Update README.md

README.md

@@ -23,3 +23,107 @@ This is basically the German translation of arpanghoshal/EmoRoBERTa. We used the
   - accuracy: 0.27
   - f1: 0.382
   - roc_auc: 0.658
+
+
+**Example Code**
+"""**Inference**"""
+# pip install transformers[torch]
+# pip install pandas, transformers, numpy, tqdm, openpyxl
+
+import pandas as pd
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
+import numpy as np
+from tqdm import tqdm
+import time
+import os
+from transformers import DataCollatorWithPadding
+import json
+
+# create base path
+base_path = "/share/users/staff/c/clalk/Emotionen"
+
+#create input and output path for the model folder and the file folder
+model_path = os.path.join(base_path, 'Modell')
+file_path = os.path.join(base_path, 'Datensatz')
+
+
+MODEL = "intfloat/multilingual-e5-large"
+tokenizer = AutoTokenizer.from_pretrained(MODEL, do_lower_case=False)
+model = AutoModelForSequenceClassification.from_pretrained(
+    model_path,
+    from_tf=False,
+    from_flax=False,
+    trust_remote_code=False,
+    num_labels=28,
+    ignore_mismatched_sizes=True
+)
+
+data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
+
+# Path to the file
+os.chdir(file_path)
+
+df_full = pd.read_excel("speech_turns_pat.xlsx", index_col=None)
+
+if 'Unnamed: 0' in df_full.columns:
+    df_full = df_full.drop(columns=['Unnamed: 0'])
+
+
+df_full.reset_index(drop=True, inplace=True)
+
+
+# Funktion zur Tokenisierung und Inferenz
+def infer_texts(texts):
+    tokenized_texts = tokenizer(texts, return_tensors="pt", padding=True, truncation=True)
+    class SimpleDataset:
+        def __init__(self, tokenized_texts):
+            self.tokenized_texts = tokenized_texts
+        def __len__(self):
+            return len(self.tokenized_texts["input_ids"])
+        def __getitem__(self, idx):
+            return {k: v[idx] for k, v in self.tokenized_texts.items()}
+    test_dataset = SimpleDataset(tokenized_texts)
+    trainer = Trainer(model=model, data_collator=data_collator)
+    predictions = trainer.predict(test_dataset)
+    sigmoid = torch.nn.Sigmoid()
+    probs = sigmoid(torch.Tensor(predictions.predictions))
+
+    return np.round(np.array(probs), 3).tolist()
+
+start_time = time.time()
+
+df = df_full
+
+# Save results in a dict
+results = []
+for index, row in tqdm(df.iterrows(), total=df.shape[0]):
+    patient_texts = row['Patient']
+    prob_list = infer_texts(patient_texts)
+    results.append({
+        "File": row['Class']+"_"+row['session'],
+        "Class": row['Class'],
+        "session": row['session'],
+        "short_id": row["short_id"],
+        "long_id": row["long_id"],
+        "Sentence": patient_texts,
+        "Prediction": prob_list[0],
+        "hscl-11": row["Gesamtscore_hscl"],
+        "srs": row["srs_ges"],
+    })
+
+# Convert results to df
+df_results = pd.DataFrame(results)
+df_results.to_json("emo_speech_turn_inference.json")
+
+end_time = time.time()
+elapsed_time = end_time - start_time
+print(f"Elapsed time: {elapsed_time:.2f} seconds")
+print(df_results)
+
+
+emo_df = pd.DataFrame(df_results['Prediction'].tolist(), index=df_results["Class"].index)
+col_names = ['admiration', 'amusement', 'anger', 'annoyance', 'approval', 'caring', 'confusion', 'curiosity', 'desire', 'disappointment', 'disapproval', 'disgust', 'embarrassment', 'excitement', 'fear', 'gratitude', 'grief', 'joy', 'love', 'nervousness', 'optimism', 'pride', 'realization', 'relief', 'remorse', 'sadness', 'surprise', 'neutral']
+emo_df.columns = col_names
+
+print(emo_df)