def all_grids():
mg = MongoDB()
mg.connect()
griddb = GridDB()
print('querying grid volumes...')
results = mg.group_by([{'$match': {'created_at': {'$gt': datetime.strptime('2012-10-15T20:00:02Z', '%Y-%m-%dT%H:%M:%SZ'),
'$lt': datetime.strptime('2012-11-15T20:00:02Z', '%Y-%m-%dT%H:%M:%SZ')}}}]) # print(results)
griddb.add(results)
ret = Grid.get_raw_pandas_ts(results, 'D')
STL.seasonal_decomposition(ret)
def filter_seasonal_outliers(tweets, aggregation):
ts = Grid.get_raw_pandas_ts(tweets, aggregation)
seasonal_ci = STL.seasonal_decomposition(ts)
ret = []
for step in ts:
if seasonal_ci[0] <= step[1] <= seasonal_ci[1]:
continue
ret += step
return ret
def single_grid(grid_id):
mg = MongoDB()
mg.connect()
start_time = datetime.strptime('2012-10-15T20:00:02Z', '%Y-%m-%dT%H:%M:%SZ')
end_time = datetime.strptime('2012-11-15T20:00:02Z', '%Y-%m-%dT%H:%M:%SZ')
print('querying grid volumes...')
# results = mg.group_by([{'$match': {'created_at': {'$gt': start_time, '$lt': end_time}, 'grid_id': grid_id}},
# {'$group': {'_id': '$grid_id', 'count': {'$sum': 1}}}])
results = mg.group_by([{'$match': {'created_at': {'$gt': datetime.strptime('2012-10-15T00:00:00Z', '%Y-%m-%dT%H:%M:%SZ'),
'$lt': datetime.strptime('2012-11-15T00:00:00Z', '%Y-%m-%dT%H:%M:%SZ')},
'grid_id': grid_id}}]) # print(results)
print(results)
ret = Grid.get_raw_pandas_ts(results, 'H')
# print('------------')
# print(ret)
print(STL.seasonal_decomposition(ret))
results = mg.group_by(
[
{
"$match": {
"created_at": {
"$gt": datetime.strptime("2012-10-15T20:00:02Z", "%Y-%m-%dT%H:%M:%SZ"),
"$lt": datetime.strptime("2012-10-22T20:00:02Z", "%Y-%m-%dT%H:%M:%SZ"),
}
}
}
]
) # print(results)
# results = mg.group_by([{'$match': {'created_at': {'$gt': datetime.strptime('2012-10-15T20:00:02Z', '%Y-%m-%dT%H:%M:%SZ'),
# '$lt': datetime.strptime('2012-11-15T20:00:02Z', '%Y-%m-%dT%H:%M:%SZ')}, 'grid_id': '34013011500'}}]) # print(results)
ret = Grid.get_raw_pandas_ts(results, "D")
# print('ret: ', ret)
# for result in Grid.get_ts(results, 'H'):
# print(result[0])
# # print('result: ', result)
# for tup in result:
# obj = []
# obj.append(result[0])
# ret.append(result[1])
# # print(tup)
# obj['date'] = tup #strftime('%Y-%m-%dT%H:%M:%SZ')
# ret.append(obj)
STL.seasonal_decomposition(ret)
print("grids initialized")
def get_seasonal_outliers(tweets, aggregation):
ts = Grid.get_raw_pandas_ts(tweets, aggregation)
if len(ts) > 1:
return STL.seasonal_decomposition(ts)
else:
return None