chispa

import os from pyspark.sql import SparkSession from chispa.dataframe_comparer import assert_df_equality # Initialize SparkSession (for local testing, typically done in a pytest fixture) spark = SparkSession.builder.appName("ChispaQuickstart").getOrCreate() # Create an 'actual' DataFrame data_actual = [ ("john", 1), ("jane", 2), ("doe", 3) ] df_actual = spark.createDataFrame(data_actual, ["name", "id"]) # Create an 'expected' DataFrame (identical for a passing test) data_expected = [ ("john", 1), ("jane", 2), ("doe", 3) ] df_expected = spark.createDataFrame(data_expected, ["name", "id"]) # Assert equality - this test should pass try: assert_df_equality(df_actual, df_expected) print("Assertion Passed: df_actual and df_expected are equal.") except Exception as e: print(f"Assertion Failed: {e}") # Create a different 'expected' DataFrame to demonstrate a failing test data_expected_fail = [ ("john", 1), ("jane", 99), # Intentional difference ("doe", 3) ] df_expected_fail = spark.createDataFrame(data_expected_fail, ["name", "id"]) # Assert equality - this test should fail, showing descriptive error try: assert_df_equality(df_actual, df_expected_fail) print("Assertion Passed (unexpectedly): df_actual and df_expected_fail are equal.") except Exception as e: print(f"Assertion Failed (as expected): {e}") # Stop SparkSession spark.stop()