This is a project to determine the average diameter of planets in the solar system.

In [1]:

# Average diameter of planets in the solar system.

In [2]:

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

In [3]:

# Reading the file.
data = pd.read_csv('planets.csv.txt', usecols= [0, 1, 2]) 
data

Out[3]:

	planet	mass	diameter
0	Mercury	0.3300	4879
1	Venus	4.8700	12104
2	Earth	5.9700	12756
3	Mars	0.6420	6792
4	Jupiter	1898.0000	142984
5	Saturn	568.0000	120536
6	Uranus	86.8000	51118
7	Neptune	102.0000	49528
8	Pluto	0.0146	2370

In [4]:

# Extracting the information that we need.
diameters = np.array(data['diameter'])
planets = np.array(data['planet'])
print(planets)
print(diameters)

['Mercury' 'Venus' 'Earth' 'Mars' 'Jupiter' 'Saturn' 'Uranus' 'Neptune'
 'Pluto']
[  4879  12104  12756   6792 142984 120536  51118  49528   2370]

In [5]:

# Computing a variaty of summary statistics:
print("Mean diameter: ", diameters.mean())
print("Standard deviation:", diameters.std())
print("Minimum diameter: ", diameters.min())
print("Maximum diameter: ", diameters.max())

Mean diameter:  44785.22222222222
Standard deviation: 49858.41537299569
Minimum diameter:  2370
Maximum diameter:  142984

In [6]:

# In each case, the aggregation operation reduced the entire array to a single summarizing value, 
# giving the information about the distribution of values.

In [7]:

# Computing quantiles:
print("25th percentile: ", np.percentile(diameters, 25))
print("Median: ", np.median(diameters))
print("75th percentile: ", np.percentile(diameters, 75))

25th percentile:  6792.0
Median:  12756.0
75th percentile:  51118.0

In [8]:

# We can see that the median diameter of the planets in the solar system, is 12756.0 km(kilometers). 

In [9]:

# Visualizing the data:

In [10]:

import matplotlib.pyplot as plt

In [11]:

plt.style.use('fivethirtyeight') # Set the plot style.

plt.figure(figsize=(14, 8))
plt.hist(diameters)
plt.title('Diameter Distribution of planets in the solar system')
plt.xlabel('diameter (km)')
plt.ylabel('number')

plt.show()