diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | python-pyspark-test.spec | 310 | ||||
| -rw-r--r-- | sources | 1 |
3 files changed, 312 insertions, 0 deletions
@@ -0,0 +1 @@ +/pyspark_test-0.2.0.tar.gz diff --git a/python-pyspark-test.spec b/python-pyspark-test.spec new file mode 100644 index 0000000..028cc94 --- /dev/null +++ b/python-pyspark-test.spec @@ -0,0 +1,310 @@ +%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 @@ -0,0 +1 @@ +1e1975b8d80865b0396e5fb71db0a639 pyspark_test-0.2.0.tar.gz |