75e60e148a55a9198f0c41765/folium-0.10.0-py2.py3-none-any.whl (91kB)\n", "\u001b[K |████████████████████████████████| 92kB 5.7MB/s eta 0:00:011\n", "\u001b[?25hRequirement already satisfied: branca>=0.3.0 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from folium==0.10) (0.3.1)\n", "Requirement already satisfied: numpy in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from folium==0.10) (1.16.2)\n", "Requirement already satisfied: jinja2>=2.9 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from folium==0.10) (2.10.3)\n", "Requirement already satisfied: requests in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from folium==0.10) (2.22.0)\n", "Requirement already satisfied: six in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from branca>=0.3.0->folium==0.10) (1.13.0)\n", "Requirement already satisfied: MarkupSafe>=0.23 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from jinja2>=2.9->folium==0.10) (1.1.1)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from requests->folium==0.10) (1.25.7)\n", "Requirement already satisfied: chardet<3.1.0,>=3.0.2 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from requests->folium==0.10) (3.0.4)\n", "Requirement already satisfied: idna<2.9,>=2.5 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from requests->folium==0.10) (2.8)\n", "Requirement already satisfied: certifi>=2017.4.17 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from requests->folium==0.10) (2019.9.11)\n", "Installing collected packages: folium\n", " Found existing installation: folium 0.5.0\n", " Uninstalling folium-0.5.0:\n", " Successfully uninstalled folium-0.5.0\n", "Successfully installed folium-0.10.0\n" ] } ], "source": [ "!pip install folium==0.10" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [], "source": [ "import folium as flm" ] }, { "cell_type": "code", "execution_count": 29, "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", "
CodeCountrylatitudelongitude
0ADAndorra42.5462451.601554
1AEUnited Arab Emirates23.42407653.847818
2AFAfghanistan33.93911067.709953
3AGAntigua and Barbuda17.060816-61.796428
4AIAnguilla18.220554-63.068615
\n", "
" ], "text/plain": [ " Code Country latitude longitude\n", "0 AD Andorra 42.546245 1.601554\n", "1 AE United Arab Emirates 23.424076 53.847818\n", "2 AF Afghanistan 33.939110 67.709953\n", "3 AG Antigua and Barbuda 17.060816 -61.796428\n", "4 AI Anguilla 18.220554 -63.068615" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# loading world coordinates file\n", "\n", "world_coordinates = pd.read_csv('world_coordinates.csv')\n", "world_coordinates.head() " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "dropping code from world_coordinates Dataframe" ] }, { "cell_type": "code", "execution_count": 30, "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", "
Countrylatitudelongitude
0Andorra42.5462451.601554
1United Arab Emirates23.42407653.847818
2Afghanistan33.93911067.709953
3Antigua and Barbuda17.060816-61.796428
4Anguilla18.220554-63.068615
\n", "
" ], "text/plain": [ " Country latitude longitude\n", "0 Andorra 42.546245 1.601554\n", "1 United Arab Emirates 23.424076 53.847818\n", "2 Afghanistan 33.939110 67.709953\n", "3 Antigua and Barbuda 17.060816 -61.796428\n", "4 Anguilla 18.220554 -63.068615" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "world_coordinates.drop('Code',axis=1,inplace=True)\n", "world_coordinates.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Merging world_coordinates with country wise df" ] }, { "cell_type": "code", "execution_count": 31, "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", "
CountryConfirmedDeathsRecoveredlatitudelongitude
0Australia19.00.010.0-25.274398133.775136
1Belgium1.00.01.050.5038874.469936
2Brazil0.00.00.0-14.235004-51.925280
3Cambodia1.00.01.012.565679104.990963
4Canada11.00.01.056.130366-106.346771
5China72366.01864.012455.035.861660104.195397
6Egypt1.00.00.026.82055330.802498
7Finland1.00.01.061.92411025.748151
8France12.01.04.046.2276382.213749
9Germany23.00.01.051.16569110.451526
10Hong Kong60.01.02.022.396428114.109497
11India3.00.03.020.59368478.962880
12Italy3.00.00.041.87194012.567380
13Ivory Coast0.00.00.0NaNNaN
14Japan66.01.012.036.204824138.252924
15Macau10.00.05.022.198745113.543873
16Malaysia22.00.07.04.210484101.975766
17Mexico0.00.00.023.634501-102.552784
18Nepal1.00.01.028.39485784.124008
19Philippines3.01.01.012.879721121.774017
20Russia2.00.02.061.524010105.318756
21Singapore77.00.024.01.352083103.819836
22South Korea30.00.010.035.907757127.766922
23Spain2.00.02.040.463667-3.749220
24Sri Lanka1.00.01.07.87305480.771797
25Sweden1.00.00.060.12816118.643501
26Taiwan22.01.02.023.697810120.960515
27Thailand35.00.015.015.870032100.992541
28UK9.00.08.055.378051-3.435973
29US23.00.03.037.090240-95.712891
30United Arab Emirates9.00.04.023.42407653.847818
31Vietnam16.00.07.014.058324108.277199
\n", "
" ], "text/plain": [ " Country Confirmed Deaths Recovered latitude longitude\n", "0 Australia 19.0 0.0 10.0 -25.274398 133.775136\n", "1 Belgium 1.0 0.0 1.0 50.503887 4.469936\n", "2 Brazil 0.0 0.0 0.0 -14.235004 -51.925280\n", "3 Cambodia 1.0 0.0 1.0 12.565679 104.990963\n", "4 Canada 11.0 0.0 1.0 56.130366 -106.346771\n", "5 China 72366.0 1864.0 12455.0 35.861660 104.195397\n", "6 Egypt 1.0 0.0 0.0 26.820553 30.802498\n", "7 Finland 1.0 0.0 1.0 61.924110 25.748151\n", "8 France 12.0 1.0 4.0 46.227638 2.213749\n", "9 Germany 23.0 0.0 1.0 51.165691 10.451526\n", "10 Hong Kong 60.0 1.0 2.0 22.396428 114.109497\n", "11 India 3.0 0.0 3.0 20.593684 78.962880\n", "12 Italy 3.0 0.0 0.0 41.871940 12.567380\n", "13 Ivory Coast 0.0 0.0 0.0 NaN NaN\n", "14 Japan 66.0 1.0 12.0 36.204824 138.252924\n", "15 Macau 10.0 0.0 5.0 22.198745 113.543873\n", "16 Malaysia 22.0 0.0 7.0 4.210484 101.975766\n", "17 Mexico 0.0 0.0 0.0 23.634501 -102.552784\n", "18 Nepal 1.0 0.0 1.0 28.394857 84.124008\n", "19 Philippines 3.0 1.0 1.0 12.879721 121.774017\n", "20 Russia 2.0 0.0 2.0 61.524010 105.318756\n", "21 Singapore 77.0 0.0 24.0 1.352083 103.819836\n", "22 South Korea 30.0 0.0 10.0 35.907757 127.766922\n", "23 Spain 2.0 0.0 2.0 40.463667 -3.749220\n", "24 Sri Lanka 1.0 0.0 1.0 7.873054 80.771797\n", "25 Sweden 1.0 0.0 0.0 60.128161 18.643501\n", "26 Taiwan 22.0 1.0 2.0 23.697810 120.960515\n", "27 Thailand 35.0 0.0 15.0 15.870032 100.992541\n", "28 UK 9.0 0.0 8.0 55.378051 -3.435973\n", "29 US 23.0 0.0 3.0 37.090240 -95.712891\n", "30 United Arab Emirates 9.0 0.0 4.0 23.424076 53.847818\n", "31 Vietnam 16.0 0.0 7.0 14.058324 108.277199" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corona_df_with_geo_location = countrywise_df.merge(world_coordinates,how='left',on='Country')\n", "corona_df_with_geo_location" ] }, { "cell_type": "code", "execution_count": 32, "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", "
CountryConfirmedDeathsRecoveredlatitudelongitude
0Australia19.00.010.0-25.274398133.775136
1Belgium1.00.01.050.5038874.469936
2Brazil0.00.00.0-14.235004-51.925280
3Cambodia1.00.01.012.565679104.990963
4Canada11.00.01.056.130366-106.346771
5China72366.01864.012455.035.861660104.195397
6Egypt1.00.00.026.82055330.802498
7Finland1.00.01.061.92411025.748151
8France12.01.04.046.2276382.213749
9Germany23.00.01.051.16569110.451526
10Hong Kong60.01.02.022.396428114.109497
11India3.00.03.020.59368478.962880
12Italy3.00.00.041.87194012.567380
14Japan66.01.012.036.204824138.252924
15Macau10.00.05.022.198745113.543873
16Malaysia22.00.07.04.210484101.975766
17Mexico0.00.00.023.634501-102.552784
18Nepal1.00.01.028.39485784.124008
19Philippines3.01.01.012.879721121.774017
20Russia2.00.02.061.524010105.318756
21Singapore77.00.024.01.352083103.819836
22South Korea30.00.010.035.907757127.766922
23Spain2.00.02.040.463667-3.749220
24Sri Lanka1.00.01.07.87305480.771797
25Sweden1.00.00.060.12816118.643501
26Taiwan22.01.02.023.697810120.960515
27Thailand35.00.015.015.870032100.992541
28UK9.00.08.055.378051-3.435973
29US23.00.03.037.090240-95.712891
30United Arab Emirates9.00.04.023.42407653.847818
31Vietnam16.00.07.014.058324108.277199
\n", "
" ], "text/plain": [ " Country Confirmed Deaths Recovered latitude longitude\n", "0 Australia 19.0 0.0 10.0 -25.274398 133.775136\n", "1 Belgium 1.0 0.0 1.0 50.503887 4.469936\n", "2 Brazil 0.0 0.0 0.0 -14.235004 -51.925280\n", "3 Cambodia 1.0 0.0 1.0 12.565679 104.990963\n", "4 Canada 11.0 0.0 1.0 56.130366 -106.346771\n", "5 China 72366.0 1864.0 12455.0 35.861660 104.195397\n", "6 Egypt 1.0 0.0 0.0 26.820553 30.802498\n", "7 Finland 1.0 0.0 1.0 61.924110 25.748151\n", "8 France 12.0 1.0 4.0 46.227638 2.213749\n", "9 Germany 23.0 0.0 1.0 51.165691 10.451526\n", "10 Hong Kong 60.0 1.0 2.0 22.396428 114.109497\n", "11 India 3.0 0.0 3.0 20.593684 78.962880\n", "12 Italy 3.0 0.0 0.0 41.871940 12.567380\n", "14 Japan 66.0 1.0 12.0 36.204824 138.252924\n", "15 Macau 10.0 0.0 5.0 22.198745 113.543873\n", "16 Malaysia 22.0 0.0 7.0 4.210484 101.975766\n", "17 Mexico 0.0 0.0 0.0 23.634501 -102.552784\n", "18 Nepal 1.0 0.0 1.0 28.394857 84.124008\n", "19 Philippines 3.0 1.0 1.0 12.879721 121.774017\n", "20 Russia 2.0 0.0 2.0 61.524010 105.318756\n", "21 Singapore 77.0 0.0 24.0 1.352083 103.819836\n", "22 South Korea 30.0 0.0 10.0 35.907757 127.766922\n", "23 Spain 2.0 0.0 2.0 40.463667 -3.749220\n", "24 Sri Lanka 1.0 0.0 1.0 7.873054 80.771797\n", "25 Sweden 1.0 0.0 0.0 60.128161 18.643501\n", "26 Taiwan 22.0 1.0 2.0 23.697810 120.960515\n", "27 Thailand 35.0 0.0 15.0 15.870032 100.992541\n", "28 UK 9.0 0.0 8.0 55.378051 -3.435973\n", "29 US 23.0 0.0 3.0 37.090240 -95.712891\n", "30 United Arab Emirates 9.0 0.0 4.0 23.424076 53.847818\n", "31 Vietnam 16.0 0.0 7.0 14.058324 108.277199" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# dropping rows with NaN values\n", "corona_df_with_geo_location.dropna(axis=0,inplace=True)\n", "corona_df_with_geo_location" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "world_map = flm.Map(location=[10,-10],zoom_start=2)\n", "for country,confirmed,lat,lng in zip(corona_df_with_geo_location.Country,\n", " corona_df_with_geo_location.Confirmed,\n", " corona_df_with_geo_location.latitude,\n", " corona_df_with_geo_location.longitude):\n", " \n", " flm.CircleMarker(\n", " location=[lat,lng],\n", " radius=5,\n", " tooltip=str(confirmed),\n", " fill=True,\n", " fill_color='red',\n", " fill_opacity=0.8).add_to(world_map)\n", "world_map" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In the above world map circle marker presents that these countries have been affected by corona virus." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Choropleth map**" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "myscale = [0,15000,30000,45000,60000,73090] # manually defining threshold scale\n", "\n", "choropleth_map = flm.Map(location=[10,-10],zoom_start=2)\n", "\n", "\n", "flm.Choropleth(\n", " geo_data = world_geoJson,\n", " data = corona_df_with_geo_location,\n", " columns = ['Country','Confirmed'],\n", " key_on='feature.properties.name',\n", " fill_color= 'YlOrRd',\n", " fill_opacity=0.7, \n", " line_opacity=0.2,\n", " legend_name='No. of confirmed cases',\n", " threshold_scale = myscale,\n", " nan_fill_color='black',\n", " nan_fill_opacity=0.4,\n", " highlight=True\n", " ).add_to(choropleth_map)\n", "choropleth_map" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "- Black colored areas represents that there is no data for these countries in dataset.\n", "- Light yellow colored areas have less no of cases.\n", "- China is red colored because there are very large no. of cases.\n", "\n", "for more you can refer to threshold scale on map." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Now visualizing the choropleth map for china only(Province wise)**" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [], "source": [ "# loading china geoJson file\n", "\n", "import json\n", "\n", "with open(china_geoJson) as file:\n", " china = json.load(file)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Checking whether province/state name in china geoJson file are in chinese language or in english language." ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['新疆维吾尔自治区',\n", " '西藏自治区',\n", " '内蒙古自治区',\n", " '青海省',\n", " '四川省',\n", " '黑龙江省',\n", " '甘肃省',\n", " '云南省',\n", " '广西壮族自治区',\n", " '湖南省',\n", " '陕西省',\n", " '广东省',\n", " '吉林省',\n", " '河北省',\n", " '湖北省',\n", " '贵州省',\n", " '山东省',\n", " '江西省',\n", " '河南省',\n", " '辽宁省',\n", " '山西省',\n", " '安徽省',\n", " '福建省',\n", " '浙江省',\n", " '江苏省',\n", " '重庆市',\n", " '宁夏回族自治区',\n", " '海南省',\n", " '台湾省',\n", " '北京市',\n", " '天津市',\n", " '上海市',\n", " '香港特别行政区',\n", " '澳门特别行政区']" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "name_lst = []\n", "for i in range(len(china['features'])):\n", " name_lst.append(china['features'][i]['properties']['name'])\n", "name_lst" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Province/State name are in chinese language, need to translate in english because data present in dataset are in english language." ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Collecting googletrans\n", " Downloading https://files.pythonhosted.org/packages/fd/f0/a22d41d3846d1f46a4f20086141e0428ccc9c6d644aacbfd30990cf46886/googletrans-2.4.0.tar.gz\n", "Requirement already satisfied: requests in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from googletrans) (2.22.0)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from requests->googletrans) (1.25.7)\n", "Requirement already satisfied: chardet<3.1.0,>=3.0.2 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from requests->googletrans) (3.0.4)\n", "Requirement already satisfied: idna<2.9,>=2.5 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from requests->googletrans) (2.8)\n", "Requirement already satisfied: certifi>=2017.4.17 in /home/jupyterlab/conda/envs/python/lib/python3.6/site-packages (from requests->googletrans) (2019.9.11)\n", "Building wheels for collected packages: googletrans\n", " Building wheel for googletrans (setup.py) ... \u001b[?25ldone\n", "\u001b[?25h Stored in directory: /home/jupyterlab/.cache/pip/wheels/50/d6/e7/a8efd5f2427d5eb258070048718fa56ee5ac57fd6f53505f95\n", "Successfully built googletrans\n", "Installing collected packages: googletrans\n", "Successfully installed googletrans-2.4.0\n" ] } ], "source": [ "# installing google translator library \n", "\n", "!pip install googletrans" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Xinjiang Uygur Autonomous Region',\n", " 'Tibet Autonomous Region',\n", " 'Inner Mongolia Autonomous Region',\n", " 'Qinghai Province',\n", " 'Sichuan Province',\n", " 'Heilongjiang Province',\n", " 'Gansu province',\n", " 'Yunnan Province',\n", " 'Guangxi Zhuang Autonomous Region',\n", " 'Hunan Province',\n", " 'Shaanxi Province',\n", " 'Guangdong Province',\n", " 'Jilin Province',\n", " 'Hebei Province',\n", " 'Hubei Province',\n", " 'Guizhou Province',\n", " 'Shandong Province',\n", " 'Jiangxi',\n", " 'Henan Province',\n", " 'Liaoning Province',\n", " 'Shanxi Province',\n", " 'Anhui Province',\n", " 'Fujian Province',\n", " 'Zhejiang Province',\n", " 'Jiangsu Province',\n", " 'Chongqing',\n", " 'Ningxia Hui Autonomous Region',\n", " 'Hainan',\n", " 'Taiwan Province',\n", " 'Beijing',\n", " 'Tianjin',\n", " 'Shanghai',\n", " 'Hong Kong SAR',\n", " 'Macao Special Administrative Region']" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from googletrans import Translator # importing translator \n", "translator = Translator() # creating an object of translator\n", "\n", "name_lst_en = []\n", "for text in name_lst:\n", " name_lst_en.append(translator.translate(text).text)\n", "name_lst_en" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Comparing above list of Province/State with Province/State in corona dataset.**" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 Anhui\n", "1 Beijing\n", "2 Chongqing\n", "3 Fujian\n", "4 Gansu\n", "5 Guangdong\n", "6 Guangxi\n", "7 Guizhou\n", "8 Hainan\n", "9 Hebei\n", "10 Heilongjiang\n", "11 Henan\n", "12 Hong Kong\n", "13 Hubei\n", "14 Hunan\n", "15 Inner Mongolia\n", "16 Jiangsu\n", "17 Jiangxi\n", "18 Jilin\n", "19 Liaoning\n", "20 Macau\n", "21 Ningxia\n", "22 Qinghai\n", "23 Shaanxi\n", "24 Shandong\n", "25 Shanghai\n", "26 Shanxi\n", "27 Sichuan\n", "28 Taiwan\n", "29 Tianjin\n", "30 Tibet\n", "31 Xinjiang\n", "32 Yunnan\n", "33 Zhejiang\n", "Name: Province/State, dtype: object" ] }, "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ "China_data_state_wise['Province/State']" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Need to modify name_lst_en according to dataset.**" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Xinjiang',\n", " 'Tibet',\n", " 'Inner',\n", " 'Qinghai',\n", " 'Sichuan',\n", " 'Heilongjiang',\n", " 'Gansu',\n", " 'Yunnan',\n", " 'Guangxi',\n", " 'Hunan',\n", " 'Shaanxi',\n", " 'Guangdong',\n", " 'Jilin',\n", " 'Hebei',\n", " 'Hubei',\n", " 'Guizhou',\n", " 'Shandong',\n", " 'Jiangxi',\n", " 'Henan',\n", " 'Liaoning',\n", " 'Shanxi',\n", " 'Anhui',\n", " 'Fujian',\n", " 'Zhejiang',\n", " 'Jiangsu',\n", " 'Chongqing',\n", " 'Ningxia',\n", " 'Hainan',\n", " 'Taiwan',\n", " 'Beijing',\n", " 'Tianjin',\n", " 'Shanghai',\n", " 'Hong',\n", " 'Macao']" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Keeping only first word in every item of name_lst_en\n", "\n", "for i in range(len(name_lst_en)):\n", " name_lst_en[i] = name_lst_en[i].split(\" \")[0]\n", "name_lst_en" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**now translated names are matching with the names present in dataset.**" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [], "source": [ "# writing the tranlated name of province/state in china geoJson file\n", "\n", "for i in range(len(name_lst_en)):\n", " china['features'][i]['properties']['name']=name_lst_en[i]" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "China_lat = 35.8617\n", "China_lng = 104.1954\n", "\n", "China_map = flm.Map(location=[China_lat,China_lng],zoom_start=4)\n", "\n", "flm.Choropleth(\n", " geo_data=china,\n", " data=China_data_state_wise,\n", " columns=['Province/State','Confirmed'],\n", " key_on='feature.properties.name',\n", " fill_color='YlOrRd',\n", " fill_opacity=0.7,\n", " nan_fill_color='black',\n", " nan_fill_opacity=0.7,\n", " highlight=True,\n", " legend_name='No. of confirmed cases',\n", " ).add_to(China_map)\n", "China_map" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "- Black colored areas represents that there is no data for these states in dataset.\n", "- Light yellow colored areas have less no of cases.\n", "\n", "for more you can refer to threshold scale on map." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Only one province is of red color, indicates mostly infected people are here. It's Hubie." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Thank you for reading" ] } ], "metadata": { "kernelspec": { "display_name": "Python", "language": "python", "name": "conda-env-python-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.7" } }, "nbformat": 4, "nbformat_minor": 4 }