Update README.md
Browse files
README.md
CHANGED
@@ -13,29 +13,37 @@ tags:
|
|
13 |
# gbpatentdata/lt-patent-inventor-linking
|
14 |
|
15 |
This is a [LinkTransformer](https://linktransformer.github.io/) model. At its core this model this is a sentence transformer model [sentence-transformers](https://www.SBERT.net) model - it just wraps around the class.
|
16 |
-
Take a look at the documentation of [sentence-transformers](https://www.sbert.net/index.html) if you want to use this model for more than what we support in our applications.
|
17 |
-
|
18 |
This model has been fine-tuned on the model: `sentence-transformers/all-mpnet-base-v2`. It is pretrained for the language: `en`.
|
19 |
|
20 |
-
## Usage (
|
21 |
|
22 |
-
|
23 |
|
|
|
|
|
|
|
|
|
|
|
24 |
```
|
25 |
-
pip install -U linktransformer
|
26 |
-
```
|
27 |
|
28 |
-
|
|
|
|
|
29 |
|
30 |
```python
|
31 |
import linktransformer as lt
|
32 |
import pandas as pd
|
33 |
|
34 |
-
df_lm_matched = lt.cluster_rows(df,
|
35 |
-
model='
|
36 |
-
on=['name', 'occupation', 'year', 'address', 'firm', 'patent_title'],
|
37 |
-
cluster_type='SLINK',
|
38 |
-
cluster_params={
|
|
|
|
|
|
|
|
|
|
|
39 |
)
|
40 |
|
41 |
```
|
|
|
13 |
# gbpatentdata/lt-patent-inventor-linking
|
14 |
|
15 |
This is a [LinkTransformer](https://linktransformer.github.io/) model. At its core this model this is a sentence transformer model [sentence-transformers](https://www.SBERT.net) model - it just wraps around the class.
|
|
|
|
|
16 |
This model has been fine-tuned on the model: `sentence-transformers/all-mpnet-base-v2`. It is pretrained for the language: `en`.
|
17 |
|
18 |
+
## Usage (Sentence-Transformers)
|
19 |
|
20 |
+
To use this model using sentence-transformers:
|
21 |
|
22 |
+
```python
|
23 |
+
from sentence_transformers import SentenceTransformer
|
24 |
+
|
25 |
+
# load
|
26 |
+
model = SentenceTransformer("all-MiniLM-L6-v2")
|
27 |
```
|
|
|
|
|
28 |
|
29 |
+
## Usage (LinkTransformer)
|
30 |
+
|
31 |
+
To use this model for clustering with [LinkTransformer](https://github.com/dell-research-harvard/linktransformer) installed:
|
32 |
|
33 |
```python
|
34 |
import linktransformer as lt
|
35 |
import pandas as pd
|
36 |
|
37 |
+
df_lm_matched = lt.cluster_rows(df, # df should be a dataset of unique patent-inventors
|
38 |
+
model='matthewleechen/lt-patent-inventor-linking',
|
39 |
+
on=['name', 'occupation', 'year', 'address', 'firm', 'patent_title'], # cluster on these variables
|
40 |
+
cluster_type='SLINK', # use SLINK algorithm
|
41 |
+
cluster_params={ # default params
|
42 |
+
'threshold': 0.1,
|
43 |
+
'min cluster size': 1,
|
44 |
+
'metric': 'cosine'
|
45 |
+
}
|
46 |
+
)
|
47 |
)
|
48 |
|
49 |
```
|