From: Michael Hanke <michael.hanke@gmail.com>
Date: Mon, 16 May 2011 16:06:23 +0000 (-0400)
Subject: Merge branch 'master' of alioth:/git/pkg-exppsy/neurodebian
X-Git-Url: https://git.donarmstrong.com/?a=commitdiff_plain;h=04b0231662753d7945da60aeb842cb3dbe7c4d48;p=neurodebian.git

Merge branch 'master' of alioth:/git/pkg-exppsy/neurodebian

* 'master' of alioth:/git/pkg-exppsy/neurodebian:
  adding those basic stats (employer/country/venue) to report (TODO: nice names extract)
  RF: unify plotting of basic barplots (submissions_per_key)

Conflicts:
	survey/makestats
---

04b0231662753d7945da60aeb842cb3dbe7c4d48
diff --cc survey/makestats
index a9648ed,540e209..7b229b1
--- a/survey/makestats
+++ b/survey/makestats
@@@ -168,7 -160,7 +168,7 @@@ class DB(dict)
  
      def get_nice_name(self, id):
          srcs = [DB.os_dict, os_cat_names, DB.sw_dict, sw_categories,
-                 resource_categories, time_categories]
 -                resource_categories, DB.datamod_dict]
++                resource_categories, time_categories, DB.datamod_dict]
          for src in srcs:
              if id in src:
                  return src[id]
@@@ -206,45 -199,38 +206,66 @@@ def mkpic_os_per_env(db, destdir)
      pl.savefig('%s/ospref_by_env.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.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))
+ def mkpic_submissions_per_key(db, destdir, key, title, sortby='name',
+                             multiple=False):
+     counts = db.get_counts(key)
      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)
+     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.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))
+         yl = "Number of submissions"
+         if multiple:
+             yl += "\n(multiple choices per submission possible)"
+         pl.ylabel(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')
@@@ -307,8 -276,22 +311,22 @@@ def main(srcdir, destdir)
      db = DB(srcdir)
      if not os.path.exists(destdir):
          os.makedirs(destdir)
-     for pic in [mkpic_submissions_per_datamod, mkpic_os_per_env, mkpic_software,
+ 
+     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_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")