-
Notifications
You must be signed in to change notification settings - Fork 476
/
Copy pathdataframe-session-2022-05-12.txt
174 lines (156 loc) · 4.51 KB
/
dataframe-session-2022-05-12.txt
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
>>> spark
<pyspark.sql.session.SparkSession object at 0x1034a29d0>
>>> spark.version
'3.2.0'
>>> # create a Python collection as data
>>> data =
[
('alex', 20, 12000),
('jane', 30, 45000),
('rafa', 40, 56000),
('ted', 30, 145000),
('xo2', 10, 1332000),
('mary', 44, 555000)
]
>>> data
[
('alex', 20, 12000),
('jane', 30, 45000),
('rafa', 40, 56000),
('ted', 30, 145000),
('xo2', 10, 1332000),
('mary', 44, 555000)
]
>>> #define column names
>>> column_names = ['name', 'age', 'salary']
>>> column_names
['name', 'age', 'salary']
>>> # create a DataFrame as df
>>> df = spark.createDataFrame(data, column_names)
>>>
>>> # inspect created DataFrame
>>> df
DataFrame[name: string, age: bigint, salary: bigint]
>>> # inspect created DataFrame's Schema
>>> df.printSchema()
root
|-- name: string (nullable = true)
|-- age: long (nullable = true)
|-- salary: long (nullable = true)
>>> # display the first 20 rows of a DataFrame
>>> df.show()
+----+---+-------+
|name|age| salary|
+----+---+-------+
|alex| 20| 12000|
|jane| 30| 45000|
|rafa| 40| 56000|
| ted| 30| 145000|
| xo2| 10|1332000|
|mary| 44| 555000|
+----+---+-------+
>>> # count the number of rows
>>> df.count()
6
>>> # Creates or replaces a local temporary view with this DataFrame
>>> df.createOrReplaceTempView("people")
>>> df2 = spark.sql("select * from people where salary > 67000")
>>> df2.show()
+----+---+-------+
|name|age| salary|
+----+---+-------+
| ted| 30| 145000|
| xo2| 10|1332000|
|mary| 44| 555000|
+----+---+-------+
>>> df3 = spark.sql("select * from people where salary > 67000 and age > 11")
>>> df3.show()
+----+---+------+
|name|age|salary|
+----+---+------+
| ted| 30|145000|
|mary| 44|555000|
+----+---+------+
>>> df.show()
+----+---+-------+
|name|age| salary|
+----+---+-------+
|alex| 20| 12000|
|jane| 30| 45000|
|rafa| 40| 56000|
| ted| 30| 145000|
| xo2| 10|1332000|
|mary| 44| 555000|
+----+---+-------+
>>> df4 = spark.sql("select * from people")
>>> df4.show()
+----+---+-------+
|name|age| salary|
+----+---+-------+
|alex| 20| 12000|
|jane| 30| 45000|
|rafa| 40| 56000|
| ted| 30| 145000|
| xo2| 10|1332000|
|mary| 44| 555000|
+----+---+-------+
>>> cart = spark.sql("select * from people p1, people p2")
>>> cart.show()
+----+---+------+----+---+-------+
|name|age|salary|name|age| salary|
+----+---+------+----+---+-------+
|alex| 20| 12000|alex| 20| 12000|
|alex| 20| 12000|jane| 30| 45000|
|alex| 20| 12000|rafa| 40| 56000|
|alex| 20| 12000| ted| 30| 145000|
|alex| 20| 12000| xo2| 10|1332000|
|alex| 20| 12000|mary| 44| 555000|
|jane| 30| 45000|alex| 20| 12000|
|jane| 30| 45000|jane| 30| 45000|
|jane| 30| 45000|rafa| 40| 56000|
|jane| 30| 45000| ted| 30| 145000|
|jane| 30| 45000| xo2| 10|1332000|
|jane| 30| 45000|mary| 44| 555000|
|rafa| 40| 56000|alex| 20| 12000|
|rafa| 40| 56000|jane| 30| 45000|
|rafa| 40| 56000|rafa| 40| 56000|
|rafa| 40| 56000| ted| 30| 145000|
|rafa| 40| 56000| xo2| 10|1332000|
|rafa| 40| 56000|mary| 44| 555000|
| ted| 30|145000|alex| 20| 12000|
| ted| 30|145000|jane| 30| 45000|
+----+---+------+----+---+-------+
only showing top 20 rows
>>> cart
>>> Frame[name: string, age: bigint, salary: bigint, name: string, age: bigint, salary: bigint]
>>>
>>> cart2 = spark.sql("select p1.name as name, p2.age as age, p1.salary as salary, p2.name as name2, p2.age as age2, p2.salary as salary2 from people p1, people p2")
>>> cart2.show()
+----+---+------+-----+----+-------+
|name|age|salary|name2|age2|salary2|
+----+---+------+-----+----+-------+
|alex| 20| 12000| alex| 20| 12000|
|alex| 30| 12000| jane| 30| 45000|
|alex| 40| 12000| rafa| 40| 56000|
|alex| 30| 12000| ted| 30| 145000|
|alex| 10| 12000| xo2| 10|1332000|
|alex| 44| 12000| mary| 44| 555000|
|jane| 20| 45000| alex| 20| 12000|
|jane| 30| 45000| jane| 30| 45000|
|jane| 40| 45000| rafa| 40| 56000|
|jane| 30| 45000| ted| 30| 145000|
|jane| 10| 45000| xo2| 10|1332000|
|jane| 44| 45000| mary| 44| 555000|
|rafa| 20| 56000| alex| 20| 12000|
|rafa| 30| 56000| jane| 30| 45000|
|rafa| 40| 56000| rafa| 40| 56000|
|rafa| 30| 56000| ted| 30| 145000|
|rafa| 10| 56000| xo2| 10|1332000|
|rafa| 44| 56000| mary| 44| 555000|
| ted| 20|145000| alex| 20| 12000|
| ted| 30|145000| jane| 30| 45000|
+----+---+------+-----+----+-------+
only showing top 20 rows
>>>
>>> cart2
DataFrame[name: string, age: bigint, salary: bigint, name2: string, age2: bigint, salary2: bigint]