#!/usr/bin/python

from mvpa.misc.plot.base import plot_bars
from glob import glob
try:
    from json import load as jload
    def jsonload(f):
        return jload(f)
except ImportError:
    from json import read as jread
    def jsonload(f):
        return jread(f.read())
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_order = ['linux', 'mac', 'win', 'otheros']
# resources
resource_categories = {
    'vendor': 'Vendor/Project website',
    'retailer': 'Retailer',
    'os': 'Operating system',
    'cpan': 'CPAN',
    'cran': 'CRAN',
    'epel': 'EPEL',
    'fink': 'Fink',
    'freebsdports': 'FreeBSD ports',
    'incf': 'INCF',
    'macports': 'Macports',
    'matlabcentral': 'Matlab Central',
    'neurodebian': 'NeuroDebian',
    'nitrc': 'NITRC',
    'pypi': 'PyPi',
    'pythonbundles': 'Python bundles',
    'sourceforge': 'Sourceforge',
    'other': 'Other resource'
    }
# software categories
sw_categories = {
        'general': 'General computing',
        'dc': 'Distributed computing',
        'img': 'Brain imaging',
        'datamanage': 'Data management',
        'neusys': 'Neural systems modeling',
        'electro': 'Electrophysiology, MEG/EEG',
        'bci': 'Brain-computer interface',
        'acq': 'Hardware interface/Data acquisition',
        'rt': 'Real-time solutions',
        'psychophys': 'Psychophysics/Experiment control'
        }

# some meaningful groups of OSes
redhat_family = ["rhel", "centos", "fedora", "scilinux"]
debian_family = ["debian", "ubuntu", "biolinux"]
suse_family = ["suse", "slel"]
other_linux_family = ["gentoo", "mandriva", "arch", "slackware", "otherlinux"]
other_family = ["starbsd", "unix", "qnx", "beos", "solaris", "other"]

os_cat_names = {
        'win': 'Windows',
        'mac': 'Mac OS',
        'linux': 'GNU/Linux',
        'otheros': 'Other OS'
        }

os_family = {
        'win': ["windows"],
        'mac': ["macosx"],
        'linux': redhat_family + debian_family + suse_family + other_linux_family,
        'otheros': other_family
        }
# end the reverse mapping
os_family_rev = {}
for ost in os_family:
    for os_ in os_family[ost]:
        os_family_rev[os_] = ost


def load_list2dict(name):
    d = {}
    lfile = open(name)
    for line in lfile:
        kv = line.split(':')
        d[kv[0]] = kv[1].strip().strip('"')
    return d



class DB(dict):
    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')

    def __init__(self, srcdir):
        # eats the whole directory
        if srcdir is None:
            return
        datafilenames = glob('%s/*.json' % srcdir)
        for dfn in datafilenames:
            rawdata = jsonload(open(dfn))
            self[rawdata['timestamp']] = rawdata

    def get_unique(self, key):
        # return a set of all (unique) values for a field id
        uniq = set()
        for d in self.values():
            if key in d:
                el = d[key]
                if isinstance(el, list):
                    uniq = uniq.union(el)
                else:
                    uniq = uniq.union((el,))
        return uniq

    def get_not_none(self, key):
        # return a list of all values of a specific field id
        # the second return value is count of submission that did not have data
        # for this field id
        val = []
        missing = 0
        for d in self.values():
            if key in d:
                el = d[key]
                if isinstance(el, list):
                    val.extend(el)
                else:
                    if el == 'none':
                        missing += 1
                    else:
                        val.append(el)
            else:
                missing += 1
        return val, missing

    def get_counts(self, key):
        # return a dict with field values as keys and respective submission 
        # count as value
        vals = self.get_not_none(key)[0]
        uniq = np.unique(vals)
        counts = dict(zip(uniq, [vals.count(u) for u in uniq]))
        return counts

    def select_match(self, key, values):
        # return a db with all submissions were a field id has one of the
        # supplied values
        match = DB(None)
        for k, v in self.items():
            if not key in v:
                continue
            el = v[key]
            if isinstance(el, list):
                if len(set(values).intersection(el)):
                    match[k] = v
            elif el in values:
                match[k] = v
        return match

    def get_nice_name(self, id):
        srcs = [DB.os_dict, os_cat_names, DB.sw_dict, sw_categories,
                resource_categories, DB.datamod_dict, DB.position_dict,
                DB.employer_dict]
        for src in srcs:
            if id in src:
                return src[id]
        # not found, nothing nicer
        return id


def mkpic_os_per_env(db, destdir):
    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)))
        for os in counts:
            stats[os_family_rev[os]] += counts[os]
        total_count = np.sum(stats.values())
        for osf in stats:
            stats[osf] = float(stats[osf]) / total_count
        env_stats[env] = stats
    # make stacked barplot
    pl.figure(figsize=(6.4, 4.8))
    x = np.arange(len(envs))
    bottoms = np.zeros(len(envs))
    for i, os in enumerate(os_order):
        stat = [env_stats[e][os] for e in envs]
        pl.bar(x, stat, bottom=bottoms, color=os_colors[i],
               label=db.get_nice_name(os), width=0.8)
        bottoms += stat
    pl.legend(loc='lower right')
    pl.xticks(x + 0.4,  [db.get_nice_name(e) for e in env_names])
    pl.xlim(-0.25, len(envs))
    pl.title("Operating system preference by environment")
    pl.ylabel("Fraction of submissions")
    pl.savefig('%s/ospref_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, 4.8))
    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')
    res = res.items()
    x = np.arange(len(res))
    pl.figure(figsize=(6.4, 4.8))
    pl.title('Software resources')
    pl.bar(x + (1./8), [s[1] for s in res], width=0.75, color = '#008200')
    pl.xticks(x + 0.5,  ['' for s in res])
    for i, s in enumerate(res):
        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.ylabel('Number of submissions')
    pl.savefig('%s/software_resources.png' % destdir, format='png', dpi=80)

def mkpic_software(db, destdir):
    for typ in sw_categories.keys():
        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))
    for i, os in enumerate(os_order):
        ratings = [db.select_match(env,
                        os_family[os]).get_not_none('%s' % (it,))[0]
                            for it in items]
        plot_bars(ratings, offset=((i+1)*0.2)-0.1, color=os_colors[i],
                  title=title, ylabel="Mean rating", label=db.get_nice_name(os))
    pl.ylim((0,3))
    pl.xlim((0,len(items)))
    pl.yticks((0, 3), ['Disagree', 'Agree'], rotation=90)
    pl.xticks(np.arange(len(items))+0.5, [i[-2:] for i in items],
              horizontalalignment='center')
    pl.legend(loc='lower right')
    pl.savefig('%s/ratings_%s.png' % (destdir, env), format='png', dpi=80)


def main(srcdir, destdir):
    db = DB(srcdir)
    if not os.path.exists(destdir):
        os.makedirs(destdir)

    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]:
        pic(db, destdir)
    mkpic_rating_by_os(db, 'pers_os', ['pers_r%i' % i for i in range(1, 9)], destdir,
                       "Ratings: Personal environment")
    mkpic_rating_by_os(db, 'man_os', ['man_r%i' % i for i in range(1, 5)], destdir,
                       "Ratings: Managed environment")
    mkpic_rating_by_os(db, 'virt_host_os', ['virt_r%i' % i for i in range(1, 4)], destdir,
                       "Ratings: Virtual environment (by host OS)")
    # submission stats: this is RST
    statsfile = open('%s/stats.txt' % destdir, 'w')
    statsfile.write('::\n\n  Number of submissions: %i\n' % len(db))
    statsfile.write('  Statistics last updated: %s\n\n' \
            % time.strftime('%A, %B %d %Y, %H:%M:%S UTC', time.gmtime()))
    statsfile.close()

if __name__ == '__main__':
    main(sys.argv[1], sys.argv[2])