def get_model_stats_from_es(cfg, model_name, model_version):
'''
[{'date': '2020-01-17', 'model': {'name': 's32', 'version': 1},
'stats': {'g_g_m': [0.32095959595959594, 0.4668649491714752], 'g_g_f': [0.3654040404040404, 0.4815635452904544], 'g_g_x': [0.31363636363636366, 0.46398999646418304], 'a_1': [0.198989898989899, 0.3992572317838901], 'a_2': [0.2474747474747475, 0.4315630593164027], 'a_3': [0.295959595959596, 0.45649211860504146], 'a_4': [0.25757575757575757, 0.43731748751040456], 't_3G': [0.0, 1.0], 't_4G': [0.0, 1.0], 'si_1': [0.37424242424242427, 0.4839470491115894], 'si_2': [0.4042929292929293, 0.49077533664980666], 'si_3': [0.22146464646464648, 0.4152500106648333], 'price_cat_0': [0.0, 1.0], 'price_cat_1': [0.3333333333333333, 0.4714243623012701], 'price_cat_2': [0.3333333333333333, 0.47142436230126994], 'price_cat_3': [0.3333333333333333, 0.47142436230126994], 'holiday_stats': [0.044444444444444446, 0.20723493215097805]}}]
'''
es = ESClient(cfg['es_host'], cfg['es_port'], cfg['es_model_index'],
cfg['es_model_type'])
body = {
"query": {
"bool": {
"must": [{
"match": {
"model.name": model_name
}
}, {
"match": {
"model.version": model_version
}
}]
}
}
}
doc = es.search(body)
if doc == None or len(doc) != 1:
raise Exception('model/version {}/{} not valid'.format(
model_name, model_version))
return doc[0]
def test_es_predictions_search(self):
es_client_predictions = ESClient(self.cfg['es_host'],
self.cfg['es_port'],
self.cfg['es_predictions_index'],
self.cfg['es_predictions_type'])
predictions = es_client_predictions.search({"size": 100})
self.assertTrue(len(predictions) > 0)
self.assertTrue(len(predictions) >= 40)
def test_4(cfg):
es_client_booking = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_booking_index'],
cfg['es_booking_type'])
bookings = es_client_booking.search({}) # get at most 1000 results for now
bookings = optimizer.util.adjust_booking_dates(bookings)
bookings_map = optimizer.util.get_bookings_map(bookings)
ands = ['b1', 'b2']
day = cfg['today']
r = optimizer.main.get_bb_count(cfg, bookings_map)(ands, [], day)
print(r)
def test_2(cfg):
es_client_tbr = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_tbr_index'], cfg['es_tbr_type'])
es_client_booking = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_booking_index'],
cfg['es_booking_type'])
bookings = es_client_booking.search({}) # get at most 1000 results for now
bookings_map = optimizer.util.get_bookings_map(bookings)
ands = ['b1', 'b2']
query = optimizer.dao.query_builder.get_tbr_ratio(ands, bookings_map,
es_client_tbr)
print(query)
def test_3(cfg):
es_client_predictions = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_predictions_index'],
cfg['es_predictions_type'])
es_client_booking = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_booking_index'],
cfg['es_booking_type'])
bookings = es_client_booking.search({}) # get at most 1000 results for now
bookings_map = optimizer.util.get_bookings_map(bookings)
ands = ['b1', 'b2']
day = cfg['today']
(query, result) = optimizer.dao.query_builder.get_prediction_count(
ands, [], bookings_map, day, es_client_predictions)
print(query)
print(result)
def test_1(cfg):
es_client_predictions = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_predictions_index'],
cfg['es_predictions_type'])
es_client_booking = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_booking_index'],
cfg['es_booking_type'])
bookings = es_client_booking.search({}) # get at most 1000 results for now
bookings_map = optimizer.util.get_bookings_map(bookings)
ands = ['b6']
ors = ['b7']
day = cfg['today']
day = optimizer.util.convert_date(day)
query = optimizer.dao.query_builder.get_prediction_count(
ands, ors, bookings_map, day, es_client_predictions)
print(query)
def get_model_stats(cfg, model_name, model_version):
es = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_model_index'], cfg['es_model_type'])
body = {
"query": {"bool": {"must": [
{"match": {
"model.name": model_name
}},
{"match": {
"model.version": model_version
}}
]}}
}
doc = es.search(body)
if doc == None or len(doc) != 1:
raise Exception(
'model/version {}/{} not valid'.format(model_name, model_version))
return doc[0]
def test_5(cfg):
es_client_booking = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_booking_index'],
cfg['es_booking_type'])
bookings = es_client_booking.search({}) # get at most 1000 results for now
bookings = optimizer.util.adjust_booking_dates(bookings)
bookings_map = optimizer.util.get_bookings_map(bookings)
ands = ['b1', 'b2']
day = cfg['today']
df_day = day
df_ands = ['b1']
df_allocated = {}
# inventory of bb (df row)
df_amount = 4000
booking = bookings[0]
# total inventory of connected resources
total_inventory = 10000
h, _ = optimizer.algo.hwm.update_allocation_for_booking(
None, day, booking, total_inventory)
r = h(df_day, df_ands, df_allocated, df_amount)
print(r)
def run(cfg):
global hive_context
sc = SparkContext()
hive_context = HiveContext(sc)
sc.setLogLevel('WARN')
# ESClient requires host ip
es_client_booking = ESClient(cfg['es_host'], cfg['es_port'],
cfg['es_booking_index'], cfg['es_booking_type'])
bookings = es_client_booking.search({}) # get at most 1000 results for now
bookings = optimizer.util.filter_valid_bookings(bookings)
# adjust dates in bookings
bookings = optimizer.util.adjust_booking_dates(bookings)
bookings_map = optimizer.util.get_bookings_map(bookings)
df = hive_context.createDataFrame(sc.emptyRDD(), optimizer.util.get_common_pyspark_schema())
today = cfg['today'] # YYYY-MM-DD
days = optimizer.util.get_days_from_bookings(today, bookings)
df = generate_resources(cfg, df, bookings_map, days, bookings, hive_context)
# Row(day='2018-04-02', ands=['b1', 'b3', 'b2'], minus=[], allocated={}, amount=43562)
print('defining resources')
df.cache()
print(df.take(1))
# run the allocation
df = hwm_allocation(df, bookings, days)
# Row(day='2018-04-02', ands=['b1', 'b3', 'b2'], minus=[], amount=43562, allocated={'b2': 800, 'b3': 1000, 'b1': 500})
print('bb-bookings allocation')
df.cache()
print(df.take(1))
# lock bookings
lock_booking(es_client_booking, True)
# remove bbs
remove_booking_buckets(cfg, days)
# save new booking-buckets into es
df = save_booking_buckets_in_es(cfg, df)
print('bbs saved')
df.cache()
print(df.take(1))
# unlock bookings
lock_booking(es_client_booking, False)
day = days[-1]
tomorrow = optimizer.util.get_next_date(day)
# use only tomorrow to create the allocation plan
df = df.filter(df.day == tomorrow)
# this method add the bbs ucdocs allocation_map with their values
df = add_ucdoc_bb_allocation_map(cfg, df, bookings_map)
# [Row(day='2018-04-02', ands=['b1', 'b3', 'b2'], minus=[], amount=43562, allocated={'b2': 800, 'b3': 1000, 'b1': 500}, allocation_map={'minusonepage,3,5G,g_x,2,pt,1002,icc': {'b2': 1, 'b3': 2, 'b1': 1}, 'magazinelock,2,3G,g_x,3,pt,1005,icc': {'b2': 56, 'b3': 70, 'b1': 35}, 'magazinelock,2,4G,g_x,3,pt,1005,icc': {'b2': 56, 'b3': 70, 'b1': 35}, 'minusonepage,3,5G,g_x,2,pt,1003,icc': {'b2': 6, 'b3': 8, 'b1': 4}, 'minusonepage,1,4G,g_x,2,pt,1003,icc': {'b2': 16, 'b3': 20, 'b1': 10}, 'minusonepage,2,4G,g_f,4,pt,1002,icc': {'b2': 12, 'b3': 15, 'b1': 8}, 'cloudFolder,2,5G,g_x,3,pt,1005,icc': {'b2': 57, 'b3': 72, 'b1': 36}, 'minusonepage,2,3G,g_x,3,pt,1002,icc': {'b2': 3, 'b3': 4, 'b1': 2}, 'minusonepage,1,3G,g_x,1,pt,1005,icc': {'b2': 27, 'b3': 33, 'b1': 17}, 'minusonepage,1,3G,g_x,4,pt,1004,icc': {'b2': 72, 'b3': 90, 'b1': 45}, 'magazinelock,2,5G,g_x,4,pt,1004,icc': {'b2': 32, 'b3': 40, 'b1': 20}, 'cloudFolder,2,3G,g_f,3,pt,1002,icc': {'b2': 16, 'b3': 20, 'b1': 10}, 'cloudFolder,3,5G,g_f,2,pt,1004,icc': {'b2': 27, 'b3': 34, 'b1': 17}})]
print('ucdocs-bookings allocation')
df.cache()
print(df.take(1))
# at this point we have a df which is a allocation of bookings to bbs
df = df.select(df.day, explode(df.allocation_map))
# Row(day='2018-04-02', key='magazinelock,3,5G,g_x,2,pt,1004,icc', value={'b2': 14, 'b3': 18, 'b1': 9})
print('exploded')
df.cache()
print(df.take(1))
# agg all the allocation maps for a ucdoc
_map_type = MapType(StringType(), IntegerType())
_audf = udf(agg_allocation_maps, _map_type)
df = df.groupBy('key').agg(_audf(collect_list('value')).alias('allmap'))
# [Row(key='cloudFolder,3,5G,g_f,2,pt,1004,icc', allmap={'b2': 27, 'b3': 34, 'b1': 17})]
print('final aggregation')
df.cache()
print(df.take(1))
# writing into hdfs
filename = 'allmap-{}-{}'.format(
optimizer.util.convert_date_remove_dash(day), str(int(time.time())))
df.write.save(filename, format='json')
from imscommon.es.ims_esclient import ESClient
from pyspark import SparkContext, SparkConf, Row
from pyspark.sql.functions import concat_ws, count, lit, col, udf, expr, collect_list
from pyspark.sql import HiveContext
from pyspark.sql.types import IntegerType, StringType
import math
# read es
es_host = '10.193.217.111'
es_port = '9200'
es_index = 'predictions_02052020'
es_type = 'doc'
es = ESClient(es_host, es_port, es_index, es_type)
hits = es.search({"size": 1000})
es_records = {}
for ucdoc in hits:
uckey = ucdoc['uckey']
predictions = ucdoc['ucdoc']['predictions']
for day, hours in predictions.items():
hour = -1
for hour_doc in hours:
hour += 1
es_records[(uckey, day, hour, '0')] = hour_doc['h0']
es_records[(uckey, day, hour, '1')] = hour_doc['h1']
es_records[(uckey, day, hour, '2')] = hour_doc['h2']
es_records[(uckey, day, hour, '3')] = hour_doc['h3']
# print(next(iter(es_records.items())))
# print('************')