def feeder(start_date, end_date, e1, e2, q):
conf = SparkConf().setAppName("Simple App").setMaster(
"spark://127.0.0.1:7077").set("spark.cassandra.connection.host",
"127.0.0.1")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
a = ""
l = ['"SP1"', '"SP2"']
asia = pytz.timezone("Asia/Kolkata")
#creating a dataframe for the date range and ric names
rdd = sc.cassandraTable("testkeyspace", "stock_test").select(
"ric", "time_stamp", "high",
"low").where("ric in ?", ["SP1", "SP2", "SP3"]).where(
"time_stamp > ? and time_stamp < ?",
datetime(2010, 11, 26, 12, 30, tzinfo=asia),
datetime(2010, 12, 10, 12, 30, tzinfo=asia)).toDF()
# making a batch according to the time_stamp
rdd = rdd.orderBy("time_stamp").groupBy("time_stamp").agg(
collect_list(struct('ric', 'time_stamp', 'high', 'low'))).collect()
# sending one batch to analytical engine
for gr in rdd:
e2.clear()
send = gr[1]
q.put(send) #adding the batch to the queue
e2.set()
e1.wait()
def run_driver(keyspace, table):
conf = SparkConf().setAppName("PySpark Cassandra Sample Driver")
conf.set("spark.cassandra.connection.host", "127.0.0.1")
sc = CassandraSparkContext(conf=conf)
# Read some data from Cassandra
pixels = sc.cassandraTable(keyspace, table)
print pixels.first()
# Count unique visitors, notice that the data returned by Cassandra is
# a dict-like, you can access partition, clustering keys as well as
# columns by name. CQL collections: lists, sets and maps are converted
# to proper Python data types
visitors = pixels.map(lambda p: (p["data"]["visitor_id"],))\
.distinct()
print "Visitors: {:,}".format(visitors.count())
# Insert some new pixels into the table
pixels = (
{
"customer_id": "example.com",
"url": "http://example.com/article1/",
"hour": dt.datetime(2014, 1, 2, 1),
"ts": dt.datetime(2014, 1, 2, 1, 8, 23),
"pixel_id": str(uuid4()),
"data": {"visitor_id": "xyz"}
},
)
saveToCassandra(sc.parallelize(pixels), keyspace, table)
print "Wrote new pixels to Cassandra {!r}.{!r}".format(keyspace, table)
def run_driver(keyspace, table, cass_host):
conf = SparkConf().setAppName("PySpark Cassandra Sample Driver")
conf.set("spark.cassandra.connection.host", cass_host)
sc = CassandraSparkContext(conf=conf)
# Read some data from Cassandra
pixels = sc.cassandraTable(keyspace, table)
print pixels.first()
# Count unique visitors, notice that the data returned by Cassandra is
# a dict-like, you can access partition, clustering keys as well as
# columns by name. CQL collections: lists, sets and maps are converted
# to proper Python data types
visitors = pixels.map(lambda p: (p["data"]["visitor_id"],))\
.distinct()
print "Visitors: {:,}".format(visitors.count())
# Insert some new pixels into the table
pixels = ({
"customer_id": "example.com",
"url": "http://example.com/article1/",
"hour": dt.datetime(2014, 1, 2, 1),
"ts": dt.datetime(2014, 1, 2, 1, 8, 23),
"pixel_id": str(uuid4()),
"data": {
"visitor_id": "xyz"
}
}, )
saveToCassandra(sc.parallelize(pixels), keyspace, table)
print "Wrote new pixels to Cassandra {!r}.{!r}".format(keyspace, table)
spark-submit --packages anguenot:pyspark-cassandra:0.7.0 spark-calculate-device.py
"""
if __name__ == '__main__':
if len(sys.argv) != 1:
print("Usage: spark-calculate-device.py ", file=sys.stderr)
exit(-1)
conf = SparkConf() \
.setAppName("spark-calculate-device") \
.set("spark.cassandra.connection.host", "10.88.113.74")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
sql = SQLContext(sc)
while True:
rdd = sc.cassandraTable("web_analytic", "fsa_log_visit").select(
"config_device", "fsa")
if rdd.isEmpty() == False:
x = rdd.toDF().dropDuplicates(['fsa'])
x = x.groupBy(['config_device']).count()
array = []
for row in x.collect():
x = {
'config_device': row['config_device'],
'device_count': row['count'],
'bucket': 3
}
array.append(x)
result = sc.parallelize(array)
result.saveToCassandra('web_analytic', 'device_report')
# break
col_tenant_id = 1
col_user_id = 2
col_item_id = 3
num_to_recomm_per_user = 10
num_to_recomm_per_item = 10
conf = SparkConf().setAppName("PysparkCollaborativeFiltering").set("spark.cassandra.connection.host", spark_cassandra_connection_host)
print ('conf')
sc = CassandraSparkContext(conf=conf)
sc.setCheckpointDir('checkpoint/')
if LOAD_DATA_FROM_DB:
data = sc.cassandraTable(cassandra_keyspace, cassandra_table, row_format=1).collect() # row_format: tuple
# (id, tenant_id, user_id, item_id)
tenant_ids = set(list(map(lambda x:x[col_tenant_id],data)))
data_rdd = sc.parallelize(data)
# data_rdd = sc.parallelize(data).map(list)
all_results_per_user = sc.emptyRDD()
all_results_per_item = sc.emptyRDD()
for t_id in tenant_ids:
print("\nComputing recommendation for tenant {}...\n".format(t_id))
per_tenant_rdd = data_rdd.filter(
lambda x: x[col_tenant_id] == t_id).map(
lambda l: ((l[col_user_id],l[col_item_id]),1.0)).reduceByKey(
lambda x,y: x + y).map(
lambda x: (x[0][0],x[0][1],x[1]))
if len(sys.argv) != 1:
print("Usage: spark-calculate-pageview-total-user", file=sys.stderr)
exit(-1)
conf = SparkConf() \
.setAppName("spark-calculate-pageview-total-user") \
.set("spark.cassandra.connection.host", "10.88.113.74")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
# i = 1514505600
# while i <= 1514764800:
while True:
current_date = getGMT()
future_date = getNextGMT()
# date_temp = i
# i = i + 86400
raw = sc.cassandraTable("web_analytic","fsa_log_visit").select("m_date","userid","fsa","fsid","location_path")
if raw.isEmpty() == False:
df = raw.toDF()
current_day = df.filter( df.m_date >= current_date ).filter(df.m_date < future_date).dropDuplicates(['fsa',"fsid"]).select('fsa','fsid')
previous_day = df.filter(df.m_date < current_date).select('fsa','fsid')
# current_day = df.filter( df.m_date >= date_temp ).filter(df.m_date < i).dropDuplicates(['fsa',"fsid"]).select('fsa','fsid')
# previous_day = df.filter(df.m_date < date_temp).select('fsa','fsid')
result_new_user = current_day.subtract(previous_day)
total_newuser = result_new_user.count()
result_newuser = sc.parallelize([{
"bucket":1,
"m_date": int(current_date),
# "m_date": int(date_temp),
"newusers": int(total_newuser)
}])
# X varchar,
# Y varchar,
# Count int,
# PRIMARY KEY(ZipCode, TaxonomyCode1, ProviderNumber)
#);
if __name__ == "__main__":
conf = SparkConf().setAppName("Query App").setMaster(
"spark://spark01.cs.ucr.edu:7077")
sc = CassandraSparkContext(conf=conf)
sqlContext = SQLContext(sc)
# pulling data from cassandra
x = sc.cassandraTable("census", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode", "pop", "meanincome")\
.map(lambda x: (x[0], x[1], x[2]))
# BusinessPracticeLocationPostalCode -> ZipCode in providers.taxonomy_count
y = sc.cassandraTable("providers", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("businesspracticelocationpostalcode", "taxonomycode1")\
.map(lambda x: (x[0], x[1]))
df_x = sqlContext.createDataFrame(x)
df_y = sqlContext.createDataFrame(y)
# joining x and y
# (zipcode, pop, meanincome, zipcode, businesspracticelocationpostalcode, taxonomycode1)
# -> (zipcode, pop, meanincome, taxonomycode1)
# -> (zipcode, pop, meanincome, taxonomycode1, count)
def x_y_joinSeparator():
from pyspark_cassandra import CassandraSparkContext, Row
from pyspark import SparkContext, SparkConf
from subprocess import call
import subprocess
import commands
aa=commands.getstatusoutput("b=0")
conf = SparkConf() \
.setAppName("User Food Migration") \
.setMaster("spark://128.138.202.110:7077") \
.set("spark.cassandra.connection.host", "128.138.202.117")
sc = CassandraSparkContext(conf=conf)
users = sc.cassandraTable("junk", "trump2")
trump = users.map(lambda x:
{"tweet_id":x['tweet_id'],
"tweet":x['tweet']} )
#to access Twitter API
consumer_key = "43b4urzsW8nMY3oGzB5tIIM8B"
consumer_secret = "fbGLMhkFyipYbTAz0s0S6yrN6cDGGWnEMmNaciceYjr4sgEdP2"
garbage = 0
access_token = "2990432317-eYMpYm2Ck2G1YBPvWEq7Mf9wdgzBlOydabaxmzN"
access_token_secret = "lQYcmiMlFdic9KSdmd6PClGQ3Swq8y9BgvVPOmqwhHjV2"
mongo_client.drop_database(db_out)
mongo_client.close()
print 'database cleared'
col_tenant_id = 1
col_user_id = 2
col_item_id = 3
num_to_recomm_per_user = 10
num_to_recomm_per_item = 10
conf = SparkConf().setAppName("PysparkCollaborativeFiltering").set("spark.cassandra.connection.host", spark_cassandra_connection_host)
sc = CassandraSparkContext(conf=conf)
sc.setCheckpointDir('checkpoint/')
data = sc.cassandraTable("mykeyspace", "transactions",row_format=1).collect() # row_format: tuple
# (id, tenant_id, user_id, item_id)
tenant_ids = set(list(map(lambda x:x[col_tenant_id],data)))
data_rdd = sc.parallelize(data)
# data_rdd = sc.parallelize(data).map(list)
all_results_per_user = sc.emptyRDD()
all_results_per_item = sc.emptyRDD()
for t_id in tenant_ids:
print("\nComputing recommendation for tenant {}...\n".format(t_id))
per_tenant_rdd = data_rdd.filter(
lambda x: x[col_tenant_id] == t_id).map(
lambda l: ((l[col_user_id],l[col_item_id]),1.0)).reduceByKey(
lambda x,y: x + y).map(
lambda x: (x[0][0],x[0][1],x[1]))
sqlContext = SQLContext(sc)
# Make Spark less verbose
logger = sc._jvm.org.apache.log4j
logger.LogManager.getLogger("org").setLevel(logger.Level.ERROR)
logger.LogManager.getLogger("akka").setLevel(logger.Level.ERROR)
def parsePoint(data):
#return LabeledPoint(data[3],np.append(data[0:3],data[4:]))
return LabeledPoint(data[0], data[1:])
# store the data from cassandra to a data frame and remove the NA value
data = sc.cassandraTable("msd_01",
"songs").select("song_hotttnesss", "loudness", "year",
"sentiment", "tempo",
"unique_words").toDF()
data = data.filter("year>0").na.drop()
print data.count()
# Scale the features with Standard Scaler
data2 = data.map(lambda x: [
x.song_hotttnesss, x.loudness, x.year, x.sentiment, x.tempo, x.unique_words
]) #Convert each sql.row to an array
scaler = StandardScaler(withMean=True, withStd=True).fit(
data2) #fit a scaler on the every column
scaledData = scaler.transform(data2) # transform our data
# Transform to a labelled vector
parsedData = scaledData.map(parsePoint)
#from pyspark.storagelevel import StorageLevel
import atexit
from pyspark_cassandra import CassandraSparkContext
from datetime import tzinfo, timedelta, datetime
from pytz import timezone
conf = SparkConf()
#conf.setMaster("local")
conf.setAppName("My app")
conf.set("spark.cassandra.connection.host", "10.0.40.42")
sc = CassandraSparkContext(conf=conf)
atexit.register(lambda: sc.stop())
rdd = sc.cassandraTable("el_test", "cockpit2_testTogether")
# for( d in range 2015-10-01 ~ 2015-10-10 ) do:
#
# SELECT url,date,site,cnts,cnt from cockpit2_allTogether where `date` = d and site = giga and tags contains resort:android
#
# after this query, every row has to be updated with new value for cnts:
#
# UPDATE cnts = ga_videoPlays + sda_downloads + fb_socialFacebookLikes + fb_socialFacebookShares + fb_socialFacebookComments + tw_socialTwitterShares + ga_socialGooglePlusShares + gigya_socialComments
def filterDateRage(_from, _to, col):
loc = timezone('Europe/Berlin')
dtf = loc.localize(datetime.strptime(_from, "%Y-%d-%m %H:%M"))
dtt = loc.localize(datetime.strptime(_to, "%Y-%d-%m %H:%M"))
from pyspark_cassandra import CassandraSparkContext, Row
from pyspark import SparkContext, SparkConf
from pyspark.sql import SQLContext
conf = SparkConf().setAppName("NBARetrieval") \
.set("spark.cassandra.connection.timeout_ms","20000") \
.set("spark.cassandra.connection.host", "192.168.0.10") \
.set("spark.cassandra.auth.username", "mdi") \
.set("spark.cassandra.auth.password", "W2yIJw6ntl5RYC54VChe3lJoXa")
sc = CassandraSparkContext(conf=conf)
rdd = sc.cassandraTable("test", "kv")
print rdd.first()
mongo_client= MongoClient()
mongo_client.drop_database(db_out)
# print 'database cleared'
num_to_recomm_per_user = 10
num_to_recomm_per_item = 10
conf = SparkConf().setAppName("PysparkCollaborativeFiltering")
print 'conf'
sc = CassandraSparkContext(conf=conf)
sc.setCheckpointDir('checkpoint/')
if LOAD_DATA_FROM_DB:
data_rdd = sc.cassandraTable(cassandra_keyspace, cassandra_table) # row_format: Row
# print data
t1 = time.time()
tenant_ids = data_rdd.map(lambda trans:trans[col_tenant_id]).distinct().collect()
elapsed = (time.time() - t0)
print ("\nIt took %.2fsec to complete" % elapsed)
t1 = time.time()
cluster = Cluster()
session = cluster.connect(cassandra_keyspace)
string = 'SELECT DISTINCT ' + col_tenant_id + ' from ' + cassandra_table
tenant_ids = ession.execute(string)
elapsed = (time.time() - t0)
print ("\nIt took %.2fsec to complete" % elapsed)
conf = SparkConf().setAppName("Regression on Song Hotness Analysis").setMaster("spark://muziki:7077")
sc= CassandraSparkContext(conf=conf)
sqlContext = SQLContext(sc)
# Make Spark less verbose
logger = sc._jvm.org.apache.log4j
logger.LogManager.getLogger("org"). setLevel( logger.Level.ERROR )
logger.LogManager.getLogger("akka").setLevel( logger.Level.ERROR )
def parsePoint(data):
#return LabeledPoint(data[3],np.append(data[0:3],data[4:]))
return LabeledPoint(data[0],data[1:])
# store the data from cassandra to a data frame and remove the NA value
data=sc.cassandraTable("msd_01", "songs").select("song_hotttnesss","loudness","year","sentiment","tempo","unique_words").toDF()
data=data.filter("year>0").na.drop()
print data.count()
# Scale the features with Standard Scaler
data2=data.map(lambda x: [x.song_hotttnesss, x.loudness,x.year, x.sentiment,x.tempo,x.unique_words])#Convert each sql.row to an array
scaler= StandardScaler(withMean=True, withStd=True).fit(data2) #fit a scaler on the every column
scaledData = scaler.transform(data2)# transform our data
# Transform to a labelled vector
parsedData = scaledData.map(parsePoint)
# # Build the model
model = LinearRegressionWithSGD.train(parsedData, iterations=1000,regParam=1.0,regType="l2",intercept=True)
"""
spark-submit --packages anguenot:pyspark-cassandra:0.7.0 recommendation_engine/backup_user_event.py
"""
if __name__ == '__main__':
if len(sys.argv) != 1:
print("Usage: last_like.py ", file=sys.stderr)
exit(-1)
conf = SparkConf() \
.setAppName("last-like") \
.set("spark.cassandra.connection.host", "10.88.113.74")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
sql = SQLContext(sc)
while True:
current_date = getGMT()
future_date = getNextGMT()
rdd = sc.cassandraTable("db","user_event_model").select("idx_user","idx_movie","rating","time","type_event")\
.filter(lambda x: current_date <= int(x['time']) < future_date)
if rdd.isEmpty() == False:
rdd.toDF().write\
.format('com.databricks.spark.csv')\
.option("header", "true")\
.save('/home/trantu/Desktop/engine_recommendation.git/trunk/meta-data/user_event/' \
+datetime.now().strftime('%Y_%m_%d_%H_%M_%S.csv'))
# rdd.toDF().write.csv('/home/tutn6/Desktop/engine_recommendation.git/trunk/mycsv')
# rdd.deleteFromCassandra("db","user_event_model")
break
if len(sys.argv) != 1:
print("Usage: spark-calculate-pageview", file=sys.stderr)
exit(-1)
conf = SparkConf() \
.setAppName("spark-calculate-pageview") \
.set("spark.cassandra.connection.host", "10.88.113.74")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
i = 1511740800
while i <= 1514505600:
# while True:
date_temp = i
i = i + 86400
# current_date = getGMT()
# future_date = getNextGMT()
rdd = sc.cassandraTable("web_analytic","fsa_log_visit").select("m_date","location_path")\
.filter(lambda x: date_temp <= int(x['m_date']) < i)
if rdd.isEmpty() == False:
x = rdd.toDF().groupBy(['location_path']).count()
# x.show()
array = []
for row in x.collect():
x = {
'location_path': row['location_path'],
'm_date': date_temp,
'count':row['count'],
'bucket':5}
array.append(x)
result = sc.parallelize(array)
result.saveToCassandra('web_analytic','page_view_report')
break
pass
spark-submit --packages anguenot:pyspark-cassandra:0.7.0 spark-calculate-language.py
"""
if __name__ == '__main__':
if len(sys.argv) != 1:
print("Usage: spark-calculate-language.py ", file=sys.stderr)
exit(-1)
conf = SparkConf() \
.setAppName("spark-calculate-language") \
.set("spark.cassandra.connection.host", "10.88.113.74")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
sql = SQLContext(sc)
while True:
rdd = sc.cassandraTable("web_analytic", "fsa_log_visit").select(
"location_browser_lan", "fsa")
if rdd.isEmpty() == False:
x = rdd.toDF().dropDuplicates(['fsa'])
x = x.groupBy(['location_browser_lan']).count()
array = []
for row in x.collect():
x = {
'browser_language': row['location_browser_lan'],
'count': row['count'],
'bucket': 6
}
array.append(x)
result = sc.parallelize(array)
result.saveToCassandra('web_analytic', 'browser_language_report')
# break
from pyspark_cassandra import CassandraSparkContext
from operator import add
start_time = time.time()
if __name__ == "__main__":
conf = SparkConf().setAppName("Query App").setMaster(
"spark://spark01.cs.ucr.edu:7077")
sc = CassandraSparkContext(conf=conf)
sqlContext = SQLContext(sc)
# pulling data from cassandra
x = sc.cassandraTable("census", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode", "pop", "meanincome")\
.map(lambda x: (x[0], x[1], x[2])) \
y = sc.cassandraTable("hospitals", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode", "numberofdoctors")\
.map(lambda x: (x[0], x[1]))\
.reduceByKey(lambda x,y: x + y)
df_x = sqlContext.createDataFrame(x)
df_y = sqlContext.createDataFrame(y)
# (zipcode, pop, meanincome, zipcode, numberofdoctors) -> (zipcode, pop, meanincome, numberofdoctors, pop/numberofdoctors)
def joinSeparator():
return lambda x: (x[0], x[1], x[2], x[4], float(x[1]) / x[4])
cond = [df_x._1 == df_y._1]
popDoctorRatioQueryRDD = df_x.join(df_y, cond) \
.map(joinSeparator()) \
from pyspark_cassandra import CassandraSparkContext
from pyspark import SparkConf
conf = SparkConf()
conf.set("spark.cassandra.connection.host", "192.168.15.87")
sc = CassandraSparkContext("spark://192.168.15.87:7077",
"Simple App",
conf=conf)
rdd = sc.cassandraTable("testkeyspace",
"stock2").select("ric", "time_stamp", "high",
"low").spanBy('time_stamp').collect()
for gr in rdd:
print(gr) #one batch
print("+++++++++++++++")
from operator import add
start_time = time.time()
if __name__ == "__main__":
conf = SparkConf().setAppName("Query App").setMaster("spark://spark01.cs.ucr.edu:7077")
sc = CassandraSparkContext(conf=conf)
sqlContext = SQLContext(sc)
# pulling data from cassandra
# num of hospitals RDD (zipcode, numofhospitals)
x = sc.cassandraTable("hospitals", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode")\
.map(lambda x: (x, 1))\
.reduceByKey(add)\
.map(lambda x: (x[0][0], x[1]))
y = sc.cassandraTable("hospitals", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode", "providernumber", "hospitalname", "x", "y", "numberofdoctors")\
.map(lambda x: (x[0], x[1], x[2], x[3], x[4], x[5]))
z = sc.cassandraTable("census", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode", "pop", "meanincome")\
.map(lambda x: (x[0], x[1], x[2]))
df_x = sqlContext.createDataFrame(x)
df_y = sqlContext.createDataFrame(y)
df_z = sqlContext.createDataFrame(z)
# (zipcode, numofhospitals, zipcode, providernumber, hospitalname, x, y, numberofdoctors) -> (zipcode, numofhospitals, providernumber, hospitalname, x, y, numberofdoctors)
def x_y_joinSeparator(): return lambda x: (x[0], x[1], x[3], x[4], x[5], x[6], x[7])
# Y varchar,
# Count int,
# MeanIncome int,
# PRIMARY KEY(ZipCode, TaxonomyCode1, ProviderNumber)
#);
if __name__ == "__main__":
conf = SparkConf().setAppName("Query App").setMaster(
"spark://spark01.cs.ucr.edu:7077")
sc = CassandraSparkContext(conf=conf)
sqlContext = SQLContext(sc)
# pulling data from cassandra
x = sc.cassandraTable("census", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode", "pop", "meanincome")\
.map(lambda x: (x[0], x[1], x[2]))
y = sc.cassandraTable("hospitals", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode", "providernumber", "hospitalname", "x", "y")\
.map(lambda x: (x[0], x[1], x[2], x[3], x[4]))
# BusinessPracticeLocationPostalCode -> ZipCode in providers.taxonomy_count
z = sc.cassandraTable("providers", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("businesspracticelocationpostalcode", "taxonomycode1")\
.map(lambda x: (x[0], x[1]))
# num of hospitals RDD (zipcode, numberofhospitals)
a = sc.cassandraTable("hospitals", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("zipcode")\
.map(lambda x: (x, 1))\
.reduceByKey(add)\
.map(lambda x: (x[0][0], x[1]))
df_x = sqlContext.createDataFrame(x)
if __name__ == "__main__":
conf = SparkConf().setAppName("UserUserRelevance").setMaster(config.SPARK_MASTER).set("spark.cassandra.connection.host", config.CASSANDRA_SEED_NODE_IP)
sc = CassandraSparkContext(conf=conf)
filename = datetime.now().strftime("%Y-%m-%d")+"-usersonglog.txt"
users = sc.textFile(config.HDFS_URL+":"+config.HDFS_PORT+config.LOG_FOLDER+filename) \
.filter(time_range_filter) \
.map(parse_log_entry) \
.keys() \
.collect()
song_map = {} # store song to user mapping for use in later stages
usersongdb = sc.cassandraTable(config.CASSANDRA_KEYSPACE, "user_to_song")
songuserdb = sc.cassandraTable(config.CASSANDRA_KEYSPACE, "song_to_user")
for user in users:
user_suggest = []
song_list = usersongdb.select("song_id") \
.where("user_id=? and req_time > ? and req_time < ?", int(user), five_weeks_back, now+1) \
.map(lambda row: row.song_id) \
.distinct() \
.collect()
songs = list(set(song_list))
for song in songs:
if song in song_map:
listeners = song_map[song]
else:
spark-submit --packages anguenot:pyspark-cassandra:0.7.0 spark-calculate-total-user.py
"""
if __name__ == '__main__':
if len(sys.argv) != 1:
print("Usage: spark-process-data", file=sys.stderr)
exit(-1)
conf = SparkConf() \
.setAppName("spark-calculate-total-user") \
.set("spark.cassandra.connection.host", "10.88.113.74")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
while True:
current_date = getGMT()
future_date = getNextGMT()
rdd = sc.cassandraTable("web_analytic","fsa_log_visit").select("m_date","userid","fsa","fsid")\
.filter(lambda x: current_date <= int(x['m_date']) < future_date)
if rdd.isEmpty() == False:
table = rdd.toDF()
# table.show(truncate=False)
total = table.dropDuplicates(['fsa', "fsid"]).count()
result = sc.parallelize([{
"bucket": 0,
"m_date": int(current_date),
"users": int(total)
}])
else:
result = sc.parallelize([{
"bucket": 0,
"m_date": int(current_date),
result = ''
for i in range(3000):
if vecFirst[0] > 0:
result = '%s;%d %.4f' % (result, i, vecFirst[i])
return result
conf = SparkConf()\
.set("spark.cassandra.connection.host", "localhost")
sc = CassandraSparkContext(conf=conf)
vecSum = sc.cassandraTable('reishi', 'dockmeans')\
.select("cluster_id", "vector")\
.where("cluster_id=?", 0)\
.map(lambda x: (x['cluster_id'], x['vector']))\
.reduceByKey(lambda x, y: maxVector(x, y))\
.collect()
vector = []
#print(vecSum)
v = vecSum[0]
v = v[1]
#print('=================================' + v)
splt = v.split(';')
for t in splt:
p = t.split(' ')
if len(p) > 1:
tp = tpVector(int(p[0]), float(p[1]))
vector.append(tp)
sc = CassandraSparkContext(conf=conf)
def retTuple(r):
age = int(r["age"])
if age < 20:
return ("<20", 1)
if age < 40:
return ("20 < 40", 1)
if age < 60:
return ("40 < 60", 1)
return (">60", 1)
result = sc.cassandraTable("zeus", "node") \
.select("age") \
.where("type=?", "person") \
.map(retTuple) \
.reduceByKey(lambda a, b: a + b) \
.collect()
print
print "================================"
print "AGE DEMOGRAPHICS"
print "================================"
for row in result:
print str(row[0]) + "\t\t" + str(row[1])
print
print "================================"
print
spark-submit --packages anguenot:pyspark-cassandra:0.7.0 spark-calculate-location.py
"""
if __name__ == '__main__':
if len(sys.argv) != 1:
print("Usage: spark-calculate-location.py ", file=sys.stderr)
exit(-1)
conf = SparkConf() \
.setAppName("spark-calculate-location") \
.set("spark.cassandra.connection.host", "10.88.113.74")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
sql = SQLContext(sc)
while True:
rdd = sc.cassandraTable("web_analytic", "fsa_log_visit").select(
"location_country_name", "location_country_code", "fsa")
# rdd.toDF().show()
if rdd.isEmpty() == False:
x = rdd.toDF().dropDuplicates(['fsa'])
x = x.groupBy(['location_country_name',
'location_country_code']).count()
array = []
for row in x.collect():
x = {
'location_country_name': row['location_country_name'],
'location_country_code': row['location_country_code'],
'location_count': row['count'],
'bucket': 2
}
array.append(x)
from pyspark_cassandra import CassandraSparkContext
from operator import add
start_time = time.time()
if __name__ == "__main__":
conf = SparkConf().setAppName("Tool App").setMaster(
"spark://spark01.cs.ucr.edu:7077")
sc = CassandraSparkContext(conf=conf)
sqlContext = SQLContext(sc)
# pulling data from cassandra
taxonomyRDD = sc.cassandraTable(
"providers", "test",
row_format=pyspark_cassandra.RowFormat.TUPLE).select("taxonomycode1")
customSchema = StructType(
[StructField("TaxonomyCode1", StringType(), True)])
taxonomyDF = sqlContext.createDataFrame(taxonomyRDD,
customSchema).distinct()
with open("/home/cs179g/logs/taxonomyList", "w") as outfile:
for row in taxonomyDF.rdd.collect():
outfile.write(row[0] + '\n')
sc.stop()
from pyspark_cassandra import CassandraSparkContext
from pyspark import SparkConf
conf = SparkConf() \
.setAppName("ZeusDB") \
.setMaster("local") \
.set("spark.cassandra.connection.host", "YOUR_CLUSTER_HOST_NAME")
sc = CassandraSparkContext(conf=conf)
result = sc.cassandraTable("zeus", "edge") \
.select("destination", "type") \
.filter(lambda x: x["type"] == "friend") \
.map(lambda x: (x["destination"], 1)) \
.reduceByKey(lambda a, b: a + b) \
.top(10, key=lambda x: x[1])
print
print "================================"
print "TOP 10 PEOPLE WITH MOST FRIENDS"
print "================================"
for row in result:
print str(row[0]) + "\t\t" + str(row[1])
print
print "================================"
print
# i = 1514505600
# while i <= 1515110400:
while True:
# date_temp = i
# i = i + 86400
current_date = getGMT()
future_date = getNextGMT()
rdd = sc.cassandraTable("web_analytic","fsa_log_visit")\
.select(
"config_browser",
"config_device",
"fsa",
"location_browser_lan",
"location_country_name",
"location_country_code",
"m_date",
"location_path",
"location_city_name",
"config_resolution",
"location_os"
)\
.filter(lambda x: current_date <= int(x['m_date']) < future_date)
# .filter(lambda x: date_temp <= int(x['m_date']) < i)
# 1514332800
if rdd.isEmpty() == False:
table_drop = rdd.toDF().dropDuplicates(['fsa'])
# table_drop.show()
# break
result_config_browser = table_drop.groupBy(['config_browser'
#from pyspark.storagelevel import StorageLevel
import atexit
from pyspark_cassandra import CassandraSparkContext
from datetime import tzinfo, timedelta, datetime
from pytz import timezone
conf = SparkConf()
#conf.setMaster("local")
conf.setAppName("My app")
conf.set("spark.cassandra.connection.host", "10.0.40.42")
sc = CassandraSparkContext(conf = conf)
atexit.register(lambda: sc.stop())
rdd = sc.cassandraTable("el_test", "cockpit2_testIndexes")
# for( d in range 2015-10-01 ~ 2015-10-10 ) do:
#
# SELECT url,date,site,cnts,cnt from cockpit2_allTogether where `date` = d and site = giga and tags contains resort:android
#
# after this query, every row has to be updated with new value for cnts:
#
# UPDATE cnts = ga_videoPlays + sda_downloads + fb_socialFacebookLikes + fb_socialFacebookShares + fb_socialFacebookComments + tw_socialTwitterShares + ga_socialGooglePlusShares + gigya_socialComments
def filterDateRage(_from, _to, col):
loc = timezone('Europe/Berlin')
dtf = loc.localize(datetime.strptime(_from, "%Y-%d-%m %H:%M"))
dtt = loc.localize(datetime.strptime(_to, "%Y-%d-%m %H:%M"))
def inner(row):
startDate = str(sys.argv[1])
endDate = str(sys.argv[2])
conf = (
SparkConf()
.setAppName("User Food Migration")
.setMaster("spark://128.138.202.110:7077")
.set("spark.cassandra.connection.host", "128.138.202.117")
)
sc = CassandraSparkContext(conf=conf)
if __name__ == "__main__":
rdd = sc.cassandraTable("junk", "bernie4")
temp = 0
# returns list of tweets
listBernie = (
rdd.filter(lambda row: row.created_at[4:] > startDate)
.filter(lambda row: row.created_at[4:] < endDate)
.collect()
)
for tweet in listBernie:
if tweet.retweet_count > 0:
print tweet.retweet_count
temp += 1
if tweet.favorite_count > 0:
print tweet.favorite_count
temp += 1
if tweet.coordinates != None:
from pyspark_cassandra import CassandraSparkContext, Row
from pyspark import SparkContext, SparkConf
from pyspark.sql import SQLContext # needed for toDF()
conf = SparkConf() \
.setAppName("User Food Migration") \
.setMaster("spark://127.0.0.1:7077") \
.set("spark.cassandra.connection.host", "127.0.0.1")
sc = CassandraSparkContext(conf=conf)
sql = SQLContext(sc)
users = sc.cassandraTable("demo", "user").toDF()
food_count = users.select("favorite_food").groupBy("favorite_food").count()
KEYSPACE = "undefined" # mettez "share" si vous n'avez pas fait l'injection des données
# vérification que le keyspace a bien été défini correctement
if KEYSPACE == "undefined": raise Exception("Vous n'avez pas changé le keyspace, éditez le début du script")
# lancement par spark-submit --py-files /usr/lib/spark/jars/pyspark-cassandra-0.7.0.jar livres.py
# nom de l'application
appName = "TP5 partie Spark/Cassandra"
# bibliothèques pour travailler avec Cassandra
from pyspark import SparkConf
from pyspark_cassandra import CassandraSparkContext
# contexte d'exécution pour spark-submit
conf = SparkConf() \
.setAppName(appName) \
.setMaster("spark://master:7077") \
.set("spark.cassandra.connection.host", "master")
csc = CassandraSparkContext(conf=conf)
# ouvrir une table Cassandra à l'aide de csc
livres = csc.cassandraTable(KEYSPACE, "livres");
# nombre de livres de Jules Verne
print livres.filter(lambda livre: livre.auteur=="Jules Verne").count()
from pyspark_cassandra import CassandraSparkContext
from pyspark import SparkConf
conf = SparkConf() \
.setAppName("ZeusDB") \
.setMaster("local") \
.set("spark.cassandra.connection.host", "YOUR_CLUSTER_HOST_NAME")
sc = CassandraSparkContext(conf=conf)
result = sc.cassandraTable("zeus", "edge") \
.select("destination", "visit_count", "type") \
.filter(lambda x: x["type"] == "visited") \
.map(lambda x: (x["destination"], int(x["visit_count"]))) \
.reduceByKey(lambda a, b: a + b) \
.top(10, key=lambda x: x[1]) \
print
print "================================"
print "TOP 10 FREQUENTLY VISITED PLACES"
print "================================"
for row in result:
print str(row[0]) + "\t\t" + str(row[1])
print
print "================================"
print
from operator import add
start_time = time.time()
if __name__ == "__main__":
conf = SparkConf().setAppName("Query App").setMaster(
"spark://spark01.cs.ucr.edu:7077")
sc = CassandraSparkContext(conf=conf)
sqlContext = SQLContext(sc)
# pulling data from cassandra
hospitalNameList = sc.cassandraTable("hospitals", "test", row_format=pyspark_cassandra.RowFormat.TUPLE).select("hospitalname", "numberofdoctors")\
.map(lambda x: (x[0], x[1]))\
.reduceByKey(lambda x,y: x + y)
#for row in popDoctorRatioRDD:
#print (row)
dfList = hospitalNameList.collect()
# if you do left outer join, the results that are null for the census show up because hospitals have them
customSchema = StructType([ \
StructField("HospitalName", StringType(), True), \
StructField("NumberOfDoctors", IntegerType(), True) ])
hospitalNameDF = sqlContext.createDataFrame(dfList, customSchema)
dfJSONRDD = hospitalNameDF.toJSON().collect()
from pyspark_cassandra import CassandraSparkContext, Row
from pyspark import SparkContext, SparkConf
conf = SparkConf().setAppName("PySpark Cassandra Test").set("spark.cassandra.connection.host", "127.0.0.1")
sc = CassandraSparkContext(conf=conf)
data = sc.cassandraTable("mykeyspace", "user",row_format = 1).collect()
rdd = sc.parallelize(data)
print (rdd.collect())
ETNIA = {
1: 'BRANCA',
2: 'PRETA',
3: 'PARDA',
4: 'AMARELA',
5: 'INDÍGENA',
}
# Cria o SparkContext
conf = SparkConf() \
.setAppName("Pergunta1") \
.set("spark.cassandra.connection.host", "10.7.40.94")
csc = CassandraSparkContext(conf=conf)
# Prepara os RDDs das tabelas.
candidatos = csc.cassandraTable("eleicoes", "candidatos2014")
resultados = csc.cassandraTable("eleicoes", "resultados2014")
# Busca o código dos candidatos eleitos e dinstintos (para desconsiderar segundo turno).
# Existem 3 tipos de candidatos eleitos (1, 2, 3).
cod_eleitos1 = resultados.select('sq_candidato').where(
"codigo_sit_cand_tot=? ", 1)
cod_eleitos2 = resultados.select('sq_candidato').where(
"codigo_sit_cand_tot=? ", 2)
cod_eleitos3 = resultados.select('sq_candidato').where(
"codigo_sit_cand_tot=? ", 3)
# Une os códigos dos candidatos eleitos (os 3 tipos).
cod_eleitos = cod_eleitos1.union(cod_eleitos2).union(cod_eleitos3).map(
lambda row: (row['sq_candidato'], 0))
#from pyspark.storagelevel import StorageLevel
import atexit
from pyspark_cassandra import CassandraSparkContext
from datetime import tzinfo, timedelta, datetime
from pytz import timezone
conf = SparkConf()
#conf.setMaster("local")
conf.setAppName("My app")
conf.set("spark.cassandra.connection.host", "10.0.40.42")
sc = CassandraSparkContext(conf = conf)
atexit.register(lambda: sc.stop())
rdd = sc.cassandraTable("el_test", "cockpit2_testTogether")
# for( d in range 2015-10-01 ~ 2015-10-10 ) do:
#
# SELECT url,date,site,cnts,cnt from cockpit2_allTogether where `date` = d and site = giga and tags contains resort:android
#
# after this query, every row has to be updated with new value for cnts:
#
# UPDATE cnts = ga_videoPlays + sda_downloads + fb_socialFacebookLikes + fb_socialFacebookShares + fb_socialFacebookComments + tw_socialTwitterShares + ga_socialGooglePlusShares + gigya_socialComments
def filterDateRage(_from, _to, col):
loc = timezone('Europe/Berlin')
dtf = loc.localize(datetime.strptime(_from, "%Y-%d-%m %H:%M"))
dtt = loc.localize(datetime.strptime(_to, "%Y-%d-%m %H:%M"))
def inner(row):
"""
spark-submit --packages anguenot:pyspark-cassandra:0.7.0 spark-calculate-last-like.py
"""
if __name__ == '__main__':
if len(sys.argv) != 1:
print("Usage: spark-calculate-last-like.py ", file=sys.stderr)
exit(-1)
conf = SparkConf() \
.setAppName("spark-calculate-last-like") \
.set("spark.cassandra.connection.host", "10.88.113.74")
sc = CassandraSparkContext(conf=conf)
spark = SparkSession(sc)
sql = SQLContext(sc)
while True:
rdd = sc.cassandraTable("db","user_event_model").select("config_browser","m_date")
if rdd.isEmpty() == False:
x = rdd.toDF().groupBy(['config_browser']).count()
array = []
for row in x.collect():
x = {
'config_browser': row['config_browser'],
'browser_count': row['count'],
'bucket':4
}
array.append(x)
result = sc.parallelize(array)
result.saveToCassandra('test','browser_report')
from pyspark import SparkConf, SparkContext
import pyspark_cassandra
from pyspark_cassandra import CassandraSparkContext
conf = SparkConf()\
.setAppName("PySpark Cassandra Test") \
.setMaster("local[2]") \
.set("spark.cassandra.connection.host","52.25.173.31, 35.165.251.179, 52.27.187.234, 52.38.246.84")
# .set("spark.cassandra.connection.host","52.25.173.31, 35.165.251.179, 52.27.187.234, 52.38.246.84")
sc = CassandraSparkContext(conf=conf)
print((sc.cassandraTable(
"tweetdb", "tweettable").select("tweet").map(lambda a: a).collect()))
#sc.pprint()
#rdd = sc.parallelize([{"tweet":"first second third tweet"}])
#rdd.saveToCassandra(
# "tweetdb",
# "tweettable")
from pyspark_cassandra import CassandraSparkContext
from pyspark import SparkConf
conf = SparkConf()
conf.set("spark.cassandra.connection.host", "192.168.15.87")
sc = CassandraSparkContext("spark://192.168.15.87:7077",
"Simple App",
conf=conf)
rdd = sc.cassandraTable("testkeyspace", "stock").select(
"ric", "date", "time", "high", "low").groupBy(
lambda r: r["date"] > 20050613 and r["date"] < 20170511).collect()
for gr in rdd:
if gr[0]:
new_rdd = sc.parallelize(list(gr[1]))
for time in [
"9:30:00 AM", "10:30:00 AM", "11:30:00 AM", "12:30:00 PM",
"1:30:00 PM", "2:30:00 PM"
]:
rdd_temp = new_rdd.groupBy(lambda r: r["time"] == time)
for r in rdd_temp.collect():
if r[0]:
for i in r[1]:
print(i) #each batch
