-
Notifications
You must be signed in to change notification settings - Fork 0
/
data_stream.py
104 lines (79 loc) · 3.45 KB
/
data_stream.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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
import logging
import json
from pyspark.sql import SparkSession
from pyspark.sql.types import *
import pyspark.sql.functions as psf
BOOTSTRAP = "localhost:9091"
# TODO Create a schema for incoming resources
schema = StructType([
StructField("crime_id", StringType(), True),
StructField("original_crime_type_name", StringType(), True),
StructField("report_date", StringType(), True),
StructField("call_date", StringType(), True),
StructField("offense_date", StringType(), True),
StructField("call_time", StringType(), True),
StructField("call_date_time", StringType(), True),
StructField("disposition", StringType(), True),
StructField("address", StringType(), True),
StructField("city", StringType(), True),
StructField("state", StringType(), True),
StructField("agency_id", StringType(), True),
StructField("address_type", StringType(), True),
StructField("common_location", StringType(), True)
])
def run_spark_job(spark):
# TODO Create Spark Configuration
# Create Spark configurations with max offset of 200 per trigger
# set up correct bootstrap server and port
df = spark \
.readStream \
.format("kafka") \
.option("kafka.bootstrap.servers", BOOTSTRAP) \
.option("subscribe", "service.calls") \
.option("startingOffsets", "earliest") \
.option("maxRatePerPartition", 100) \
.option("maxOffsetPerTrigger", 200) \
.load()
# Show schema for the incoming resources for checks
df.printSchema()
# TODO extract the correct column from the kafka input resources
# Take only value and convert it to String
kafka_df = df.selectExpr("CAST(value AS STRING)")
service_table = kafka_df\
.select(psf.from_json(psf.col('value'), schema).alias("DF"))\
.select("DF.*")
# TODO select original_crime_type_name and disposition
distinct_table = service_table.select(
psf.col("original_crime_type_name"),
psf.to_timestamp(psf.col("call_date_time")).alias("call_date_time"),
psf.col("disposition")
)
# count the number of original crime type
agg_df = distinct_table.groupBy("original_crime_type_name", psf.window("call_date_time", "60 minutes")).count()
# TODO Q1. Submit a screen shot of a batch ingestion of the aggregation
# TODO write output stream
query = agg_df.writeStream.outputMode("Complete").format("console").start()
# TODO attach a ProgressReporter
query.awaitTermination()
# TODO get the right radio code json path
radio_code_json_filepath = "radio_code.json"
radio_code_df = spark.read.json(radio_code_json_filepath)
# clean up your data so that the column names match on radio_code_df and agg_df
# we will want to join on the disposition code
# TODO rename disposition_code column to disposition
radio_code_df = radio_code_df.withColumnRenamed("disposition_code", "disposition")
# TODO join on disposition column
join_query = agg_df.join(radio_code_df, "disposition").writeStream.format("console").queryName("join").start()
join_query.awaitTermination()
if __name__ == "__main__":
logger = logging.getLogger(__name__)
# TODO Create Spark in Standalone mode
spark = SparkSession \
.builder \
.master("local[*]") \
.config("spark.ui.port", 3000) \
.appName("KafkaSparkStructuredStreaming") \
.getOrCreate()
logger.info("Spark started")
run_spark_job(spark)
spark.stop()