In [ ]:

    

%matplotlib inline
import matplotlib.pyplot as plt


    

In [ ]:

    

plt.plot([2,4,6,9],[1,4,9,16], 'ro')
plt.axis([0, 10, 0, 20])
plt.show()


    

In [ ]:

    

fig = plt.figure()  # create an empty figure with no axes
fig, ax = plt.subplots(2, 2)  # a figure with a 2x2 grid of Axes


    

In [ ]:

    

# define data as lists
x1 = [2,4,6,8]
y1 = [5.5,7,2,4]
x2 = [4,6,8,10,12,14]
y2 = [-12,-14,-7,-12,-3.3,-1]
#let's draw the first line
# if no x-value is given an incrementing index, beginning from zero, will be used
plt.plot(y1)

#draw x, y plot
#plt.plot(x1,y1)

#draw two lines in one plot
#plt.plot(x1,y1,x2,y2)

plt.show()


    

In [ ]:

    

#-g : line in green 
plt.plot(y1,'-g')

#ro- : red circle with line
plt.plot(x1,y1,'ro-')

#g* : star symbols in green
plt.plot(x1,y1,'ro-',x2,y2,'g*')
plt.show()


    

In [ ]:

    

plt.plot(x2, y2, color='green', linestyle='dashed', marker='o',
     markerfacecolor='blue', markersize=12,label='line1',linewidth=3)
plt.axis([2, 16, -16, 2])
plt.legend()
plt.show()


    

In [ ]:

    

lines = plt.plot(x1, y1, x2, y2)
# use keyword args
plt.setp(lines, color='r', linewidth=2.0) 
# or MATLAB style string value pairs
plt.setp(lines, 'color', 'r', 'linewidth', 2.0)
plt.show()


    

In [ ]:

    

line1 = plt.plot(x1, y1)
line2 = plt.plot(x2, y2)
plt.setp(line1, color='r', linewidth=2.0, label='mouse')
plt.setp(line2, color='b', linewidth=2.0, label='pig')
plt.title('test results', color='g',fontsize=18)
plt.xlabel('days',fontsize=16,style='italic')
plt.ylabel('value',fontsize=16,style='italic', rotation='horizontal')
plt.legend() # to show legend
plt.show()


    

In [ ]:

    

import numpy as np
import math

# [linear space](http://docs.scipy.org/doc/numpy/reference/generated/numpy.linspace.html),
# returns a list of equally evenly spaced numbers in the given interval
x1 = np.linspace(0.0, 5.0)
x2 = np.linspace(0.0, 1.0, 1000)

# f(x) = cos(2*pi*x) * e^(-x)
y1 = np.cos(2 * np.pi * x1) * np.exp(-x1)

# second plot without numpy array for the y-axis
def f(x):
    return math.sin(x**x)

y2 = [ f(x*math.pi) for x in x2 ]

plt.title('Two subplots')
plt.subplot(2, 1, 1)
plt.plot(x1, y1, 'yo-')
plt.ylabel(r'$\cos(2\pi*x) * e^{-x}$', fontsize=16)

plt.subplot(2, 1, 2)
plt.plot(x2, y2, 'r.-')
plt.xlabel('radiant')
plt.ylabel(r'$\sin(\pi*x^{\pi*x})$', fontsize=16)

# change the plot size
from pylab import rcParams
xSize, ySize = rcParams['figure.figsize']
# run this cell three times and the plot size will change, global state magic!
rcParams['figure.figsize'] = (16, 9)
plt.show()


    

In [ ]:

    

# reset global size
rcParams['figure.figsize'] = (6.0, 4.0)


    

In [ ]:

    

# dataset
datasetpath = 'data/EWR_Ortsteile_2012-12-31.csv'
data = None
with open(datasetpath) as f:
    data = f.readlines()

for i in range(10):
    print(data[i])
print('...')


    

In [ ]:

    

# distribution of age and population for Berlin districts divided by foreigners and locals
import csv
from statistics import mean
import numpy as np
from collections import defaultdict

def clean(age, count):
    if 'und' in age:
        # fix inconsistent values
        agerange = '95-100+'
    else:
        ages = age.split('_')
        agerange = '{}-{}'.format(ages[0], ages[1])
    return agerange, int(count.split(',')[0])

data = { 
'total': {
    'foreigner': defaultdict(list),
    'local': defaultdict(list)
    }
}
with open(datasetpath) as f:
    # automatically uses csv header to generate keys
    # regardless of their name, csv files are not always delimited by `,`
    csvdata = csv.DictReader(f, delimiter=';') 
    # csvdata is a list of dict's, one dictionary for each line of data
    for dict_row in csvdata:
        # collect values for each district
        district = dict_row['Bez-Name']
        # maybe I should use defaultdicts ...
        if not district in data:
            data[district] = {
                'foreigner': {},
                'local': {}
            }
        citizenship = dict_row['Staatsangeh']
        # clean up inconsistent values
        age, cnt = clean(dict_row['Altersgr'], dict_row['Häufigkeit'])
        if citizenship == 'A':
            # totals could be accumulated by a seperate function, but it's more convenient this way
            data['total']['foreigner'][age].append(cnt)
            data[district]['foreigner'][age] = cnt
        elif citizenship == 'D':
            data['total']['local'][age].append(cnt)
            data[district]['local'][age] = cnt

# calculate the average age of each district for foreigner and locals
foreigners = {
    'age': [],   # x-axis
    'means': []  # y-axis
}

locals = {
    'age':[],
    'means': []
}

# iterate over the sorted keys and add the values in order to the list
for age, number in sorted(data['total']['foreigner'].items()):
    # number is a list containing the number of foreigners/locals of the specific age for each district
    foreigners['age'].append(age)
    # add the arithmetic mean over all numbers of foreigners/local for that age in each district
    foreigners['means'].append(mean(number))
for age, number in sorted(data['total']['local'].items()):
    locals['age'].append(age)
    locals['means'].append(mean(number))

# import pprint
# pp = pprint.PrettyPrinter()
# pp.pprint(locals)

# numpy.arange returns evenly spaced for the given range, g.e. arange(3) returns [0, 1, 2]
# this will be used to set the x-coordinate of each bar in the plot
# http://docs.scipy.org/doc/numpy/reference/generated/numpy.arange.html
indices = np.arange(len(foreigners['means']))
# http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.bar
# plt.bar("x-coord from the left", "bar height", ...)
fplt = plt.bar(indices, foreigners['means'], color='r')
# bottom - distance from the x-axis
lplt = plt.bar(indices, locals['means'], color='y', bottom=foreigners['means'])
# http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.xticks
plt.xticks(indices, locals['age'], rotation='vertical')
# labels
plt.xlabel('age groups')
plt.ylabel('citizens')
# prints the legend
# http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.legend
plt.legend((fplt, lplt), ('foreigners', 'locals'))
# show the plot
plt.show()


    

In [ ]: