Analysing tabular data

We are going to use a LIBRARY called numpy


In [1]:
import numpy

In [2]:
numpy.loadtxt(fname = 'data/weather-01.csv',delimiter = ',')


Out[2]:
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.]])

Variables


In [3]:
weight_kg = 55

In [4]:
print (weight_kg)


55

In [5]:
print ('Weight in pounds:', weight_kg * 2.2)


Weight in pounds: 121.00000000000001

In [6]:
weight_kg = 57.5

In [7]:
print ('New Weight: ',weight_kg*2.2)


New Weight:  126.50000000000001

In [8]:
%whos


Variable    Type      Data/Info
-------------------------------
numpy       module    <module 'numpy' from '/Us<...>kages/numpy/__init__.py'>
weight_kg   float     57.5

In [9]:
data = numpy.loadtxt(fname = 'data/weather-01.csv',delimiter = ',')

In [10]:
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 [12]:
print(type(data))


<class 'numpy.ndarray'>

In [13]:
%whos


Variable    Type       Data/Info
--------------------------------
data        ndarray    60x40: 2400 elems, type `float64`, 19200 bytes
numpy       module     <module 'numpy' from '/Us<...>kages/numpy/__init__.py'>
weight_kg   float      57.5

In [14]:
# Finding out the data type
print (data.dtype)


float64

In [15]:
# Find out the shape
print(data.shape)


(60, 40)

In [16]:
# This is 60 rows by 40 columns

In [17]:
# getting a single number out of the array
print ("First value in data: ", data [0, 0])


First value in data:  0.0

In [18]:
print ('a middle value: ', data[30, 20])


a middle value:  13.0

In [19]:
# Lets get the first 10 columns for the first 4 rows
print (data[0:4,0:10]) 
# index says start at 0 and go up to but dont include 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 [20]:
# we dont need to start sices at zero
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 [21]:
# we dont 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 [22]:
# aritmetic on arrays
doublesmallchunk = smallchunk * 2.0

In [23]:
print(doublesmallchunk)


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

In [24]:
triplesmallchunk = smallchunk + doublesmallchunk

In [25]:
print(triplesmallchunk)


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

In [26]:
print(numpy.mean(data))


6.14875

In [27]:
print(numpy.mean(triplesmallchunk))


3.5

In [28]:
print(numpy.max(data))


20.0

In [29]:
print(numpy.min(data))


0.0

In [30]:
# get a set of data from the first station
station_0 = data [0, :]

In [31]:
print (numpy.max(station_0))


18.0

In [32]:
# We dont need to create 'temporary' array slices
# We can refer to what we call array axes

In [35]:
# 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 [36]:
# axis  = 0 gets the mean across each column , 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 [37]:
# Do some simple visulisations

In [38]:
import matplotlib.pyplot

In [39]:
%matplotlib inline

In [40]:
image = matplotlib.pyplot.imshow(data)



In [41]:
# let's look at the average temperature over time
avg_temperature = numpy.mean(data,axis =0)

In [42]:
avg_plot = matplotlib.pyplot.plot(avg_temperature)



In [43]:
min_temperature = numpy.min(data,axis = 0)
max_temperature = numpy.max(data,axis = 0)

In [44]:
min_plot = matplotlib.pyplot.plot(min_temperature)



In [45]:
max_plot = matplotlib.pyplot.plot(max_temperature)



In [46]:
avg_plot = matplotlib.pyplot.plot(avg_temperature)
max_plot = matplotlib.pyplot.plot(max_temperature)
min_plot = matplotlib.pyplot.plot(min_temperature)



In [ ]: