diff --git a/analysis/word_freq.sh b/analysis/word_freq.sh
new file mode 100755
index 0000000..0abbf44
--- /dev/null
+++ b/analysis/word_freq.sh
@@ -0,0 +1,3 @@
+#!/bin/bash
+#calculate no occurances of each word
+bzcat $1 | tr -s '[:punct:][:space:]' '\n' | grep -E "^[^\x00-\x7F]*[[:alpha:]][^\x00-\x7F]*$" | sort | uniq -c | sort -nr > word_freq.txt
\ No newline at end of file