init for app

README.md

@@ -1,13 +1,2 @@
----
-title: Dark Pattern Detector App
-emoji: 😻
-colorFrom: gray
-colorTo: indigo
-sdk: streamlit
-sdk_version: 1.33.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+### Dark Pattern Detection using Fine Tuned BERT Model 
+A web app built using streamlit powered by CogniGuard project 

app.py

@@ -0,0 +1,117 @@
+import streamlit as st
+import torch
+from transformers import BertTokenizer, BertForSequenceClassification
+
+from tqdm import tqdm  # Import tqdm for progress bar
+
+import time # for time taken calc
+
+# Load pre-trained model
+label_dict = {"Urgency": 0, "Not Dark Pattern": 1, "Scarcity": 2, "Misdirection": 3, "Social Proof": 4, "Obstruction": 5, "Sneaking": 6, "Forced Action": 7}
+model = BertForSequenceClassification.from_pretrained("bert-base-uncased", num_labels=len(label_dict))
+
+# Load fine-tuned weights
+fine_tuned_model_path = r"models\finetuned_BERT_epoch_5.model"
+model.load_state_dict(torch.load(fine_tuned_model_path, map_location=torch.device('cpu')))
+
+# Preprocess the new text
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased', do_lower_case=True)
+
+# Function to map numeric label to dark pattern name
+def get_dark_pattern_name(label):
+    reverse_label_dict = {v: k for k, v in label_dict.items()}
+    return reverse_label_dict[label]
+
+def find_dark_pattern(text_predict):
+    encoded_text = tokenizer.encode_plus(
+        text_predict,
+        add_special_tokens=True,
+        return_attention_mask=True,
+        pad_to_max_length=True,
+        max_length=256,
+        return_tensors='pt'
+    )
+
+    # Making the predictions
+    model.eval()
+
+    with torch.no_grad():
+        inputs = {
+            'input_ids': encoded_text['input_ids'],
+            'attention_mask': encoded_text['attention_mask']
+        }
+        outputs = model(**inputs)
+
+    predictions = outputs.logits
+
+    # Post-process the predictions
+    probabilities = torch.nn.functional.softmax(predictions, dim=1)
+    predicted_label = torch.argmax(probabilities, dim=1).item()
+
+    return get_dark_pattern_name(predicted_label)
+
+# Streamlit app
+def main():
+
+    # navigation
+    st.page_link("app.py", label="Home", icon="🏠")
+    st.page_link("pages/page_1.py", label="Training Metrics", icon="1️⃣")
+    # st.page_link("pages/page_2.py", label="Page 2", icon="2️⃣")
+    st.page_link("https://github.com/4darsh-Dev/CogniGaurd", label="GitHub", icon="🌎")
+    # Set page title
+    st.title("Dark Pattern Detector")
+
+    # Display welcome message
+    st.write("Welcome to Dark Pattern Detector powered by CogniGuard")
+    
+    #
+    st.write("#### Built with Fine-Tuned BERT and Hugging Face Transformers")
+    
+
+    # Get user input
+    text_to_predict = st.text_input("Enter the text to find Dark Pattern")
+
+    if st.button("Predict"):
+        # Record the start time
+        start_time = time.time()
+
+        # Add a simple progress message
+        st.write("Predicting Dark Pattern...")
+
+
+        progress_bar = st.progress(0)
+
+        for i in tqdm(range(10), desc="Predicting", unit="prediction"):
+            predicted_darkp = find_dark_pattern(text_to_predict)
+            progress_bar.progress((i + 1) * 10)
+            time.sleep(0.5)  # Simulate some processing time
+
+        # Record the end time
+        end_time = time.time()
+
+        # Calculate the total time taken
+        total_time = end_time - start_time
+
+        # Display the predicted dark pattern and total time taken
+        st.write(f"Result: {predicted_darkp}")
+        st.write(f"Total Time Taken: {total_time:.2f} seconds")
+
+        
+
+
+    # Add footer
+    st.markdown('<p style="text-align:center;">Made with ❤️ by <a href="https://www.adarshmaurya.onionreads.com">Adarsh Maurya</a></p>', unsafe_allow_html=True)
+
+    # Add page visit count
+    page_visits = st.session_state.get('page_visits', 0)
+    page_visits += 1
+    st.session_state['page_visits'] = page_visits
+
+    # Display page visit count
+    st.markdown(f'<p style="text-align:center;">Page Visits: {page_visits}</p>', unsafe_allow_html=True)
+
+
+# Run the app
+if __name__ == "__main__":
+    main()
+

pages/page_1.py

@@ -0,0 +1,10 @@
+import streamlit as st 
+
+def main():
+    st.title("Training Metrics")
+    
+
+if __name__ == "__main__":
+    main()
+
+    

requirements.txt

@@ -0,0 +1,70 @@
+aiohttp==3.9.3
+aiosignal==1.3.1
+altair==5.3.0
+asgiref==3.8.1
+attrs==23.2.0
+blinker==1.8.1
+cachetools==5.3.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+datasets==2.18.0
+dill==0.3.8
+Django==5.0.3
+filelock==3.13.4
+frozenlist==1.4.1
+fsspec==2024.2.0
+gitdb==4.0.11
+GitPython==3.1.43
+huggingface-hub==0.22.2
+idna==3.6
+Jinja2==3.1.3
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.5
+multiprocess==0.70.16
+mysqlclient==2.2.4
+networkx==3.3
+numpy==1.26.4
+packaging==24.0
+pandas==2.2.1
+pillow==10.3.0
+protobuf==4.25.3
+pyarrow==15.0.2
+pyarrow-hotfix==0.6
+pydeck==0.9.0b1
+Pygments==2.17.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.0
+regex==2024.4.16
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+safetensors==0.4.3
+six==1.16.0
+smmap==5.0.1
+sqlparse==0.4.4
+streamlit==1.33.0
+sympy==1.12
+tenacity==8.2.3
+tokenizers==0.19.1
+toml==0.10.2
+toolz==0.12.1
+torch==2.2.2
+tornado==6.4
+tqdm==4.66.2
+transformers==4.40.1
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+watchdog==4.0.0
+xxhash==3.4.1
+yarl==1.9.4