Update README.md

README.md

@@ -6,6 +6,78 @@ license: apache-2.0
 The repo contains the weights for the custom architecture presented in [Bertolini et al., 2023](https://arxiv.org/abs/2302.14828). 
 Working example on how to load and use the model can be found in the [Git repo](https://github.com/lorenzoscottb/Dream_Reports_Annotation/tree/main/Experiments/Supervised_Learning).
 
+#### Use 
+
+```py
+import torch, os
+import pandas as pd
+from tqdm import tqdm
+import transformers
+from transformers import AutoModel
+from transformers import AutoConfig
+from transformers import BertTokenizerFast
+from SL_utils import *
+
+Coding_emotions = {
+    "AN": "Anger",
+    "AP": "Apprehension",
+    "SD": "Sadness",
+    "CO": "Confusion",
+    "HA": "Happiness",
+}
+
+emotions_list = list(Coding_emotions.keys())
+
+test_sentences = [
+    "In my dream I was follwed by the scary monster.",
+    "I was walking in a forest, sorrounded by singing birds. I was in calm and peace."
+]
+
+test_sentences_target = len(test_sentences)*[[0, 0, 0, 0, 0]]
+test_sentences_df     = pd.DataFrame.from_dict(
+                {
+                "report":test_sentences,
+                "Report_as_Multilabel":test_sentences_target
+                }
+)
+```
+
+```py
+model_name   = "bert-large-cased"
+model_config = AutoConfig.from_pretrained(model_name)
+tokenizer    = BertTokenizerFast.from_pretrained(model_name, do_lower_case=False)
+testing_set  = CustomDataset(test_sentences_df, tokenizer, max_length=512)
+
+test_params = {
+    'batch_size': 2,
+    'shuffle': True,
+    'num_workers': 0
+}
+
+testing_loader  = DataLoader(testing_set, **test_params)
+
+model = BERT_PTM(
+    model_config,
+    model_name=model_name, 
+    n_classes=len(emotions_list), 
+    freeze_BERT=False,
+)
+
+# Load the models' weights from the pre-treined model
+model.load_state_dict(torch.load("path/to/pytorch_model.bin"))
+model.to("cuda")
+```
+
+```py
+outputs, targets, ids = validation(model, testing_loader, device="cuda", return_inputs=True)
+
+corr_outputs    = np.array(outputs) >= 0.5 
+corr_outputs_df = pd.DataFrame(corr_outputs, columns=emotions_list)
+corr_outputs_df = corr_outputs_df.astype(int)
+
+corr_outputs_df["report"] = decoded_ids = [decode_clean(x, tokenizer) for x in tqdm(ids)]
+```
+
 ### Cite 
 If you use the model, please cite the pre-print.
 ```bibtex