numpy_1

import numpy

world_alcohol = numpy.genfromtxt("world_alcohol.txt", delimiter=",")
print(type(world_alcohol))
print(world_alcohol)

<class 'numpy.ndarray'>
[[      nan       nan       nan       nan       nan]
 [1.986e+03       nan       nan       nan 0.000e+00]
 [1.986e+03       nan       nan       nan 5.000e-01]
 ...
 [1.987e+03       nan       nan       nan 7.500e-01]
 [1.989e+03       nan       nan       nan 1.500e+00]
 [1.985e+03       nan       nan       nan 3.100e-01]]

#The numpy.array() function can take a list or list of lists as input. When we input a list, we get a one-dimensional array as a result:
vector = numpy.array([5, 10, 15, 20])
#When we input a list of lists, we get a matrix as a result:
matrix = numpy.array([[5, 10, 15], [20, 25, 30], [35, 40, 45]])
print (vector)
print (matrix)

[ 5 10 15 20]
[[ 5 10 15]
 [20 25 30]
 [35 40 45]]

#We can use the ndarray.shape property to figure out how many elements are in the array
vector = numpy.array([1, 2, 3, 4])
print(vector.shape)
#For matrices, the shape property contains a tuple with 2 elements.
matrix = numpy.array([[5, 10, 15], [20, 25, 30]])
print(matrix.shape)

(4,)
(2, 3)

#Each value in a NumPy array has to have the same data type
#NumPy will automatically figure out an appropriate data type when reading in data or converting lists to arrays. 
#You can check the data type of a NumPy array using the dtype property.
numbers = numpy.array([1, 2, 3, 4])
numbers.dtype

dtype('int32')

#When NumPy can't convert a value to a numeric data type like float or integer, it uses a special nan value that stands for Not a Number
#nan is the missing data
#1.98600000e+03 is actually 1.986 * 10 ^ 3
world_alcohol

array([[             nan,              nan,              nan,
                     nan,              nan],
       [  1.98600000e+03,              nan,              nan,
                     nan,   0.00000000e+00],
       [  1.98600000e+03,              nan,              nan,
                     nan,   5.00000000e-01],
       ..., 
       [  1.98700000e+03,              nan,              nan,
                     nan,   7.50000000e-01],
       [  1.98900000e+03,              nan,              nan,
                     nan,   1.50000000e+00],
       [  1.98500000e+03,              nan,              nan,
                     nan,   3.10000000e-01]])

world_alcohol = numpy.genfromtxt("world_alcohol.txt", delimiter=",",
                                 dtype="U75", skip_header=1)
print(world_alcohol)

[['Year' 'WHO region' 'Country' 'Beverage Types' 'Display Value']
 ['1986' 'Western Pacific' 'Viet Nam' 'Wine' '0']
 ['1986' 'Americas' 'Uruguay' 'Other' '0.5']
 ...
 ['1987' 'Africa' 'Malawi' 'Other' '0.75']
 ['1989' 'Americas' 'Bahamas' 'Wine' '1.5']
 ['1985' 'Africa' 'Malawi' 'Spirits' '0.31']]

uruguay_other_1986 = world_alcohol[1,4]
third_country = world_alcohol[2,2]
print(world_alcohol[0,2])

Country

vector = numpy.array([5, 10, 15, 20])
print(vector[0:3])  

[ 5 10 15]

matrix = numpy.array([
                    [5, 10, 15], 
                    [20, 25, 30],
                    [35, 40, 45]
                 ])
print(matrix[:,1])

[10 25 40]

matrix = numpy.array([
                    [5, 10, 15], 
                    [20, 25, 30],
                    [35, 40, 45]
                 ])
print(matrix[:,0:2])

[[ 5 10]
 [20 25]
 [35 40]]

matrix = numpy.array([
                    [5, 10, 15], 
                    [20, 25, 30],
                    [35, 40, 45]
                 ])
print(matrix[1:3,0:2])

[[20 25]
 [35 40]]