7/14/2020 Week 2
You are currently looking at version 1.0 of this notebook. To download notebooks and datafiles, as
well as get help on Jupyter notebooks in the Coursera platform, visit the Jupyter Notebook FAQ
([Link] course resource.
The Series Data Structure
In [ ]: import pandas as pd
[Link]?
In [ ]: animals = ['Tiger', 'Bear', 'Moose']
[Link](animals)
In [ ]: numbers = [1, 2, 3]
[Link](numbers)
In [ ]: animals = ['Tiger', 'Bear', None]
[Link](animals)
In [ ]: numbers = [1, 2, None]
[Link](numbers)
In [ ]: import numpy as np
[Link] == None
In [ ]: [Link] == [Link]
In [ ]: [Link]([Link])
In [ ]: sports = {'Archery': 'Bhutan',
'Golf': 'Scotland',
'Sumo': 'Japan',
'Taekwondo': 'South Korea'}
s = [Link](sports)
s
In [ ]: [Link]
In [ ]: s = [Link](['Tiger', 'Bear', 'Moose'], index=['India', 'America', 'Canada'])
s
[Link] [Link] 1/8
7/14/2020 Week 2
In [ ]: sports = {'Archery': 'Bhutan',
'Golf': 'Scotland',
'Sumo': 'Japan',
'Taekwondo': 'South Korea'}
s = [Link](sports, index=['Golf', 'Sumo', 'Hockey'])
s
Querying a Series
In [ ]: sports = {'Archery': 'Bhutan',
'Golf': 'Scotland',
'Sumo': 'Japan',
'Taekwondo': 'South Korea'}
s = [Link](sports)
s
In [ ]: [Link][3]
In [ ]: [Link]['Golf']
In [ ]: s[3]
In [ ]: s['Golf']
In [ ]: sports = {99: 'Bhutan',
100: 'Scotland',
101: 'Japan',
102: 'South Korea'}
s = [Link](sports)
In [ ]: s[0] #This won't call [Link][0] as one might expect, it generates an error instead
In [ ]: s = [Link]([100.00, 120.00, 101.00, 3.00])
s
In [ ]: total = 0
for item in s:
total+=item
print(total)
In [ ]: import numpy as np
total = [Link](s)
print(total)
[Link] [Link] 2/8
7/14/2020 Week 2
In [ ]: #this creates a big series of random numbers
s = [Link]([Link](0,1000,10000))
[Link]()
In [ ]: len(s)
In [ ]: %%timeit -n 100
summary = 0
for item in s:
summary+=item
In [ ]: %%timeit -n 100
summary = [Link](s)
In [ ]: s+=2 #adds two to each item in s using broadcasting
[Link]()
In [ ]: for label, value in [Link]():
s.set_value(label, value+2)
[Link]()
In [ ]: %%timeit -n 10
s = [Link]([Link](0,1000,10000))
for label, value in [Link]():
[Link][label]= value+2
In [ ]: %%timeit -n 10
s = [Link]([Link](0,1000,10000))
s+=2
In [ ]: s = [Link]([1, 2, 3])
[Link]['Animal'] = 'Bears'
s
In [ ]: original_sports = [Link]({'Archery': 'Bhutan',
'Golf': 'Scotland',
'Sumo': 'Japan',
'Taekwondo': 'South Korea'})
cricket_loving_countries = [Link](['Australia',
'Barbados',
'Pakistan',
'England'],
index=['Cricket',
'Cricket',
'Cricket',
'Cricket'])
all_countries = original_sports.append(cricket_loving_countries)
[Link] [Link] 3/8
7/14/2020 Week 2
In [ ]: original_sports
In [ ]: cricket_loving_countries
In [ ]: all_countries
In [ ]: all_countries.loc['Cricket']
The DataFrame Data Structure
In [ ]: import pandas as pd
purchase_1 = [Link]({'Name': 'Chris',
'Item Purchased': 'Dog Food',
'Cost': 22.50})
purchase_2 = [Link]({'Name': 'Kevyn',
'Item Purchased': 'Kitty Litter',
'Cost': 2.50})
purchase_3 = [Link]({'Name': 'Vinod',
'Item Purchased': 'Bird Seed',
'Cost': 5.00})
df = [Link]([purchase_1, purchase_2, purchase_3], index=['Store 1', 'Store 1
[Link]()
In [ ]: [Link]['Store 2']
In [ ]: type([Link]['Store 2'])
In [ ]: [Link]['Store 1']
In [ ]: [Link]['Store 1', 'Cost']
In [ ]: df.T
In [ ]: [Link]['Cost']
In [ ]: df['Cost']
In [ ]: [Link]['Store 1']['Cost']
In [ ]: [Link][:,['Name', 'Cost']]
In [ ]: [Link]('Store 1')
[Link] [Link] 4/8
7/14/2020 Week 2
In [ ]: df
In [ ]: copy_df = [Link]()
copy_df = copy_df.drop('Store 1')
copy_df
In [ ]: copy_df.drop?
In [ ]: del copy_df['Name']
copy_df
In [ ]: df['Location'] = None
df
Dataframe Indexing and Loading
In [ ]: costs = df['Cost']
costs
In [ ]: costs+=2
costs
In [ ]: df
In [ ]: !cat [Link]
In [ ]: df = pd.read_csv('[Link]')
[Link]()
In [ ]: df = pd.read_csv('[Link]', index_col = 0, skiprows=1)
[Link]()
In [ ]: [Link]
[Link] [Link] 5/8
7/14/2020 Week 2
In [ ]: for col in [Link]:
if col[:2]=='01':
[Link](columns={col:'Gold' + col[4:]}, inplace=True)
if col[:2]=='02':
[Link](columns={col:'Silver' + col[4:]}, inplace=True)
if col[:2]=='03':
[Link](columns={col:'Bronze' + col[4:]}, inplace=True)
if col[:1]=='№':
[Link](columns={col:'#' + col[1:]}, inplace=True)
[Link]()
Querying a DataFrame
In [ ]: df['Gold'] > 0
In [ ]: only_gold = [Link](df['Gold'] > 0)
only_gold.head()
In [ ]: only_gold['Gold'].count()
In [ ]: df['Gold'].count()
In [ ]: only_gold = only_gold.dropna()
only_gold.head()
In [ ]: only_gold = df[df['Gold'] > 0]
only_gold.head()
In [ ]: len(df[(df['Gold'] > 0) | (df['Gold.1'] > 0)])
In [ ]: df[(df['Gold.1'] > 0) & (df['Gold'] == 0)]
Indexing Dataframes
In [ ]: [Link]()
In [ ]: df['country'] = [Link]
df = df.set_index('Gold')
[Link]()
In [ ]: df = df.reset_index()
[Link]()
[Link] [Link] 6/8
7/14/2020 Week 2
In [ ]: df = pd.read_csv('[Link]')
[Link]()
In [ ]: df['SUMLEV'].unique()
In [ ]: df=df[df['SUMLEV'] == 50]
[Link]()
In [ ]: columns_to_keep = ['STNAME',
'CTYNAME',
'BIRTHS2010',
'BIRTHS2011',
'BIRTHS2012',
'BIRTHS2013',
'BIRTHS2014',
'BIRTHS2015',
'POPESTIMATE2010',
'POPESTIMATE2011',
'POPESTIMATE2012',
'POPESTIMATE2013',
'POPESTIMATE2014',
'POPESTIMATE2015']
df = df[columns_to_keep]
[Link]()
In [ ]: df = df.set_index(['STNAME', 'CTYNAME'])
[Link]()
In [ ]: [Link]['Michigan', 'Washtenaw County']
In [ ]: [Link][ [('Michigan', 'Washtenaw County'),
('Michigan', 'Wayne County')] ]
Missing values
In [ ]: df = pd.read_csv('[Link]')
df
In [ ]: [Link]?
In [ ]: df = df.set_index('time')
df = df.sort_index()
df
[Link] [Link] 7/8
7/14/2020 Week 2
In [ ]: df = df.reset_index()
df = df.set_index(['time', 'user'])
df
In [ ]: df = [Link](method='ffill')
[Link]()
[Link] [Link] 8/8