Python function to add binary columns to a pyspark df

Question

I have a dataframe productusage like :

featureSk	PersonNumber
A	1001
B	1001
C	1003
C	1004
A	1002
B	1005

I need to create a python function that has a list of person numbers as input and outputs a dateframe which has the values of featureSk column from productusage as columns. Basically there should be a column for each featureSk value and a 0 on a row if the PersonNumber doesnt exist in productusage and a 1 if it does exist in productusage

output should be a pandas dataframe like :

PersonNumber	A	B	C
1001	1	1	0
1002	0	0	0
1003	0	0	1

This is what I tried

def add_featureSk_to_dataframe(Person_list):
    Person_list = pd.DataFrame(Person_list)
    df = productusage
    unique_values = df[featureSk].unique()
    for value in unique_vaues:
      for person in Persons_list:
        df = df.withColumn(value, lambda person: 1 if person in Persons_list else 0)
    return df
person_test = [1001,1002,1003]
add_featureSk_to_dataframe(person_test)

Getting an error that featureSk is not defined even though the productusage is defined

Answer 1

def person_has_product(person_list):
    df = dfPersonQuery
    
    #Distinct product names
    products = df.select("featureSk").distinct()
    
    # Filter df for the required persons
    filtered_df = df.filter(col("personnumber").isin(person_list))

    # Perform crosstab on the person and product columns
    cross_tab_result = filtered_df.crosstab("personnumber", "featureSk").withColumnRenamed("personnumber_featureSk", "personnumber")
    # Iterate through the distinct products in featureSk column
    
    for column in cross_tab_result.drop("personnumber").columns:
        cross_tab_result = cross_tab_result.withColumn(column,when(col(column) > 0, 1).otherwise(0))

    return print(cross_tab_result.toPandas())
    
person_lst =[1001, 1002, 1003]
person_has_product(person_lst)
`