PySpark row-wise function composition

Question

As a simplified example, I have a dataframe \"df\" with columns \"col1,col2\" and I want to compute a row-wise maximum after applying a function to each column :

<         


        

Answer 1

Below a useful code especially made to create any new column by simply calling a top-level business rule, completely isolated from the technical and heavy Spark's stuffs (no need to spend $ and to feel dependant of Databricks libraries anymore). My advice is, in your organization try to do things simply and cleanly in life, for the benefits of top-level data users:

def createColumnFromRule(df, columnName, ruleClass, ruleName, inputColumns=None, inputValues=None, columnType=None):
    from pyspark.sql import functions as F
    from pyspark.sql import types as T
    def _getSparkClassType(shortType):
        defaultSparkClassType = "StringType"
        typesMapping = {
            "bigint"    : "LongType",
            "binary"    : "BinaryType",
            "boolean"   : "BooleanType",
            "byte"      : "ByteType",
            "date"      : "DateType",
            "decimal"   : "DecimalType",
            "double"    : "DoubleType",
            "float"     : "FloatType",
            "int"       : "IntegerType",
            "integer"   : "IntegerType",
            "long"      : "LongType",
            "numeric"   : "NumericType",
            "string"    : defaultSparkClassType,
            "timestamp" : "TimestampType"
        }
        sparkClassType = None
        try:
            sparkClassType = typesMapping[shortType]
        except:
            sparkClassType = defaultSparkClassType
        return sparkClassType
    if (columnType != None): sparkClassType = _getSparkClassType(columnType)
    else: sparkClassType = "StringType"
    aUdf = eval("F.udf(ruleClass." + ruleName + ", T." + sparkClassType + "())")
    columns = None
    values = None
    if (inputColumns != None): columns = F.struct([df[column] for column in inputColumns])
    if (inputValues != None): values = F.struct([F.lit(value) for value in inputValues])
    # Call the rule
    if (inputColumns != None and inputValues != None): df = df.withColumn(columnName, aUdf(columns, values))
    elif (inputColumns != None): df = df.withColumn(columnName, aUdf(columns, F.lit(None)))
    elif (inputValues != None): df = df.withColumn(columnName, aUdf(F.lit(None), values))
    # Create a Null column otherwise
    else:
        if (columnType != None):
            df = df.withColumn(columnName, F.lit(None).cast(columnType))
        else:
            df = df.withColumn(columnName, F.lit(None))
    # Return the resulting dataframe
    return df

Usage example:

# Define your business rule (you can get columns and values)
class CustomerRisk:
    def churnRisk(self, columns=None, values=None):
        isChurnRisk = False
        # ... Rule implementation starts here
        if (values != None):
            if (values[0] == "FORCE_CHURN=true"): isChurnRisk = True
        if (isChurnRisk == False and columns != None):
            if (columns["AGE"]) <= 25): isChurnRisk = True
        # ...
        return isChurnRisk

# Execute the rule, it will create your new column in one line of code, that's all, easy isn't ?
# And look how to pass columns and values, it's really easy !
df = createColumnFromRule(df, columnName="CHURN_RISK", ruleClass=CustomerRisk(), ruleName="churnRisk", columnType="boolean", inputColumns=["NAME", "AGE", "ADDRESS"], inputValues=["FORCE_CHURN=true", "CHURN_RISK=100%"])