Update README.md

README.md

@@ -18,9 +18,27 @@ This model is a fine-tuned version of [sentence-transformers/all-MiniLM-L6-v2](h
 - Epoch: 14
 - Final Macro F1-score: 0.79
 
+
 <b>Labels</b>: 
-0 or F -> Functional;
-1 or NF -> Non-functional;
+0 or A -> Availability;
+1 or AC -> Access Control;
+2 or AU -> Audit;
+3 or B -> Behaviour;
+4 or D -> Data;
+5 or FT -> Fault Tolerance;
+6 or I -> Interface/Interoperability;
+7 or LE -> Legal;
+8 or LF -> Look and Feel;
+9 or MN -> Maintainability;
+10 or O -> Operational;
+11 or PE -> Performance;
+12 or PO -> Portability;
+13 or RL -> Reliability;
+14 or SA -> Safety;
+15 or SC -> Scalability;
+16 or SE -> Security;
+17 or ST -> Stability;
+18 or US -> Usability;
 
 
 ## Usage Pipeline
@@ -33,12 +51,16 @@ model_ckpt = 'kasrahabib/KM35NCDF-NF-SUBCLASSES-cls'
 
 software_requirment_cls = pipeline(task = task, model = model_ckpt, framework = frame_work)
 
-example_1_f = 'The START NEW PROJECT function shall allow the user to create a new project.'
-example_2_nf = 'The email string consists of [email protected] and is less than 31 characters in length and is not empty.'
+example_1_US = 'Application needs to keep track of subtasks in a task.'
+example_2_PE = 'The system shall allow users to enter time in several different formats.'
+example_3_AC = 'The system shall allow users who hold any of the ORES/ORELSE/PROVIDER keys to be viewed as a clinical user and has full access privileges to all problem list options.'
+
+software_requirment_cls([example_1_US, example_2_PE, example_3_AC])
 ```
 ```
-[{'label': 'F', 'score': 0.9998922348022461},
- {'label': 'NF', 'score': 0.999846339225769}]
+[{'label': 'US', 'score': 0.9712953567504883},
+ {'label': 'PE', 'score': 0.9457865953445435},
+ {'label': 'AC', 'score': 0.9639136791229248}]
 ```
 
 ## Model Inference:
@@ -51,9 +73,10 @@ model_ckpt = 'kasrahabib/KM35NCDF-NF-SUBCLASSES-cls'
 tokenizer = AutoTokenizer.from_pretrained(model_ckpt)
 model = TFAutoModelForSequenceClassification.from_pretrained(model_ckpt)
 
-example_1_f = 'The START NEW PROJECT function shall allow the user to create a new project.'
-example_2_nf = 'The email string consists of [email protected] and is less than 31 characters in length and is not empty.'
-requirements = [example_1_f, example_2_nf]
+example_1_US = 'Application needs to keep track of subtasks in a task.'
+example_2_PE = 'The system shall allow users to enter time in several different formats.'
+example_3_AC = 'The system shall allow users who hold any of the ORES/ORELSE/PROVIDER keys to be viewed as a clinical user and has full access privileges to all problem list options.'
+requirements = [example_1_US, example_2_PE, example_3_AC]
 
 encoded_requirements = tokenizer(requirements, return_tensors = 'np', padding = 'longest')
 
@@ -64,7 +87,7 @@ classifications = [model.config.id2label[output] for output in classifications]
 print(classifications)
 ```
 ```
-['F', 'NF']
+['US', 'PE', 'AC']
 ```
 
 ## Usage Locally Downloaded (e.g., GitHub):
@@ -83,13 +106,14 @@ Then modify the code as below:
 import numpy as np
 from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
 
-model_ckpt = 'rest_of_the_path/KM35NCDF-NF-SUBCLASSES-cls'
+model_ckpt =  'rest_of_the_path/KM35NCDF-NF-SUBCLASSES-cls'
 tokenizer = AutoTokenizer.from_pretrained(model_ckpt)
 model = TFAutoModelForSequenceClassification.from_pretrained(model_ckpt)
 
-example_1_f = 'The START NEW PROJECT function shall allow the user to create a new project.'
-example_2_nf = 'The email string consists of [email protected] and is less than 31 characters in length and is not empty.'
-requirements = [example_1_f, example_2_nf]
+example_1_US = 'Application needs to keep track of subtasks in a task.'
+example_2_PE = 'The system shall allow users to enter time in several different formats.'
+example_3_AC = 'The system shall allow users who hold any of the ORES/ORELSE/PROVIDER keys to be viewed as a clinical user and has full access privileges to all problem list options.'
+requirements = [example_1_US, example_2_PE, example_3_AC]
 
 encoded_requirements = tokenizer(requirements, return_tensors = 'np', padding = 'longest')
 
@@ -99,9 +123,6 @@ classifications = np.argmax(y_pred, axis = 1)
 classifications = [model.config.id2label[output] for output in classifications]
 print(classifications)
 ```
-```
-[{'label': 'F', 'score': 0.9998922348022461},
- {'label': 'NF', 'score': 0.999846339225769}]
 
 ### Training hyperparameters