Take a look here for options,
http://spark.apache.org/docs/latest/api/python/pyspark.sql.html?highlight=dataframereader#pyspark.sq...
If a csv file has commas then the tradition is to quote the string that contains the comma,
In particular see if adding some of the options from that documentation such as.
quote – sets a single character used for escaping quoted values where the separator can be part of the value. If None is set, it uses the default value,
"
. If you would like to turn off quotations, you need to set an empty string.
Also,
You may have poorly formatted data, in that case you might need to read the whole line as a string and then parse as a dataframe with single column and use tools to split the string to create the needed final dataframe
