In [26]:

    

import numpy


    

In [27]:

    

numpy.loadtxt(fname='data/weather-01.csv', delimiter = ',')


    

    
Out[27]:





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

In [28]:

    

numpy.loadtxt(fname='data/weather-01.csv', delimiter = ',')


    

    
Out[28]:





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

In [29]:

    

weight_kg = 55


    

In [30]:

    

print (weight_kg)


    

    




55

In [31]:

    

print ('Weight in pounds: ', weight_kg * 2.2)


    

    




Weight in pounds:  121.00000000000001

In [32]:

    

weight_kg = 57.5


    

In [33]:

    

print ('New weight: ', weight_kg * 2.2)


    

    




New weight:  126.50000000000001

In [34]:

    

%whos


    

    




Variable     Type       Data/Info
---------------------------------
data         ndarray    60x40: 2400 elems, type `float64`, 19200 bytes
numpy        module     <module 'numpy' from 'C:\<...>ges\\numpy\\__init__.py'>
smallchunk   ndarray    3x4: 12 elems, type `float64`, 96 bytes
weight_kg    float      57.5

In [35]:

    

data = numpy.loadtxt(fname='data/weather-01.csv', delimiter = ',')


    

In [36]:

    

print (data)


    

    




[[ 0.  0.  1. ...,  3.  0.  0.]
 [ 0.  1.  2. ...,  1.  0.  1.]
 [ 0.  1.  1. ...,  2.  1.  1.]
 ..., 
 [ 0.  1.  1. ...,  1.  1.  1.]
 [ 0.  0.  0. ...,  0.  2.  0.]
 [ 0.  0.  1. ...,  1.  1.  0.]]

In [37]:

    

print (type(data))


    

    




<class 'numpy.ndarray'>

In [38]:

    

%whos


    

    




Variable     Type       Data/Info
---------------------------------
data         ndarray    60x40: 2400 elems, type `float64`, 19200 bytes
numpy        module     <module 'numpy' from 'C:\<...>ges\\numpy\\__init__.py'>
smallchunk   ndarray    3x4: 12 elems, type `float64`, 96 bytes
weight_kg    float      57.5

In [39]:

    

# Finding out the data type
print (data.dtype)


    

    




float64

In [40]:

    

# Find out the shape
print (data.shape)


    

    




(60, 40)

In [41]:

    

# This is 60 rows * 40 columns


    

In [42]:

    

# Getting a single number out of the array
print ("First value in data: ", data [0, 0])


    

    




First value in data:  0.0

In [43]:

    

print ('A middle vaule: ', data[30, 20])


    

    




A middle vaule:  13.0

In [44]:

    

# Lets get the first 10 columns for the first 4 rows
print (data[0:4, 0:10])
# Start at index 0 and go up to BUT NOT INCLUDING index 4


    

    




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

In [45]:

    

# We don't need to start slicing at 0
print (data[5:10, 7:15])


    

    




[[  1.   6.   4.   7.   6.   6.   9.   9.]
 [  5.   5.   8.   6.   5.  11.   9.   4.]
 [  3.   5.   3.   7.   8.   8.   5.  10.]
 [  5.   5.   8.   2.   4.  11.  12.  10.]
 [  3.   5.   8.   6.   8.  12.   5.  13.]]

In [46]:

    

# We don't even need to include the UPPER and LOWER bounds
smallchunk = data [:3, 36:]
print (smallchunk)


    

    




[[ 2.  3.  0.  0.]
 [ 1.  1.  0.  1.]
 [ 2.  2.  1.  1.]]

In [47]:

    

# We don't even need to include the UPPER and LOWER bounds
smallchunk =data [:3, 36:]
print (smallchunk)


    

    




[[ 2.  3.  0.  0.]
 [ 1.  1.  0.  1.]
 [ 2.  2.  1.  1.]]

In [48]:

    

# Arithmetic on arrays
doublesmallchunk = smallchunk * 2.0


    

In [49]:

    

print (doublesmallchunk)


    

    




[[ 4.  6.  0.  0.]
 [ 2.  2.  0.  2.]
 [ 4.  4.  2.  2.]]

In [50]:

    

triplesmallchunk = smallchunk + doublesmallchunk


    

In [51]:

    

print (triplesmallchunk)


    

    




[[ 6.  9.  0.  0.]
 [ 3.  3.  0.  3.]
 [ 6.  6.  3.  3.]]

In [52]:

    

print (numpy.mean(data))


    

    




6.14875

In [53]:

    

print (numpy.min(data))


    

    




0.0

In [54]:

    

# Get a set of data fro the first station
station_0 = data [0, :]


    

In [55]:

    

print (numpy.max(station_0))


    

    




18.0

In [56]:

    

# We don't need to create ' tempory' array slices
# We can refer to what we call array axes


    

In [57]:

    

# axis = 0 gets the mean DOWN each column, so the mean temperature 
# for each recording period
print (numpy.mean(data, axis = 0))


    

    




[  0.           0.45         1.11666667   1.75         2.43333333   3.15
   3.8          3.88333333   5.23333333   5.51666667   5.95         5.9
   8.35         7.73333333   8.36666667   9.5          9.58333333
  10.63333333  11.56666667  12.35        13.25        11.96666667
  11.03333333  10.16666667  10.           8.66666667   9.15         7.25
   7.33333333   6.58333333   6.06666667   5.95         5.11666667   3.6
   3.3          3.56666667   2.48333333   1.5          1.13333333
   0.56666667]

In [58]:

    

# axis = 0 gets the mean ACROSSS each row, so the mean temperature 
# for each station for all periods
print (numpy.mean(data, axis = 1))


    

    




[ 5.45   5.425  6.1    5.9    5.55   6.225  5.975  6.65   6.625  6.525
  6.775  5.8    6.225  5.75   5.225  6.3    6.55   5.7    5.85   6.55
  5.775  5.825  6.175  6.1    5.8    6.425  6.05   6.025  6.175  6.55
  6.175  6.35   6.725  6.125  7.075  5.725  5.925  6.15   6.075  5.75
  5.975  5.725  6.3    5.9    6.75   5.925  7.225  6.15   5.95   6.275  5.7
  6.1    6.825  5.975  6.725  5.7    6.25   6.4    7.05   5.9  ]

In [59]:

    

# Do some simple visualisations


    

In [60]:

    

import matplotlib.pyplot


    

In [61]:

    

%matplotlib inline


    

In [62]:

    

image = matplotlib.pyplot.imshow(data)


    

In [63]:

    

# Let's take a look at the average temperature over time
avg_temperature = numpy.mean(data, axis = 0)


    

In [64]:

    

avg_plot = matplotlib.pyplot.plot(avg_temperature)


    

In [65]:

    

avg_plot = matplotlib.pyplot.plot(avg_temperature)
max_plot = matplotlib.pyplot.plot(max_temperature)
min_plot = matplotlib.pyplot.plot(min_temperature)


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-65-2033bfed1b05> in <module>()
      1 avg_plot = matplotlib.pyplot.plot(avg_temperature)
----> 2 max_plot = matplotlib.pyplot.plot(max_temperature)
      3 min_plot = matplotlib.pyplot.plot(min_temperature)

NameError: name 'max_temperature' is not defined





    

In [66]:

    

max_temperature = numpy.max(data, axis = 0)


    

In [67]:

    

min_temperature = numpy.min(data, axis = 0)


    

In [68]:

    

avg_plot = matplotlib.pyplot.plot(avg_temperature)
max_plot = matplotlib.pyplot.plot(max_temperature)
min_plot = matplotlib.pyplot.plot(min_temperature)


    

In [ ]: