from json import read as jread
def jsonload(f):
return jread(f.read())
-import sys
+import sys, os
import pylab as pl
import numpy as np
import time
# uniform colors for OS results
-os_colors = ['#B63537', '#4E4DA0', '#008200', 'gray']
+os_colors = ['#AA2029', '#D1942B', '#7FB142', '#69A7CE']
os_order = ['linux', 'mac', 'win', 'otheros']
+time_order = ['notime', 'little', 'most', 'always']
+time_colors = ['#FF0000', '#FF5500', '#FFAC00', '#FFFD08']
+time_categories = {
+ 'notime': "don't use it",
+ 'little': "less than 50%",
+ 'most': "more than 50%",
+ 'always': "always"
+ }
# resources
resource_categories = {
'vendor': 'Vendor/Project website',
# end the reverse mapping
os_family_rev = {}
for ost in os_family:
- for os in os_family[ost]:
- os_family_rev[os] = ost
+ for os_ in os_family[ost]:
+ os_family_rev[os_] = ost
def load_list2dict(name):
d = {}
lfile = open(name)
for line in lfile:
+ if line.strip() == "":
+ continue
kv = line.split(':')
+ if kv[0] in d:
+ raise RuntimeError(
+ "Got a line %s with a duplicate key %s whenever value for it "
+ "is known already to be %r" % (line, kv[0], d[kv[0]]))
d[kv[0]] = kv[1].strip().strip('"')
return d
os_dict = load_list2dict('oslist.txt')
datamod_dict = load_list2dict('datamodlist.txt')
sw_dict = load_list2dict('swlist.txt')
+ position_dict = load_list2dict('position-dd-list.txt')
+ employer_dict = load_list2dict('employer-dd-list.txt')
+ ratings_dict = load_list2dict('ratingslist.txt')
+ vm_dict = load_list2dict('vmlist.txt')
def __init__(self, srcdir):
# eats the whole directory
def get_nice_name(self, id):
srcs = [DB.os_dict, os_cat_names, DB.sw_dict, sw_categories,
- resource_categories]
+ resource_categories, time_categories,
+ DB.datamod_dict, DB.position_dict, DB.employer_dict,
+ DB.vm_dict]
for src in srcs:
if id in src:
return src[id]
envs = ['pers_os', 'man_os', 'virt_host_os', 'virt_guest_os']
env_names = ['Personal', 'Managed', 'Virt. Host', 'Virt. Guest']
env_stats = {}
- offset = 0
for env in envs:
counts = db.get_counts(env)
stats = dict(zip(os_family.keys(), [0] * len(os_family)))
stats[os_family_rev[os]] += counts[os]
total_count = np.sum(stats.values())
for osf in stats:
- stats[osf] = float(stats[osf]) / total_count
+ if not total_count:
+ stats[osf] = 0
+ else:
+ stats[osf] = float(stats[osf]) / total_count
env_stats[env] = stats
# make stacked barplot
pl.figure(figsize=(6.4, 4.8))
pl.ylabel("Fraction of submissions")
pl.savefig('%s/ospref_by_env.png' % destdir, format='png', dpi=80)
-def mkpic_submissions_per_datamod(db, destdir):
- # simple demo
- spd = db.get_counts('bg_datamod')
- spd = sorted(spd.items(), cmp=lambda x, y: cmp(x[1], y[1]))[::-1]
- x = np.arange(len(spd))
- pl.figure(figsize=(6.4, 4.8))
- pl.title('Submissions per data modality')
- pl.bar(x, [s[1] for s in spd])
- pl.xticks(x + 0.5, [db.datamod_dict[k[0]] for k in spd], rotation=-10)
- pl.ylabel('Survey submissions per data modality\n(multiple choices per submission possible)')
- pl.savefig('%s/submissions_per_datamod.png' % destdir, format='png', dpi=80)
+
+def mkpic_time_per_env(db, destdir):
+ envs = ['pers_time', 'man_time', 'virt_time']
+ env_names = ['Personal', 'Managed', 'Virtual']
+ env_stats = {}
+ for env in envs:
+ counts = dict(zip(time_order, [0] * len(time_order)))
+ counts.update(db.get_counts(env))
+ total_count = np.sum(counts.values())
+ for c in counts:
+ counts[c] = float(counts[c]) / total_count
+ env_stats[env] = counts
+ # make stacked barplot
+ pl.figure(figsize=(7.5, 4))
+ x = np.arange(len(envs))
+ bottoms = np.zeros(len(envs))
+ for i, t in enumerate(time_order):
+ stat = [env_stats[e][t] for e in envs]
+ pl.barh(x, stat, left=bottoms, color=time_colors[i],
+ label=db.get_nice_name(t), height=.6)
+ bottoms += stat
+ pl.legend(loc='center left')
+ pl.yticks(x + 0.2, env_names)
+ pl.ylim(-0.4, len(envs))
+ pl.title("Research activity time by environment")
+ pl.xlabel("Fraction of submissions")
+ pl.subplots_adjust(right=0.97)
+ pl.savefig('%s/time_by_env.png' % destdir, format='png', dpi=80)
+
+
+def mkpic_submissions_per_key(db, destdir, key, title, sortby='name',
+ multiple=False):
+ counts = db.get_counts(key)
+ pl.figure(figsize=(6.4, (len(counts)-2) * 0.4 + 2))
+ tmargin = .8/len(counts)
+ if tmargin > 0.3: tmargin = 0.3
+ pl.subplots_adjust(left=0.03, right=0.97, top=1-tmargin, bottom=tmargin)
+ pl.title(title)
+ if not len(counts):
+ pl.text(.5, .5, "[Insufficient data for this figure]",
+ horizontalalignment='center')
+ pl.axis('off')
+ else:
+ # sort by name
+ if sortby == 'name':
+ stats = sorted(counts.items(), cmp=lambda x, y: cmp(x[0], y[0]))
+ elif sortby == 'count':
+ stats = sorted(counts.items(), cmp=lambda x, y: cmp(x[1], y[1]))[::-1]
+ else:
+ raise ValueError("Specify either name or count for sortby")
+ x = np.arange(len(stats))
+ pl.barh(x + (1./8), [s[1] for s in stats[::-1]], height=0.75, color = '#008200')
+ pl.yticks(x + 0.5, ['' for s in stats])
+ text_offset = pl.gca().get_xlim()[1] / 30.
+ for i, s in enumerate(stats[::-1]):
+ pl.text(text_offset, i+.5, db.get_nice_name(s[0]),
+ horizontalalignment='left',
+ verticalalignment='center',
+ bbox=dict(facecolor='white', alpha=0.8, edgecolor='white'))
+ pl.ylim(0, len(stats))
+ yl = "Number of submissions"
+ if multiple:
+ yl += "\n(multiple choices per submission possible)"
+ pl.xlabel(yl)
+ pl.savefig('%s/submissions_per_%s.png' % (destdir, key), format='png', dpi=80)
+
def mkpic_resources(db, destdir):
res = db.get_counts('software_resource')
def mkpic_software(db, destdir):
for typ in sw_categories.keys():
- counts = db.get_counts('sw_%s' % typ)
- pl.figure(figsize=(6.4, 4.8))
- pl.title("Software popularity: %s" % db.get_nice_name(typ))
- if not len(counts):
- pl.text(.5, .5, "[Insufficient data for this figure]",
- horizontalalignment='center')
- pl.axis('off')
- else:
- # sort by name
- stats = sorted(counts.items(), cmp=lambda x, y: cmp(x[0], y[0]))
- x = np.arange(len(stats))
- pl.bar(x + (1./8), [s[1] for s in stats], width=0.75, color = '#008200')
- pl.xticks(x + 0.5, ['' for s in stats])
- for i, s in enumerate(stats):
- pl.text(i+.5, 0.1, db.get_nice_name(s[0]), rotation=90,
- horizontalalignment='center',
- verticalalignment='bottom',
- bbox=dict(facecolor='white', alpha=0.8, edgecolor='white'))
- pl.xlim(0, len(stats))
- pl.ylabel("Number of submissions")
- pl.savefig('%s/sw_%s.png' % (destdir, typ), format='png', dpi=80)
+ mkpic_submissions_per_key(
+ db, destdir, 'sw_%s' % typ,
+ title="Software popularity: %s" % db.get_nice_name(typ),
+ sortby='name')
def mkpic_rating_by_os(db, env, items, destdir, title):
pl.figure(figsize=(6.4, 4.8))
def main(srcdir, destdir):
db = DB(srcdir)
- for pic in [mkpic_submissions_per_datamod, mkpic_os_per_env, mkpic_software,
- mkpic_resources]:
+ if not os.path.exists(destdir):
+ os.makedirs(destdir)
+
+ mkpic_submissions_per_key(
+ db, destdir, 'virt_prod', sortby='name',
+ title='Virtualization product popularity\n(multiple choices per submission possible)')
+
+ mkpic_submissions_per_key(
+ db, destdir, 'bg_datamod', sortby='count',
+ title='Submissions per data modality\n(multiple choices per submission possible)')
+
+ mkpic_submissions_per_key(
+ db, destdir, 'bg_position', title='Submissions per position', sortby='count')
+
+ mkpic_submissions_per_key(
+ db, destdir, 'bg_country', title='Submissions per country', sortby='count')
+
+ mkpic_submissions_per_key(
+ db, destdir, 'bg_employer', title='Submissions per venue', sortby='count')
+
+ for pic in [mkpic_os_per_env, mkpic_software,
+ mkpic_resources, mkpic_time_per_env]:
pic(db, destdir)
mkpic_rating_by_os(db, 'pers_os', ['pers_r%i' % i for i in range(1, 9)], destdir,
"Ratings: Personal environment")