forked from databricks/Spark-The-Definitive-Guide
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathStructured_APIs-Chapter_5_Basic_Structured_Operations.py
273 lines (146 loc) · 5.05 KB
/
Structured_APIs-Chapter_5_Basic_Structured_Operations.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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
df = spark.read.format("json").load("/data/flight-data/json/2015-summary.json")
# COMMAND ----------
spark.read.format("json").load("/data/flight-data/json/2015-summary.json").schema
# COMMAND ----------
from pyspark.sql.types import StructField, StructType, StringType, LongType
myManualSchema = StructType([
StructField("DEST_COUNTRY_NAME", StringType(), True),
StructField("ORIGIN_COUNTRY_NAME", StringType(), True),
StructField("count", LongType(), False, metadata={"hello":"world"})
])
df = spark.read.format("json").schema(myManualSchema)\
.load("/data/flight-data/json/2015-summary.json")
# COMMAND ----------
from pyspark.sql.functions import col, column
col("someColumnName")
column("someColumnName")
# COMMAND ----------
from pyspark.sql.functions import expr
expr("(((someCol + 5) * 200) - 6) < otherCol")
# COMMAND ----------
from pyspark.sql import Row
myRow = Row("Hello", None, 1, False)
# COMMAND ----------
myRow[0]
myRow[2]
# COMMAND ----------
df = spark.read.format("json").load("/data/flight-data/json/2015-summary.json")
df.createOrReplaceTempView("dfTable")
# COMMAND ----------
from pyspark.sql import Row
from pyspark.sql.types import StructField, StructType, StringType, LongType
myManualSchema = StructType([
StructField("some", StringType(), True),
StructField("col", StringType(), True),
StructField("names", LongType(), False)
])
myRow = Row("Hello", None, 1)
myDf = spark.createDataFrame([myRow], myManualSchema)
myDf.show()
# COMMAND ----------
df.select("DEST_COUNTRY_NAME").show(2)
# COMMAND ----------
df.select("DEST_COUNTRY_NAME", "ORIGIN_COUNTRY_NAME").show(2)
# COMMAND ----------
from pyspark.sql.functions import expr, col, column
df.select(
expr("DEST_COUNTRY_NAME"),
col("DEST_COUNTRY_NAME"),
column("DEST_COUNTRY_NAME"))\
.show(2)
# COMMAND ----------
df.select(expr("DEST_COUNTRY_NAME AS destination")).show(2)
# COMMAND ----------
df.select(expr("DEST_COUNTRY_NAME as destination").alias("DEST_COUNTRY_NAME"))\
.show(2)
# COMMAND ----------
df.selectExpr("DEST_COUNTRY_NAME as newColumnName", "DEST_COUNTRY_NAME").show(2)
# COMMAND ----------
df.selectExpr(
"*", # all original columns
"(DEST_COUNTRY_NAME = ORIGIN_COUNTRY_NAME) as withinCountry")\
.show(2)
# COMMAND ----------
df.selectExpr("avg(count)", "count(distinct(DEST_COUNTRY_NAME))").show(2)
# COMMAND ----------
from pyspark.sql.functions import lit
df.select(expr("*"), lit(1).alias("One")).show(2)
# COMMAND ----------
df.withColumn("numberOne", lit(1)).show(2)
# COMMAND ----------
df.withColumn("withinCountry", expr("ORIGIN_COUNTRY_NAME == DEST_COUNTRY_NAME"))\
.show(2)
# COMMAND ----------
df.withColumnRenamed("DEST_COUNTRY_NAME", "dest").columns
# COMMAND ----------
dfWithLongColName = df.withColumn(
"This Long Column-Name",
expr("ORIGIN_COUNTRY_NAME"))
# COMMAND ----------
dfWithLongColName.selectExpr(
"`This Long Column-Name`",
"`This Long Column-Name` as `new col`")\
.show(2)
# COMMAND ----------
dfWithLongColName.select(expr("`This Long Column-Name`")).columns
# COMMAND ----------
df.where(col("count") < 2).where(col("ORIGIN_COUNTRY_NAME") != "Croatia")\
.show(2)
# COMMAND ----------
df.select("ORIGIN_COUNTRY_NAME", "DEST_COUNTRY_NAME").distinct().count()
# COMMAND ----------
df.select("ORIGIN_COUNTRY_NAME").distinct().count()
# COMMAND ----------
seed = 5
withReplacement = False
fraction = 0.5
df.sample(withReplacement, fraction, seed).count()
# COMMAND ----------
dataFrames = df.randomSplit([0.25, 0.75], seed)
dataFrames[0].count() > dataFrames[1].count() # False
# COMMAND ----------
from pyspark.sql import Row
schema = df.schema
newRows = [
Row("New Country", "Other Country", 5L),
Row("New Country 2", "Other Country 3", 1L)
]
parallelizedRows = spark.sparkContext.parallelize(newRows)
newDF = spark.createDataFrame(parallelizedRows, schema)
# COMMAND ----------
df.union(newDF)\
.where("count = 1")\
.where(col("ORIGIN_COUNTRY_NAME") != "United States")\
.show()
# COMMAND ----------
df.sort("count").show(5)
df.orderBy("count", "DEST_COUNTRY_NAME").show(5)
df.orderBy(col("count"), col("DEST_COUNTRY_NAME")).show(5)
# COMMAND ----------
from pyspark.sql.functions import desc, asc
df.orderBy(expr("count desc")).show(2)
df.orderBy(col("count").desc(), col("DEST_COUNTRY_NAME").asc()).show(2)
# COMMAND ----------
spark.read.format("json").load("/data/flight-data/json/*-summary.json")\
.sortWithinPartitions("count")
# COMMAND ----------
df.limit(5).show()
# COMMAND ----------
df.orderBy(expr("count desc")).limit(6).show()
# COMMAND ----------
df.rdd.getNumPartitions() # 1
# COMMAND ----------
df.repartition(5)
# COMMAND ----------
df.repartition(col("DEST_COUNTRY_NAME"))
# COMMAND ----------
df.repartition(5, col("DEST_COUNTRY_NAME"))
# COMMAND ----------
df.repartition(5, col("DEST_COUNTRY_NAME")).coalesce(2)
# COMMAND ----------
collectDF = df.limit(10)
collectDF.take(5) # take works with an Integer count
collectDF.show() # this prints it out nicely
collectDF.show(5, False)
collectDF.collect()
# COMMAND ----------