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
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
|
%global _empty_manifest_terminate_build 0
Name: python-pyspark-test
Version: 0.2.0
Release: 1
Summary: Check that left and right spark DataFrame are equal.
License: Apache Software License (Apache 2.0)
URL: https://github.com/debugger24/pyspark-test
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/f8/a9/3ca6c0f3289da348d25693adb4f80e3d8b2389dea603f222feae4dd78e76/pyspark_test-0.2.0.tar.gz
BuildArch: noarch
Requires: python3-pyspark
%description
# pyspark-test
[](https://github.com/ambv/black)
[](https://opensource.org/licenses/Apache-2.0)
[](https://github.com/debugger24/pyspark-test/actions?query=workflow%3A%22Unit+Test%22)
[](https://badge.fury.io/py/pyspark-test)
[](https://pepy.tech/project/pyspark-test)
Check that left and right spark DataFrame are equal.
This function is intended to compare two spark DataFrames and output any differences. It is inspired from pandas testing module but for pyspark, and for use in unit tests. Additional parameters allow varying the strictness of the equality checks performed.
# Installation
```
pip install pyspark-test
```
# Usage
```py
assert_pyspark_df_equal(left_df, actual_df)
```
## Additional Arguments
* `check_dtype` : To compare the data types of spark dataframe. Default true
* `check_column_names` : To compare column names. Default false. Not required of we are checking data types.
* `check_columns_in_order` : To check the columns should be in order or not. Default to false
* `order_by` : Column names with which dataframe must be sorted before comparing. Default None.
# Example
```py
import datetime
from pyspark import SparkContext
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from pyspark_test import assert_pyspark_df_equal
sc = SparkContext.getOrCreate(conf=conf)
spark_session = SparkSession(sc)
df_1 = spark_session.createDataFrame(
data=[
[datetime.date(2020, 1, 1), 'demo', 1.123, 10],
[None, None, None, None],
],
schema=StructType(
[
StructField('col_a', DateType(), True),
StructField('col_b', StringType(), True),
StructField('col_c', DoubleType(), True),
StructField('col_d', LongType(), True),
]
),
)
df_2 = spark_session.createDataFrame(
data=[
[datetime.date(2020, 1, 1), 'demo', 1.123, 10],
[None, None, None, None],
],
schema=StructType(
[
StructField('col_a', DateType(), True),
StructField('col_b', StringType(), True),
StructField('col_c', DoubleType(), True),
StructField('col_d', LongType(), True),
]
),
)
assert_pyspark_df_equal(df_1, df_2)
```
%package -n python3-pyspark-test
Summary: Check that left and right spark DataFrame are equal.
Provides: python-pyspark-test
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-pyspark-test
# pyspark-test
[](https://github.com/ambv/black)
[](https://opensource.org/licenses/Apache-2.0)
[](https://github.com/debugger24/pyspark-test/actions?query=workflow%3A%22Unit+Test%22)
[](https://badge.fury.io/py/pyspark-test)
[](https://pepy.tech/project/pyspark-test)
Check that left and right spark DataFrame are equal.
This function is intended to compare two spark DataFrames and output any differences. It is inspired from pandas testing module but for pyspark, and for use in unit tests. Additional parameters allow varying the strictness of the equality checks performed.
# Installation
```
pip install pyspark-test
```
# Usage
```py
assert_pyspark_df_equal(left_df, actual_df)
```
## Additional Arguments
* `check_dtype` : To compare the data types of spark dataframe. Default true
* `check_column_names` : To compare column names. Default false. Not required of we are checking data types.
* `check_columns_in_order` : To check the columns should be in order or not. Default to false
* `order_by` : Column names with which dataframe must be sorted before comparing. Default None.
# Example
```py
import datetime
from pyspark import SparkContext
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from pyspark_test import assert_pyspark_df_equal
sc = SparkContext.getOrCreate(conf=conf)
spark_session = SparkSession(sc)
df_1 = spark_session.createDataFrame(
data=[
[datetime.date(2020, 1, 1), 'demo', 1.123, 10],
[None, None, None, None],
],
schema=StructType(
[
StructField('col_a', DateType(), True),
StructField('col_b', StringType(), True),
StructField('col_c', DoubleType(), True),
StructField('col_d', LongType(), True),
]
),
)
df_2 = spark_session.createDataFrame(
data=[
[datetime.date(2020, 1, 1), 'demo', 1.123, 10],
[None, None, None, None],
],
schema=StructType(
[
StructField('col_a', DateType(), True),
StructField('col_b', StringType(), True),
StructField('col_c', DoubleType(), True),
StructField('col_d', LongType(), True),
]
),
)
assert_pyspark_df_equal(df_1, df_2)
```
%package help
Summary: Development documents and examples for pyspark-test
Provides: python3-pyspark-test-doc
%description help
# pyspark-test
[](https://github.com/ambv/black)
[](https://opensource.org/licenses/Apache-2.0)
[](https://github.com/debugger24/pyspark-test/actions?query=workflow%3A%22Unit+Test%22)
[](https://badge.fury.io/py/pyspark-test)
[](https://pepy.tech/project/pyspark-test)
Check that left and right spark DataFrame are equal.
This function is intended to compare two spark DataFrames and output any differences. It is inspired from pandas testing module but for pyspark, and for use in unit tests. Additional parameters allow varying the strictness of the equality checks performed.
# Installation
```
pip install pyspark-test
```
# Usage
```py
assert_pyspark_df_equal(left_df, actual_df)
```
## Additional Arguments
* `check_dtype` : To compare the data types of spark dataframe. Default true
* `check_column_names` : To compare column names. Default false. Not required of we are checking data types.
* `check_columns_in_order` : To check the columns should be in order or not. Default to false
* `order_by` : Column names with which dataframe must be sorted before comparing. Default None.
# Example
```py
import datetime
from pyspark import SparkContext
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from pyspark_test import assert_pyspark_df_equal
sc = SparkContext.getOrCreate(conf=conf)
spark_session = SparkSession(sc)
df_1 = spark_session.createDataFrame(
data=[
[datetime.date(2020, 1, 1), 'demo', 1.123, 10],
[None, None, None, None],
],
schema=StructType(
[
StructField('col_a', DateType(), True),
StructField('col_b', StringType(), True),
StructField('col_c', DoubleType(), True),
StructField('col_d', LongType(), True),
]
),
)
df_2 = spark_session.createDataFrame(
data=[
[datetime.date(2020, 1, 1), 'demo', 1.123, 10],
[None, None, None, None],
],
schema=StructType(
[
StructField('col_a', DateType(), True),
StructField('col_b', StringType(), True),
StructField('col_c', DoubleType(), True),
StructField('col_d', LongType(), True),
]
),
)
assert_pyspark_df_equal(df_1, df_2)
```
%prep
%autosetup -n pyspark-test-0.2.0
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-pyspark-test -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Tue Apr 11 2023 Python_Bot <Python_Bot@openeuler.org> - 0.2.0-1
- Package Spec generated
|
