Python Numpy Tutorial #1

Numpy is the major library for scientific computing in Python.NumPy enriches the programming language Python with powerful data structures for efficient computation of multi-dimensional arrays and matrices. If you are familiar with Octave or Matlab, you will find this tutorial easy.

NB: Numpy can be imported using

import numpy as np

 Arrays: You can create an array as follows:

  a = np.array([1,2,3,4])  #creates a 1x 4  array

  b = np.array([[1,2,3],[1,2,3]]) #creates 2x3 array

Along with the array, some important parameters taken by np.array()  are:

   1. dtype: It helps you to pass the desired datatype of the array. The       permitted  datatypes are -> int8, int16, int32, int64, float16, float32, float64, complex64 and complex128. Int is for integers, float can store real numbers and complex can store complex numbers. The number represents the bit of data stored, for example, int16 represents a 16-bit int. You can pass the data type by :

 a = np.array([1,2,3,4] dtype = complex) 

You can create custom datatype using:

import numpy as np

student = np.dtype([('age','int32' ),('money','float32')])

a = np.array([('32','500.16'), ('45', '4000.25')], dtype = student)  

print a 

The output would be:

[(32,  500.16) (45, 4000.25)]

 You can view the type of your array using :

a.dtype 

where a is the array name. 

   2. ndmin: Specifies minimum dimension of the array. Use it as :

a = np.array([1,2,3], ndmin = 2)

It would create the array as :

 [[1 2 3]] 

It also allows you to create some special array such as:

a = np.zeros((2,2))  # Create an array of all zeros
b = np.ones((1,2))    # Create an array of all ones
c = np.full((2,2), 7)  # Create a constant array
d = np.eye(2)         # Create a 2x2 identity matrix
e = np.random.random((2,2))  # Create an array filled with random values

The ndmin of an array can view using:

a.ndmin

Array Indexing: Arrays can be indexed in several ways :

1. Individual elements: Individual elements can be indexed using :

import numpy as np
a = np.array([[1,2,3], [5,6,7], [9,10,11]])
a[0, 1]
#it will print the element at index 1 of 0th coloumn

2. Slicing :

import numpy as np
a = np.array([[1,2,3], [5,6,7], [9,10,11]])
b = a[:2, 1:3]
#it slices/ creates a subarray the array as
#[[2 3] [6 7]]
#taking the elements from index 1 to 3 of coloums 0 to 2

3.  Individual rows and columns can be accessed as :

import numpy as np
a = np.array([[1,2,3], [5,6,7], [9,10,11]])
a[0,:]
#it will display the 0th row

a[:,0]
#it will display the 0th column

4.  Two or more rows and columns can be  accessed as:

import numpy as np
a = np.array([[1,2,3], [5,6,7], [9,10,11]])
a[0:3,:]
#it will display from 0th row to 3rd row

a[:, 1:3]
#it will display the 0th column to 3rd coloumn

.
5. Array indexing with conditions :

import numpy as np
a = np.array([[1,2,3], [5,6,7], [9,10,11]])
a[a>5]
#returns a 1d array containing the values from a which are greater than a
#the condition specified can be >, <, >=, <=, =

The first part of the tutorial finishes her. Read the next part of the tutorial from here.