1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22

# A example from https://spark.apache.org/docs/latest/sql-data-sources-hive-tables.html

from os.path import abspath
from pyspark.sql import SparkSession
from pyspark.sql import Row

# warehouse_location points to the default location for managed databases and tables
warehouse_location = abspath('spark-warehouse')

spark = SparkSession \
    .builder \
    .appName("Python Spark SQL Hive integration example") \
    .config("spark.sql.warehouse.dir", warehouse_location) \
    .enableHiveSupport() \
    .getOrCreate()

# spark is an existing SparkSession
spark.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING hive")
spark.sql("LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src")

# The results of SQL queries are themselves DataFrames and support all normal functions.
sqlDF = spark.sql("SELECT key, value FROM src WHERE key < 10 ORDER BY key")

 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

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

"""
An interactive shell.

This file is designed to be launched as a PYTHONSTARTUP script.
"""

import atexit
import os
import platform
import warnings

import py4j

from pyspark import SparkConf
from pyspark.context import SparkContext
from pyspark.sql import SparkSession, SQLContext

if os.environ.get("SPARK_EXECUTOR_URI"):
    SparkContext.setSystemProperty("spark.executor.uri", os.environ["SPARK_EXECUTOR_URI"])

SparkContext._ensure_initialized()

try:
    # Try to access HiveConf, it will raise exception if Hive is not added
    conf = SparkConf()
    if conf.get('spark.sql.catalogImplementation', 'hive').lower() == 'hive':
        SparkContext._jvm.org.apache.hadoop.hive.conf.HiveConf()
        spark = SparkSession.builder\
            .enableHiveSupport()\
            .getOrCreate()
    else:
        spark = SparkSession.builder.getOrCreate()
except py4j.protocol.Py4JError:
    if conf.get('spark.sql.catalogImplementation', '').lower() == 'hive':
        warnings.warn("Fall back to non-hive support because failing to access HiveConf, "
                      "please make sure you build spark with hive")
    spark = SparkSession.builder.getOrCreate()
except TypeError:
    if conf.get('spark.sql.catalogImplementation', '').lower() == 'hive':
        warnings.warn("Fall back to non-hive support because failing to access HiveConf, "
                      "please make sure you build spark with hive")
    spark = SparkSession.builder.getOrCreate()

sc = spark.sparkContext
sql = spark.sql
atexit.register(lambda: sc.stop())

# for compatibility
sqlContext = spark._wrapped
sqlCtx = sqlContext

print("""Welcome to
      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /__ / .__/\_,_/_/ /_/\_\   version %s
      /_/
""" % sc.version)
print("Using Python version %s (%s, %s)" % (
    platform.python_version(),
    platform.python_build()[0],
    platform.python_build()[1]))
print("SparkSession available as 'spark'.")

# The ./bin/pyspark script stores the old PYTHONSTARTUP value in OLD_PYTHONSTARTUP,
# which allows us to execute the user's PYTHONSTARTUP file:
_pythonstartup = os.environ.get('OLD_PYTHONSTARTUP')
if _pythonstartup and os.path.isfile(_pythonstartup):
    with open(_pythonstartup) as f:
        code = compile(f.read(), _pythonstartup, 'exec')
        exec(code)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

raw_data = sc.textFile("./kddcup.data.gz")
## Comma-Separated Value
csv = raw_data.map(lambda x: x.split(","))

metrics = csv.map(lambda x: [x[0], x[4], x[5]])

from pyspark.mllib.stat import Statistics

Statistics.corr(metrics, method="spearman")
Statistics.corr(metrics, method="pearson")

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

# A example from https://docs.microsoft.com/en-us/azure/databricks/spark/latest/spark-sql/spark-pandas

import numpy as np
import pandas as pd

# Enable Arrow-based columnar data transfers
spark.conf.set("spark.sql.execution.arrow.enabled", "true")

# Generate a pandas DataFrame
pdf = pd.DataFrame(np.random.rand(100, 3))

# Create a Spark DataFrame from a pandas DataFrame using Arrow
df = spark.createDataFrame(pdf)

# Convert the Spark DataFrame back to a pandas DataFrame using Arrow
result_pdf = df.select("*").toPandas()

1
2

spark_df.write.mode("overwrite").format("hive").saveAsTable("dbName.tableName")
# 注意是 overwrite 

1
2
3
4

spark_df.createOrReplaceTempView("myTempTableName")

spark.sql("drop table if exists dbName.tableName")
spark.sql("create table dbName.tableName as select * from myTempTableName")