Consulting - Quality
Difference makes the DIFFERENCE
PANDAS - SERIES
class work
In [ ]:
import pandas as pd
import numpy as np
In [ ]:
s = pd.Series([0,1,1,2,3,5,8,13])
In [ ]:
print(s)
In [ ]:
s = pd.Series([0.0,1,1,2,3,5,8,13])
In [ ]:
print(s)
In [ ]:
s.values
Out[ ]:
In [ ]:
s.index
Out[ ]:
In [ ]:
print(s.index)
In [ ]:
for v in s.values: print(v)
In [ ]:
for i in s.index: print (i)
returns a tuple with values and indicies¶
In [ ]:
for item in zip(s.values, s.index): print (item)
In [ ]:
s[0]
Out[ ]:
In [ ]:
s[2]
Out[ ]:
In [ ]:
mercury = pd.Series([0.33, 57.9, 4222.6], ['mass', 'diameter', 'dayLength'])
In [ ]:
print(mercury)
pd.Series(data=None, index=None, dtype: ExtensionDtype | str | dtype | Type[str] | Type[float] | Type[int] | Type[complex] | Type[bool] | Type[object] | None = None, name=None, copy: bool = False, fastpath: bool = False) -> None¶
In [ ]:
print(mercury('mass'))
In [ ]:
print(mercury['mass'])
In [ ]:
print(mercury['dayLength'])
In [ ]:
mercury.mass
Out[ ]:
In [ ]:
mercury.dayLength
Out[ ]:
In [ ]:
arr = np.random.randint(0, 10, 10)
In [ ]:
print(arr)
In [ ]:
arr
Out[ ]:
In [ ]:
rand_series = pd.Series(arr)
In [ ]:
print(rand_series)
In [ ]:
ind = np.arange(10, 20)
In [ ]:
rand_seriess = pd.Series(arr, ind)
In [ ]:
print(rand_seriess)
In [ ]:
## mercury = pd.Series([0.33, 57.9, 4222.6], ['mass', 'diameter', 'dayLength'])
d = {}
d['mass'] = 0.33
d['diameter'] = 57.9
d['dayLength'] = 4222.6
In [ ]:
mercury = pd.Series(d)
In [ ]:
print(mercury)
In [ ]:
mercury = pd.Series(d, index = ['mass', 'diameter'])
In [ ]:
print(mercury)
In [ ]:
mercury = pd.Series(d, index = ['mass', 'diameter', 'dayLength'])
In [ ]:
print(mercury)
In [ ]:
import pandas as pd
import numpy as np
In [ ]:
s = pd.Series([0.0,1,1,2,3,5,8,13], index=[1,2,3,4,5,6,7,8])
In [ ]:
print(s)
In [ ]:
s.loc[4]
Out[ ]:
In [ ]:
s.iloc[4]
Out[ ]:
In [ ]:
s.iloc[0]
Out[ ]:
the following code results in an error because, loc looks for zero and doesn't find it.¶
In [ ]:
s.loc[0]
In [ ]:
mercury.iloc[0]
Out[ ]:
In [ ]:
mercury.loc['mass']
Out[ ]:
In [ ]:
mercury.iloc[-1]
Out[ ]:
In [ ]:
mercury.iloc[0:2] # 2 is exclusive
Out[ ]:
In [ ]:
mercury.iloc[:2]
Out[ ]:
In [ ]:
mercury.iloc[2:]
Out[ ]:
In [ ]:
mercury.loc['dayLength']
Out[ ]:
Simple operations with Series¶
In [ ]:
mass = pd.Series([0.33, 4.87, 5.97, 0.642, 1898, 568, 86.8, 102, 0.0146],
index=['Mercury', 'Venus', 'Earth', 'Mars', 'Jupiter', 'Saturn', 'Uranus', 'Neptune', 'Pluto'])
In [ ]:
print(mass)
In [ ]:
mass.iloc[3:]
Out[ ]:
In [ ]:
mass.iloc[1]
Out[ ]:
In [ ]:
mass.loc['Earth']
Out[ ]:
In [ ]:
mass['Earth']
Out[ ]:
In [ ]:
mass['Earth':'Jupiter'] # here Jupiter is inclusive, unlike lists being exclusive
Out[ ]:
In [ ]:
mass.iloc[2:5]
Out[ ]:
In [ ]:
print(mass)
In [ ]:
mass > 100
Out[ ]:
In [ ]:
mass[mass > 100]
Out[ ]:
In [ ]:
mass_gr_100 = mass[mass > 100]
In [ ]:
print(mass_gr_100)
In [ ]:
mass[(mass > 100) & (mass < 1000)]
Out[ ]:
standard basic operations are applicable here... like any other numpy array¶
In [ ]:
mass * 2
Out[ ]:
In [ ]:
mass / 10
Out[ ]:
In [ ]:
np.mean(mass)
Out[ ]:
In [ ]:
np.median(mass)
Out[ ]:
In [ ]:
np.amin(mass)
Out[ ]:
In [ ]:
np.amax(mass)
Out[ ]:
In [ ]:
mass + mass
Out[ ]:
In [ ]:
big_mass = mass[(mass > 100)]
In [ ]:
big_mass
Out[ ]:
In [ ]:
new_mass = mass + big_mass
In [ ]:
new_mass
Out[ ]:
In [ ]:
pd.isnull(new_mass)
Out[ ]:
In [ ]:
new_mass[~pd.isnull(new_mass)]
Out[ ]:
to add another element to the existing series...¶
In [ ]:
mass['Moon'] = 0.7346
In [ ]:
mass
Out[ ]:
In [ ]:
mass.drop(['Pluto'])
Out[ ]:
In [ ]:
mass
Out[ ]:
In [ ]:
mass.drop(['Moon'], inplace=True)
In [ ]:
mass
Out[ ]:
Collect number for diameters of these planets and store it in a series object. Then given the two series objects mass and diamter, compute the density of each planet¶
- density equals mass over volume (d = m/v):
- volume v = 4/1 pi r cube
In [ ]:
print(0.330 * 4879)
In [ ]:
diameter = pd.Series([4879, 120104, 12756, 6792, 142984, 120536, 51118, 49528, 2376],
index=['Mercury', 'Venus', 'Earth', 'Mars', 'Jupiter', 'Saturn', 'Uranus', 'Neptune', 'Pluto'])
In [ ]:
mass
Out[ ]:
In [ ]:
diameter
Out[ ]:
In [ ]:
radius = diameter / 2
In [ ]:
print(radius)
In [ ]:
volume = 4/3 * ((3.14) * diamter ** 3)
In [ ]:
volume
Out[ ]:
In [ ]:
density = mass / volume
In [ ]:
density
Out[ ]:
In [ ]:
dnsity = mass / ((4/3) * ((3.14) * radius ** 3))
In [ ]:
dnsity
Out[ ]:
working with Nifty dataset¶
In [ ]:
nift = pd.read_csv("/content/nifty.csv", index_col = 0).iloc[:,0]
In [ ]:
nift.head()
Out[ ]:
In [ ]:
nift.tail()
Out[ ]:
In [ ]:
data = [0,1,1,2,3,5,8,13,21]
s = pd.Series(data)
b = s.diff()
print(b.iloc[5])
In [ ]:
s = pd.Series("a", index=[1,2,3,4])
print(s.loc[2])
In [2]:
!pip install nbconvert
In [ ]: