numpy.ipynb

Kernel: Python 2

NumPy

Credits: Forked from Parallel Machine Learning with scikit-learn and IPython by Olivier Grisel

• NumPy Arrays, dtype, and shape

• Common Array Operations

• Reshape and Update In-Place

• Combine Arrays

• Create Sample Data

import numpy as np

NumPy Arrays, dtypes, and shapes

a = np.array([1, 2, 3])
print(a)
print(a.shape)
print(a.dtype)

[1 2 3]
(3,)
int64

b = np.array([[0, 2, 4], [1, 3, 5]])
print(b)
print(b.shape)
print(b.dtype)

[[0 2 4]
 [1 3 5]]
(2, 3)
int64

np.zeros(5)

array([ 0.,  0.,  0.,  0.,  0.])

np.ones(shape=(3, 4), dtype=np.int32)

array([[1, 1, 1, 1],
       [1, 1, 1, 1],
       [1, 1, 1, 1]], dtype=int32)

Common Array Operations

c = b * 0.5
print(c)
print(c.shape)
print(c.dtype)

[[ 0.   1.   2. ]
 [ 0.5  1.5  2.5]]
(2, 3)
float64

d = a + c
print(d)

[[ 1.   3.   5. ]
 [ 1.5  3.5  5.5]]

d[0]

array([ 1.,  3.,  5.])

d[0, 0]

1.0

d[:, 0]

array([ 1. ,  1.5])

d.sum()

19.5

d.mean()

3.25

d.sum(axis=0)

array([  2.5,   6.5,  10.5])

d.mean(axis=1)

array([ 3. ,  3.5])

Reshape and Update In-Place

e = np.arange(12)
print(e)

[ 0  1  2  3  4  5  6  7  8  9 10 11]

# f is a view of contents of e
f = e.reshape(3, 4)
print(f)

[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]

# Set values of e from index 5 onwards to 0
e[5:] = 0
print(e)

[0 1 2 3 4 0 0 0 0 0 0 0]

# f is also updated
f

array([[0, 1, 2, 3],
       [4, 0, 0, 0],
       [0, 0, 0, 0]])

# OWNDATA shows f does not own its data
f.flags

  C_CONTIGUOUS : True
  F_CONTIGUOUS : False
  OWNDATA : False
  WRITEABLE : True
  ALIGNED : True
  UPDATEIFCOPY : False

Combine Arrays

a

array([1, 2, 3])

b

array([[0, 2, 4],
       [1, 3, 5]])

d

array([[ 1. ,  3. ,  5. ],
       [ 1.5,  3.5,  5.5]])

np.concatenate([a, a, a])

array([1, 2, 3, 1, 2, 3, 1, 2, 3])

# Use broadcasting when needed to do this automatically
np.vstack([a, b, d])

array([[ 1. ,  2. ,  3. ],
       [ 0. ,  2. ,  4. ],
       [ 1. ,  3. ,  5. ],
       [ 1. ,  3. ,  5. ],
       [ 1.5,  3.5,  5.5]])

# In machine learning, useful to enrich or 
# add new/concatenate features with hstack
np.hstack([b, d])

array([[ 0. ,  2. ,  4. ,  1. ,  3. ,  5. ],
       [ 1. ,  3. ,  5. ,  1.5,  3.5,  5.5]])

Create Sample Data

%matplotlib inline

import pylab as plt
import seaborn

seaborn.set()

# Create evenly spaced numbers over the specified interval
x = np.linspace(0, 2, 10)
plt.plot(x, 'o-');
plt.show()

# Create sample data, add some noise
x = np.random.uniform(1, 100, 1000)
y = np.log(x) + np.random.normal(0, .3, 1000)

plt.scatter(x, y)
plt.show()