Update Readme.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,54 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
pipeline_tag: text-classification
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
-
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
```python
|
| 8 |
from transformers import pipeline
|
| 9 |
|
| 10 |
-
clf = pipeline(
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language: en
|
| 3 |
pipeline_tag: text-classification
|
| 4 |
+
tags:
|
| 5 |
+
- bert
|
| 6 |
+
- sentiment-analysis
|
| 7 |
+
- text-classification
|
| 8 |
+
license: mit
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# Bert_sentiment_classifier
|
| 12 |
|
| 13 |
+
A BERT (`bert-base-uncased`) model fine-tuned for **3-class sentiment classification**:
|
| 14 |
+
|
| 15 |
+
- **Positive**
|
| 16 |
+
- **Neutral**
|
| 17 |
+
- **Negative**
|
| 18 |
+
|
| 19 |
+
## Labels
|
| 20 |
+
|
| 21 |
+
| id | label |
|
| 22 |
+
|---:|----------|
|
| 23 |
+
| 0 | Neutral |
|
| 24 |
+
| 1 | Positive |
|
| 25 |
+
| 2 | Negative |
|
| 26 |
+
|
| 27 |
+
## Test Drive
|
| 28 |
+
|
| 29 |
+
Try one of these examples into the widget:
|
| 30 |
+
|
| 31 |
+
- **Negative:** "Dirty. Generally poor attitude among the nurses, even the good know the place sucks. When patients are crying for help nurse should not be busy watching Tik-Tok. Too many mistakes made too often. Teaching nurses instructing student nurse procedures incorrectly. Yes, it is bad."
|
| 32 |
+
- **Neutral:** "I received the update and will review it later this week."
|
| 33 |
+
- **Positive:** "I had surgery last month. and I was very impressed with the quality of service from the moment I got in till I left. Also I like to mention the nurses they were out standing"
|
| 34 |
+
|
| 35 |
+
## How to use
|
| 36 |
+
|
| 37 |
+
### Transformers pipeline
|
| 38 |
```python
|
| 39 |
from transformers import pipeline
|
| 40 |
|
| 41 |
+
clf = pipeline(
|
| 42 |
+
"text-classification",
|
| 43 |
+
model="pokwir/Bert_sentiment_classifier",
|
| 44 |
+
tokenizer="pokwir/Bert_sentiment_classifier",
|
| 45 |
+
return_all_scores=True
|
| 46 |
+
)
|
| 47 |
+
|
| 48 |
+
texts = [
|
| 49 |
+
"Dirty. Generally poor attitude among the nurses, even the good know the place sucks. When patients are crying for help nurse should not be busy watching Tik-Tok. Too many mistakes made too often. Teaching nurses instructing student nurse procedures incorrectly. Yes, it is bad.",
|
| 50 |
+
"I had surgery last month. and I was very impressed with the quality of service from the moment I got in till I left. Also I like to mention the nurses they were out standing.",
|
| 51 |
+
"This hospital has been going downhill for years thanks to dr.billie and her know all attitude she should go back to her vet clinic."
|
| 52 |
+
]
|
| 53 |
+
|
| 54 |
+
print(clf(texts))
|