Analysing tabular data

We are going to use a LIBRARY called numpy



In [1]:

    
import numpy



In [6]:

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









    Out[6]:





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 [3]:

    
!ls









    



01-analysing-data.ipynb
Untitled.ipynb
data
data.zip



In [4]:

    
!ls data









    



__MACOSX
data



In [5]:

    
!ls data/data









    



small-01.csv
small-02.csv
small-03.csv
weather-01.csv
weather-02.csv
weather-03.csv
weather-04.csv
weather-05.csv
weather-06.csv
weather-07.csv
weather-08.csv
weather-09.csv
weather-10.csv
weather-11.csv
weather-12.csv

Variables



In [7]:

    
weight_kg = 55



In [8]:

    
print (weight_kg)



In [9]:

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









    



Weight in pounds: 121.00000000000001



In [10]:

    
weight_kg = 57.5



In [11]:

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









    



New weight: 126.50000000000001



In [12]:

    
%whos









    



Variable    Type      Data/Info
-------------------------------
numpy       module    <module 'numpy' from 'C:\<...>ges\\numpy\\__init__.py'>
weight_kg   float     57.5



In [13]:

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



In [14]:

    
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 [15]:

    
print (type(data))









    



<class 'numpy.ndarray'>



In [16]:

    
%whos









    



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



In [17]:

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









    



float64



In [18]:

    
# Find out the shape
print(data.shape)



In [19]:

    
# This is 60 rows * 40 columns



In [21]:

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









    



First value in data: 0.0



In [23]:

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









    



A middle value: 13.0



In [24]:

    
# 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 [25]:

    
# 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 [26]:

    
# 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 [27]:

    
# Arithmetic on array 
doublesmallchunk = small chunk * 2.0









    



  File "<ipython-input-27-32655b684dbb>", line 2
    doublesmallchunk = small chunk * 2.0
                                 ^
SyntaxError: invalid syntax



In [28]:

    
doublesmallchunk = smallchunk * 2.0



In [29]:

    
print doublesmallchunk









    



  File "<ipython-input-29-0e0009a1b6ea>", line 1
    print doublesmallchunk
                         ^
SyntaxError: Missing parentheses in call to 'print'



In [30]:

    
print(doublesmallchunk)









    



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



In [31]:

    
triplesmallchunk = smallchunk + doublesmallchunk



In [32]:

    
print (triplesmallchunk)









    



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



In [33]:

    
print (numpy.mean(data))



In [34]:

    
print (numpy.max(data))



In [35]:

    
print (numpy.min(data))

0.0



In [36]:

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



In [37]:

    
print (numpy.max(station_0))



In [38]:

    
# We don't neet to create 'temporary' array slices
# We can refert to what we call array axes



In [39]:

    
print (numpy.mean(data, axis = 0)









    



  File "<ipython-input-39-bfb4915e7437>", line 1
    print (numpy.mean(data, axis = 0)
                                     ^
SyntaxError: unexpected EOF while parsing



In [40]:

    
# axis = 0 gets the mean DOWN each column, so the mean temperatures for each recording time 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 [41]:

    
# axis = 1 gets the mean ACROSS each row, so the mean temperature for each station across all time 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 [42]:

    
# Do some simple visualisations



In [43]:

    
import matplotlib.pyplot



In [44]:

    
%matplotlib inline



In [45]:

    
image = matplotlib.pyplot.imshow(data)



In [46]:

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









    



  File "<ipython-input-46-c04d750f3bba>", line 2
    avg_temperature = numpy.mean(data, axis 0)
                                            ^
SyntaxError: invalid syntax



In [47]:

    
avg_temperature = numpy.mean(data, axis = 0)



In [48]:

    
avg_plot= matplotlib.pyplot.plot(avg_temperature)

Task: produce max and min plots of this data - conclusions



In [49]:

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



In [50]:

    
print max_temperature









    



  File "<ipython-input-50-6fb9a0a3183e>", line 1
    print max_temperature
                        ^
SyntaxError: Missing parentheses in call to 'print'



In [51]:

    
print (max_temperature)









    



[  0.   1.   2.   3.   4.   5.   6.   7.   8.   9.  10.  11.  12.  13.  14.
  15.  16.  17.  18.  19.  20.  19.  18.  17.  16.  15.  14.  13.  12.  11.
  10.   9.   8.   7.   6.   5.   4.   3.   2.   1.]



In [52]:

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



In [53]:

    
max_temperature plot= matplotlib.pyplot.plot(max_temperature)









    



  File "<ipython-input-53-b827fc544201>", line 1
    max_temperature plot= matplotlib.pyplot.plot(max_temperature)
                       ^
SyntaxError: invalid syntax



In [54]:

    
max_plot = matplotlib.pyplot.plot(max_temperature)



In [55]:

    
min_plot = matplotlib.pyplot.plot(min_temperature)



In [56]:

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



In [ ]: