#Export bar chart
bar_image = bar_2.get_figure().savefig('bar_image.png')
from google.colab import files
files.download('bar_image.png')  #Download window pops out

#Export line chart
line_image = line_1.get_figure().savefig('line_image.png')
from google.colab import files
files.download('line_image.png')  #Download window pops out

#Export scatter plot chart
scat_image = scatter.get_figure().savefig('scatter_image.png')
from google.colab import files
files.download('scatter_image.png')  #Download window pops out

#Uplocad csv file from your local directory
from google.colab import files
uploaded = files.upload()

import pandas as pd
df = pd.read_csv('FILENAME.csv')  #The filename of the uplpaded csv file
#df.shape
df.head()

#Uplocad Excel file from your local directory
from google.colab import files
uploaded = files.upload()

import pandas as pd
df = pd.read_excel('FILENAME.xlsx')  #The filename of the uplpaded csv file
#df.shape
df.head()

import pandas as pd
#Descriptive Statistics of one varialbe
descriptive_stats_1 = df['var1'].describe()
#Descriptive Statistics of more than one varialbes
descriptive_stats_2 = df[['var1','deaths']].describe()
#Descriptive Statistics of all numbercal varialbes in a dataframe
descriptive_stats_all = df.describe()

subset_1 = df[['var1','var2','var3']]   #Subset by column name(s)
subset_2 = df[df["var1"] > 100]  #Select rows by value (example: value =100)

#Collapse
#Collapse data by one varialbe, one aggregation method
df_1 = df.groupby(['var1'], dropna=True).sum().reset_index()

#Collapse data by one varialbe, by more than one aggregation methods
df_2 = df.groupby(['var1']).agg({'var2':['sum'], 'var3':['mean']}).reset_index() #var2, var3 need to be numeric data

#Example: NYT Github COVID-19 data
#https://raw.githubusercontent.com/nytimes/covid-19-data/master/live/us-counties.csv
url = 'The URL of data'
df = pd.read_csv(url)
#df.shape
df.head()

#gspread setup
!pip install --upgrade gspread

#Authenticate access to your Google Drive
from google.colab import auth
auth.authenticate_user()

import gspread
from oauth2client.client import GoogleCredentials
gc = gspread.authorize(GoogleCredentials.get_application_default())


import pandas as pd
worksheet = gc.open('Google Sheets NAME').sheet1   
rows = worksheet.get_all_values()    # get_all_values gives a list of rows.
df = pd.DataFrame.from_records(rows)  # Convert to a DataFrame and render.
df.head()

#gspread setup
!pip install --upgrade gspread

#Authenticate access to your Google Drive
from google.colab import auth
auth.authenticate_user()

import gspread
from oauth2client.client import GoogleCredentials
gc = gspread.authorize(GoogleCredentials.get_application_default())


worksheet = gc.open_by_key('Google Sheets ID').worksheet('NAME OF A SHEET TAB')    #Call by Sheet ID & Name
rows = worksheet.get_all_values()    # get_all_values gives a list of rows.
df = pd.DataFrame.from_records(rows[1:], columns=rows[0])   # Convert to a DataFrame and render. 1st Row as Headers
df.head()

!pip install -U -q PyDrive 

from pydrive.auth import GoogleAuth 
from pydrive.drive import GoogleDrive 
from google.colab import auth 
from oauth2client.client import GoogleCredentials 


# Authenticate and create the PyDrive client. 
auth.authenticate_user() 
gauth = GoogleAuth() 
gauth.credentials = GoogleCredentials.get_application_default() 
drive = GoogleDrive(gauth)   #Copy and paste Google Authentication code

link = 'SHARING LINK'  #The sharing link of the data file stored on your Google Drive
id = link.split("/")[-2]
#print(id)
downloaded = drive.CreateFile({'id':id})  
downloaded.GetContentFile('covid_county.csv')   
df = pd.read_csv('covid_county.csv') 
df.head()

#Mount Google Drive
from google.colab import drive
drive.mount('/content/drive')  

path = '/content/drive/PATH TO THE FILE'
df = pd.read_csv(path)
df.head()

#Syntax: DataFrame.plot.line(x=None, y=None, **kwds)
line_1 = df_state_1.plot.line(y='deaths',x='state', rot=90, figsize=(10,3))
line_2 = df_state_1.plot.line(subplots=True,x='state', rot=90,figsize=(10,5))

#Syntax: DataFrame.plot.scatter(x, y, s=None, c=None, **kwargs)
scatter = df_state_1.plot.scatter(x='cases', y='deaths')