2

app.py

@@ -4,6 +4,8 @@ import os
 import json
 import numpy as np
 import pickle
+import zipfile
+from io import BytesIO
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import accuracy_score
@@ -78,6 +80,35 @@ def classify_image(file_path):
     else:
         return "Invalid Image"
 
+# Create a sample dataset for download
+def create_sample_dataset():
+    sample_dir = "sample_dataset"
+    os.makedirs(sample_dir, exist_ok=True)
+
+    # Create Human and Alien directories
+    human_dir = os.path.join(sample_dir, "Human")
+    alien_dir = os.path.join(sample_dir, "Alien")
+    os.makedirs(human_dir, exist_ok=True)
+    os.makedirs(alien_dir, exist_ok=True)
+
+    # Add placeholder images (replace with real images in a practical application)
+    for i in range(1, 4):
+        human_image_path = os.path.join(human_dir, f"human_{i}.jpg")
+        alien_image_path = os.path.join(alien_dir, f"alien_{i}.jpg")
+        Image.new('RGB', (64, 64), color=(255, 0, 0)).save(human_image_path)
+        Image.new('RGB', (64, 64), color=(0, 255, 0)).save(alien_image_path)
+
+    # Create a ZIP file for download
+    zip_buffer = BytesIO()
+    with zipfile.ZipFile(zip_buffer, "w") as zip_file:
+        for folder_name, subfolders, filenames in os.walk(sample_dir):
+            for filename in filenames:
+                file_path = os.path.join(folder_name, filename)
+                arcname = os.path.relpath(file_path, sample_dir)
+                zip_file.write(file_path, arcname)
+
+    return zip_buffer.getvalue()
+
 # Streamlit app
 def main():
     st.title("Human or Alien Identification")
@@ -88,10 +119,11 @@ def main():
 
         - **Identify Image:** Upload an image and classify it as "Human" or "Alien." The classifications you save will be added to the training data.
         - **Train Model:** Review and manage the images already classified as "Human" or "Alien." Upload additional images to improve the training dataset.
+        - **Download Sample Dataset:** Download a pre-structured dataset to use for training and classification.
         """
     )
 
-    tab1, tab2 = st.tabs(["Identify Image", "Train Model"])
+    tab1, tab2, tab3 = st.tabs(["Identify Image", "Train Model", "Download Sample Dataset"])
 
     with tab1:
         st.header("Identify Image")
@@ -194,5 +226,17 @@ def main():
             else:
                 st.warning("No alien images found for training.")
 
+    with tab3:
+        st.header("Download Sample Dataset")
+
+        if st.button("Download Sample Dataset"):
+            sample_dataset = create_sample_dataset()
+            st.download_button(
+                label="Click to Download",
+                data=sample_dataset,
+                file_name="sample_dataset.zip",
+                mime="application/zip"
+            )
+
 if __name__ == "__main__":
     main()