Merge branch 'master' into temp_branch

.github/workflows/validate-pr.yaml

@@ -0,0 +1,51 @@
+name: Validate PR
+
+on:
+  pull_request:
+    branches: [ master ]
+    types: [opened, synchronize, reopened, ready_for_review]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        python-version: [3.12]
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v3
+
+    - name: Install Ubuntu packages
+      run: |
+        sudo apt-get update
+        sudo xargs -a packages.txt apt-get install -y
+      shell: bash
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+        architecture: 'x64'  
+
+    - name: Install Python dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+
+    - name: Validate dependencies with pip-check
+      run: |
+        pip install pip-check
+        pip-check
+      continue-on-error: false  # Fail the workflow if dependencies are invalid
+
+    - name: Test Streamlit App
+      run: |
+        pip install streamlit
+        streamlit run App.py --server.headless true --browser.gatherUsageStats false &
+        sleep 10  # Wait for the app to start
+        curl --retry 5 --retry-delay 5 http://localhost:8501
+      env:
+        STREAMLIT_SERVER_HEADLESS: true

.gitignore

@@ -1,3 +1,2 @@
 __pycache__
-venv
 *.log

App.py

@@ -108,6 +108,7 @@
 	- **GLD**:  The price of SPDR Gold Shares (GLD), which is the target variable representing gold prices.
 		"""
 	)
+
 st.write(
     "- **Car Price Predictor**: Estimate the price of a car based on various features."
 )
@@ -146,3 +147,4 @@
     - **Seats**: The number of seats in the car.
         """
     )
+

dev-requirements.txt

@@ -0,0 +1,10 @@
+# Development dependencies for the project.
+# Includes Jupyter and other tools used during development, but not required for the Streamlit app in production.
+
+jupyterlab
+notebook
+
+# jupyterlab==4.2.5
+# jupyterlab_pygments==0.3.0
+# jupyterlab_server==2.27.3
+# jupyterlab_widgets==3.0.13

models/text_sumarization/predict.py

@@ -0,0 +1,13 @@
+from transformers import pipeline
+import streamlit as st
+
+@st.cache_resource(show_spinner=True)  # Cache the model loading for faster performance
+def load_summarizer():
+	"""Load and cache the text summarization pipeline model."""
+	return pipeline("summarization", model="t5-small")
+
+def generate_summary(text: str) -> str:
+	"""Generate a summary for the given input text."""
+	summarizer = load_summarizer()
+	summary = summarizer(text, max_length=150, min_length=30, do_sample=False)
+	return summary[0]["summary_text"]

pages/Text Summarizer.py

@@ -0,0 +1,19 @@
+import streamlit as st
+from models.text_sumarization.predict import generate_summary
+
+st.title("Text Summarization Tool")
+
+st.write("Enter the text you'd like to summarize (minimum 50 words).")
+
+user_input = st.text_area("Input Text", height=250)
+
+# A button to initiate the summarization process
+if st.button("Summarize"):
+	if len(user_input.split()) < 50:
+		st.warning("Please enter at least 50 words for summarization.")
+	else:
+		# Show a spinner while the summarization is being processed
+		with st.spinner("Summarizing..."):
+			summary = generate_summary(user_input)  # Call the function from predict.py
+			st.subheader("Summary:")
+			st.code(summary, language="text", wrap_lines=True)

pages/pages.json

@@ -132,6 +132,7 @@
   },
 
   "Malware_Detection": {
+
     "title": "PDF Malware Detection",
     "page_title": "PDF Malware Detection",
     "page_icon": "\ud83d\udd12",
@@ -173,4 +174,5 @@
       }
     ]
   }
+
 }

requirements.txt

@@ -63,7 +63,7 @@ matplotlib-inline==0.1.7
 mdurl==0.1.2
 mistune==3.0.2
 narwhals==1.8.1
-numpy==2.1.1
+numpy
 openpyxl==3.1.5
 overrides==7.7.0
 packaging==24.1
@@ -78,7 +78,7 @@ pluggy==1.5.0
 prometheus_client==0.20.0
 prompt_toolkit==3.0.47
 prophet==1.1.6
-protobuf==5.28.2
+protobuf==4.25.5
 psutil==6.0.0
 pure_eval==0.2.3
 pyarrow==17.0.0
@@ -138,3 +138,5 @@ webcolors==24.8.0
 webencodings==0.5.1
 websocket-client==1.8.0
 xgboost==2.1.1
+transformers==4.45.2
+tf_keras==2.17.0