def main():
print('&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&')
client = TSDBClient(30000)
# add a trigger. notice the argument. It does not do anything here but
# could be used to save a shlep of data from client to server.
client.add_trigger('junk', 'insert_ts', None, 'db:one:ts')
# our stats trigger
client.add_trigger('stats', 'insert_ts', ['mean', 'std'], None)
# Set up 50 time series
mus = np.random.uniform(low=0.0, high=1.0, size=50)
sigs = np.random.uniform(low=0.05, high=0.4, size=50)
jits = np.random.uniform(low=0.05, high=0.2, size=50)
# dictionaries for time series and their metadata
tsdict = {}
metadict = {}
for i, m, s, j in zip(range(50), mus, sigs, jits):
meta, tsrs = tsmaker(m, s, j)
# the primary key format is ts-1, ts-2, etc
pk = "ts-{}".format(i)
tsdict[pk] = tsrs
meta[
'vp'] = False # augment metadata with a boolean asking if this is a VP.
metadict[pk] = meta
# choose 5 distinct vantage point time series
vpkeys = [
"ts-{}".format(i)
for i in np.random.choice(range(50), size=5, replace=False)
]
for i in range(5):
# add 5 triggers to upsert distances to these vantage points
client.add_trigger('corr', 'insert_ts', ["d_vp-{}".format(i)],
tsdict[vpkeys[i]])
# change the metadata for the vantage points to have meta['vp']=True
metadict[vpkeys[i]]['vp'] = True
# Having set up the triggers, now insert the time series, and upsert the metadata
for k in tsdict:
client.insert_ts(k, tsdict[k])
time.sleep(1)
client.upsert_meta(k, metadict[k])
print("UPSERTS FINISHED")
time.sleep(5)
print('---------------------')
print("STARTING SELECTS")
print('---------DEFAULT------------')
client.select()
# in this version, select has sprouted an additional keyword argument
# to allow for sorting. Limits could also be enforced through this.
print('---------ADDITIONAL------------')
client.select(additional={'sort_by': '-order'})
print('----------ORDER FIELD-----------')
_, results = client.select(fields=['order'])
for k in results:
print(k, results[k])
print('---------ALL FIELDS------------')
client.select(fields=[])
print('------------TS with order 1---------')
client.select({'order': 1}, fields=['ts'])
print('------------All fields, blarg 1 ---------')
client.select({'blarg': 1}, fields=[])
print('------------order 1 blarg 2 no fields---------')
_, bla = client.select({'order': 1, 'blarg': 2})
print(bla)
print(
'------------order >= 4 order, blarg and mean sent back, also sorted---------'
)
_, results = client.select({'order': {
'>=': 4
}},
fields=['order', 'blarg', 'mean'],
additional={'sort_by': '-order'})
for k in results:
print(k, results[k])
print('------------order 1 blarg >= 1 fields blarg and std---------')
_, results = client.select({
'blarg': {
'>=': 1
},
'order': 1
},
fields=['blarg', 'std'])
for k in results:
print(k, results[k])
print('------now computing vantage point stuff---------------------')
print("VPS", vpkeys)
#
# # we first create a query time series.
_, query = tsmaker(0.5, 0.2, 0.1)
# query = tsdict['ts-6']
#
# # your code here begins
#
# # Step 1: in the vpdist key, get distances from query to vantage points
# # this is an augmented select
res = client.augmented_select('corr', ['dist'], query, {'vp': True})
print(res)
# # 1b: choose the lowest distance vantage point
# # you can do this in local code
d_res = res[1]
sorted_res = []
for k, v in d_res.items():
sorted_res.append((v['dist'], k))
sorted_res.sort()
D = sorted_res[0][0]
D_vp = vpkeys.index(sorted_res[0][1])
print(sorted_res, 'D = ', D)
# # Step 2: find all time series within 2*d(query, nearest_vp_to_query)
# # this is an augmented select to the same proc in correlation
res2 = client.augmented_select('corr', ['dist'], query,
{'d_vp-{}'.format(D_vp): {
'<=': 2 * D
}})
print(res2)
# # 2b: find the smallest distance amongst this ( or k smallest)
d_res = res2[1]
sorted_res = []
for k, v in d_res.items():
sorted_res.append((v['dist'], k))
sorted_res.sort()
D = sorted_res[0][0]
D_k = sorted_res[0][1]
print(sorted_res, 'D = ', D, 'D_k = ', D_k)
nearestwanted = D_k
# # you can do this in local code
# # your code here ends
# # plot the timeseries to see visually how we did.
import matplotlib
matplotlib.use('qt4agg')
import matplotlib.pyplot as plt
plt.plot(query, label='')
plt.plot(tsdict[nearestwanted])
plt.show()
def main():
print('&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&')
client = TSDBClient(30000)
# add a trigger. notice the argument. It does not do anything here but
# could be used to save a shlep of data from client to server.
client.add_trigger('junk', 'insert_ts', None, 'db:one:ts')
# our stats trigger
client.add_trigger('stats', 'insert_ts', ['mean', 'std'], None)
# Set up 50 time series
mus = np.random.uniform(low=0.0, high=1.0, size=50)
sigs = np.random.uniform(low=0.05, high=0.4, size=50)
jits = np.random.uniform(low=0.05, high=0.2, size=50)
# dictionaries for time series and their metadata
tsdict = {}
metadict = {}
for i, m, s, j in zip(range(50), mus, sigs, jits):
meta, tsrs = tsmaker(m, s, j)
# the primary key format is ts-1, ts-2, etc
pk = "ts-{}".format(i)
tsdict[pk] = tsrs
meta['vp'] = False # augment metadata with a boolean asking if this is a VP.
metadict[pk] = meta
# choose 5 distinct vantage point time series
vpkeys = ["ts-{}".format(i) for i in np.random.choice(range(50), size=5, replace=False)]
for i in range(5):
# add 5 triggers to upsert distances to these vantage points
client.add_trigger('corr', 'insert_ts', ["d_vp-{}".format(i)], tsdict[vpkeys[i]])
# change the metadata for the vantage points to have meta['vp']=True
metadict[vpkeys[i]]['vp'] = True
# Having set up the triggers, now insert the time series, and upsert the metadata
for k in tsdict:
client.insert_ts(k, tsdict[k])
time.sleep(1)
client.upsert_meta(k, metadict[k])
print("UPSERTS FINISHED")
time.sleep(5)
print('---------------------')
print("STARTING SELECTS")
print('---------DEFAULT------------')
client.select()
# in this version, select has sprouted an additional keyword argument
# to allow for sorting. Limits could also be enforced through this.
print('---------ADDITIONAL------------')
client.select(additional={'sort_by': '-order'})
print('----------ORDER FIELD-----------')
_, results = client.select(fields=['order'])
for k in results:
print(k, results[k])
print('---------ALL FIELDS------------')
client.select(fields=[])
print('------------TS with order 1---------')
client.select({'order': 1}, fields=['ts'])
print('------------All fields, blarg 1 ---------')
client.select({'blarg': 1}, fields=[])
print('------------order 1 blarg 2 no fields---------')
_, bla = client.select({'order': 1, 'blarg': 2})
print(bla)
print('------------order >= 4 order, blarg and mean sent back, also sorted---------')
_, results = client.select({'order': {'>=': 4}}, fields=['order', 'blarg', 'mean'], additional={'sort_by': '-order'})
for k in results:
print(k, results[k])
print('------------order 1 blarg >= 1 fields blarg and std---------')
_, results = client.select({'blarg': {'>=': 1}, 'order': 1}, fields=['blarg', 'std'])
for k in results:
print(k, results[k])
print('------now computing vantage point stuff---------------------')
print("VPS", vpkeys)
#
# # we first create a query time series.
_, query = tsmaker(0.5, 0.2, 0.1)
# query = tsdict['ts-6']
#
# # your code here begins
#
# # Step 1: in the vpdist key, get distances from query to vantage points
# # this is an augmented select
res = client.augmented_select('corr', ['dist'], query, {'vp': True})
print(res)
# # 1b: choose the lowest distance vantage point
# # you can do this in local code
d_res = res[1]
sorted_res = []
for k, v in d_res.items():
sorted_res.append((v['dist'], k))
sorted_res.sort()
D = sorted_res[0][0]
D_vp = vpkeys.index(sorted_res[0][1])
print (sorted_res, 'D = ', D)
# # Step 2: find all time series within 2*d(query, nearest_vp_to_query)
# # this is an augmented select to the same proc in correlation
res2 = client.augmented_select('corr', ['dist'], query, {'d_vp-{}'.format(D_vp): {'<=': 2*D}})
print (res2)
# # 2b: find the smallest distance amongst this ( or k smallest)
d_res = res2[1]
sorted_res = []
for k, v in d_res.items():
sorted_res.append( (v['dist'], k) )
sorted_res.sort()
D = sorted_res[0][0]
D_k = sorted_res[0][1]
print (sorted_res, 'D = ', D, 'D_k = ', D_k)
nearestwanted = D_k
# # you can do this in local code
# # your code here ends
# # plot the timeseries to see visually how we did.
import matplotlib
matplotlib.use('qt4agg')
import matplotlib.pyplot as plt
plt.plot(query, label='')
plt.plot(tsdict[nearestwanted])
plt.show()
