ปรับขนาดข้อมูลด้วยฟังก์ชัน Scaler

def ____(____, ____):
  # Takes a dataframe and list of columns to minmax scale. Returns a dataframe.
  for col in ____:
    # Define min and max values and collect them
    max_days = df.agg({col: 'max'}).collect()[0][0]
    min_days = df.agg({____: 'min'}).collect()[0][0]
    new_column_name = 'scaled_' + col
    # Create a new column based off the scaled data
    df = df.withColumn(____, 
                      (df[____] - min_days) / (max_days - min_days))
  return ____
  
df = min_max_scaler(____, ____)
# Show that our data is now between 0 and 1
df[['DAYSONMARKET', 'scaled_DAYSONMARKET']].show()