/
examples.py
65 lines (52 loc) · 2.41 KB
/
examples.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
import sys
from pyspark.sql import SQLContext, SparkSession
from pyspark import SparkContext, SparkConf
sparkConf = SparkConf().setMaster("local").setAppName("MongoSparkConnectorTour").set("spark.app.id", "MongoSparkConnectorTour")
#If executed via pyspark, sc is already instantiated
sc = SparkContext(conf=sparkConf)
sqlContext = SQLContext(sc)
# create and load dataframe from MongoDB URI
df = sqlContext.read.format("com.mongodb.spark.sql.DefaultSource")\
.option("spark.mongodb.input.uri", "mongodb://mongodb:27017/spark.times")\
.load()
# print data frame schema
df.printSchema()
# print first dataframe row
df.first()
# convert dataframe to rdd
rdd = df.rdd
rdd.first()
# Read through using aggregation pipeline
pipeline = [{'$sort': {'timestamp': 1}},
{'$group':{'_id':{'myid':'$myid'}, 'record':{'$first':'$$ROOT'}}},
{'$project':{'_id':0, 'doc':'$record.doc', 'timestamp':'$record.timestamp', 'myid':'$record.myid'}}
]
df_pipeline = sqlContext.read.format("com.mongodb.spark.sql.DefaultSource")\
.option("spark.mongodb.input.uri", "mongodb://mongodb:27017/spark.times")\
.option("pipeline", pipeline).load()
df_pipeline.first()
# Filter by Integer and by String
df.filter(df["myid"] < 2).show()
df.filter(df["doc"] == "V ").show()
# DataFrames SQL example
df.registerTempTable("temporary")
sqlResult = sqlContext.sql("SELECT myid, doc, timestamp FROM temporary WHERE myid > 6 AND doc='V '")
sqlResult.show()
# Save out the filtered DataFrame result
sqlResult.write.format("com.mongodb.spark.sql.DefaultSource")\
.option("spark.mongodb.output.uri", "mongodb://mongodb:27017/spark.output")\
.mode("overwrite")\
.save()
# Read it back in to confirm
df = sqlContext.read.format("com.mongodb.spark.sql.DefaultSource")\
.option("spark.mongodb.input.uri", "mongodb://mongodb:27017/spark.output")\
.load()
df.show()
# Read a csv file and store into MongoDB
spark = SparkSession.builder.appName("MongoSparkConnectorTour").getOrCreate()
dataframe = spark.read.csv("./population_by_country_1980_2010.csv", header=True, mode="DROPMALFORMED")
dataframe.write.format("com.mongodb.spark.sql.DefaultSource")\
.option("spark.mongodb.output.uri", "mongodb://mongodb:27017/spark.population")\
.save()
print("Done")
sys.exit(0)