# Data analysis and Manipulation

import plotly.graph_objs as go
import plotly.io as pio
import plotly.express as px
import pandas as pd

# Data Visualization
import matplotlib.pyplot as plt

# Importing Plotly
import plotly.offline as py
py.init_notebook_mode(connected=True)

# Initializing Plotly
pio.renderers.default = 'colab'

# Importing Dataset1
dataset1 = pd.read_csv("covid.csv")
dataset1.head() # returns first 5 rows

{"summary":"{\n \"name\": \"dataset1\",\n \"rows\": 209,\n

\"fields\": [\n {\n \"column\": \"Country/Region\",\n
\"properties\": {\n \"dtype\": \"string\",\n
\"num_unique_values\": 209,\n \"samples\": [\n
\"Oman\",\n \"Martinique\",\n \"French Guiana\"\n
],\n \"semantic_type\": \"\",\n \"description\": \"\"\n
}\n },\n {\n \"column\": \"Continent\",\n
\"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 6,\n \"samples\": [\n \"North
America\",\n \"South America\",\n
\"Australia/Oceania\"\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"Population\",\n \"properties\": {\n \"dtype\":
\"number\",\n \"std\": 104766099.48117349,\n \"min\":
801.0,\n \"max\": 1381344997.0,\n \"num_unique_values\":
208,\n \"samples\": [\n 23821199.0,\n
60452568.0,\n 5794279.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"TotalCases\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
432586,\n \"min\": 10,\n \"max\": 5032179,\n
\"num_unique_values\": 206,\n \"samples\": [\n
249204,\n 354530,\n 17\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"NewCases\",\n \"properties\":
{\n \"dtype\": \"number\",\n \"std\":
3129.611424229319,\n \"min\": 20.0,\n \"max\": 6590.0,\n
\"num_unique_values\": 4,\n \"samples\": [\n 1282.0,\n
30.0,\n 6590.0\n ],\n \"semantic_type\": \"\",\
n \"description\": \"\"\n }\n },\n {\n
\"column\": \"TotalDeaths\",\n \"properties\": {\n
\"dtype\": \"number\",\n \"std\": 15487.184877168185,\n
\"min\": 1.0,\n \"max\": 162804.0,\n
\"num_unique_values\": 150,\n \"samples\": [\n 617.0,\
n 9252.0,\n 5.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"NewDeaths\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
451.1995124110841,\n \"min\": 1.0,\n \"max\": 819.0,\n
\"num_unique_values\": 3,\n \"samples\": [\n 819.0,\n
80.0,\n 1.0\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"TotalRecovered\",\n \"properties\": {\n \"dtype\":
\"number\",\n \"std\": 256698.40689838002,\n \"min\":
7.0,\n \"max\": 2576668.0,\n \"num_unique_values\":
201,\n \"samples\": [\n 652.0,\n 99852.0,\n
40539.0\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"NewRecovered\",\n \"properties\": {\n \"dtype\":
\"number\",\n \"std\": 2154.779803135346,\n \"min\":
42.0,\n \"max\": 4140.0,\n \"num_unique_values\": 3,\n
\"samples\": [\n 4140.0,\n 936.0,\n 42.0\n
],\n \"semantic_type\": \"\",\n \"description\": \"\"\n
}\n },\n {\n \"column\": \"ActiveCases\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
174632.7369279219,\n \"min\": 0.0,\n \"max\":
2292707.0,\n \"num_unique_values\": 180,\n \"samples\":
[\n 50473.0,\n 37559.0,\n 17.0\n ],\
n \"semantic_type\": \"\",\n \"description\": \"\"\n
}\n },\n {\n \"column\": \"Serious,Critical\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
2047.5186133519667,\n \"min\": 1.0,\n \"max\": 18296.0,\
n \"num_unique_values\": 74,\n \"samples\": [\n
539.0,\n 11.0,\n 384.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Tot Cases/1M pop\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
5191.986456701242,\n \"min\": 3.0,\n \"max\": 39922.0,\n
\"num_unique_values\": 202,\n \"samples\": [\n
1317.0,\n 4122.0,\n 15769.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Deaths/1M pop\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
174.9568620893644,\n \"min\": 0.08,\n \"max\": 1238.0,\n
\"num_unique_values\": 107,\n \"samples\": [\n 38.0,\n
214.0,\n 162.0\n ],\n \"semantic_type\": \"\",\
n \"description\": \"\"\n }\n },\n {\n
\"column\": \"TotalTests\",\n \"properties\": {\n
\"dtype\": \"number\",\n \"std\": 5553366.67043168,\n
\"min\": 61.0,\n \"max\": 63139605.0,\n
\"num_unique_values\": 190,\n \"samples\": [\n
1183.0,\n 4238.0,\n 29233.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Tests/1M pop\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
152730.59123995784,\n \"min\": 4.0,\n \"max\":
995282.0,\n \"num_unique_values\": 190,\n \"samples\":
[\n 22050.0,\n 3209.0,\n 11485.0\
n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\": \"WHO
Region\",\n \"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 6,\n \"samples\": [\n
\"Americas\",\n \"South-EastAsia\",\n
\"WesternPacific\"\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"iso_alpha\",\n \"properties\": {\n \"dtype\":
\"string\",\n \"num_unique_values\": 193,\n \"samples\":
[\n \"HND\",\n \"TGO\",\n \"MKD\"\
n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n }\n ]\
n}","type":"dataframe","variable_name":"dataset1"}

# Returns tuple of shape (Rows, columns)

print(dataset1.shape)

# Returns size of dataframe

print(dataset1.size)

(209, 17)
3553

# Information about Dataset1

# return concise summary of dataframe
dataset1.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 209 entries, 0 to 208
Data columns (total 17 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Country/Region 209 non-null object
1 Continent 208 non-null object
2 Population 208 non-null float64
3 TotalCases 209 non-null int64
4 NewCases 4 non-null float64
5 TotalDeaths 188 non-null float64
6 NewDeaths 3 non-null float64
7 TotalRecovered 205 non-null float64
8 NewRecovered 3 non-null float64
 9 ActiveCases 205 non-null float64
10 Serious,Critical 122 non-null float64
11 Tot Cases/1M pop 208 non-null float64
12 Deaths/1M pop 187 non-null float64
13 TotalTests 191 non-null float64
14 Tests/1M pop 191 non-null float64
15 WHO Region 184 non-null object
16 iso_alpha 209 non-null object
dtypes: float64(12), int64(1), object(4)
memory usage: 27.9+ KB

# Importing Dataset2
dataset2 = pd.read_csv("covid_grouped.csv")
dataset2.head() # return first 5 rows of dataset2

{"summary":"{\n \"name\": \"dataset2\",\n \"rows\": 35156,\n

\"fields\": [\n {\n \"column\": \"Date\",\n
\"properties\": {\n \"dtype\": \"object\",\n
\"num_unique_values\": 188,\n \"samples\": [\n \"2020-
07-23\",\n \"2020-07-02\",\n \"2020-02-09\"\n
],\n \"semantic_type\": \"\",\n \"description\": \"\"\n
}\n },\n {\n \"column\": \"Country/Region\",\n
\"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 187,\n \"samples\": [\n
\"Zambia\",\n \"Iceland\",\n \"Eritrea\"\
n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"Confirmed\",\n \"properties\": {\n \"dtype\":
\"number\",\n \"std\": 149981,\n \"min\": 0,\n
\"max\": 4290259,\n \"num_unique_values\": 10732,\n
\"samples\": [\n 2913,\n 29767,\n 169425\n
],\n \"semantic_type\": \"\",\n \"description\": \"\"\n
}\n },\n {\n \"column\": \"Deaths\",\n \"properties\":
{\n \"dtype\": \"number\",\n \"std\": 7437,\n
\"min\": 0,\n \"max\": 148011,\n \"num_unique_values\":
3598,\n \"samples\": [\n 6679,\n 312,\n
34854\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"Recovered\",\n \"properties\": {\n \"dtype\":
\"number\",\n \"std\": 64546,\n \"min\": 0,\n
\"max\": 1846641,\n \"num_unique_values\": 7649,\n
\"samples\": [\n 5223,\n 67309,\n 1303\n
],\n \"semantic_type\": \"\",\n \"description\": \"\"\n
}\n },\n {\n \"column\": \"Active\",\n \"properties\":
{\n \"dtype\": \"number\",\n \"std\": 89971,\n
\"min\": -2,\n \"max\": 2816444,\n
\"num_unique_values\": 8440,\n \"samples\": [\n 441,\n
46057,\n 1706\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\": \"New
cases\",\n \"properties\": {\n \"dtype\": \"number\",\n
\"std\": 3005,\n \"min\": 0,\n \"max\": 77255,\n
\"num_unique_values\": 2800,\n \"samples\": [\n 1496,\
n 1684,\n 4288\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"New deaths\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
115,\n \"min\": -1918,\n \"max\": 3887,\n
\"num_unique_values\": 715,\n \"samples\": [\n 839,\n
587,\n 35\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\": \"New
recovered\",\n \"properties\": {\n \"dtype\": \"number\",\
n \"std\": 2068,\n \"min\": -16298,\n \"max\":
140050,\n \"num_unique_values\": 2276,\n \"samples\": [\
n 26784,\n 1629,\n 2390\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"WHO Region\",\n
\"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 6,\n \"samples\": [\n \"Eastern
Mediterranean\",\n \"Europe\",\n \"South-East
Asia\"\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"iso_alpha\",\n \"properties\": {\n \"dtype\":
\"category\",\n \"num_unique_values\": 179,\n
\"samples\": [\n \"IDN\",\n \"BEL\",\n
\"GRC\"\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n }\n ]\
n}","type":"dataframe","variable_name":"dataset2"}

# Returns tuple of shape (Rows, columns)

print(dataset2.shape)

# Returns size of dataframe

print(dataset2.size)

(35156, 11)
386716

# Information about Dataset2

dataset2.info() # return concise summary of dataframe

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 35156 entries, 0 to 35155
Data columns (total 11 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Date 35156 non-null object
1 Country/Region 35156 non-null object
2 Confirmed 35156 non-null int64
3 Deaths 35156 non-null int64
4 Recovered 35156 non-null int64
 5 Active 35156 non-null int64
6 New cases 35156 non-null int64
7 New deaths 35156 non-null int64
8 New recovered 35156 non-null int64
9 WHO Region 35156 non-null object
10 iso_alpha 35156 non-null object
dtypes: int64(7), object(4)
memory usage: 3.0+ MB

# Columns labels of a Dataset1

dataset1.columns

Index(['Country/Region', 'Continent', 'Population', 'TotalCases',

'NewCases',
'TotalDeaths', 'NewDeaths', 'TotalRecovered', 'NewRecovered',
'ActiveCases', 'Serious,Critical', 'Tot Cases/1M pop',
'Deaths/1M pop',
'TotalTests', 'Tests/1M pop', 'WHO Region', 'iso_alpha'],
dtype='object')

# Drop NewCases, NewDeaths, NewRecovered rows from dataset1

dataset1.drop(['NewCases', 'NewDeaths', 'NewRecovered'],

axis=1, inplace=True)

# Select random set of values from dataset1

dataset1.sample(5)

{"summary":"{\n \"name\": \"dataset1\",\n \"rows\": 5,\n

\"fields\": [\n {\n \"column\": \"Country/Region\",\n
\"properties\": {\n \"dtype\": \"string\",\n
\"num_unique_values\": 5,\n \"samples\": [\n
\"Monaco\",\n \"Cambodia\",\n \"UK\"\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Continent\",\n
\"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 2,\n \"samples\": [\n
\"Europe\",\n \"Asia\"\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Population\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
112103852.12999673,\n \"min\": 39270.0,\n \"max\":
273808365.0,\n \"num_unique_values\": 5,\n \"samples\":
[\n 39270.0,\n 16741375.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"TotalCases\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
364585,\n \"min\": 125,\n \"max\": 871894,\n
\"num_unique_values\": 5,\n \"samples\": [\n 125,\n
243\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"TotalDeaths\",\n \"properties\": {\n \"dtype\":
\"number\",\n \"std\": 20744.13393387795,\n \"min\":
4.0,\n \"max\": 46413.0,\n \"num_unique_values\": 4,\n
\"samples\": [\n 4.0,\n 14606.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"TotalRecovered\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
327457.78123637557,\n \"min\": 105.0,\n \"max\":
676357.0,\n \"num_unique_values\": 4,\n \"samples\": [\n
105.0,\n 210.0\n ],\n \"semantic_type\": \"\",\
n \"description\": \"\"\n }\n },\n {\n
\"column\": \"ActiveCases\",\n \"properties\": {\n
\"dtype\": \"number\",\n \"std\": 86034.73581980323,\n
\"min\": 16.0,\n \"max\": 180931.0,\n
\"num_unique_values\": 4,\n \"samples\": [\n 16.0,\n
33.0\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"Serious,Critical\",\n \"properties\": {\n \"dtype\":
\"number\",\n \"std\": 1137.8327352178496,\n \"min\":
1.0,\n \"max\": 2300.0,\n \"num_unique_values\": 4,\n
\"samples\": [\n 73.0,\n 1.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Tot Cases/1M pop\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
2578.188569519305,\n \"min\": 15.0,\n \"max\": 5974.0,\n
\"num_unique_values\": 5,\n \"samples\": [\n 3183.0,\n
15.0\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"Deaths/1M pop\",\n \"properties\": {\n \"dtype\":
\"number\",\n \"std\": 306.88583653643366,\n \"min\":
20.0,\n \"max\": 683.0,\n \"num_unique_values\": 4,\n
\"samples\": [\n 102.0,\n 100.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"TotalTests\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
13350218.542872969,\n \"min\": 38209.0,\n \"max\":
29716907.0,\n \"num_unique_values\": 5,\n \"samples\":
[\n 38209.0,\n 67807.0\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Tests/1M pop\",\n
\"properties\": {\n \"dtype\": \"number\",\n \"std\":
399185.0325654758,\n \"min\": 4050.0,\n \"max\":
972982.0,\n \"num_unique_values\": 5,\n \"samples\": [\n
972982.0,\n 4050.0\n ],\n \"semantic_type\":
\"\",\n \"description\": \"\"\n }\n },\n {\n
\"column\": \"WHO Region\",\n \"properties\": {\n
\"dtype\": \"string\",\n \"num_unique_values\": 3,\n
\"samples\": [\n \"South-EastAsia\",\n \"Europe\"\n
],\n \"semantic_type\": \"\",\n \"description\": \"\"\n
}\n },\n {\n \"column\": \"iso_alpha\",\n
\"properties\": {\n \"dtype\": \"string\",\n
\"num_unique_values\": 5,\n \"samples\": [\n \"MCO\",\
n \"KHM\"\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n }\n ]\n}","type":"dataframe"}

# Import create_table Figure Factory

from plotly.figure_factory import create_table

colorscale = [[0, '#4d004c'], [.5, '#f2e5ff'], [1, '#ffffff']]

table = create_table(dataset1.head(15), colorscale=colorscale)
py.iplot(table)

px.bar(dataset1.head(15), x = 'Country/Region',
y = 'TotalCases',color = 'TotalCases',
height = 500,hover_data = ['Country/Region', 'Continent'])

px.bar(dataset1.head(15), x = 'Country/Region', y = 'TotalCases',

color = 'TotalDeaths', height = 500,
hover_data = ['Country/Region', 'Continent'])

px.bar(dataset1.head(15), x = 'Country/Region', y = 'TotalCases',

color = 'TotalDeaths', height = 500,
hover_data = ['Country/Region', 'Continent'])

px.bar(dataset1.head(15), x = 'Country/Region', y = 'TotalCases',

color = 'TotalTests', height = 500, hover_data =
['Country/Region', 'Continent'])

px.bar(dataset1.head(15), x = 'TotalTests', y = 'Country/Region',

color = 'TotalTests',orientation ='h', height = 500,
hover_data = ['Country/Region', 'Continent'])

px.bar(dataset1.head(15), x = 'TotalTests', y = 'Continent',

color = 'TotalTests',orientation ='h', height = 500,
hover_data = ['Country/Region', 'Continent'])

px.scatter(dataset1, x='Continent',y='TotalCases',
hover_data=['Country/Region', 'Continent'],
color='TotalCases', size='TotalCases', size_max=80)

px.scatter(dataset1.head(54), x='Continent',y='TotalTests',
hover_data=['Country/Region', 'Continent'],
color='TotalTests', size='TotalTests', size_max=80)

px.scatter(dataset1.head(50), x='Continent',y='TotalTests',
hover_data=['Country/Region', 'Continent'],
color='TotalTests', size='TotalTests', size_max=80,
log_y=True)
px.scatter(dataset1.head(10), x='Country/Region', y= 'TotalDeaths',
hover_data=['Country/Region', 'Continent'],
color='Country/Region', size= 'TotalDeaths', size_max=80)

px.scatter(dataset1.head(30), x='Country/Region', y= 'Tests/1M pop',

hover_data=['Country/Region', 'Continent'],
color='Country/Region', size= 'Tests/1M pop', size_max=80)

px.scatter(dataset1.head(30), x='Country/Region', y= 'Tests/1M pop',

hover_data=['Country/Region', 'Continent'],
color='Tests/1M pop', size= 'Tests/1M pop', size_max=80)

px.scatter(dataset1.head(30), x='TotalCases', y= 'TotalDeaths',

hover_data=['Country/Region', 'Continent'],
color='TotalDeaths', size= 'TotalDeaths', size_max=80)

px.scatter(dataset1.head(30), x='TotalCases', y= 'TotalDeaths',

hover_data=['Country/Region', 'Continent'],
color='TotalDeaths', size= 'TotalDeaths', size_max=80,
log_x=True, log_y=True)

px.scatter(dataset1.head(30), x='TotalTests', y= 'TotalCases',

hover_data=['Country/Region', 'Continent'],
color='TotalTests', size= 'TotalTests', size_max=80,
log_x=True, log_y=True)

px.bar(df_US, x="Date", y="Confirmed", color="Confirmed", height=400)

px.bar(df_US,x="Date", y="Recovered", color="Recovered", height=400)

px.line(df_US,x="Date", y="Recovered", height=400)

px.line(df_US,x="Date", y="Deaths", height=400)

px.line(df_US,x="Date", y="Confirmed", height=400)

px.line(df_US,x="Date", y="New cases", height=400)

px.bar(df_US,x="Date", y="New cases", height=400)

px.scatter(df_US, x="Confirmed", y="Deaths", height=400)

px.choropleth(dataset2,
locations="iso_alpha",
color="Confirmed",
hover_name="Country/Region",
color_continuous_scale="Blues",
animation_frame="Date")

px.choropleth(dataset2,
locations='iso_alpha',
color="Deaths",
hover_name="Country/Region",
 color_continuous_scale="Viridis",
animation_frame="Date" )

px.choropleth(dataset2,
locations='iso_alpha',
color="Recovered",
hover_name="Country/Region",
color_continuous_scale="RdYlGn",
projection="natural earth",
animation_frame="Date" )

px.bar(dataset2, x="WHO Region", y="Confirmed", color="WHO Region",

animation_frame="Date", hover_name="Country/Region")

dataset3= pd.read_csv("coviddeath.csv")
dataset3.head()

{"summary":"{\n \"name\": \"dataset3\",\n \"rows\": 12260,\n

\"fields\": [\n {\n \"column\": \"Data as of\",\n
\"properties\": {\n \"dtype\": \"object\",\n
\"num_unique_values\": 1,\n \"samples\": [\n
\"08/30/2020\"\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"Start Week\",\n \"properties\": {\n \"dtype\":
\"object\",\n \"num_unique_values\": 1,\n \"samples\":
[\n \"02/01/2020\"\n ],\n \"semantic_type\":
\"\",\n \"description\": \"\"\n }\n },\n {\n
\"column\": \"End Week\",\n \"properties\": {\n \"dtype\":
\"object\",\n \"num_unique_values\": 1,\n \"samples\":
[\n \"08/29/2020\"\n ],\n \"semantic_type\":
\"\",\n \"description\": \"\"\n }\n },\n {\n
\"column\": \"State\",\n \"properties\": {\n \"dtype\":
\"category\",\n \"num_unique_values\": 54,\n
\"samples\": [\n \"LA\"\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Condition Group\",\n
\"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 12,\n \"samples\": [\n \"All
other conditions and causes (residual)\"\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Condition\",\n
\"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 23,\n \"samples\": [\n
\"Diabetes\"\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"ICD10_codes\",\n \"properties\": {\n \"dtype\":
\"category\",\n \"num_unique_values\": 23,\n
\"samples\": [\n \"E10-E14\"\n ],\n
\"semantic_type\": \"\",\n \"description\": \"\"\n }\
n },\n {\n \"column\": \"Age Group\",\n
\"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 10,\n \"samples\": [\n \"Not
stated\"\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"Number of COVID-19 Deaths\",\n \"properties\": {\n
\"dtype\": \"number\",\n \"std\": 3411.6853195964054,\n
\"min\": 0.0,\n \"max\": 169044.0,\n
\"num_unique_values\": 1022,\n \"samples\": [\n
5915.0\n ],\n \"semantic_type\": \"\",\n
\"description\": \"\"\n }\n },\n {\n \"column\":
\"Flag\",\n \"properties\": {\n \"dtype\": \"category\",\n
\"num_unique_values\": 1,\n \"samples\": [\n \"Counts
less than 10 suppressed.\"\n ],\n \"semantic_type\":
\"\",\n \"description\": \"\"\n }\n }\n ]\
n}","type":"dataframe","variable_name":"dataset3"}

dataset3.tail()

{"repr_error":"0","type":"dataframe"}