Pandas - Ipynb - Colaboratory

11/30/23, 11:37 AM Pandas.
ipynb - Colaboratory
Aim: To practice pandas commands
import pandas
pandas.__version__
'1.5.3'
import pandas as pd
import numpy as np
import pandas as pd
data = pd.Series([0.25, 0.5, 0.75, 1.0])

data
0 0.25
1 0.50
2 0.75
3 1.00
dtype: float64
data.values
array([0.25, 0.5 , 0.75, 1. ])
data.index
RangeIndex(start=0, stop=4, step=1)
data[1]
0.5
data[1:3]
1 0.50
2 0.75
dtype: float64
data = pd.Series([0.25, 0.5, 0.75, 1.0],

index=['a', 'b', 'c', 'd'])
data
a 0.25
b 0.50
c 0.75
d 1.00
dtype: float64
data['b']
0.5
data = pd.Series([0.25, 0.5, 0.75, 1.0],

index=[2, 5, 3, 7])
data
2 0.25
5 0.50
3 0.75
7 1.00
dtype: float64
data[5]
0.5
population_dict = {'California': 38332521,

'Texas': 26448193,
'New York': 19651127,
'Florida': 19552860,
'Illinois': 12882135}
population = pd.Series(population_dict)
population
https://colab.research.google.com/drive/1kPoNQIODs3ToNLdhklAC8BpC5QHfgCmf#printMode=true 1/36
11/30/23, 11:37 AM Pandas.ipynb - Colaboratory
California 38332521
Texas 26448193
New York 19651127
Florida 19552860
Illinois 12882135
dtype: int64
population['California']
38332521
population['California':'Illinois']
California 38332521
Texas 26448193
New York 19651127
Florida 19552860
Illinois 12882135
dtype: int64
pd.Series([2, 4, 6])
0 2
1 4
2 6
dtype: int64
pd.Series(5, index=[100, 200, 300])
100 5
200 5
300 5
dtype: int64
pd.Series({2:'a', 1:'b', 3:'c'})
2 a
1 b
3 c
dtype: object
pd.Series({2:'a', 1:'b', 3:'c'}, index=[3, 2])
3 c
2 a
dtype: object
area_dict = {'California': 423967, 'Texas': 695662, 'New York': 141297,

'Florida': 170312, 'Illinois': 149995}
area = pd.Series(area_dict)
area
California 423967
Texas 695662
New York 141297
Florida 170312
Illinois 149995
dtype: int64
states = pd.DataFrame({'population': population,

'area': area})
states
population area
California 38332521 423967
Texas 26448193 695662
New York 19651127 141297
Florida 19552860 170312
Illinois 12882135 149995
states.index
Index(['California', 'Texas', 'New York', 'Florida', 'Illinois'], dtype='object')
states.columns
Index(['population', 'area'], dtype='object')
states['area']
California 423967
Texas 695662
New York 141297
Florida 170312
Illinois 149995
Name: area, dtype: int64
pd.DataFrame(population, columns=['population'])
population
California 38332521
Texas 26448193
New York 19651127
Florida 19552860
Illinois 12882135
data = [{'a': i, 'b': 2 * i}

for i in range(3)]
pd.DataFrame(data)
account_circle a b
0 0 0
1 1 2
2 2 4
pd.DataFrame([{'a': 1, 'b': 2}, {'b': 3, 'c': 4}])
a b c
0 1.0 2 NaN
1 NaN 3 4.0
pd.DataFrame({'population': population,
'area': area})
population area
California 38332521 423967
Texas 26448193 695662
New York 19651127 141297
Florida 19552860 170312
Illinois 12882135 149995
pd.DataFrame(np.random.rand(3, 2),
columns=['foo', 'bar'],
index=['a', 'b', 'c'])
foo bar
a 0.100920 0.764732
b 0.511807 0.194514
c 0.736985 0.615123
A = np.zeros(3, dtype=[('A', 'i8'), ('B', 'f8')])

A
array([(0, 0.), (0, 0.), (0, 0.)], dtype=[('A', '<i8'), ('B', '<f8')])
pd.DataFrame(A)
A B
0 0 0.0
1 0 0.0
2 0 0.0
ind = pd.Index([2, 3, 5, 7, 11])

ind
Int64Index([2, 3, 5, 7, 11], dtype='int64')
ind[1]
ind[::2]
Int64Index([2, 5, 11], dtype='int64')
print(ind.size, ind.shape, ind.ndim, ind.dtype)
5 (5,) 1 int64
indA = pd.Index([1, 3, 5, 7, 9])

indB = pd.Index([2, 3, 5, 7, 11])
indA & indB
<ipython-input-343-99513bddffa9>:1: FutureWarning: Index.__and__ operating as a set operation is deprecated, in the future this will
indA & indB
Int64Index([3, 5, 7], dtype='int64')
indA | indB
<ipython-input-344-2c4bfb638f37>:1: FutureWarning: Index.__or__ operating as a set operation is deprecated, in the future this will
indA | indB
Int64Index([1, 2, 3, 5, 7, 9, 11], dtype='int64')
indA ^ indB
<ipython-input-345-3946b5999e74>:1: FutureWarning: Index.__xor__ operating as a set operation is deprecated, in the future this will
indA ^ indB
Int64Index([1, 2, 9, 11], dtype='int64')
import pandas as pd
data = pd.Series([0.25, 0.5, 0.75, 1.0],
index=['a', 'b', 'c', 'd'])
data
a 0.25
b 0.50
c 0.75
d 1.00
dtype: float64
data['b']
0.5
'a' in data
True
data.keys()
Index(['a', 'b', 'c', 'd'], dtype='object')
list(data.items())
[('a', 0.25), ('b', 0.5), ('c', 0.75), ('d', 1.0)]
data['e'] = 1.25
data
a 0.25
b 0.50
c 0.75
d 1.00
e 1.25
dtype: float64
data['a':'c']
a 0.25
b 0.50
c 0.75
dtype: float64
data[0:2]
a 0.25
b 0.50
dtype: float64
data[(data > 0.3) & (data < 0.8)]
b 0.50
c 0.75
dtype: float64
data[['a', 'e']]
a 0.25
e 1.25
dtype: float64
data = pd.Series(['a', 'b', 'c'], index=[1, 3, 5])

data
1 a
3 b
5 c
dtype: object
data[1]
'a'
data[1:3]
3 b
5 c
dtype: object
data.loc[1]
'a'
data.loc[1:3]
1 a
3 b
dtype: object
data.iloc[1]
'b'
data.iloc[1:3]
3 b
5 c
dtype: object
area = pd.Series({'California': 423967, 'Texas': 695662,
'New York': 141297, 'Florida': 170312,
'Illinois': 149995})
pop = pd.Series({'California': 38332521, 'Texas': 26448193,
'New York': 19651127, 'Florida': 19552860,
'Illinois': 12882135})
data = pd.DataFrame({'area':area, 'pop':pop})
data
area pop
California 423967 38332521
Texas 695662 26448193
New York 141297 19651127
Florida 170312 19552860
Illinois 149995 12882135
data['area']
California 423967
Texas 695662
New York 141297
Florida 170312
Illinois 149995
data.area
California 423967
Texas 695662
New York 141297
Florida 170312
Illinois 149995
data.area is data['area']
True
data.pop is data['pop']
False
data['density'] = data['pop'] / data['area']

data
area pop density
California 423967 38332521 90.413926
Texas 695662 26448193 38.018740
New York 141297 19651127 139.076746
Florida 170312 19552860 114.806121
Illinois 149995 12882135 85.883763
data.values
array([[4.23967000e+05, 3.83325210e+07, 9.04139261e+01],

[6.95662000e+05, 2.64481930e+07, 3.80187404e+01],
[1.41297000e+05, 1.96511270e+07, 1.39076746e+02],
[1.70312000e+05, 1.95528600e+07, 1.14806121e+02],
[1.49995000e+05, 1.28821350e+07, 8.58837628e+01]])
data.T
California Texas New York Florida Illinois
area 4.239670e+05 6.956620e+05 1.412970e+05 1.703120e+05 1.499950e+05
pop 3.833252e+07 2.644819e+07 1.965113e+07 1.955286e+07 1.288214e+07
density 9.041393e+01 3.801874e+01 1.390767e+02 1.148061e+02 8.588376e+01
data.values[0]
array([4.23967000e+05, 3.83325210e+07, 9.04139261e+01])
data['area']
California 423967
Texas 695662
New York 141297
Florida 170312
Illinois 149995
data.iloc[:3, :2]
area pop
California 423967 38332521
Texas 695662 26448193
New York 141297 19651127
data.loc[:'Illinois', :'pop']
area pop
California 423967 38332521
Texas 695662 26448193
New York 141297 19651127
Florida 170312 19552860
Illinois 149995 12882135
data.loc[data.density > 100, ['pop', 'density']]
pop density
New York 19651127 139.076746
Florida 19552860 114.806121
data.iloc[0, 2] = 90
data
area pop density
California 423967 38332521 90.000000
Texas 695662 26448193 38.018740
New York 141297 19651127 139.076746
Florida 170312 19552860 114.806121
Illinois 149995 12882135 85.883763
data['Florida':'Illinois']
area pop density
Florida 170312 19552860 114.806121
Illinois 149995 12882135 85.883763
data[1:3]
area pop density
Texas 695662 26448193 38.018740
New York 141297 19651127 139.076746
data[data.density > 100]
area pop density
New York 141297 19651127 139.076746
import pandas
Florida as170312
pd 19552860 114.806121
import numpy as np
rng = np.random.RandomState(42)
ser = pd.Series(rng.randint(0, 10, 4))
ser
0 6
1 3
2 7
3 4
dtype: int64
df = pd.DataFrame(rng.randint(0, 10, (3, 4)),

columns=['A', 'B', 'C', 'D'])
df
A B C D
0 6 9 2 6
1 7 4 3 7
2 7 2 5 4
np.exp(ser)
0 403.428793
1 20.085537
2 1096.633158
3 54.598150
dtype: float64
np.sin(df * np.pi / 4)
A B C D
0 -1.000000 7.071068e-01 1.000000 -1.000000e+00
1 -0.707107 1.224647e-16 0.707107 -7.071068e-01
2 -0.707107 1.000000e+00 -0.707107 1.224647e-16
area = pd.Series({'Alaska': 1723337, 'Texas': 695662,

'California': 423967}, name='area')
population = pd.Series({'California': 38332521, 'Texas': 26448193,
'New York': 19651127}, name='population')
population / area
Alaska NaN
California 90.413926
New York NaN
Texas 38.018740
dtype: float64
area.index | population.index
<ipython-input-387-ff558a211efb>:1: FutureWarning: Index.__or__ operating as a set operation is deprecated, in the future this will
area.index | population.index
Index(['Alaska', 'California', 'New York', 'Texas'], dtype='object')
A = pd.Series([2, 4, 6], index=[0, 1, 2])

B = pd.Series([1, 3, 5], index=[1, 2, 3])
A + B
0 NaN
1 5.0
2 9.0
3 NaN
dtype: float64
A.add(B, fill_value=0)
0 2.0
1 5.0
2 9.0
3 5.0
dtype: float64
A = pd.DataFrame(rng.randint(0, 20, (2, 2)),

columns=list('AB'))
A
A B
0 1 11
1 5 1
B = pd.DataFrame(rng.randint(0, 10, (3, 3)),

columns=list('BAC'))
B
B A C
0 4 0 9
1 5 8 0
2 9 2 6
A + B
A B C
0 1.0 15.0 NaN
1 13.0 6.0 NaN
2 NaN NaN NaN
fill = A.stack().mean()
A.add(B, fill_value=fill)
A B C
0 1.0 15.0 13.5
1 13.0 6.0 4.5
2 6.5 13.5 10.5
A = rng.randint(10, size=(3, 4))

A
array([[3, 8, 2, 4],
[2, 6, 4, 8],
[6, 1, 3, 8]])
A - A[0]
array([[ 0, 0, 0, 0],
[-1, -2, 2, 4],
[ 3, -7, 1, 4]])
df = pd.DataFrame(A, columns=list('QRST'))
df - df.iloc[0]
Q R S T
0 0 0 0 0
1 -1 -2 2 4
2 3 -7 1 4
df.subtract(df['R'], axis=0)
Q R S T
0 -5 0 -6 -4
halfrow = df.iloc[0, ::2]
1 -4 0 -2 2
halfrow
2 5 0 2 7
Q 3
S 2
Name: 0, dtype: int64
df - halfrow
Q R S T
0 0.0 NaN 0.0 NaN
1 -1.0 NaN 2.0 NaN
2 3.0 NaN 1.0 NaN
import numpy as np
import pandas as pd
vals1 = np.array([1, None, 3, 4])

vals1
array([1, None, 3, 4], dtype=object)
for dtype in ['object', 'int']:

print("dtype =", dtype)
%timeit np.arange(1E6, dtype=dtype).sum()
print()
dtype = object
62.5 ms ± 2.1 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
dtype = int
983 µs ± 183 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)
vals2 = np.array([1, np.nan, 3, 4])

vals2.dtype
dtype('float64')
1 + np.nan
nan
0 * np.nan
nan
vals2.sum(), vals2.min(), vals2.max()
(nan, nan, nan)
np.nansum(vals2), np.nanmin(vals2), np.nanmax(vals2)
(8.0, 1.0, 4.0)
pd.Series([1, np.nan, 2, None])
0 1.0
1 NaN
2 2.0
3 NaN
dtype: float64
x = pd.Series(range(2), dtype=int)
x
0 0
1 1
dtype: int64
x[0] = None
x
0 NaN
1 1.0
dtype: float64
data = pd.Series([1, np.nan, 'hello', None])
data.isnull()
0 False
1 True
2 False
3 True
dtype: bool
data[data.notnull()]
0 1
2 hello
dtype: object
data.dropna()
0 1
2 hello
dtype: object
df = pd.DataFrame([[1, np.nan, 2],

[2, 3, 5],
[np.nan, 4, 6]])
df
0 1 2
0 1.0 NaN 2
1 2.0 3.0 5
2 NaN 4.0 6
df.dropna()
0 1 2
1 2.0 3.0 5
df.dropna(axis='columns')
0 2
1 5
2 6
df[3] = np.nan
df
0 1 2 3
0 1.0 NaN 2 NaN
1 2.0 3.0 5 NaN
2 NaN 4.0 6 NaN
df.dropna(axis='columns', how='all')
0 1 2
0 1.0 NaN 2
1 2.0 3.0 5
2 NaN 4.0 6
df.dropna(axis='rows', thresh=3)
0 1 2 3
1 2.0 3.0 5 NaN
data = pd.Series([1, np.nan, 2, None, 3], index=list('abcde'))

data
a 1.0
b NaN
c 2.0
d NaN
e 3.0
dtype: float64
data.fillna(0)
a 1.0
b 0.0
c 2.0
d 0.0
e 3.0
dtype: float64
data.fillna(method='ffill')
a 1.0
b 1.0
c 2.0
d 2.0
e 3.0
dtype: float64
data.fillna(method='bfill')
a 1.0
b 2.0
c 2.0
d 3.0
e 3.0
dtype: float64
df
0 1 2 3
0 1.0 NaN 2 NaN
1 2.0 3.0 5 NaN
2 NaN 4.0 6 NaN
df.fillna(method='ffill', axis=1)
0 1 2 3
0 1.0 1.0 2.0 2.0
1 2.0 3.0 5.0 5.0
2 NaN 4.0 6.0 6.0
index = [('California', 2000), ('California', 2010),

('New York', 2000), ('New York', 2010),
('Texas', 2000), ('Texas', 2010)]
populations = [33871648, 37253956,
18976457, 19378102,
20851820, 25145561]
pop = pd.Series(populations, index=index)
pop
(California, 2000) 33871648

(California, 2010) 37253956
(New York, 2000) 18976457
(New York, 2010) 19378102
(Texas, 2000) 20851820
(Texas, 2010) 25145561
dtype: int64
pop[('California', 2010):('Texas', 2000)]
(California, 2010) 37253956

(New York, 2000) 18976457
(New York, 2010) 19378102
(Texas, 2000) 20851820
dtype: int64
pop[[i for i in pop.index if i[1] == 2010]]
(California, 2010) 37253956

(New York, 2010) 19378102
(Texas, 2010) 25145561
dtype: int64
index = pd.MultiIndex.from_tuples(index)
index
MultiIndex([('California', 2000),
('California', 2010),
( 'New York', 2000),
( 'New York', 2010),
( 'Texas', 2000),
( 'Texas', 2010)],
)
pop = pop.reindex(index)
pop
California 2000 33871648

2010 37253956
New York 2000 18976457
2010 19378102
Texas 2000 20851820
2010 25145561
dtype: int64
pop[:, 2010]
California 37253956
New York 19378102
Texas 25145561
dtype: int64
pop_df = pop.unstack()
pop_df
2000 2010
California 33871648 37253956
New York 18976457 19378102
Texas 20851820 25145561
pop_df.stack()

2010 37253956
New York 2000 18976457
2010 19378102
Texas 2000 20851820
2010 25145561
dtype: int64
pop_df = pd.DataFrame({'total': pop,

'under18': [9267089, 9284094,
4687374, 4318033,
5906301, 6879014]})
pop_df
total under18
f_u18 California 2000 33871648

= pop_df['under18'] 9267089
/ pop_df['total']
f_u18.unstack()
2010 37253956 9284094
New York 20002000

18976457 4687374
2010

0.273594 4318033
0.249211
Texas
New York 2000 20851820
0.247010 5906301
0.222831
Texas 2010 25145561

0.283251 6879014
0.273568
df = pd.DataFrame(np.random.rand(4, 2),
index=[['a', 'a', 'b', 'b'], [1, 2, 1, 2]],
columns=['data1', 'data2'])
df
data1 data2
a 1 0.107411 0.623970
2 0.934661 0.889680
b 1 0.753637 0.395928
2 0.460310 0.289032
data = {('California', 2000): 33871648,

('California', 2010): 37253956,
('Texas', 2000): 20851820,
('Texas', 2010): 25145561,
('New York', 2000): 18976457,
('New York', 2010): 19378102}
pd.Series(data)

2010 37253956
Texas 2000 20851820
2010 25145561
New York 2000 18976457
2010 19378102
dtype: int64
pd.MultiIndex.from_arrays([['a', 'a', 'b', 'b'], [1, 2, 1, 2]])
MultiIndex([('a', 1),
('a', 2),
('b', 1),
('b', 2)],
)
pd.MultiIndex.from_tuples([('a', 1), ('a', 2), ('b', 1), ('b', 2)])
('a', 2),
('b', 1),
('b', 2)],
)
pd.MultiIndex.from_product([['a', 'b'], [1, 2]])
('a', 2),
('b', 1),
('b', 2)],
)
pop.index.names = ['state', 'year']

pop
state year
2010 37253956
New York 2000 18976457
2010 19378102
Texas 2000 20851820
2010 25145561
dtype: int64
index = pd.MultiIndex.from_product([[2013, 2014], [1, 2]],
names=['year', 'visit'])
columns = pd.MultiIndex.from_product([['Bob', 'Guido', 'Sue'], ['HR', 'Temp']],
names=['subject', 'type'])
data = np.round(np.random.randn(4, 6), 1)
data[:, ::2] *= 10
data += 37
health_data = pd.DataFrame(data, index=index, columns=columns)
health_data
subject Bob Guido Sue
type HR Temp HR Temp HR Temp
year visit
2013 1 19.0 37.7 41.0 37.1 34.0 36.5
2 37.0 35.6 39.0 38.0 38.0 37.0
2014 1 18.0 36.8 45.0 38.0 50.0 36.7
2 54.0 35.5 35.0 37.4 31.0 38.1
health_data['Guido']
type HR Temp
year visit
2013 1 41.0 37.1
2 39.0 38.0
2014 1 45.0 38.0
2 35.0 37.4
pop
state year
2010 37253956
New York 2000 18976457
2010 19378102
Texas 2000 20851820
2010 25145561
dtype: int64
pop['California', 2000]
33871648
pop['California']
year
2000 33871648
2010 37253956
dtype: int64
pop.loc['California':'New York']
state year
2010 37253956
New York 2000 18976457
2010 19378102
dtype: int64
pop[:, 2000]
state
California 33871648
New York 18976457
Texas 20851820
dtype: int64
pop[pop > 22000000]
state year
2010 37253956
Texas 2010 25145561
dtype: int64
pop[['California', 'Texas']]
state year
2010 37253956
Texas 2000 20851820
2010 25145561
dtype: int64
health_data
year visit
2013 1 19.0 37.7 41.0 37.1 34.0 36.5
2 37.0 35.6 39.0 38.0 38.0 37.0
2014 1 18.0 36.8 45.0 38.0 50.0 36.7
2 54.0 35.5 35.0 37.4 31.0 38.1
health_data['Guido', 'HR']
year visit
2013 1 41.0
2 39.0
2014 1 45.0
2 35.0
Name: (Guido, HR), dtype: float64
health_data.iloc[:2, :2]
subject Bob
type HR Temp
year visit
2013 1 19.0 37.7
2 37.0 35.6
health_data.loc[:, ('Bob', 'HR')]
year visit
2013 1 19.0
2 37.0
2014 1 18.0
2 54.0
Name: (Bob, HR), dtype: float64
idx = pd.IndexSlice
health_data.loc[idx[:, 1], idx[:, 'HR']]
type HR HR HR
year visit
2013 1 19.0 41.0 34.0
2014 1 18.0 45.0 50.0
index = pd.MultiIndex.from_product([['a', 'c', 'b'], [1, 2]])

data = pd.Series(np.random.rand(6), index=index)
data.index.names = ['char', 'int']
data
char int
a 1 0.053467
2 0.844292
c 1 0.516159
2 0.688637
b 1 0.539836
2 0.151731
dtype: float64
try:
data['a':'b']
except KeyError as e:
print(type(e))
print(e)
<class 'pandas.errors.UnsortedIndexError'>
'Key length (1) was greater than MultiIndex lexsort depth (0)'
data = data.sort_index()
data
char int
a 1 0.053467
2 0.844292
b 1 0.539836
2 0.151731
c 1 0.516159
2 0.688637
dtype: float64
data['a':'b']
char int
a 1 0.053467
2 0.844292
b 1 0.539836
2 0.151731
dtype: float64
pop.unstack(level=0)
state California New York Texas
year
2000 33871648 18976457 20851820
2010 37253956 19378102 25145561
pop.unstack(level=1)
year 2000 2010
state
California 33871648 37253956
New York 18976457 19378102
Texas 20851820 25145561
pop.unstack().stack()
state year
2010 37253956
New York 2000 18976457
2010 19378102
Texas 2000 20851820
2010 25145561
dtype: int64
pop_flat = pop.reset_index(name='population')
pop_flat
state year population
0 California 2000 33871648
1 California 2010 37253956
2 New York 2000 18976457
3 New York 2010 19378102
4 Texas 2000 20851820
5 Texas 2010 25145561
pop_flat.set_index(['state', 'year'])
population
state year
2010 37253956
New York 2000 18976457
2010 19378102
Texas 2000 20851820
2010 25145561
health_data
year visit
2013 1 19.0 37.7 41.0 37.1 34.0 36.5
2 37.0 35.6 39.0 38.0 38.0 37.0
2014 1 18.0 36.8 45.0 38.0 50.0 36.7
2 54.0 35.5 35.0 37.4 31.0 38.1
data_mean = health_data.mean(level='year')
data_mean
<ipython-input-469-af3ae0440116>:1: FutureWarning: Using the level keyword in DataFra

data_mean = health_data.mean(level='year')
year
2013 28.0 36.65 40.0 37.55 36.0 36.75
2014 36.0 36.15 40.0 37.70 40.5 37.40
data_mean.mean(axis=1, level='type')
<ipython-input-470-e9f5c76486ab>:1: FutureWarning: Using the level keyword in DataFra

data_mean.mean(axis=1, level='type')
type HR Temp
year
2013 34.666667 36.983333
2014 38.833333 37.083333
import pandas as pd
import numpy as np
Double-click (or enter) to edit
def make_df(cols, ind):

data = {c: [str(c) + str(i) for i in ind]
for c in cols}
return pd.DataFrame(data, ind)
make_df('ABC', range(3))
A B C
0 A0 B0 C0
1 A1 B1 C1
2 A2 B2 C2
x = [1, 2, 3]
y = [4, 5, 6]
z = [7, 8, 9]
np.concatenate([x, y, z])
array([1, 2, 3, 4, 5, 6, 7, 8, 9])
x = [[1, 2],
[3, 4]]
np.concatenate([x, x], axis=1)
array([[1, 2, 1, 2],
[3, 4, 3, 4]])
ser1 = pd.Series(['A', 'B', 'C'], index=[1, 2, 3])

ser2 = pd.Series(['D', 'E', 'F'], index=[4, 5, 6])
pd.concat([ser1, ser2])
1 A
2 B
3 C
4 D
5 E
6 F
dtype: object
df1 = make_df('AB', [1, 2])

df2 = make_df('AB', [3, 4])
print(df1); print(df2); print(pd.concat([df1, df2]))
A B
1 A1 B1
2 A2 B2
A B
3 A3 B3
4 A4 B4
A B
1 A1 B1
2 A2 B2
3 A3 B3
4 A4 B4
df3 = make_df('AB', [0, 1])

df4 = make_df('CD', [0, 1])
print(df3); print(df4); print(pd.concat([df3, df4], axis=1))
A B
0 A0 B0
1 A1 B1
C D
0 C0 D0
1 C1 D1
A B C D
0 A0 B0 C0 D0
1 A1 B1 C1 D1
x = make_df('AB', [0, 1])

y = make_df('AB', [2, 3])
y.index = x.index
print(x); print(y); print(pd.concat([x, y]))
A B
0 A0 B0
1 A1 B1
A B
0 A2 B2
1 A3 B3
A B
0 A0 B0
1 A1 B1
0 A2 B2
1 A3 B3
try:
pd.concat([x, y], verify_integrity=True)
except ValueError as e:
print("ValueError:", e)
ValueError: Indexes have overlapping values: Int64Index([0, 1], dtype='int64')
print(x); print(y); print(pd.concat([x, y], ignore_index=True))
A B
0 A0 B0
1 A1 B1
A B
0 A2 B2
1 A3 B3
A B
0 A0 B0
1 A1 B1
2 A2 B2
3 A3 B3
print(x); print(y); print(pd.concat([x, y], keys=['x', 'y']))
A B
0 A0 B0
1 A1 B1
A B
0 A2 B2
1 A3 B3
A B
x 0 A0 B0
1 A1 B1
y 0 A2 B2
1 A3 B3
df5 = make_df('ABC', [1, 2])

df6 = make_df('BCD', [3, 4])
print(df5); print(df6); print(pd.concat([df5, df6]))
A B C
1 A1 B1 C1
2 A2 B2 C2
B C D
3 B3 C3 D3
4 B4 C4 D4
A B C D
1 A1 B1 C1 NaN
2 A2 B2 C2 NaN
3 NaN B3 C3 D3
4 NaN B4 C4 D4
print(df5); print(df6);
print(pd.concat([df5, df6], join='inner'))
A B C
1 A1 B1 C1
2 A2 B2 C2
B C D
3 B3 C3 D3
4 B4 C4 D4
B C
1 B1 C1
2 B2 C2
3 B3 C3
4 B4 C4
print(pd.concat([df5, df6]))
A B C
1 A1 B1 C1
2 A2 B2 C2
B C D
3 B3 C3 D3
4 B4 C4 D4
A B C D
1 A1 B1 C1 NaN
2 A2 B2 C2 NaN
3 NaN B3 C3 D3
4 NaN B4 C4 D4
print(df1); print(df2); print(df1.append(df2))
A B
1 A1 B1
2 A2 B2
A B
3 A3 B3
4 A4 B4
A B
1 A1 B1
2 A2 B2
3 A3 B3
4 A4 B4
<ipython-input-498-f80ce5c761de>:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future
print(df1); print(df2); print(df1.append(df2))
df1 = pd.DataFrame({'employee': ['Bob', 'Jake', 'Lisa', 'Sue'],

'group': ['Accounting', 'Engineering', 'Engineering', 'HR']})
df2 = pd.DataFrame({'employee': ['Lisa', 'Bob', 'Jake', 'Sue'],
'hire_date': [2004, 2008, 2012, 2014]})
print(df1); print(df2)
employee group
0 Bob Accounting
1 Jake Engineering
2 Lisa Engineering
3 Sue HR
employee hire_date
0 Lisa 2004
1 Bob 2008
2 Jake 2012
3 Sue 2014
df3 = pd.merge(df1, df2)

df3
employee group hire_date
0 Bob Accounting 2008
1 Jake Engineering 2012
2 Lisa Engineering 2004
3 Sue HR 2014
df4 = pd.DataFrame({'group': ['Accounting', 'Engineering', 'HR'],

'supervisor': ['Carly', 'Guido', 'Steve']})
print(df3); print(df4); print(pd.merge(df3, df4))

3 Sue HR 2014
group supervisor
0 Accounting Carly
1 Engineering Guido
2 HR Steve
employee group hire_date supervisor
0 Bob Accounting 2008 Carly
1 Jake Engineering 2012 Guido
2 Lisa Engineering 2004 Guido
3 Sue HR 2014 Steve
df5 = pd.DataFrame({'group': ['Accounting', 'Accounting',

'Engineering', 'Engineering', 'HR', 'HR'],'skills': ['math', 'spreadsheets', 'coding', 'linux',
'spreadsheets', 'organization']})
employee group
0 Bob Accounting
1 Jake Engineering
2 Lisa Engineering
3 Sue HR
group skills
0 Accounting math
1 Accounting spreadsheets
2 Engineering coding
3 Engineering linux
4 HR spreadsheets
5 HR organization
employee group skills
0 Bob Accounting math
1 Bob Accounting spreadsheets
2 Jake Engineering coding
3 Jake Engineering linux
4 Lisa Engineering coding
5 Lisa Engineering linux
6 Sue HR spreadsheets
7 Sue HR organization
print(df1); print(df2); print(pd.merge(df1, df2, on='employee'))
employee group
0 Bob Accounting
1 Jake Engineering
2 Lisa Engineering
3 Sue HR
employee hire_date
0 Lisa 2004
1 Bob 2008
2 Jake 2012
3 Sue 2014
3 Sue HR 2014
df3 = pd.DataFrame({'name': ['Bob', 'Jake', 'Lisa', 'Sue'],

'salary': [70000, 80000, 120000, 90000]})
print(pd.merge(df1, df3, left_on="employee", right_on="name"))
employee group
0 Bob Accounting
1 Jake Engineering
2 Lisa Engineering
3 Sue HR
name salary
0 Bob 70000
1 Jake 80000
2 Lisa 120000
3 Sue 90000
employee group name salary
0 Bob Accounting Bob 70000
1 Jake Engineering Jake 80000
2 Lisa Engineering Lisa 120000
3 Sue HR Sue 90000
pd.merge(df1, df3, left_on="employee", right_on="name").drop('name', axis=1)
employee group salary
3 Sue HR 90000
df1a = df1.set_index('employee')
df2a = df2.set_index('employee')
print(df1a); print(df2a)
group
employee
Bob Accounting
Jake Engineering
Lisa Engineering
Sue HR
hire_date
employee
Lisa 2004
Bob 2008
Jake 2012
Sue 2014
print(df1a); print(df2a);
print(pd.merge(df1a, df2a, left_index=True, right_index=True))
group
employee
Bob Accounting
Jake Engineering
Lisa Engineering
Sue HR
hire_date
employee
Lisa 2004
Bob 2008
Jake 2012
Sue 2014
group hire_date
employee
Bob Accounting 2008
Jake Engineering 2012
Lisa Engineering 2004
Sue HR 2014
print(df1a); print(df2a); print(df1a.join(df2a))
group
employee
Bob Accounting
Jake Engineering
Lisa Engineering
Sue HR
hire_date
employee
Lisa 2004
Bob 2008
Jake 2012
Sue 2014
group hire_date
employee
Bob Accounting 2008
Jake Engineering 2012
Lisa Engineering 2004
Sue HR 2014
print(df1a); print(df3);
print(pd.merge(df1a, df3, left_index=True, right_on='name'))
group
employee
Bob Accounting
Jake Engineering
Lisa Engineering
Sue HR
name salary
0 Bob 70000
1 Jake 80000
2 Lisa 120000
3 Sue 90000
group name salary
0 Accounting Bob 70000
1 Engineering Jake 80000
2 Engineering Lisa 120000
3 HR Sue 90000
df6 = pd.DataFrame({'name': ['Peter', 'Paul', 'Mary'],

'food': ['fish', 'beans', 'bread']},
columns=['name', 'food'])
df7 = pd.DataFrame({'name': ['Mary', 'Joseph'],
'drink': ['wine', 'beer']},
columns=['name', 'drink'])
name food
0 Peter fish
1 Paul beans
2 Mary bread
name drink
0 Mary wine
1 Joseph beer
name food drink
0 Mary bread wine
pd.merge(df6, df7, how='inner')
name food drink
0 Mary bread wine
print(df6); print(df7); print(pd.merge(df6, df7, how='outer'))
name food
0 Peter fish
1 Paul beans
2 Mary bread
name drink
0 Mary wine
1 Joseph beer
name food drink
0 Peter fish NaN
1 Paul beans NaN
2 Mary bread wine
3 Joseph NaN beer
print(df6); print(df7); print(pd.merge(df6, df7, how='left'))
name food
0 Peter fish
1 Paul beans
2 Mary bread
name drink
0 Mary wine
1 Joseph beer
name food drink
0 Peter fish NaN
1 Paul beans NaN
2 Mary bread wine

'rank': [1, 2, 3, 4]})
'rank': [3, 1, 4, 2]})
print(df8); print(df9); print(pd.merge(df8, df9, on="name"))
name rank
0 Bob 1
1 Jake 2
2 Lisa 3
3 Sue 4
name rank
0 Bob 3
1 Jake 1
2 Lisa 4
3 Sue 2
name rank_x rank_y
0 Bob 1 3
1 Jake 2 1
2 Lisa 3 4
3 Sue 4 2
print(pd.merge(df8, df9, on="name", suffixes=["_L", "_R"]))
name rank
0 Bob 1
1 Jake 2
2 Lisa 3
3 Sue 4
name rank
0 Bob 3
1 Jake 1
2 Lisa 4
3 Sue 2
name rank_L rank_R
0 Bob 1 3
1 Jake 2 1
2 Lisa 3 4
3 Sue 4 2
import seaborn as sns

planets = sns.load_dataset('planets')
planets.shape
(1035, 6)
planets.head()
method number orbital_period mass distance year
0 Radial Velocity 1 269.300 7.10 77.40 2006
1 Radial Velocity 1 874.774 2.21 56.95 2008
2 Radial Velocity 1 763.000 2.60 19.84 2011
3 Radial Velocity 1 326.030 19.40 110.62 2007
4 Radial Velocity 1 516.220 10.50 119.47 2009
ser = pd.Series(rng.rand(5))
ser
0 0.374540
1 0.950714
2 0.731994
3 0.598658
4 0.156019
dtype: float64
ser.sum()
2.811925491708157
ser.mean()
0.5623850983416314
df = pd.DataFrame({'A': rng.rand(5),
'B': rng.rand(5)})
df
A B
0 0.155995 0.020584
1 0.058084 0.969910
2 0.866176 0.832443
3 0.601115 0.212339
4 0.708073 0.181825
df.mean()
A 0.477888
B 0.443420
dtype: float64
df.mean(axis='columns')
0 0.088290
1 0.513997
2 0.849309
3 0.406727
4 0.444949
dtype: float64
planets.dropna().describe()
number orbital_period mass distance year
count 498.00000 498.000000 498.000000 498.000000 498.000000
mean 1.73494 835.778671 2.509320 52.068213 2007.377510
std 1.17572 1469.128259 3.636274 46.596041 4.167284
min 1.00000 1.328300 0.003600 1.350000 1989.000000
25% 1.00000 38.272250 0.212500 24.497500 2005.000000
50% 1.00000 357.000000 1.245000 39.940000 2009.000000
75% 2.00000 999.600000 2.867500 59.332500 2011.000000
max 6.00000 17337.500000 25.000000 354.000000 2014.000000
df = pd.DataFrame({'key': ['A', 'B', 'C', 'A', 'B', 'C'],

'data': range(6)}, columns=['key', 'data'])
df
key data
0 A 0
1 B 1
2 C 2
3 A 3
4 B 4
5 C 5
df.groupby('key')
<pandas.core.groupby.generic.DataFrameGroupBy object at 0x7b56d3feb220>
df.groupby('key').sum()
data
key
A 3
B 5
C 7
planets.groupby('method')
<pandas.core.groupby.generic.DataFrameGroupBy object at 0x7b56d4030b20>
planets.groupby('method')['orbital_period']
<pandas.core.groupby.generic.SeriesGroupBy object at 0x7b56d4030ee0>
planets.groupby('method')['orbital_period'].median()
method
Astrometry 631.180000
Eclipse Timing Variations 4343.500000
Imaging 27500.000000
Microlensing 3300.000000
Orbital Brightness Modulation 0.342887
Pulsar Timing 66.541900
Pulsation Timing Variations 1170.000000
Radial Velocity 360.200000
Transit 5.714932
Transit Timing Variations 57.011000
Name: orbital_period, dtype: float64
for (method, group) in planets.groupby('method'):

print("{0:30s} shape={1}".format(method, group.shape))
Astrometry shape=(2, 6)
Eclipse Timing Variations shape=(9, 6)
Imaging shape=(38, 6)
Microlensing shape=(23, 6)
Orbital Brightness Modulation shape=(3, 6)
Pulsar Timing shape=(5, 6)
Pulsation Timing Variations shape=(1, 6)
Radial Velocity shape=(553, 6)
Transit shape=(397, 6)
Transit Timing Variations shape=(4, 6)
planets.groupby('method')['year'].describe().unstack()
method
count Astrometry 2.0
Eclipse Timing Variations 9.0
Imaging 38.0
Microlensing 23.0
Orbital Brightness Modulation 3.0
...
max Pulsar Timing 2011.0
Pulsation Timing Variations 2007.0
Radial Velocity 2014.0
Transit 2014.0
Transit Timing Variations 2014.0
Length: 80, dtype: float64
df = pd.DataFrame({'key': ['A', 'B', 'C', 'A', 'B', 'C'],
'data1': range(6),
'data2': rng.randint(0, 10, 6)},
columns = ['key', 'data1', 'data2'])
df
key data1 data2
0 A 0 5
1 B 1 0
df.groupby('key').aggregate(['min',
2 C 2 3 np.median, max])
3 A 3 3
data1 data2
4 B 4 7
min median max min median max
5 C 5 9
key
A 0 1.5 3 3 4.0 5
B 1 2.5 4 0 3.5 7
C 2 3.5 5 3 6.0 9
df.groupby('key').aggregate({'data1': 'min',
'data2': 'max'})
data1 data2
key
A 0 5
B 1 7
C 2 9
def filter_func(x):
return x['data2'].std() > 4
print(df); print(df.groupby('key').std());
print(df.groupby('key').filter(filter_func))
key data1 data2

0 A 0 5
1 B 1 0
2 C 2 3
3 A 3 3
4 B 4 7
5 C 5 9
data1 data2
key
A 2.12132 1.414214
B 2.12132 4.949747
C 2.12132 4.242641
key data1 data2
1 B 1 0
2 C 2 3
4 B 4 7
5 C 5 9
df.groupby('key').transform(lambda x: x - x.mean())
def norm_by_data2(x):
x['data1'] /= x['data2'].sum()
return x
print(df); print(df.groupby('key').apply(norm_by_data2))
key data1 data2

0 A 0 5
1 B 1 0
2 C 2 3
3 A 3 3
4 B 4 7
5 C 5 9
key data1 data2
0 A 0.000000 5
1 B 0.142857 0
2 C 0.166667 3
3 A 0.375000 3
4 B 0.571429 7
5 C 0.416667 9
<ipython-input-548-05fb1586265c>:4: FutureWarning: Not prepending group keys to the result index of transform-like apply. In the fut
To preserve the previous behavior, use
>>> .groupby(..., group_keys=False)
To adopt the future behavior and silence this warning, use
>>> .groupby(..., group_keys=True)
print(df); print(df.groupby('key').apply(norm_by_data2))
L = [0, 1, 0, 1, 2, 0]
print(df); print(df.groupby(L).sum())
key data1 data2

0 A 0 5
1 B 1 0
2 C 2 3
3 A 3 3
4 B 4 7
5 C 5 9
data1 data2
0 7 17
1 4 3
2 4 7
<ipython-input-549-b7449fcee4bf>:2: FutureWarning: The default value of numeric_only in DataFrameGroupBy.sum is deprecated. In a fut
print(df); print(df.groupby(L).sum())
print(df); print(df.groupby(df['key']).sum())
key data1 data2

0 A 0 5
1 B 1 0
2 C 2 3
3 A 3 3
4 B 4 7
5 C 5 9
data1 data2
key
A 3 8
B 5 7
C 7 12
df2 = df.set_index('key')
mapping = {'A': 'vowel', 'B': 'consonant', 'C': 'consonant'}
print(df2); print(df2.groupby(mapping).sum())
data1 data2
key
A 0 5
B 1 0
C 2 3
A 3 3
B 4 7
C 5 9
data1 data2
key
consonant 12 19
vowel 3 8
print(df2); print(df2.groupby(str.lower).mean())
data1 data2
key
A 0 5
B 1 0
C 2 3
A 3 3
B 4 7
C 5 9
data1 data2
key
a 1.5 4.0
b 2.5 3.5
c 3.5 6.0
df2.groupby([str.lower, mapping]).mean()
data1 data2
key key
a vowel 1.5 4.0
b consonant 2.5 3.5
c consonant 3.5 6.0
decade = 10 * (planets['year'] // 10)
decade = decade.astype(str) + 's'
decade.name = 'decade'
planets.groupby(['method', decade])['number'].sum().unstack().fillna(0)
decade 1980s 1990s 2000s 2010s
method
Astrometry 0.0 0.0 0.0 2.0
Eclipse Timing Variations 0.0 0.0 5.0 10.0
Imaging 0.0 0.0 29.0 21.0
Microlensing 0.0 0.0 12.0 15.0
Orbital Brightness Modulation 0.0 0.0 0.0 5.0
Pulsar Timing 0.0 9.0 1.0 1.0
Pulsation Timing Variations 0.0 0.0 1.0 0.0
Radial Velocity 1.0 52.0 475.0 424.0
Transit 0.0 0.0 64.0 712.0
Transit Timing Variations 0.0 0.0 0.0 9.0
import numpy as np
import pandas as pd
import seaborn as sns
titanic = sns.load_dataset('titanic')
titanic.head()
survived pclass sex age sibsp parch fare embarked class who adult
0 0 3 male 22.0 1 0 7.2500 S Third man
1 1 1 female 38.0 1 0 71.2833 C First woman
2 1 3 female 26.0 0 0 7.9250 S Third woman
3 1 1 female 35.0 1 0 53.1000 S First woman
4 0 3 male 35.0 0 0 8.0500 S Third man
titanic.groupby('sex')[['survived']].mean()
survived
sex
female 0.742038
male 0.188908
titanic.groupby(['sex', 'class'])['survived'].aggregate('mean').unstack()
class First Second Third
sex
female 0.968085 0.921053 0.500000
male 0.368852 0.157407 0.135447
titanic.pivot_table('survived', index='sex', columns='class')
sex
female 0.968085 0.921053 0.500000
male 0.368852 0.157407 0.135447
age = pd.cut(titanic['age'], [0, 18, 80])

titanic.pivot_table('survived', ['sex', age], 'class')
sex age
female (0, 18] 0.909091 1.000000 0.511628
(18, 80] 0.972973 0.900000 0.423729
male (0, 18] 0.800000 0.600000 0.215686
(18, 80] 0.375000 0.071429 0.133663

fare = pd.qcut(titanic['fare'], 2)
titanic.pivot_table('survived', ['sex', age], [fare, 'class'])
fare (-0.001, 14.454] (14.454, 512.329]
class First Second Third First Second Third
sex age
female (0, 18] NaN 1.000000 0.714286 0.909091 1.000000 0.318182
(18, 80] NaN 0.880000 0.444444 0.972973 0.914286 0.391304
male (0, 18] NaN 0.000000 0.260870 0.800000 0.818182 0.178571
(18, 80] 0.0 0.098039 0.125000 0.391304 0.030303 0.192308
titanic.pivot_table(index='sex', columns='class',
aggfunc={'survived':sum, 'fare':'mean'})
fare survived
class First Second Third First Second Third
sex
female 106.125798 21.970121 16.118810 91 70 72
male 67.226127 19.741782 12.661633 45 17 47
titanic.pivot_table('survived', index='sex', columns='class', margins=True)
class First Second Third All
sex
female 0.968085 0.921053 0.500000 0.742038
male 0.368852 0.157407 0.135447 0.188908
All 0.629630 0.472826 0.242363 0.383838
import numpy as np
x = np.array([2, 3, 5, 7, 11, 13])
x * 2
array([ 4, 6, 10, 14, 22, 26])
data = ['peter', 'Paul', 'MARY', 'gUIDO']

[s.capitalize() for s in data]
['Peter', 'Paul', 'Mary', 'Guido']
import pandas as pd
names = pd.Series(data)
names
0 peter
1 Paul
2 MARY
3 gUIDO
dtype: object
names.str.capitalize()
0 Peter
1 Paul
2 Mary
3 Guido
dtype: object
monte = pd.Series(['Graham Chapman', 'John Cleese', 'Terry Gilliam',

'Eric Idle', 'Terry Jones', 'Michael Palin'])
monte.str.lower()
0 graham chapman
1 john cleese
2 terry gilliam
3 eric idle
4 terry jones
5 michael palin
dtype: object
monte.str.len()
0 14
1 11
2 13
3 9
4 11
5 13
dtype: int64
monte.str.startswith('T')
0 False
1 False
2 True
3 False
4 True
5 False
dtype: bool
monte.str.split()
0 [Graham, Chapman]
1 [John, Cleese]
2 [Terry, Gilliam]
3 [Eric, Idle]
4 [Terry, Jones]
5 [Michael, Palin]
dtype: object
monte.str.extract('([A-Za-z]+)')
0 Graham
1 John
2 Terry
3 Eric
4 Terry
5 Michael
monte.str.findall(r'^[^AEIOU].*[^aeiou]$')
0 [Graham Chapman]
1 []
2 [Terry Gilliam]
3 []
4 [Terry Jones]
5 [Michael Palin]
dtype: object
monte.str[0:3]
0 Gra
1 Joh
2 Ter
3 Eri
4 Ter
5 Mic
dtype: object
monte.str.split().str.get(-1)
0 Chapman
1 Cleese
2 Gilliam
3 Idle
4 Jones
5 Palin
dtype: object
full_monte = pd.DataFrame({'name': monte,

'info': ['B|C|D', 'B|D', 'A|C', 'B|D', 'B|C',
'B|C|D']})
full_monte
name info
0 Graham Chapman B|C|D
1 John Cleese B|D
2 Terry Gilliam A|C
3 Eric Idle B|D
4 Terry Jones B|C
5 Michael Palin B|C|D
full_monte['info'].str.get_dummies('|')
A B C D
0 0 1 1 1
1 0 1 0 1
2 1 0 1 0
3 0 1 0 1
4 0 1 1 0
5 0 1 1 1
spice_list = ['salt', 'pepper', 'oregano', 'sage', 'parsley',

'rosemary', 'tarragon', 'thyme', 'paprika', 'cumin']
from datetime import datetime

datetime(year=2015, month=7, day=4)
datetime.datetime(2015, 7, 4, 0, 0)
from dateutil import parser

date = parser.parse("4th of July, 2015")
date
datetime.datetime(2015, 7, 4, 0, 0)
date.strftime('%A')
'Saturday'
import numpy as np
date = np.array('2015-07-04', dtype=np.datetime64)
date
array('2015-07-04', dtype='datetime64[D]')
date + np.arange(12)
array(['2015-07-04', '2015-07-05', '2015-07-06', '2015-07-07',

'2015-07-08', '2015-07-09', '2015-07-10', '2015-07-11',
'2015-07-12', '2015-07-13', '2015-07-14', '2015-07-15'],
dtype='datetime64[D]')
np.datetime64('2015-07-04')
numpy.datetime64('2015-07-04')
np.datetime64('2015-07-04 12:00')
numpy.datetime64('2015-07-04T12:00')
np.datetime64('2015-07-04 12:59:59.50', 'ns')
numpy.datetime64('2015-07-04T12:59:59.500000000')
import pandas as pd
date = pd.to_datetime("4th of July, 2015")
date
Timestamp('2015-07-04 00:00:00')
date.strftime('%A')
'Saturday'
date + pd.to_timedelta(np.arange(12), 'D')
DatetimeIndex(['2015-07-04', '2015-07-05', '2015-07-06', '2015-07-07',

'2015-07-08', '2015-07-09', '2015-07-10', '2015-07-11',
'2015-07-12', '2015-07-13', '2015-07-14', '2015-07-15'],
dtype='datetime64[ns]', freq=None)
index = pd.DatetimeIndex(['2014-07-04', '2014-08-04',

'2015-07-04', '2015-08-04'])
data = pd.Series([0, 1, 2, 3], index=index)
data
2014-07-04 0
2014-08-04 1
2015-07-04 2
2015-08-04 3
dtype: int64
data['2014-07-04':'2015-07-04']
2014-07-04 0
2014-08-04 1
2015-07-04 2
dtype: int64
data['2015']
2015-07-04 2
2015-08-04 3
dtype: int64
dates = pd.to_datetime([datetime(2015, 7, 3), '4th of July, 2015',

'2015-Jul-6', '07-07-2015', '20150708'])
dates
DatetimeIndex(['2015-07-03', '2015-07-04', '2015-07-06', '2015-07-07',

'2015-07-08'],
dtype='datetime64[ns]', freq=None)
dates.to_period('D')
PeriodIndex(['2015-07-03', '2015-07-04', '2015-07-06', '2015-07-07',

'2015-07-08'],
dtype='period[D]')
dates - dates[0]
TimedeltaIndex(['0 days', '1 days', '3 days', '4 days', '5 days'], dtype='timedelta64[ns]', freq=None)
pd.date_range('2015-07-03', '2015-07-10')
DatetimeIndex(['2015-07-03', '2015-07-04', '2015-07-05', '2015-07-06',

'2015-07-07', '2015-07-08', '2015-07-09', '2015-07-10'],
dtype='datetime64[ns]', freq='D')
pd.date_range('2015-07-03', periods=8)
DatetimeIndex(['2015-07-03', '2015-07-04', '2015-07-05', '2015-07-06',

'2015-07-07', '2015-07-08', '2015-07-09', '2015-07-10'],
dtype='datetime64[ns]', freq='D')
pd.date_range('2015-07-03', periods=8, freq='H')
DatetimeIndex(['2015-07-03 00:00:00', '2015-07-03 01:00:00',

'2015-07-03 02:00:00', '2015-07-03 03:00:00',
'2015-07-03 04:00:00', '2015-07-03 05:00:00',
'2015-07-03 06:00:00', '2015-07-03 07:00:00'],
dtype='datetime64[ns]', freq='H')
pd.period_range('2015-07', periods=8, freq='M')
PeriodIndex(['2015-07', '2015-08', '2015-09', '2015-10', '2015-11', '2015-12',

'2016-01', '2016-02'],
dtype='period[M]')
pd.timedelta_range(0, periods=10, freq='H')
TimedeltaIndex(['0 days 00:00:00', '0 days 01:00:00', '0 days 02:00:00',

'0 days 03:00:00', '0 days 04:00:00', '0 days 05:00:00',
'0 days 06:00:00', '0 days 07:00:00', '0 days 08:00:00',
'0 days 09:00:00'],
dtype='timedelta64[ns]', freq='H')
pd.timedelta_range(0, periods=9, freq="2H30T")
TimedeltaIndex(['0 days 00:00:00', '0 days 02:30:00', '0 days 05:00:00',

'0 days 07:30:00', '0 days 10:00:00', '0 days 12:30:00',
'0 days 15:00:00', '0 days 17:30:00', '0 days 20:00:00'],
dtype='timedelta64[ns]', freq='150T')
from pandas.tseries.offsets import BDay

pd.date_range('2015-07-01', periods=5, freq=BDay())
DatetimeIndex(['2015-07-01', '2015-07-02', '2015-07-03', '2015-07-06',

'2015-07-07'],
dtype='datetime64[ns]', freq='B')
import pandas as pd
nrows, ncols = 100000, 100
df1, df2, df3, df4 = (pd.DataFrame(rng.rand(nrows, ncols))
for i in range(4))
%timeit df1 + df2 + df3 + df4
110 ms ± 14.5 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
%timeit pd.eval('df1 + df2 + df3 + df4')
56.8 ms ± 11 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
np.allclose(df1 + df2 + df3 + df4,

pd.eval('df1 + df2 + df3 + df4'))
True
df1, df2, df3, df4, df5 = (pd.DataFrame(rng.randint(0, 1000, (100, 3)))

for i in range(5))
result1 = -df1 * df2 / (df3 + df4) - df5

result2 = pd.eval('-df1 * df2 / (df3 + df4) - df5')
np.allclose(result1, result2)
True
result1 = (df1 < df2) & (df2 <= df3) & (df3 != df4)
result2 = pd.eval('df1 < df2 <= df3 != df4')
True
result1 = (df1 < 0.5) & (df2 < 0.5) | (df3 < df4)
result2 = pd.eval('(df1 < 0.5) & (df2 < 0.5) | (df3 < df4)')
True
result3 = pd.eval('(df1 < 0.5) and (df2 < 0.5) or (df3 < df4)')
True
result1 = df2.T[0] + df3.iloc[1]

result2 = pd.eval('df2.T[0] + df3.iloc[1]')
True
df = pd.DataFrame(rng.rand(1000, 3), columns=['A', 'B', 'C'])

df.head()
A B C
0 0.375506 0.406939 0.069938
1 0.069087 0.235615 0.154374
2 0.677945 0.433839 0.652324
3 0.264038 0.808055 0.347197
4 0.589161 0.252418 0.557789
result1 = (df['A'] + df['B']) / (df['C'] - 1)

result2 = pd.eval("(df.A + df.B) / (df.C - 1)")
True
result3 = df.eval('(A + B) / (C - 1)')

True
df.head()
A B C
0 0.375506 0.406939 0.069938
1 0.069087 0.235615 0.154374
2 0.677945 0.433839 0.652324
3 0.264038 0.808055 0.347197
4 0.589161 0.252418 0.557789
df.eval('D = (A + B) / C', inplace=True)

df.head()
A B C D
0 0.375506 0.406939 0.069938 11.187620
1 0.069087 0.235615 0.154374 1.973796
2 0.677945 0.433839 0.652324 1.704344
3 0.264038 0.808055 0.347197 3.087857
4 0.589161 0.252418 0.557789 1.508776
df.eval('D = (A - B) / C', inplace=True)

df.head()
A B C D
column_mean = df.mean(1)
0 0.375506 0.406939 0.069938 -0.449425
result1 = df['A'] + column_mean
result2
1 =0.069087
df.eval('A + @column_mean')
0.235615 0.154374 -1.078728
2 0.677945 0.433839 0.652324 0.374209
True
3 0.264038 0.808055 0.347197 -1.566886
4 =0.589161
result1 df[(df.A 0.252418
< 0.5) & 0.557789 0.603708
(df.B < 0.5)]
result2 = pd.eval('df[(df.A < 0.5) & (df.B < 0.5)]')
True
result2 = df.query('A < 0.5 and B < 0.5')

True
Cmean = df['C'].mean()
result1 = df[(df.A < Cmean) & (df.B < Cmean)]
result2 = df.query('A < @Cmean and B < @Cmean')
True
x = df[(df.A < 0.5) & (df.B < 0.5)]
tmp1 = df.A < 0.5

tmp2 = df.B < 0.5
tmp3 = tmp1 & tmp2
x = df[tmp3]
df l b t

Pandas - Ipynb - Colaboratory

Uploaded by

Copyright:

Available Formats

Pandas - Ipynb - Colaboratory

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Pandas - Ipynb - Colaboratory

Uploaded by

Copyright:

Available Formats

11/30/23, 11:37 AM Pandas.

Aim: To practice pandas commands

data = pd.Series([0.25, 0.5, 0.75, 1.0])

array([0.25, 0.5 , 0.75, 1. ])

RangeIndex(start=0, stop=4, step=1)

data = pd.Series([0.25, 0.5, 0.75, 1.0],

data = pd.Series([0.25, 0.5, 0.75, 1.0],

population_dict = {'California': 38332521,

pd.Series(5, index=[100, 200, 300])

pd.Series({2:'a', 1:'b', 3:'c'})

pd.Series({2:'a', 1:'b', 3:'c'}, index=[3, 2])

area_dict = {'California': 423967, 'Texas': 695662, 'New York': 141297,

states = pd.DataFrame({'population': population,

California 38332521 423967

Texas 26448193 695662

New York 19651127 141297

Florida 19552860 170312

Illinois 12882135 149995

Index(['California', 'Texas', 'New York', 'Florida', 'Illinois'], dtype='object')

Index(['population', 'area'], dtype='object')

New York 19651127

data = [{'a': i, 'b': 2 * i}

pd.DataFrame([{'a': 1, 'b': 2}, {'b': 3, 'c': 4}])

California 38332521 423967

Texas 26448193 695662

New York 19651127 141297

Florida 19552860 170312

Illinois 12882135 149995

A = np.zeros(3, dtype=[('A', 'i8'), ('B', 'f8')])

ind = pd.Index([2, 3, 5, 7, 11])

Int64Index([2, 3, 5, 7, 11], dtype='int64')

Int64Index([2, 5, 11], dtype='int64')

print(ind.size, ind.shape, ind.ndim, ind.dtype)

indA = pd.Index([1, 3, 5, 7, 9])

indA & indB

Index(['a', 'b', 'c', 'd'], dtype='object')

[('a', 0.25), ('b', 0.5), ('c', 0.75), ('d', 1.0)]

data[(data > 0.3) & (data < 0.8)]

data = pd.Series(['a', 'b', 'c'], index=[1, 3, 5])

California 423967 38332521

Texas 695662 26448193

New York 141297 19651127

Florida 170312 19552860

Illinois 149995 12882135

data['density'] = data['pop'] / data['area']

area pop density

California 423967 38332521 90.413926

Texas 695662 26448193 38.018740

New York 141297 19651127 139.076746

Florida 170312 19552860 114.806121

Illinois 149995 12882135 85.883763

array([[4.23967000e+05, 3.83325210e+07, 9.04139261e+01],

California Texas New York Florida Illinois

area 4.239670e+05 6.956620e+05 1.412970e+05 1.703120e+05 1.499950e+05

pop 3.833252e+07 2.644819e+07 1.965113e+07 1.955286e+07 1.288214e+07

density 9.041393e+01 3.801874e+01 1.390767e+02 1.148061e+02 8.588376e+01

array([4.23967000e+05, 3.83325210e+07, 9.04139261e+01])

California 423967 38332521

Texas 695662 26448193