Update README.md

README.md

@@ -1,199 +1,113 @@
----
-library_name: transformers
-tags: []
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+```python
+from huggingface_hub import login
+import torch
+import torch.nn as nn
+from transformers import RobertaForSequenceClassification, RobertaTokenizer
+from torch.utils.data import Dataset, DataLoader
+import pandas as pd
+from sklearn.metrics import accuracy_score
+from huggingface_hub import login
+from transformers import AutoModel, AutoTokenizer
+import pandas as pd
+
+from huggingface_hub import login
+login("Replace with the key")
+
+import torch
+from torch.utils.data import Dataset, DataLoader
+from transformers import RobertaTokenizer, RobertaForSequenceClassification
+import pandas as pd
+import numpy as np
+from sklearn.metrics import accuracy_score
+import re
+
+# Define the preprocessing and dataset class
+class NewsDataset(Dataset):
+    def __init__(self, texts, labels, tokenizer, max_len=128):
+        self.texts = texts
+        self.labels = labels
+        self.tokenizer = tokenizer
+        self.max_len = max_len
+
+    def __len__(self):
+        return len(self.texts)
+
+    def __getitem__(self, idx):
+        text = self.texts[idx]
+        label = self.labels[idx]
+        encoding = self.tokenizer(
+            text,
+            max_length=self.max_len,
+            padding="max_length",
+            truncation=True,
+            return_tensors="pt"
+        )
+        return {
+            "input_ids": encoding["input_ids"].squeeze(),
+            "attention_mask": encoding["attention_mask"].squeeze(),
+            "labels": torch.tensor(label, dtype=torch.long)
+        }
+
+def preprocess_text(text):
+    """Clean and preprocess text."""
+    text = str(text)
+    contractions = {
+        "n't": " not",
+        "'s": " is",
+        "'ll": " will",
+        "'ve": " have"
+    }
+    for contraction, expansion in contractions.items():
+        text = text.replace(contraction, expansion)
+    text = re.sub(r'\$\\d+\.?\\d*\s*(million|billion|trillion)?', r'$ \1', text, flags=re.IGNORECASE)
+    text = re.sub(r'http\\S+', '', text)
+    text = re.sub(r'-', ' ', text)
+    text = text.lower()
+    text = ' '.join(text.split())
+    return text
+
+
+
+# Step 1: Load the model and tokenizer from Hugging Face Hub
+print("Loading model and tokenizer...")
+REPO_NAME = "CIS5190GoGo/CustomModel"  # Replace with your repo name on Hugging Face Hub
+model = RobertaForSequenceClassification.from_pretrained(REPO_NAME)
+tokenizer = RobertaTokenizer.from_pretrained(REPO_NAME)
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+print("Model and tokenizer loaded successfully!")
+
+# Step 2: Load test dataset
+print("Loading test data...")
+test_data_path = "/content/drive/MyDrive/5190_project/test_data_random_subset.csv"  # Replace with your test set path
+test_data = pd.read_csv(test_data_path)
+
+# Preprocess test data
+X_test = test_data['title'].apply(preprocess_text).values
+y_test = test_data['labels'].values
+
+# Step 3: Prepare the dataset and dataloader
+test_dataset = NewsDataset(X_test, y_test, tokenizer)
+test_loader = DataLoader(test_dataset, batch_size=16, num_workers=2)
+
+# Step 4: Evaluate the model
+print("Evaluating the model...")
+model.eval()
+all_preds, all_labels = [], []
+
+with torch.no_grad():
+    for batch in test_loader:
+        input_ids = batch["input_ids"].to(device)
+        attention_mask = batch["attention_mask"].to(device)
+        labels = batch["labels"].to(device)
+
+        outputs = model(input_ids=input_ids, attention_mask=attention_mask)
+        preds = torch.argmax(outputs.logits, dim=-1)
+
+        all_preds.extend(preds.cpu().numpy())
+        all_labels.extend(labels.cpu().numpy())
+
+# Step 5: Calculate accuracy
+accuracy = accuracy_score(all_labels, all_preds)
+print(f"Test Accuracy: {accuracy:.4f}")