Challenge #205: Taynalysis

[CollinBeckham]

At first, I was having trouble with getting my unique vs. duplicate values to tie...see spoiler.

Spoiler

Spoiler

Using the Unique tool before any data cleansing (to remove punctuation, stop words) got me to my solution!

[RichoBsJ]

Hi! Here my solution 🙂

[ZenonH]

Hard to shake off the punctuation and symbol discrepancies depending how you approach the problem.  It was also interesting to play with different ways of tokenizing what a 'word' is.  I.e. is everything after a space (\s) a word? Does Regex (\<\w+\>) Identify a word best? Overall very close to the solution depending on tweaks in cleansing or parsing.

Spoiler

[huynv96]

It's not 100 percents accuracy. Hihi

Spoiler

[mikeprice17]

Uniqueness was definitely different. But ended up with the same top ten words. I feel like my cleaning was more robust which ended up in less unique and more duplicate words.

[Pushpita15]

Not getting the exact numbers but pretty close though...

Attached is my approach

[JanetteJohnston]

Here is my two cents 🙂

[Strohy]

Got there eventually on which characters to exclude:

Spoiler