Analaysing Tabular Data
We are going to use a LIBRARY called numpy
In [84]:
import numpy
In [85]:
numpy.loadtxt(fname='data/weather-01.csv', delimiter = ',')
Out[85]:
Variables
In [86]:
weight_kg = 55
In [87]:
print (weight_kg)
In [88]:
print ('Weight in pounds:', weight_kg * 2.2)
In [89]:
weight_kg = 57.5
In [90]:
print ('New weight:', weight_kg * 2.2)
In [91]:
%whos
In [92]:
data = numpy.loadtxt(fname='data/weather-01.csv', delimiter = ',')
In [93]:
print (data)
In [94]:
print (type (data))
In [95]:
%whos
In [96]:
# Finding out the data type
print (data.dtype)
In [97]:
# Find out the shape
print (data.shape)
In [98]:
# This is 60 rows * 40 columns
In [99]:
# Getting a single mmuber out of the array
print ("First value in data:", data [0,0])
In [100]:
print ('A mimddle value:', data [30,20])
In [101]:
# 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
In [102]:
# We don't need to start slicing at 0
print (data [5:10, 7:15])
In [103]:
# We don't need to include Upper and Lower bounds
smallchunk = data [:3, 36:]
print (smallchunk)
In [104]:
# Arithmetic on Arrays
doublesmallchunk = smallchunk * 2.0
In [105]:
print (doublesmallchunk)
In [106]:
triplesmallchunk = smallchunk + doublesmallchunk
In [107]:
print (triplesmallchunk)
In [108]:
print (numpy.mean(data))
In [109]:
print (numpy.max(data))
In [110]:
print (numpy.min(data))
In [111]:
# Get a set of data for the first station
station_0 = data [0, :]
In [112]:
print (numpy.max(station_0))
In [113]:
# We dont need to create this 'temporary' array slices
# We can refer to what we call array axes
In [114]:
# axis = 0 gets the mean Down the column, so the mean tempreature
# for each recording period
print (numpy.mean(data, axis = 0))
In [115]:
# axis = 1 gets the mean across the row, so the mean tempreature
# for each recording period
print (numpy.mean(data, axis = 1))
In [116]:
# Do some simple Visulaisations
In [117]:
import matplotlib.pyplot
In [118]:
%matplotlib inline
In [119]:
image = matplotlib.pyplot.imshow(data)
In [120]:
%whos
In [121]:
# Let's look at the average tempreture over time
avg_temperature = numpy.mean(data, axis = 0)
In [122]:
avg_plot = matplotlib.pyplot.plot(avg_temperature)
In [123]:
# Task:
# Produce maximum and minimum plots of this data
# What do you think
In [124]:
avg_temperature_max = numpy.max(data, axis = 0)
In [125]:
avg_plot_max = matplotlib.pyplot.plot(avg_temperature_max)
In [126]:
avg_temperature_min = numpy.min(data, axis = 0)
In [128]:
avg_plot_min = matplotlib.pyplot.plot(avg_temperature_min)
In [130]:
avg_combine_plot = matplotlib.pyplot.plot(avg_temperature_min, avg_temperature_max)
In [ ]: