debianforum.de

Spendenstatistiken

SNIPPET_TEXT:

1. # coding: utf-8
2.  
3. # In[1]:
4.  
5. years = range(2003, 2016)
6. donations_url = "https://wiki.debianforum.de/Debianforum.de/Spenden"
7. expenses_url = "https://wiki.debianforum.de/Debianforum.de/Ausgaben"
8.  
9.  
10. # In[2]:
11.  
12. import urllib
13. urls = {year: (donations_url + '/' + str(year) if year < years[-1] else donations_url) for year in years}
14.  
15. y = dict()
16. for year, url in urls.items():
17.     f = urllib.urlopen(url)
18.     y[year] = f.read()
19.    
20. expense_html = urllib.urlopen(expenses_url).read()
21.  
22.  
23. # In[3]:
24.  
25. def parse_html_to_list(html):
26.     """
27.    Parse HTML table to list of tuples, expecting three cells with date, note, amount in each row.
28.    """
29.     data = []
30.     parser = etree.HTMLParser()
31.     tree = etree.parse(StringIO(html.decode('utf-8')), parser)
32.     rows = tree.xpath('//table//tr')
33.     for index, row in enumerate(rows):
34.         cells = row.getchildren()
35.         if len(cells) == 3 and index > 0:
36.             date = cells[0].text.strip()
37.             try:
38.                 date = datetime.strptime(date, "%d.%m.%Y")
39.             except Exception as e:
40.                 continue
41.             note = cells[1].xpath(".//a/text()")
42.             if not note:
43.                 note = cells[1].xpath(".//text()")
44.             amount = float(cells[2].text.strip().replace(",","."))
45.  
46.             data.append((date, note[0].strip(), amount))
47.     return data
48.    
49.  
50.  
51. # In[4]:
52.  
53. from io import StringIO, BytesIO
54. from lxml import etree
55. from datetime import datetime
56.  
57.  
58. donations = []
59.  
60. for year, donate_html in y.items():
61.     yearly_list = parse_html_to_list(donate_html)
62.     donations += yearly_list
63. donations.sort()
64.  
65.  
66.  
67. # In[5]:
68.  
69. expenses = parse_html_to_list(expense_html)
70.  
71.  
72. # In[6]:
73.  
74. sum([x[2] for x in expenses])
75.  
76.  
77. # In[7]:
78.  
79. sum([x[2] for x in donations])
80.  
81.  
82. # In[8]:
83.  
84. sum([x[2] for x in donations]) - sum([x[2] for x in expenses])
85.  
86.  
87. # Donations/month
88.  
89. # In[9]:
90.  
91. from itertools import groupby
92. import numpy as np
93. import matplotlib.pyplot as plt
94. from datetime import date, timedelta
95. get_ipython().magic(u'matplotlib inline')
96.  
97. def _groupy(item):
98.     return item[0].year, item[0].month
99.  
100. def get_date_grouped_list(list_):
101.     agg_list = []
102.     for ( (year, month), items ) in groupby( list_, _groupy ):
103.         agg_list.append( ( date(year, month, 1), sum([x[2] for x in items])) )
104.     return agg_list
105.  
106. donations_prefix = [(date(donations[0][0].year, x+1, 1), '', 0) for x in range(0, donations[0][0].month-1)] # cheating. Now even better.
107. agg_donations = get_date_grouped_list(donations_prefix + donations)
108. agg_expenses = get_date_grouped_list(donations_prefix + expenses)
109.  
110. agg_donations.sort()
111. agg_expenses.sort()
112.  
113. plt.figure(figsize=(15,7))
114. # donations
115. plt.plot([x[0] for x in agg_donations], [x[1] for x in agg_donations], color="green", label="Spenden")
116. # expenses
117. plt.plot([x[0] for x in agg_expenses], [x[1] for x in agg_expenses], color="red", label="Ausgaben")
118.  
119. # spartopf
120. cash_available = []
121. cash = 0
122. d = dict(agg_donations)
123. # shitty workaround: this month is missing. probably a bug in the source table.
124. for k,v in agg_expenses + [(date(2009, 3, 1), 0)]:
125.     donation = d.pop(k, 0)
126.     cash = cash - v + donation
127.    
128.     cash_available.append((k, cash))
129. cash_available.sort()
130.  
131. plt.plot([x[0] for x in cash_available], [x[1] for x in cash_available], color="blue", label="Spendenkonto")
132. plt.xlabel("Datum")
133. plt.ylabel("Euro")
134. plt.legend()
135.  
136.  
137.  
138. # In[10]:
139.  
140. # csv thing
141. for x in agg_plot:
142.     print "%s;%.2f" % (x[0].strftime("%Y-%m-%d"), x[1])
143.  
144.  
145. # In[ ]:
146.  
147. # csv thing
148. for x in donations:
149.     print "%s;\"%s\";%.2f" % (x[0].strftime("%Y-%m-%d"), x[1], x[2])

Quellcode

Hier kannst du den Code kopieren und ihn in deinen bevorzugten Editor einfügen. PASTEBIN_DOWNLOAD_SNIPPET_EXPLAIN