Grouping issue when TFIDF.min_similarity < link_min_similarity

Nobody has claimed this yet.

In the code below (with output in attached picture) I perform a simple TFIDF matching of `["apple", "apples", "appl", "recal", "happy"]`.

The initial `min_similarity` is set to 0.2. The similarity of `happy` and `appl` is 0.24.

When grouping with a `link_min_similarity` of 0.5, `happy` should not belong in the `apples` group, though that's what happens in the output of `.get_matches()`, it is in the `apples` group.

It appears it is not in the cluster though.


Plain text code:

```python
from polyfuzz import PolyFuzz
from polyfuzz.models import TFIDF

from_list = ["apple", "apples", "appl", "recal", "happy"]
matcher = TFIDF(min_similarity=0.2)
model = PolyFuzz(matcher).match(from_list)
cm = model.cluster_mappings
model.group(link_min_similarity=0.5, group_all_strings=True)
print(model.get_matches())
```

Start with the supplied Python reproduction using PolyFuzz, TFIDF, group(link_min_similarity=0.5, group_all_strings=True), and get_matches(). Inspect how grouping handles the happy/appl similarity versus the link threshold. Done means happy is not reported in the apples group when its similarity is below link_min_similarity.

Written by the indexing model from the issue text.