Ejemplo n.º 1
0
def _store(redis, pk, dimension, metric, period, dt, count, method='set',
        rank=False):
    # Keep a list of graphs per pk
    key = keyify(pk, dimension, Period.get(period).interval, metric)
    # Store pk dimensions
    dimension_key = keyify('dimensions', pk)
    dimension_json = keyify(dimension)
    
    if not dimension_json in _added_dimensions[dimension_key]:
        redis.sadd(dimension_key, dimension_json)
        _added_dimensions[dimension_key].append(dimension_json)
    # Store dimensional subdimensions
    if dimension != '_':
        subdimension_key = keyify('subdimensions', pk, parent(dimension))
        if not dimension_json in _added_subdimensions[subdimension_key]:
            redis.sadd(subdimension_key, dimension_json)
            _added_subdimensions[subdimension_key].append(dimension_json)

    if method == 'set':
        new_val = float(count)
        redis.hset(key, dt, new_val)
    elif method == 'incr':
        new_val = redis.execute_command('HINCRBYFLOAT', key, dt, float(count))
    if rank and (isinstance(try_loads(pk), list) or dimension != '_'):
        if isinstance(pk, list) and dimension == '_':
            tgt_pk = parent(pk)
            tgt_dimension = dimension
        else:
            tgt_pk = pk
            tgt_dimension = parent(dimension)
        rank_key = keyify('rank', tgt_pk, tgt_dimension,
                Period.get(period).interval, dt, metric) 
        redis.zadd(rank_key, dimension_json, new_val)
    return new_val
Ejemplo n.º 2
0
 def totals(cls, pk, dimensions=None, metrics=None, periods=None):
     if not periods:
         periods = DEFAULT_PERIODS
     if not isinstance(periods, list):
         periods = [periods]
     metrics = metrics or ["hits"]
     if not isinstance(metrics, list):
         metrics = [metrics]
     ratios = []
     for metric in metrics:
         if "/" in metric:
             metrics.remove(metric)
             ratios.append(metric)
             metrics += metric.split("/")
     d = {}
     for p in periods:
         p_data = cls.plotpoints(pk, dimensions, metrics, period=str(p))
         p_totals = dict()
         for dim in p_data.keys():
             p_totals[dim] = dict()
             for met, vals in p_data[dim].items():
                 p_totals[dim][met] = sum([v for k, v in vals.items() if Period.get(p).flatten(k)])
             for rat in ratios:
                 top, bot = parse_formula(rat)
                 topt, bott = p_totals[dim][top], p_totals[dim][bot]
                 p_totals[dim][rat] = bott and topt / bott or 0
         d[str(p)] = p_totals
     return d
Ejemplo n.º 3
0
def _ranked(redis, pk, parent_dimension, metric, period, ats, start=0, size=10,
        sort_dir=None):
    top, bot = parse_formula(metric)
    rank_keyify = lambda ats, met: keyify('rank', pk, parent_dimension,
            Period.get(period).interval, ats, met)
    final_rank_key = rank_keyify(ats, metric)
    def squash_ats(met):
        if len(ats) > 1:
            map(lambda at: redis.zremrangebyscore(rank_keyify(at, met), 0, 0), ats)
            redis.zunionstore(rank_keyify(ats, met),
                    map(lambda at: rank_keyify(at, met), ats))
    squash_ats(top)
    if bot:
        squash_ats(bot)
        top_key, bot_key = rank_keyify(ats, top), rank_keyify(ats, bot)
        redis.execute_command("eval", """
        for key_i, key_n in ipairs(redis.call("zrange", KEYS[2], 0, -1)) do
            local top_s = tonumber(redis.call("zscore", KEYS[1], key_n))
            local bot_s = tonumber(redis.call("zscore", KEYS[2], key_n))
            if top_s and bot_s and bot_s > 0 then
                redis.call("zadd", KEYS[3], top_s/bot_s, key_n)
            end
        end
        """, 3, top_key, bot_key, final_rank_key)
        redis.zremrangebyscore(final_rank_key, 0, 0)
    return redis.zrange(final_rank_key, start, start + size,
                desc=not sort_dir or sort_dir.upper() in ['-', 'DESC', 'HIGH'])
Ejemplo n.º 4
0
    def __call__(self, *args, **kwargs):
        from whale import Whale
        from periods import Period

        if len(args) and args[0] == Whale or issubclass(args[0], Whale):
            args = args[1:]
        clear_cache = kwargs.pop("unmemoize", False)
        self.get_cache()
        if "period" in kwargs:
            p = Period.get(kwargs["period"])
            kwargs["period"] = str(p)
            ttl = int(p.interval) / 5
        else:
            ttl = 60

        key_name = self.keyify(args, kwargs)

        if clear_cache:
            self.cache.delete(key_name)

        try:
            return json.loads(self.cache[key_name])
        except KeyError:
            value = self.func(Whale, *args, **kwargs)
            self.cache[key_name] = json.dumps(value)
            self.cache.expire(key_name, ttl)
            return value
        except TypeError:
            # uncachable -- for instance, passing a list as an argument.
            # Better to not cache than to blow up entirely.
            return self.func(Whale, *args, **kwargs)
Ejemplo n.º 5
0
 def scalar_plotpoints(
     cls, pk, dimensions=None, metrics=None, depth=0, period=None, flot_time=False, points_type=dict
 ):
     metrics = metrics or ["hits"]
     if isinstance(metrics, basestring):
         metrics = [metrics]
     period = Period.get(period)
     sparse = cls.whale_driver().retrieve(pk, dimensions, metrics, period=period)
     nonsparse = defaultdict(dict)
     if flot_time:
         points_type = list
     for dim, mets in sparse.items():
         for met, points in mets.items():
             dts = period.datetimes_strs()
             nonsparse[dim][met] = []
             for dt in dts:
                 if flot_time:
                     dt_t = to_flot_time(Period.parse_dt_str(dt))
                 else:
                     dt_t = dt
                 value = points[dt] if dt in points else 0
                 nonsparse[dim][met].append([dt_t, float(value)])
             nonsparse[dim][met] = points_type(nonsparse[dim][met])
     if depth > 0:
         for sub in cls.get_subdimensions(pk, dimensions):
             nonsparse = dict(
                 nonsparse.items()
                 + cls.plotpoints(
                     pk, sub, metrics, depth=depth - 1, period=period, flot_time=flot_time, points_type=points_type
                 ).items()
             )
     return nonsparse
Ejemplo n.º 6
0
 def retrieve(self, pk, dimensions, metrics, period=None, dt=None):
     nested = defaultdict(dict)
     period = str(Period.get(period))
     for dimension in map(maybe_dumps, iterate_dimensions(dimensions)):
         for metric in map(maybe_dumps, metrics):
             hash_key = keyify(pk, dimension, period, metric)
             value_dict = self.hgetall(hash_key)
             nested[dimension][metric] = dict([(k, float(v)) for k, v in value_dict.items()])
     return dict(nested)
Ejemplo n.º 7
0
 def update_count_to(cls, pk, dimensions='_', metrics=None, period=False,
         at=False, rank=False):
     period = Period.get(period)
     at = at or cls.now()
     dt = period.flatten_str(at)
     pipe = cls.whale_driver().pipeline(transaction=False)
     for (metric, i) in metrics.iteritems():
         _store(pipe, pk, dimensions, metric, period, dt, i,
                 rank=rank)
     pipe.execute()
Ejemplo n.º 8
0
def _store(redis,
           pk,
           dimension,
           metric,
           period,
           dt,
           count,
           method='set',
           rank=False):
    # Keep a list of graphs per pk
    key = keyify(pk, dimension, Period.get(period).interval, metric)
    # Store pk dimensions
    dimension_key = keyify('dimensions', pk)
    dimension_json = keyify(dimension)

    if not dimension_json in _added_dimensions[dimension_key]:
        redis.sadd(dimension_key, dimension_json)
        _added_dimensions[dimension_key].append(dimension_json)
    # Store dimensional subdimensions
    if dimension != '_':
        subdimension_key = keyify('subdimensions', pk, parent(dimension))
        if not dimension_json in _added_subdimensions[subdimension_key]:
            redis.sadd(subdimension_key, dimension_json)
            _added_subdimensions[subdimension_key].append(dimension_json)

    if method == 'set':
        new_val = float(count)
        redis.hset(key, dt, new_val)
    elif method == 'incr':
        new_val = redis.execute_command('HINCRBYFLOAT', key, dt, float(count))
    if rank and (isinstance(try_loads(pk), list) or dimension != '_'):
        if isinstance(pk, list) and dimension == '_':
            tgt_pk = parent(pk)
            tgt_dimension = dimension
        else:
            tgt_pk = pk
            tgt_dimension = parent(dimension)
        rank_key = keyify('rank', tgt_pk, tgt_dimension,
                          Period.get(period).interval, dt, metric)
        redis.zadd(rank_key, dimension_json, new_val)
    return new_val
Ejemplo n.º 9
0
def _retrieve(redis, pk, dimensions, metrics, period=None, dt=None):
    nested = defaultdict(dict)
    interval = Period.get(period).interval
    for dimension in iterate_dimensions(dimensions)+['_']:
        for metric in metrics:
            if ':' in metric:
                metric_name = metric.split(':')[0]
            else: metric_name = metric
            hash_key = keyify(pk, dimension, interval, metric_name)
            value_dict = redis.hgetall(hash_key)
            nested[maybe_dumps(dimension)][maybe_dumps(metric)] = dict([
                    (k, float(v)) for k, v in value_dict.items()])
    return dict(nested)
Ejemplo n.º 10
0
 def update_count_to(cls,
                     pk,
                     dimensions='_',
                     metrics=None,
                     period=False,
                     at=False,
                     rank=False):
     period = Period.get(period)
     at = at or cls.now()
     dt = period.flatten_str(at)
     pipe = cls.whale_driver().pipeline(transaction=False)
     for (metric, i) in metrics.iteritems():
         _store(pipe, pk, dimensions, metric, period, dt, i, rank=rank)
     pipe.execute()
Ejemplo n.º 11
0
def table_graph():
    from periods import Period
    params = {
        'tzoffset': g('tzoffset', 0.0),
        'period': g('period', str(Period.get(None))),
    }
    debug = g('debug', False)
    table = g('table', '')
    height = g('height', '300px')
    delay = g('delay', 5000)
    hwurl = req.GET.get('hwurl', '/' or req.url.split('table_graph.js')[0])
    include_string = \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/jquery.min.js'></script>\");"%hwurl
    include_string += \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/hailwhale.js'></script>\");"%hwurl
    include_string += \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/d3.js'></script>\");"%hwurl
    include_string += \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/nvd3.js'></script>\");"%hwurl

    return_string = '''
appended=false;\n
function jqinit() {{\n
    if(typeof(jQuery) == 'undefined' || typeof(jQuery.hailwhale) == 'undefined') {{\n
        if(!appended) {{\n
            appended = true;\n
            {include_string}\n
        }}\n
        setTimeout(jqinit, 250);\n
    }} else {{\n
        $(function() {{\n
        init_graphs =function() {{
                $.hailwhale('{hwurl}').graph_tables('{table}', {options});\n
                }}
        setTimeout(init_graphs, {delay});
        if(ui_loaded_funcs)
            ui_loaded_funcs.init_graphs = init_graphs;
        }});\n
    }}
}}
jqinit();\n


    '''.format(include_string=include_string,
               table=table,
               delay=delay,
               hwurl=hwurl,
               options=util.maybe_dumps(params))
    return return_string
Ejemplo n.º 12
0
    def reasons_for(cls, pk, formula="value/hits", known_data=None, period=None, recursive=True):
        metric, denomenator = parse_formula(formula)
        period = Period.get(period)
        pk_base, decision, option = pk
        base = "_"
        best = worst = None
        ranks = cls.cached_rank(pk, formula=formula, dimension=base, period=period, recursive=recursive, points=False)
        overall = cls.cached_rank(
            [pk_base, decision], formula=formula, dimension=base, period=period, recursive=recursive, points=False
        )
        parent_score = overall[base]["score"]
        parent_count = overall[base]["count"]
        ranks[base]["effect"] = ranks[base]["count"] * ranks[base]["difference"]

        def delta(info):
            diff = info["score"] - parent_score
            info["value_diff"] = info["value"] - overall[base]["value"]
            info["difference"] += diff
            if math.fabs(diff) > 0 and info["count"] > 0:
                info["effect"] += diff * info["count"]
                info["significance"] = ((0.5 * info["effect"]) ** 2) / parent_count
            else:
                info["effect"] = 0
                info["significance"] = 0
            return info

        known_dimensions = iterate_dimensions(known_data)
        for dim, info in ranks.items():
            ranks[dim] = info = delta(info)
            if try_loads(dim) in known_dimensions and info["important"]:
                best_score = best and ranks[best]["score"]
                worst_score = worst and ranks[worst]["score"]
                if info["score"] > best_score:
                    best = dim
                if info["score"] < worst_score:
                    worst = dim
        i = {
            "good": best and ranks[best] or {},
            "bad": worst and ranks[worst] or {},
            #'ranks': ranks,
            "base": ranks[base],
            "parent": overall[base],
        }
        i["high"] = i["good"].get("difference", 0)
        i["high_sig"] = i["good"].get("significance", 0) > 4
        i["low"] = i["bad"].get("difference", 0)
        i["low_sig"] = i["bad"].get("significance", 0) > 4
        return i
Ejemplo n.º 13
0
def _retrieve(redis, pk, dimensions, metrics, period=None, dt=None):
    nested = defaultdict(dict)
    interval = Period.get(period).interval
    for dimension in iterate_dimensions(dimensions) + ['_']:
        for metric in metrics:
            if ':' in metric:
                metric_name = metric.split(':')[0]
            else:
                metric_name = metric

            hash_key = keyify(pk, dimension, interval, metric_name)
            value_dict = redis.hgetall(hash_key)
            nested[maybe_dumps(dimension)][maybe_dumps(metric)] = dict([
                (k, float(v)) for k, v in value_dict.items()
            ])
    return dict(nested)
Ejemplo n.º 14
0
def table_graph():
    from periods import Period
    params = {
            'tzoffset': g('tzoffset', 0.0),
            'period': g('period', str(Period.get(None))),
            }
    debug = g('debug', False)
    table = g('table', '')
    height = g('height', '300px')
    delay = g('delay', 5000)
    hwurl = req.GET.get('hwurl', '/' or req.url.split('table_graph.js')[0])
    include_string = \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/jquery.min.js'></script>\");"%hwurl
    include_string += \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/hailwhale.js'></script>\");"%hwurl
    include_string += \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/d3.js'></script>\");"%hwurl
    include_string += \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/nvd3.js'></script>\");"%hwurl

    return_string = '''
appended=false;\n
function jqinit() {{\n
    if(typeof(jQuery) == 'undefined' || typeof(jQuery.hailwhale) == 'undefined') {{\n
        if(!appended) {{\n
            appended = true;\n
            {include_string}\n
        }}\n
        setTimeout(jqinit, 250);\n
    }} else {{\n
        $(function() {{\n
        init_graphs =function() {{
                $.hailwhale('{hwurl}').graph_tables('{table}', {options});\n
                }}
        setTimeout(init_graphs, {delay});
        if(ui_loaded_funcs)
            ui_loaded_funcs.init_graphs = init_graphs;
        }});\n
    }}
}}
jqinit();\n


    '''.format( include_string=include_string, table=table, delay=delay,
            hwurl=hwurl, options=util.maybe_dumps(params))
    return return_string
Ejemplo n.º 15
0
    def reasons_for(cls, pk, formula='value/hits', known_data=None, period=None, recursive=True):
        metric, denomenator = parse_formula(formula)
        period = Period.get(period)
        pk_base, decision, option = pk
        base = '_'
        best = worst = None
        ranks = cls.cached_rank(pk, formula=formula, dimension=base,
            period=period, recursive=recursive, points=False)
        overall = cls.cached_rank([pk_base, decision], formula=formula, dimension=base,
            period=period, recursive=recursive, points=False)
        parent_score = overall[base]['score']
        parent_count = overall[base]['count']
        ranks[base]['effect'] = ranks[base]['count'] * ranks[base]['difference']

        def delta(info):
            diff = info['score'] - parent_score
            info['value_diff'] = info['value'] - overall[base]['value']
            info['difference'] += diff
            if math.fabs(diff) > 0  and info['count'] > 0:
                info['effect'] += diff * info['count']
                info['significance'] = ((.5 * info['effect']) ** 2) / parent_count
            else:
                info['effect'] = 0
                info['significance'] = 0
            return info
        known_dimensions = iterate_dimensions(known_data)
        for dim, info in ranks.items():
            ranks[dim] = info = delta(info)
            if try_loads(dim) in known_dimensions and info['important']:
                best_score = best and ranks[best]['score']
                worst_score = worst and ranks[worst]['score']
                if info['score'] > best_score:
                    best = dim
                if info['score'] < worst_score:
                    worst = dim
        i = {'good': best and ranks[best] or {},
                'bad': worst and ranks[worst] or {},
                #'ranks': ranks,
                'base': ranks[base],
                'parent': overall[base]}
        i['high'] = i['good'].get('difference', 0)
        i['high_sig'] = i['good'].get('significance', 0) > 4
        i['low'] = i['bad'].get('difference', 0)
        i['low_sig'] = i['bad'].get('significance', 0) > 4
        return i
Ejemplo n.º 16
0
def _ranked(redis,
            pk,
            parent_dimension,
            metric,
            period,
            ats,
            start=0,
            size=10,
            sort_dir=None):
    top, bot = parse_formula(metric)
    rank_keyify = lambda ats, met: keyify('rank', pk, parent_dimension,
                                          Period.get(period).interval, ats, met
                                          )
    final_rank_key = rank_keyify(ats, metric)

    def squash_ats(met):
        if len(ats) > 1:
            map(lambda at: redis.zremrangebyscore(rank_keyify(at, met), 0, 0),
                ats)
            redis.zunionstore(rank_keyify(ats, met),
                              map(lambda at: rank_keyify(at, met), ats))

    squash_ats(top)
    if bot:
        squash_ats(bot)
        top_key, bot_key = rank_keyify(ats, top), rank_keyify(ats, bot)
        redis.execute_command(
            "eval", """
        for key_i, key_n in ipairs(redis.call("zrange", KEYS[2], 0, -1)) do
            local top_s = tonumber(redis.call("zscore", KEYS[1], key_n))
            local bot_s = tonumber(redis.call("zscore", KEYS[2], key_n))
            if top_s and bot_s and bot_s > 0 then
                redis.call("zadd", KEYS[3], top_s/bot_s, key_n)
            end
        end
        """, 3, top_key, bot_key, final_rank_key)
        redis.zremrangebyscore(final_rank_key, 0, 0)
    return redis.zrange(final_rank_key,
                        start,
                        start + size,
                        desc=not sort_dir
                        or sort_dir.upper() in ['-', 'DESC', 'HIGH'])
Ejemplo n.º 17
0
    def plotpoints(cls, pk, dimensions=None, metrics=None,
            depth=0, period=None, flot_time=False, points_type=dict):
        metrics = metrics or ['hits']
        if isinstance(metrics, basestring):
            metrics = [metrics]
        period = Period.get(period)
        dts = period.datetimes_strs()
        nonsparse = defaultdict(defaultdict)

        # Hardwire time-based metrics for lulz
        time_metrics = {'second': 1, 'minute': 60, 'hour': 3600, 'day': 3600*24, 'week': 3600*24*7}
        #for t_m, factor in time_metrics.items():
        #    if t_m in metrics:
        #        metrics.remove(t_m)
        #        for dimension in dimensions:
        #            nonsparse[dimension][t_m] = list()
        #            for dt in dts:
        #                if flot_time:
        #                    dt = to_flot_time(Period.parse_dt_str(dt))
        #                nonsparse[dimension][t_m].append([dt, period.interval / factor])
        #            nonsparse[dimension][t_m] = points_type(nonsparse[dimension][t_m])
        # Pull the plotpoints that exist from Redis
        sparse = cls.whale_driver().retrieve(pk, dimensions, metrics, period=period)
        
        for dimensions, metrics in sparse.items():
            for metric, points in metrics.items():
                #if metric in time_metrics: continue
                nonsparse[dimensions][metric] = []
                for dt in dts:
                    if flot_time:
                        dt = to_flot_time(Period.parse_dt_str(dt))
                    value = points[dt] if dt in points else 0
                    nonsparse[dimensions][metric].append([dt, float(value)])
                nonsparse[dimensions][metric] = points_type(nonsparse[dimensions][metric])
        if depth > 0:
            for sub in cls.get_subdimensions(pk, dimensions):
                nonsparse = dict(nonsparse.items() +
                    cls.plotpoints(pk, sub, metrics, depth=depth - 1, period=period,
                        flot_time=flot_time, points_type=points_type).items())
        return nonsparse
Ejemplo n.º 18
0
 def totals(cls, pk, dimensions=None, metrics=None, periods=None):
     if not periods:
         periods = DEFAULT_PERIODS
     if not isinstance(periods, list):
         periods = [periods]
     metrics = metrics or ['hits']
     if not isinstance(metrics, list):
         metrics = [metrics]
     d = {}
     for p in periods:
         p_data = cls.plotpoints(pk, dimensions, metrics, period=str(p))
         p_totals = dict()
         for dim, mets in p_data.items():
             p_totals[dim] = dict()
             for met, vals in mets.items():
                 p_totals[dim][met] = sum([
                     v for k, v in vals.items()
                     if Period.get(p).flatten(k)])
         d[str(p)] = p_totals
     d['alltime'] = cls.whale_driver().retrieve(
             pk, dimensions, metrics, period='all')
     return d
Ejemplo n.º 19
0
def graph():
    from periods import Period
    params = {'pk': g('pk', '_', False),
            'dimension': g('dimension', '_', False),
            'metric': g('metric', 'hits', False),
            'depth': g('depth', 0),
            'tzoffset': g('tzoffset', 0.0),
            'period': g('period', str(Period.get(None))),
            'area': g('area', ''),
            }
    pk = params['pk']
    dimension = params['dimension']
    metric = params['metric']
    period = Period.get(params['period'])
    debug = g('debug', False)
    parent_div = g('parent_div', 'hailwhale_graphs')
    table = g('table', False)
    height = g('height', '300px')
    params['title'] = g('title', '')
    if not params['title']:
        pkname = g('pk', '')
        dimname = util.try_loads(g('dimension', 'Overall'))
        dimname = isinstance(dimname, list) and dimname[-1] or dimname
        params['title'] = '%s [%s]' % (util.maybe_dumps(pkname), util.maybe_dumps(dimname))
    if isinstance(table, basestring):
        table = table.lower() == 'true'
    hwurl = req.GET.get('hwurl', req.url.split('graph.js')[0])
    params['autoupdate'] = g('live', True)
    params['interval'] = g('interval', 6000)
    graph_id = hashlib.md5(str(params)).hexdigest()
    include_string = \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/jquery.min.js'></script>\");"%hwurl
    if table:
        try:
            columns = int(g('table', 6, int))
        except:
            columns = 6
        pps = Whale.plotpoints(pk, dimension, metric, period=period,
                depth=params['depth'])
        dates = [p for p in
                Period.get(period).datetimes_strs()][(-1*columns - 1):]

        table_str = '''
            $('#{id} .table').html('<table style="width: 100%"> <tr> <th></th> <th></th> {columns} </tr>
        '''.strip().format(id=graph_id,columns=' '.join([
            '<th>%s</th>'%date.replace('00:00:00 ', '') for date in dates]))

        dimensions = pps.keys()
        if '_' in dimensions:
            dimensions.remove('_')
            dimensions = ['_'] + dimensions
        for dimension_counter, dimension in enumerate(dimensions):
            checked = 'off'
            if dimension_counter < 10:
                checked = 'on'
            if dimension == '_':
                if params['depth']:
                    continue
                dimension_name = '<b>Overall</b>'
            else:
                dimension_name = dimension.capitalize()
            table_str += '''
                <tr> <td><input id="" style="display: none" type="checkbox" value="{checked}" name="checkbox-{pk}-{dimension}"></td> <td>{dimension_name}</td> {columns} </tr>
                '''.format(pk=pk, dimension=dimension, checked=checked,
                        dimension_name=dimension_name,
                        columns=' '.join([
                "<td>%s</td>"%int(pps[dimension][metric][date]) for date in dates])).strip()

        table_str += '''</table>');'''
    else:
        table_str = ''
    include_string = \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/hailwhale.min.js'></script>\");"%hwurl

    return_string = '''
appended=false;\n
document.write('<div id="{id}"><div class="graph" style="height: {height}"></div><div class="table"></div></div>');\n
function jqinit() {{\n
    if(typeof(jQuery) == 'undefined' || typeof(jQuery.hailwhale) == 'undefined') {{\n
        if(!appended) {{\n
            appended = true;\n
            {include_string}\n
        }}\n
        setTimeout(jqinit, 250);\n
    }} else {{\n
        $(function() {{\n
                $.hailwhale('{hwurl}').add_graph('{id} .graph', {options});\n
                {table_str}
        }});\n
    }}
}}
jqinit();\n


    '''.format(parent_div=parent_div, include_string=include_string,
            hwurl=hwurl, table_str=table_str, height=height,
            id=graph_id,
            options=util.maybe_dumps(params))
    return return_string
Ejemplo n.º 20
0
    def reasons_for(cls,
                    pk,
                    formula='value/hits',
                    known_data=None,
                    period=None,
                    recursive=True):
        metric, denomenator = parse_formula(formula)
        period = Period.get(period)
        pk_base, decision, option = pk
        base = '_'
        best = worst = None
        ranks = cls.cached_rank(pk,
                                formula=formula,
                                dimension=base,
                                period=period,
                                recursive=recursive,
                                points=False)
        overall = cls.cached_rank([pk_base, decision],
                                  formula=formula,
                                  dimension=base,
                                  period=period,
                                  recursive=recursive,
                                  points=False)
        parent_score = overall[base]['score']
        parent_count = overall[base]['count']
        ranks[base][
            'effect'] = ranks[base]['count'] * ranks[base]['difference']

        def delta(info):
            diff = info['score'] - parent_score
            info['value_diff'] = info['value'] - overall[base]['value']
            info['difference'] += diff
            if math.fabs(diff) > 0 and info['count'] > 0:
                info['effect'] += diff * info['count']
                info['significance'] = (
                    (.5 * info['effect'])**2) / parent_count
            else:
                info['effect'] = 0
                info['significance'] = 0
            return info

        known_dimensions = iterate_dimensions(known_data)
        for dim, info in ranks.items():
            ranks[dim] = info = delta(info)
            if try_loads(dim) in known_dimensions and info['important']:
                best_score = best and ranks[best]['score']
                worst_score = worst and ranks[worst]['score']
                if info['score'] > best_score:
                    best = dim
                if info['score'] < worst_score:
                    worst = dim
        i = {
            'good': best and ranks[best] or {},
            'bad': worst and ranks[worst] or {},
            #'ranks': ranks,
            'base': ranks[base],
            'parent': overall[base]
        }
        i['high'] = i['good'].get('difference', 0)
        i['high_sig'] = i['good'].get('significance', 0) > 4
        i['low'] = i['bad'].get('difference', 0)
        i['low_sig'] = i['bad'].get('significance', 0) > 4
        return i
Ejemplo n.º 21
0
def graph():
    from periods import Period
    params = {
        'pk': g('pk', '_', False),
        'dimension': g('dimension', '_', False),
        'metric': g('metric', 'hits', False),
        'depth': g('depth', 0),
        'tzoffset': g('tzoffset', 0.0),
        'period': g('period', str(Period.get(None))),
        'area': g('area', ''),
    }
    pk = params['pk']
    dimension = params['dimension']
    metric = params['metric']
    period = Period.get(params['period'])
    debug = g('debug', False)
    parent_div = g('parent_div', 'hailwhale_graphs')
    table = g('table', False)
    height = g('height', '300px')
    params['title'] = g('title', '')
    if not params['title']:
        pkname = g('pk', '')
        dimname = util.try_loads(g('dimension', 'Overall'))
        dimname = isinstance(dimname, list) and dimname[-1] or dimname
        params['title'] = '%s [%s]' % (util.maybe_dumps(pkname),
                                       util.maybe_dumps(dimname))
    if isinstance(table, basestring):
        table = table.lower() == 'true'
    hwurl = req.GET.get('hwurl', req.url.split('graph.js')[0])
    params['autoupdate'] = g('live', True)
    params['interval'] = g('interval', 6000)
    graph_id = hashlib.md5(str(params)).hexdigest()
    include_string = \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/jquery.min.js'></script>\");"%hwurl
    if table:
        try:
            columns = int(g('table', 6, int))
        except:
            columns = 6
        pps = Whale.plotpoints(pk,
                               dimension,
                               metric,
                               period=period,
                               depth=params['depth'])
        dates = [p for p in Period.get(period).datetimes_strs()
                 ][(-1 * columns - 1):]

        table_str = '''
            $('#{id} .table').html('<table style="width: 100%"> <tr> <th></th> <th></th> {columns} </tr>
        '''.strip().format(id=graph_id,
                           columns=' '.join([
                               '<th>%s</th>' % date.replace('00:00:00 ', '')
                               for date in dates
                           ]))

        dimensions = pps.keys()
        if '_' in dimensions:
            dimensions.remove('_')
            dimensions = ['_'] + dimensions
        for dimension_counter, dimension in enumerate(dimensions):
            checked = 'off'
            if dimension_counter < 10:
                checked = 'on'
            if dimension == '_':
                if params['depth']:
                    continue
                dimension_name = '<b>Overall</b>'
            else:
                dimension_name = dimension.capitalize()
            table_str += '''
                <tr> <td><input id="" style="display: none" type="checkbox" value="{checked}" name="checkbox-{pk}-{dimension}"></td> <td>{dimension_name}</td> {columns} </tr>
                '''.format(pk=pk,
                           dimension=dimension,
                           checked=checked,
                           dimension_name=dimension_name,
                           columns=' '.join([
                               "<td>%s</td>" %
                               int(pps[dimension][metric][date])
                               for date in dates
                           ])).strip()

        table_str += '''</table>');'''
    else:
        table_str = ''
    include_string = \
"document.write(\"<scr\" + \"ipt type='text/javascript' src='%sjs/hailwhale.min.js'></script>\");"%hwurl

    return_string = '''
appended=false;\n
document.write('<div id="{id}"><div class="graph" style="height: {height}"></div><div class="table"></div></div>');\n
function jqinit() {{\n
    if(typeof(jQuery) == 'undefined' || typeof(jQuery.hailwhale) == 'undefined') {{\n
        if(!appended) {{\n
            appended = true;\n
            {include_string}\n
        }}\n
        setTimeout(jqinit, 250);\n
    }} else {{\n
        $(function() {{\n
                $.hailwhale('{hwurl}').add_graph('{id} .graph', {options});\n
                {table_str}
        }});\n
    }}
}}
jqinit();\n


    '''.format(parent_div=parent_div,
               include_string=include_string,
               hwurl=hwurl,
               table_str=table_str,
               height=height,
               id=graph_id,
               options=util.maybe_dumps(params))
    return return_string