Next Exercise

Replace words with their abbreviations

• Modify the method column to have only the abbreviation of each method
• eg: instead of 'Radial Velocity', just make it RV and TR for 'Transit'

import numpy as np
import pandas as pd
import seaborn as sns

planets = sns.load_dataset('planets')

planets = pd.DataFrame(planets)

dfplanets = planets

dfplanets.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1035 entries, 0 to 1034
Data columns (total 6 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   method          1035 non-null   object 
 1   number          1035 non-null   int64  
 2   orbital_period  992 non-null    float64
 3   mass            513 non-null    float64
 4   distance        808 non-null    float64
 5   year            1035 non-null   int64  
dtypes: float64(3), int64(2), object(1)
memory usage: 48.6+ KB

dfplanets.method.unique()

array(['Radial Velocity', 'Imaging', 'Eclipse Timing Variations',
       'Transit', 'Astrometry', 'Transit Timing Variations',
       'Orbital Brightness Modulation', 'Microlensing', 'Pulsar Timing',
       'Pulsation Timing Variations'], dtype=object)

s = 'Radial Velocity'

s.split()

['Radial', 'Velocity']

[x[0] for x in s.split()]

['R', 'V']

"".join([x[0] for x in s.split()])

'RV'

s = 'Pulsation Timing Variations'

"".join([x[0] for x in s.split()])

'PTV'

apply the above procedure to all the unique elements in the dataframe

short_names = {}
for x in planets.method.unique():
    short_names[x] = "".join([x[0] for x in x.split()])

short_names

{'Astrometry': 'A',
 'Eclipse Timing Variations': 'ETV',
 'Imaging': 'I',
 'Microlensing': 'M',
 'Orbital Brightness Modulation': 'OBM',
 'Pulsar Timing': 'PT',
 'Pulsation Timing Variations': 'PTV',
 'Radial Velocity': 'RV',
 'Transit': 'T',
 'Transit Timing Variations': 'TTV'}

for i, r in planets.iterrows():
    planets.loc[i, 'short_method'] = short_names.get(r['method'], r['method'])

planets.head()

	method	number	orbital_period	mass	distance	year	short_method
0	Radial Velocity	1	269.300	7.10	77.40	2006	RV
1	Radial Velocity	1	874.774	2.21	56.95	2008	RV
2	Radial Velocity	1	763.000	2.60	19.84	2011	RV
3	Radial Velocity	1	326.030	19.40	110.62	2007	RV
4	Radial Velocity	1	516.220	10.50	119.47	2009	RV

planets.tail()

	method	number	orbital_period	mass	distance	year	short_method
1030	Transit	1	3.941507	NaN	172.0	2006	T
1031	Transit	1	2.615864	NaN	148.0	2007	T
1032	Transit	1	3.191524	NaN	174.0	2007	T
1033	Transit	1	4.125083	NaN	293.0	2008	T
1034	Transit	1	4.187757	NaN	260.0	2008	T

revise

s = "Radial Velocity"

s.split()

['Radial', 'Velocity']

p = s.split()

p

['Radial', 'Velocity']

p[0]

'Radial'

p[1]

'Velocity'

[x[0] for x in p]

['R', 'V']

"".join([x[0] for x in p])

'RV'

s = '-'
str = ['a', 'b','c']
s.join(str)

'a-b-c'

s = '-'
str1 = ['a', 'b','c']
str2 = ['1', '2', '3']
s.join(str1, str2)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-27-bb78c376e328> in <module>()
      2 str1 = ['a', 'b','c']
      3 str2 = ['1', '2', '3']
----> 4 s.join(str1, str2)

TypeError: join() takes exactly one argument (2 given)

planets.method.unique()

array(['Radial Velocity', 'Imaging', 'Eclipse Timing Variations',
       'Transit', 'Astrometry', 'Transit Timing Variations',
       'Orbital Brightness Modulation', 'Microlensing', 'Pulsar Timing',
       'Pulsation Timing Variations'], dtype=object)

s = 'Orbital Brightness Modulation'

s.split()

['Orbital', 'Brightness', 'Modulation']

s.split()[1]

'Brightness'

[x[0] for x in s.split()]

['O', 'B', 'M']

"".join(x[0] for x in s.split())

'OBM'

short_names = planets.method.unique()

print(x[i] for i in planets.method.unique())

<generator object <genexpr> at 0x7f4a5b2bde50>

print(short_names)

['Radial Velocity' 'Imaging' 'Eclipse Timing Variations' 'Transit'
 'Astrometry' 'Transit Timing Variations' 'Orbital Brightness Modulation'
 'Microlensing' 'Pulsar Timing' 'Pulsation Timing Variations']

short_names[1]

'Imaging'

short_names[2].split()

['Eclipse', 'Timing', 'Variations']

"".join([x[0] for x in short_names[5].split()])

'TTV'

• take an empty dictionary to accomodate both the long form and short forms
• take each element in the planets.method.unique() - say 's'
• split s to get first character of each word in s
• join each character

planets_dic = {}
for s in planets.method.unique():
    planets_dic[s] = "".join([x[0] for x in s.split()])

planets_dic

{'Astrometry': 'A',
 'Eclipse Timing Variations': 'ETV',
 'Imaging': 'I',
 'Microlensing': 'M',
 'Orbital Brightness Modulation': 'OBM',
 'Pulsar Timing': 'PT',
 'Pulsation Timing Variations': 'PTV',
 'Radial Velocity': 'RV',
 'Transit': 'T',
 'Transit Timing Variations': 'TTV'}

for i, r in planets.iterrows():
    planets.loc[i, "abbrev"] = planets_dic.get(r['method'], r['method'])

planets.head()

	method	number	orbital_period	mass	distance	year	abbrev
0	Radial Velocity	1	269.300	7.10	77.40	2006	RV
1	Radial Velocity	1	874.774	2.21	56.95	2008	RV
2	Radial Velocity	1	763.000	2.60	19.84	2011	RV
3	Radial Velocity	1	326.030	19.40	110.62	2007	RV
4	Radial Velocity	1	516.220	10.50	119.47	2009	RV

planets.tail()

	method	number	orbital_period	mass	distance	year	abbrev
1030	Transit	1	3.941507	NaN	172.0	2006	T
1031	Transit	1	2.615864	NaN	148.0	2007	T
1032	Transit	1	3.191524	NaN	174.0	2007	T
1033	Transit	1	4.125083	NaN	293.0	2008	T
1034	Transit	1	4.187757	NaN	260.0	2008	T

for i, r in planets.iterrows():
    planets.loc[i, "abbre"] = planets_dic.get(r['method'], r['method'])

planets.head()

	method	number	orbital_period	mass	distance	year	abbrev	abbre
0	Radial Velocity	1	269.300	7.10	77.40	2006	RV	RV
1	Radial Velocity	1	874.774	2.21	56.95	2008	RV	RV
2	Radial Velocity	1	763.000	2.60	19.84	2011	RV	RV
3	Radial Velocity	1	326.030	19.40	110.62	2007	RV	RV
4	Radial Velocity	1	516.220	10.50	119.47	2009	RV	RV

planets.drop('abbre', axis=1, inplace = True)

planets.head()

	method	number	orbital_period	mass	distance	year	abbrev
0	Radial Velocity	1	269.300	7.10	77.40	2006	RV
1	Radial Velocity	1	874.774	2.21	56.95	2008	RV
2	Radial Velocity	1	763.000	2.60	19.84	2011	RV
3	Radial Velocity	1	326.030	19.40	110.62	2007	RV
4	Radial Velocity	1	516.220	10.50	119.47	2009	RV

Pandas way of doing the above activity

• creating dictionary is common step

df_planets = sns.load_dataset('planets')

method_list = df_planets.method.unique()

method_list

array(['Radial Velocity', 'Imaging', 'Eclipse Timing Variations',
       'Transit', 'Astrometry', 'Transit Timing Variations',
       'Orbital Brightness Modulation', 'Microlensing', 'Pulsar Timing',
       'Pulsation Timing Variations'], dtype=object)

method_dic = {}
for i in method_list:
    method_dic[i] = "".join(x[0] for x in i.split())

method_dic

{'Astrometry': 'A',
 'Eclipse Timing Variations': 'ETV',
 'Imaging': 'I',
 'Microlensing': 'M',
 'Orbital Brightness Modulation': 'OBM',
 'Pulsar Timing': 'PT',
 'Pulsation Timing Variations': 'PTV',
 'Radial Velocity': 'RV',
 'Transit': 'T',
 'Transit Timing Variations': 'TTV'}

def method_shorts(s):
   return method_dic.get(s, s)

df_planets['short_method'] = df_planets['method'].apply(method_shorts)

df_planets

	method	number	orbital_period	mass	distance	year	short_method
0	Radial Velocity	1	269.300000	7.10	77.40	2006	RV
1	Radial Velocity	1	874.774000	2.21	56.95	2008	RV
2	Radial Velocity	1	763.000000	2.60	19.84	2011	RV
3	Radial Velocity	1	326.030000	19.40	110.62	2007	RV
4	Radial Velocity	1	516.220000	10.50	119.47	2009	RV
...	...	...	...	...	...	...	...
1030	Transit	1	3.941507	NaN	172.00	2006	T
1031	Transit	1	2.615864	NaN	148.00	2007	T
1032	Transit	1	3.191524	NaN	174.00	2007	T
1033	Transit	1	4.125083	NaN	293.00	2008	T
1034	Transit	1	4.187757	NaN	260.00	2008	T

1035 rows × 7 columns

Next Task

• count of planets discovered per method type