Python spark_session_from_config Beispiele

Beispiel #1

def test_smoke_test_table_three():
    spark = spark_session_from_config()

    result = invoke_compute(
        TableThree,
        inputs={
            'table_one': spark.createDataFrame([Row(num=1)]),
            'table_two': spark.createDataFrame([Row(num=2)]),
        },
    )

    assert result.success
    assert set(result.output_value().collect()) == set([Row(num=1), Row(num=2)])

Beispiel #2

 def get_table(table_def):
     spark = spark_session_from_config()
     return spark.read.parquet(
         os.path.join(temp_dir, table_def.metadata[FEATURE_AREA],
                      table_def.name)).collect()

Beispiel #3

Datei: test_basic_pyspark_lakehouse.py Projekt: yangchenghuang/dagster

 def get_table(name):
     spark = spark_session_from_config()
     return spark.read.csv(os.path.join(temp_dir, name),
                           header=True,
                           inferSchema=True).collect()