def get_json_data(self): df = self.get_df() chart_data = self.to_series(df) time_compare = self.form_data.get('time_compare') if time_compare: query_object = self.query_obj() delta = utils.parse_human_timedelta(time_compare) query_object['inner_from_dttm'] = query_object['from_dttm'] query_object['inner_to_dttm'] = query_object['to_dttm'] query_object['from_dttm'] -= delta query_object['to_dttm'] -= delta df2 = self.get_df(query_object) df2.index += delta chart_data += self.to_series( df2, classed='dashed', title_suffix="---") chart_data = sorted(chart_data, key=lambda x: x['key']) data = { 'chart_data': chart_data, 'query': self.results.query, 'duration': self.results.duration, } return dumps(data)
def get_json_data(self): df = self.get_df() chart_data = self.to_series(df) time_compare = self.form_data.get('time_compare') if time_compare: query_object = self.query_obj() delta = utils.parse_human_timedelta(time_compare) query_object['inner_from_dttm'] = query_object['from_dttm'] query_object['inner_to_dttm'] = query_object['to_dttm'] query_object['from_dttm'] -= delta query_object['to_dttm'] -= delta df2 = self.get_df(query_object) df2.index += delta chart_data += self.to_series(df2, classed='dashed', title_suffix="---") chart_data = sorted(chart_data, key=lambda x: x['key']) data = { 'chart_data': chart_data, 'query': self.results.query, 'duration': self.results.duration, } return dumps(data)
def query_obj(self): """ Building a query object """ form_data = self.form_data groupby = form_data.get("groupby") or [] metrics = form_data.get("metrics") or ['count'] granularity = form_data.get("granularity", "1 day") if granularity != "all": granularity = utils.parse_human_timedelta( granularity).total_seconds() * 1000 limit = int(form_data.get("limit", 0)) row_limit = int( form_data.get("row_limit", config.get("ROW_LIMIT"))) since = form_data.get("since", "1 year ago") from_dttm = utils.parse_human_datetime(since) if from_dttm > datetime.now(): from_dttm = datetime.now() - (from_dttm-datetime.now()) until = form_data.get("until", "now") to_dttm = utils.parse_human_datetime(until) if from_dttm >= to_dttm: flash("The date range doesn't seem right.", "danger") from_dttm = to_dttm # Making them identical to not raise # extras are used to query elements specific to a datasource type # for instance the extra where clause that applies only to Tables extras = { 'where': form_data.get("where", '') } d = { 'granularity': granularity, 'from_dttm': from_dttm, 'to_dttm': to_dttm, 'is_timeseries': True, 'groupby': groupby, 'metrics': metrics, 'row_limit': row_limit, 'filter': self.query_filters(), 'timeseries_limit': limit, 'extras': extras, } return d
def get_json_data(self): df = self.get_df() chart_data = self.to_series(df) time_compare = self.form_data.get("time_compare") if time_compare: query_object = self.query_obj() delta = utils.parse_human_timedelta(time_compare) query_object["inner_from_dttm"] = query_object["from_dttm"] query_object["inner_to_dttm"] = query_object["to_dttm"] query_object["from_dttm"] -= delta query_object["to_dttm"] -= delta df2 = self.get_df(query_object) df2.index += delta chart_data += self.to_series(df2, classed="dashed", title_suffix="---") chart_data = sorted(chart_data, key=lambda x: x["key"]) data = {"chart_data": chart_data, "query": self.results.query, "duration": self.results.duration} return dumps(data)
def query_obj(self): """ Building a query object """ form_data = self.form_data groupby = form_data.get("groupby") or [] metrics = form_data.get("metrics") or ['count'] granularity = form_data.get("granularity", "1 day") if granularity != "all": granularity = utils.parse_human_timedelta( granularity).total_seconds() * 1000 limit = int(form_data.get("limit", 0)) row_limit = int(form_data.get("row_limit", config.get("ROW_LIMIT"))) since = form_data.get("since", "1 year ago") from_dttm = utils.parse_human_datetime(since) if from_dttm > datetime.now(): from_dttm = datetime.now() - (from_dttm - datetime.now()) until = form_data.get("until", "now") to_dttm = utils.parse_human_datetime(until) if from_dttm >= to_dttm: flash("The date range doesn't seem right.", "danger") from_dttm = to_dttm # Making them identical to not raise # extras are used to query elements specific to a datasource type # for instance the extra where clause that applies only to Tables extras = {'where': form_data.get("where", '')} d = { 'granularity': granularity, 'from_dttm': from_dttm, 'to_dttm': to_dttm, 'is_timeseries': True, 'groupby': groupby, 'metrics': metrics, 'row_limit': row_limit, 'filter': self.query_filters(), 'timeseries_limit': limit, 'extras': extras, } return d
def query_obj(self): """ Building a query object """ ds = self.datasource args = self.form_data groupby = args.getlist("groupby") or [] metrics = args.getlist("metrics") or ['count'] granularity = args.get("granularity", "1 day") if granularity != "all": granularity = utils.parse_human_timedelta( granularity).total_seconds() * 1000 limit = int(args.get("limit", 0)) row_limit = int( args.get("row_limit", config.ROW_LIMIT)) since = args.get("since", "1 year ago") from_dttm = utils.parse_human_datetime(since) if from_dttm > datetime.now(): from_dttm = datetime.now() - (from_dttm-datetime.now()) until = args.get("until", "now") to_dttm = utils.parse_human_datetime(until) if from_dttm >= to_dttm: flash("The date range doesn't seem right.", "danger") from_dttm = to_dttm # Making them identicial to not raise d = { 'granularity': granularity, 'from_dttm': from_dttm, 'to_dttm': to_dttm, 'is_timeseries': True, 'groupby': groupby, 'metrics': metrics, 'row_limit': row_limit, 'filter': self.query_filters(), 'timeseries_limit': limit, } return d
def query( self, groupby, metrics, granularity, from_dttm, to_dttm, limit_spec=None, filter=None, is_timeseries=True, timeseries_limit=None, row_limit=None, inner_from_dttm=None, inner_to_dttm=None, extras=None): qry_start_dttm = datetime.now() inner_from_dttm = inner_from_dttm or from_dttm inner_to_dttm = inner_to_dttm or to_dttm # add tzinfo to native datetime with config from_dttm = from_dttm.replace(tzinfo=config.get("DRUID_TZ")) to_dttm = to_dttm.replace(tzinfo=config.get("DRUID_TZ")) query_str = "" aggregations = { m.metric_name: m.json_obj for m in self.metrics if m.metric_name in metrics } if granularity != "all": granularity = utils.parse_human_timedelta( granularity).total_seconds() * 1000 if not isinstance(granularity, basestring): granularity = {"type": "duration", "duration": granularity} qry = dict( datasource=self.datasource_name, dimensions=groupby, aggregations=aggregations, granularity=granularity, intervals=from_dttm.isoformat() + '/' + to_dttm.isoformat(), ) filters = None for col, op, eq in filter: cond = None if op == '==': cond = Dimension(col) == eq elif op == '!=': cond = ~(Dimension(col) == eq) elif op in ('in', 'not in'): fields = [] splitted = eq.split(',') if len(splitted) > 1: for s in eq.split(','): s = s.strip() fields.append(Filter.build_filter(Dimension(col) == s)) cond = Filter(type="or", fields=fields) else: cond = Dimension(col) == eq if op == 'not in': cond = ~cond if filters: filters = Filter(type="and", fields=[ Filter.build_filter(cond), Filter.build_filter(filters) ]) else: filters = cond if filters: qry['filter'] = filters client = self.cluster.get_pydruid_client() orig_filters = filters if timeseries_limit and is_timeseries: # Limit on the number of timeseries, doing a two-phases query pre_qry = deepcopy(qry) pre_qry['granularity'] = "all" pre_qry['limit_spec'] = { "type": "default", "limit": timeseries_limit, 'intervals': inner_from_dttm.isoformat() + '/' + inner_to_dttm.isoformat(), "columns": [{ "dimension": metrics[0] if metrics else self.metrics[0], "direction": "descending", }], } client.groupby(**pre_qry) query_str += "// Two phase query\n// Phase 1\n" query_str += json.dumps(client.query_dict, indent=2) + "\n" query_str += "//\nPhase 2 (built based on phase one's results)\n" df = client.export_pandas() if df is not None and not df.empty: dims = qry['dimensions'] filters = [] for index, row in df.iterrows(): fields = [] for dim in dims: f = Filter.build_filter(Dimension(dim) == row[dim]) fields.append(f) if len(fields) > 1: filt = Filter(type="and", fields=fields) filters.append(Filter.build_filter(filt)) elif fields: filters.append(fields[0]) if filters: ff = Filter(type="or", fields=filters) if not orig_filters: qry['filter'] = ff else: qry['filter'] = Filter(type="and", fields=[ Filter.build_filter(ff), Filter.build_filter(orig_filters)]) qry['limit_spec'] = None if row_limit: qry['limit_spec'] = { "type": "default", "limit": row_limit, "columns": [{ "dimension": metrics[0] if metrics else self.metrics[0], "direction": "descending", }], } client.groupby(**qry) query_str += json.dumps(client.query_dict, indent=2) df = client.export_pandas() return QueryResult( df=df, query=query_str, duration=datetime.now() - qry_start_dttm)
def query(self, groupby, metrics, granularity, from_dttm, to_dttm, limit_spec=None, filter=None, is_timeseries=True, timeseries_limit=None, row_limit=None, inner_from_dttm=None, inner_to_dttm=None, extras=None, select=None): qry_start_dttm = datetime.now() inner_from_dttm = inner_from_dttm or from_dttm inner_to_dttm = inner_to_dttm or to_dttm # add tzinfo to native datetime with config from_dttm = from_dttm.replace(tzinfo=config.get("DRUID_TZ")) to_dttm = to_dttm.replace(tzinfo=config.get("DRUID_TZ")) query_str = "" aggregations = { m.metric_name: m.json_obj for m in self.metrics if m.metric_name in metrics } granularity = granularity or "all" if granularity != "all": granularity = utils.parse_human_timedelta( granularity).total_seconds() * 1000 if not isinstance(granularity, string_types): granularity = {"type": "duration", "duration": granularity} qry = dict( datasource=self.datasource_name, dimensions=groupby, aggregations=aggregations, granularity=granularity, intervals=from_dttm.isoformat() + '/' + to_dttm.isoformat(), ) filters = None for col, op, eq in filter: cond = None if op == '==': cond = Dimension(col) == eq elif op == '!=': cond = ~(Dimension(col) == eq) elif op in ('in', 'not in'): fields = [] splitted = eq.split(',') if len(splitted) > 1: for s in eq.split(','): s = s.strip() fields.append(Filter.build_filter(Dimension(col) == s)) cond = Filter(type="or", fields=fields) else: cond = Dimension(col) == eq if op == 'not in': cond = ~cond if filters: filters = Filter(type="and", fields=[ Filter.build_filter(cond), Filter.build_filter(filters) ]) else: filters = cond if filters: qry['filter'] = filters client = self.cluster.get_pydruid_client() orig_filters = filters if timeseries_limit and is_timeseries: # Limit on the number of timeseries, doing a two-phases query pre_qry = deepcopy(qry) pre_qry['granularity'] = "all" pre_qry['limit_spec'] = { "type": "default", "limit": timeseries_limit, 'intervals': inner_from_dttm.isoformat() + '/' + inner_to_dttm.isoformat(), "columns": [{ "dimension": metrics[0] if metrics else self.metrics[0], "direction": "descending", }], } client.groupby(**pre_qry) query_str += "// Two phase query\n// Phase 1\n" query_str += json.dumps(client.query_dict, indent=2) + "\n" query_str += "//\nPhase 2 (built based on phase one's results)\n" df = client.export_pandas() if df is not None and not df.empty: dims = qry['dimensions'] filters = [] for index, row in df.iterrows(): fields = [] for dim in dims: f = Filter.build_filter(Dimension(dim) == row[dim]) fields.append(f) if len(fields) > 1: filt = Filter(type="and", fields=fields) filters.append(Filter.build_filter(filt)) elif fields: filters.append(fields[0]) if filters: ff = Filter(type="or", fields=filters) if not orig_filters: qry['filter'] = ff else: qry['filter'] = Filter( type="and", fields=[ Filter.build_filter(ff), Filter.build_filter(orig_filters) ]) qry['limit_spec'] = None if row_limit: qry['limit_spec'] = { "type": "default", "limit": row_limit, "columns": [{ "dimension": metrics[0] if metrics else self.metrics[0], "direction": "descending", }], } client.groupby(**qry) query_str += json.dumps(client.query_dict, indent=2) df = client.export_pandas() if df is None or df.size == 0: raise Exception("No data was returned.") if (not is_timeseries and granularity == "all" and 'timestamp' in df.columns): del df['timestamp'] # Reordering columns cols = [] if 'timestamp' in df.columns: cols += ['timestamp'] cols += [col for col in groupby if col in df.columns] cols += [col for col in metrics if col in df.columns] cols += [col for col in df.columns if col not in cols] df = df[cols] return QueryResult(df=df, query=query_str, duration=datetime.now() - qry_start_dttm)