def sqlType(cls):
return StructType([
StructField("type", ByteType(), False),
StructField("size", IntegerType(), True),
StructField("indices", ArrayType(IntegerType(), False), True),
StructField("values", ArrayType(DoubleType(), False), True)
])
def run(self):
sc = SparkContext("local", "gender")
sqlContext = SQLContext(sc)
#StringType =(str, unicode)
_out = self.output().open('w')
#lines = sc.textFile("myUser.csv")
#fobj = self.input().open("r")
#lines = sc.textFile(fobj.name)
print(type(self.required_tasks['insert_source'].output()))
print(self.required_tasks['insert_source'])
#print(self.input()['insert_source'].input())
lines = sc.textFile("myUser.csv")
parts = lines.map(lambda l: l.split(","))
users = parts.map(lambda p: (p[0], p[1], p[2], p[3], p[4], p[5], p[
6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[14], p[15], p[
16], p[17], p[18], p[19]))
schemaString = "userId lmsUserId lmsName orgName name gender registrationDate emailId mothertounge highestEduDegree goals city state active firstAccesDate lastAccessDate allowCert yearOfBirth pincode aadharId"
print(schemaString)
_out.write(schemaString)
fields = [
StructField(field_name, StringType(), True)
for field_name in schemaString.split()
]
schema = StructType(fields)
#schemaUser = sqlContext.createDataFrame(users, schema)
schemaUser = sqlContext.applySchema(users, schema)
schemaUser.registerTempTable("users")
results = sqlContext.sql("SELECT gender FROM users")
genders = results.map(lambda p: (p, 1))
counts = genders.reduceByKey(
lambda a, b: a + b
) #.map(lambda t : ("Gender " + t(0) + " No " + t(1))).collect()
for name in counts.collect():
_out.write(str(name))
_out.close()
def table2():
#####################################################
# Import/Create Second Schema
#
# Another RDD is created from a list of tuples
another_rdd = sc.parallelize([("John", "England", 120),
("Jenny", "Spain", 45),
("Sarah", "Japan", 55)])
# Schema with two fields - person_name and person_age
schema = StructType([
StructField("Person_First_Name", StringType(), False),
StructField("Person_Location_Country", StringType(), False),
StructField("Person_Avg_Spend", IntegerType(), False)
])
# Create a SchemaRDD by applying the schema to the RDD and print the schema
another_schemardd = sqlCtx.applySchema(another_rdd, schema)
# Print Schema on Screen
print('Print the Second Schema - People_Details\n')
another_schemardd.printSchema()
#####################################################
# Save Data Above as a Parqet File
# SchemaRDDs can be saved as Parquet files, maintaining the schema
# information.
another_schemardd.saveAsParquetFile(
"/home/dan/Desktop/People_Details.parquet")
# Register this SchemaRDD as a table.
return another_schemardd.registerAsTable("People_Details")
def dshape_to_schema(ds):
"""Convert datashape to SparkSQL type system.
Examples
--------
>>> print(dshape_to_schema('int32')) # doctest: +SKIP
IntegerType
>>> print(dshape_to_schema('5 * int32') # doctest: +SKIP
ArrayType(IntegerType,false)
>>> print(dshape_to_schema('5 * ?int32')) # doctest: +SKIP
ArrayType(IntegerType,true)
>>> print(dshape_to_schema('{name: string, amount: int32}')) # doctest: +SKIP
StructType(List(StructField(name,StringType,false),StructField(amount,IntegerType,false) # doctest: +SKIP))
>>> print(dshape_to_schema('10 * {name: string, amount: ?int32}')) # doctest: +SKIP
ArrayType(StructType(List(StructField(name,StringType,false),StructField(amount,IntegerType,true))),false)
"""
if isinstance(ds, str):
return dshape_to_schema(dshape(ds))
if isinstance(ds, Tuple):
raise TypeError('Please provide a Record dshape for these column '
'types: %s' % (ds.dshapes, ))
if isinstance(ds, Record):
return StructType([
StructField(name, dshape_to_schema(deoption(typ)),
isinstance(typ, datashape.Option))
for name, typ in ds.fields
])
if isinstance(ds, DataShape):
if isdimension(ds[0]):
elem = ds.subshape[0]
if isinstance(elem, DataShape) and len(elem) == 1:
elem = elem[0]
return ArrayType(dshape_to_schema(deoption(elem)),
isinstance(elem, Option))
else:
return dshape_to_schema(ds[0])
if ds in dshape_to_sparksql:
return dshape_to_sparksql[ds]
raise NotImplementedError()
sc = SparkContext(conf=conf)
hc = HiveContext(sc)
source = sc.parallelize([
"row1_col1 row1_col2 row1_col3", "row2_col1 row2_col2 row3_col3",
"row3_col1 row3_col2 row3_col3"
])
columns = source.map(lambda line: line.split(" ")).filter(
lambda columns: columns and len(columns) == 3)
rows = columns.map(lambda columns: (columns[0], columns[1], columns[2]))
schema = StructType([
StructField("col1", StringType(), False),
StructField("col2", StringType(), False),
StructField("col3", StringType(), False)
])
table = hc.applySchema(rows, schema)
table.registerAsTable("temp_mytable")
rdd = hc.sql("select count(*) from temp_mytable where col1 = '' group by col2")
print rdd.toDebugString()
sc.stop()
sc = SparkContext(conf=conf)
hc = HiveContext(sc)
datas = ["1 a 28", "2 b 29", "3 c 30"]
source = sc.parallelize(datas)
splits = source.map(lambda line: line.split(" "))
rows = splits.map(lambda words: (int(words[0]), words[1], int(words[2])))
fields = []
fields.append(StructField("id", IntegerType(). True))
fields.append(StructField("name", StringType(). True))
fields.append(StructField("age", IntegerType(). True))
schema = StructType(fields)
people = hc.applySchema(rows, schema)
people.registerTempTable("people")
results = hc.sql("select * from people where age>28 and age<30").collect()
sc.stop()
for result in results:
print("id: %s, name: %s, age: %s" % (result.id, result.name, result.age))
from pyspark.sql import StructType, StructField, ArrayType, MapType
conf = SparkConf().setAppName("spark_sql_datatype_complex")
sc = SparkContext(conf=conf)
hc = HiveContext(sc)
source = sc.parallelize([([1, 2, 3], {"key1": 1, "key2": 2}, (1, 2.0, "3.0"))])
schema = StructType([
StructField("array", ArrayType(IntegerType(), False), False),
StructField("col_map", MapType(StringType(), IntegerType(), False), False),
StructField(
"struct",
StructType([
StructField("first", IntegerType(), False),
StructField("second", FloatType(), False),
StructField("third", StringType(), False)
]), False)
])
table = hc.applySchema(source, schema)
table.registerAsTable("temp_table")
rows = hc.sql(
"select array[0], array[1], array[2], col_map['key1'], col_map['key2'], struct.first, struct.second, struct.third from temp_table"
).collect()
sc.stop()
if __name__ == "__main__":
sc = SparkContext(appName="PythonSQL")
sqlContext = SQLContext(sc)
# RDD is created from a list of rows
some_rdd = sc.parallelize([Row(name="John", age=19),
Row(name="Smith", age=23),
Row(name="Sarah", age=18)])
# Infer schema from the first row, create a SchemaRDD and print the schema
some_schemardd = sqlContext.inferSchema(some_rdd)
some_schemardd.printSchema()
# Another RDD is created from a list of tuples
another_rdd = sc.parallelize([("John", 19), ("Smith", 23), ("Sarah", 18)])
# Schema with two fields - person_name and person_age
schema = StructType([StructField("person_name", StringType(), False),
StructField("person_age", IntegerType(), False)])
# Create a SchemaRDD by applying the schema to the RDD and print the schema
another_schemardd = sqlContext.applySchema(another_rdd, schema)
another_schemardd.printSchema()
# root
# |-- age: integer (nullable = true)
# |-- name: string (nullable = true)
# A JSON dataset is pointed to by path.
# The path can be either a single text file or a directory storing text files.
path = os.path.join(os.environ['SPARK_HOME'], "examples/src/main/resources/people.json")
# Create a SchemaRDD from the file(s) pointed to by path
people = sqlContext.jsonFile(path)
# root
# |-- person_name: string (nullable = false)
# |-- person_age: integer (nullable = false)
from pyspark import SparkConf, SparkContext
from pyspark.sql import HiveContext
from datetime import datetime, date
from pyspark.sql import StructType, StructField, DateType, TimestampType
conf = SparkConf().setAppName("spark_sql_datatype_date_or_datetime")
sc = SparkContext(conf=conf)
hc = HiveContext(sc)
source = sc.parallelize([(date(2015, 9, 22), datetime(2015, 9, 22, 9, 39,
45))])
schema = StructType([
StructField("date", DateType(), False),
StructField("timestamp", TimestampType(), False)
])
table = hc.applySchema(source, schema)
table.registerAsTable("temp_table")
rows = hc.sql("select date, timestamp from temp_table").collect()
sc.stop()
for row in rows:
print row
from pyspark import SparkConf, SparkContext
from pyspark.sql import HiveContext
from pyspark.sql import StructType, StructField, StringType, BooleanType, BinaryType, NullType
conf = SparkConf().setAppName("spark_sql_datatype_str_bool_binary_none")
sc = SparkContext(conf=conf)
hc = HiveContext(sc)
source = sc.parallelize([("str", False, bytearray(range(0, 256)), None)])
schema = StructType([
StructField("str", StringType(), False),
StructField("bool", BooleanType(), False),
StructField("bytes", BinaryType(), False),
StructField("none", NullType())
])
table = hc.applySchema(source, schema)
table.registerAsTable("temp_table")
rows = hc.sql("select str, bool, bytes, none from temp_table").collect()
sc.stop()
for row in rows:
print row
# coding: utf-8
from pyspark import SparkConf, SparkContext
from pyspark.sql import HiveContext
from pyspark.sql import StructType, StructField, ArrayType, IntegerType
conf = SparkConf().setAppName("spark_sql_datatype_array")
sc = SparkContext(conf=conf)
hc = HiveContext(sc)
source = sc.parallelize([([1, 2, 3], )])
schema = StructType(
[StructField("array", ArrayType(IntegerType(), False), False)])
table = hc.applySchema(source, schema)
table.registerAsTable("temp_table")
rows = hc.sql("select array[0], array[1], array[2] from temp_table").collect()
sc.stop()
for row in rows:
print row
from pyspark.sql import HiveContext
from pyspark.sql import StructType, StructField, IntegerType, FloatType, StringType
conf = SparkConf().setAppName("spark_sql_datatype_struct")
sc = SparkContext(conf=conf)
hc = HiveContext(sc)
source = sc.parallelize([((1, 2.0, "3.0"), )])
schema = StructType([
StructField(
"struct",
StructType([
StructField("first", IntegerType(), False),
StructField("second", FloatType(), False),
StructField("third", StringType(), False)
]), False)
])
table = hc.applySchema(source, schema)
table.registerAsTable("temp_table")
rows = hc.sql(
"select struct.first, struct.second, struct.third from temp_table"
).collect()
sc.stop()
datetime(2015, 9, 22, 9, 39, 45), date(2015, 9, 22), [1, 2, 3], {
"key": "value"
}, (1, 2.0, "3.0"))
])
schema = StructType([
StructField("byte", ByteType(), False),
StructField("short", ShortType(), False),
StructField("int", IntegerType(), False),
StructField("long", LongType(), False),
StructField("float", FloatType(), False),
StructField("double", DoubleType(), False),
StructField("decimal", DecimalType(), False),
StructField("string", StringType(), False),
StructField("boolean", BooleanType(), False),
StructField("timestamp", TimestampType(), False),
StructField("date", DateType(), False),
StructField("array", ArrayType(IntegerType(), False), False),
StructField("col_map", MapType(StringType(), StringType(), False), False),
StructField(
"struct",
StructType([
StructField("first", IntegerType(), False),
StructField("second", FloatType(), False),
StructField("third", StringType(), False)
]), False)
])
table = hc.applySchema(source, schema)
table.registerAsTable("temp_table")
# coding: utf-8
from pyspark import SparkConf, SparkContext
from pyspark.sql import HiveContext
from pyspark.sql import StructType, StructField, MapType, StringType, IntegerType
conf = SparkConf().setAppName("spark_sql_datatype_map")
sc = SparkContext(conf=conf)
hc = HiveContext(sc)
source = sc.parallelize([({"key1": 1, "key2": 2}, )])
schema = StructType([
StructField("col_map", MapType(StringType(), IntegerType(), False), False)
])
table = hc.applySchema(source, schema)
table.registerAsTable("temp_table")
rows = hc.sql(
"select col_map['key1'], col_map['key2'] from temp_table").collect()
sc.stop()
for row in rows:
print row
