Estimate size of Spark DataFrame in bytes

spark_dataframe_size_estimator.py

# Function to convert python object to Java objects
def _to_java_object_rdd(rdd):  
    """ Return a JavaRDD of Object by unpickling
    It will convert each Python object into Java object by Pyrolite, whenever the
    RDD is serialized in batch or not.
    """
    rdd = rdd._reserialize(AutoBatchedSerializer(PickleSerializer()))
    return rdd.ctx._jvm.org.apache.spark.mllib.api.python.SerDe.pythonToJava(rdd._jrdd, True)

# Convert DataFrame to an RDD 
JavaObj = _to_java_object_rdd(df.rdd)

# Estimate size in bytes
bytes = sc._jvm.org.apache.spark.util.SizeEstimator.estimate(JavaObj)

I am getting 43 Mb with your code, but in my storage stats it shows that this df has 82Mb, any suggestions?