i have spark data frame following: +----------+-------------------------------------------------+ |col1 |words | +----------+-------------------------------------------------+ |an |[an, attractive, ,, thin, low, profile] | |attractive|[an, attractive, ,, thin, low, profile] | |, |[an, attractive, ,, thin, low, profile] | |thin |[an, attractive, ,, thin, low, profile] | |rail |[an, attractive, ,, thin, low, profile] | |profile |[an, attractive, ,, thin, low, profile] | |lighter |[lighter, than, metal, ,, level, ,, and, tes] | |than |[lighter, than, metal, ,, level, ,, and, tww] | |steel |[lighter, than, metal, ,, level, ,, and, test] | |, |[lighter, than, metal, ,, level, ,, and, test] | |level |[lighter, than, metal, ,, level, ,, and, test] | |, |[lighter, than, meta...