forked from IATI/IATI-Dashboard
-
Notifications
You must be signed in to change notification settings - Fork 0
/
plots.py
104 lines (87 loc) · 3.61 KB
/
plots.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
#!/usr/bin/env python
"""
Show how to make date plots in matplotlib using date tick locators and
formatters. See major_minor_demo1.py for more information on
controlling major and minor ticks
All matplotlib date plotting is done by converting date instances into
days since the 0001-01-01 UTC. The conversion, tick locating and
formatting is done behind the scenes so this is most transparent to
you. The dates module provides several converter functions date2num
and num2date
"""
import datetime
import numpy as np
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import json, re
git_stats = json.load(open('./stats-calculated/gitaggregate-dated.json'))
import csv
failed_downloads = csv.reader(open('data/downloads/history.csv'))
git_stats['failed_downloads'] = dict((row[0],row[1]) for row in failed_downloads)
from vars import expected_versions
for stat_path in [
'activities',
'publishers',
'activity_files',
'spend',
'file_size',
'failed_downloads',
'invalidxml',
'nonstandardroots',
('validation', lambda x: x=='fail', ''),
('publishers_validation', lambda x: x=='fail', ''),
('publisher_has_org_file', lambda x: x=='no', ''),
('versions', lambda x: x in expected_versions, '_expected'),
('versions', lambda x: x not in expected_versions, '_other'),
('publishers_per_version', lambda x: x in expected_versions, '_expected'),
('publishers_per_version', lambda x: x not in expected_versions, '_other'),
('file_size_bins', lambda x: True, ''),
]:
if type(stat_path) == tuple:
stat_name = stat_path[0]
else:
stat_name = stat_path
print stat_name
items = sorted(git_stats.get(stat_name).items())
x_values = [ datetime.date(int(x[0:4]), int(x[5:7]), int(x[8:10])).toordinal() for x,y in items ]
if type(stat_path) == tuple:
y_values = [ dict((k,v) for k,v in y.items() if stat_path[1](k)) for x,y in items ]
else:
y_values = [ y for x,y in items ]
#years = mdates.YearLocator() # every year
#months = mdates.MonthLocator() # every month
dateFmt = mdates.DateFormatter('%Y-%m-%d')
fig, ax = plt.subplots()
ax.set_color_cycle(['b', 'g', 'r', 'c', 'm', 'y', 'k', '#00ff00', '#fc5ab8', '#af31f2'])
fig_legend = plt.figure()
dpi = 96
fig.set_size_inches(600.0/dpi, 600.0/dpi)
if type(y_values[0]) == dict:
keys = set([ tm for y in y_values for tm in y.keys() ])
plots = {}
for key in keys:
plots[key], = ax.plot(x_values, [ y.get(key) or 0 for y in y_values ])
fig_legend.legend(plots.values(), plots.keys(), 'center', ncol=4)
fig_legend.set_size_inches(600.0/dpi, 100.0/dpi)
fig_legend.savefig('out/{0}{1}_legend.png'.format(stat_name,stat_path[2]))
else:
ax.plot(x_values, y_values)
# format the ticks
#ax.xaxis.set_major_locator(years)
ax.xaxis.set_major_formatter(dateFmt)
#ax.xaxis.set_minor_locator(months)
#datemin = datetime.date(r.date.min().year, 1, 1)
#datemax = datetime.date(r.date.max().year+1, 1, 1)
#ax.set_xlim(datemin, datemax)
# format the coords message box
#def price(x): return '$%1.2f'%x
ax.format_xdata = mdates.DateFormatter('%Y-%m-%d')
#ax.format_ydata = price
ax.grid(True)
# rotates and right aligns the x labels, and moves the bottom of the
# axes up to make room for them
fig.autofmt_xdate()
fig.savefig('out/{0}{1}.png'.format(stat_name,stat_path[2] if type(stat_path) == tuple else ''), dpi=dpi)
plt.close()