transform one (or more) column(s) into Vector

Now you scan scale the data using StandardScaler

Add everything to a `Pipeline` to make it easier

#transform one column into Vector that is required input data type for Scalers. 

from pyspark.ml.feature import StandardScaler

from pyspark.ml.feature import VectorAssembler

vector_assembler = VectorAssembler(inputCols=["avg_price"],

outputCol="avg_price_vector")

data = vector_assembler.transform(data)

# Now you scan scale the data using StandardScaler

standard_scaler = StandardScaler(withMean=True, withStd=True,

inputCol="avg_price_vector",

outputCol="avg_price_scaled")

final_data_prepared = standard_scaler.fit(data).transform(data)