Update app.py

app.py

@@ -41,17 +41,52 @@ DATA_DIR = os.path.join(BASE_DIR, "data")
 DOG_DIR = os.path.join(DATA_DIR, "dog")
 HUMAN_DIR = os.path.join(DATA_DIR, "human")
 
-# Explicit paths for Colab environment
-CSV_DOG = "/content/cmt_dog_sound_analysis.csv"
-CSV_HUMAN = "/content/cmt_human_speech_analysis.csv"
+# Paths for different deployment environments
+# Priority order: 1) Hugging Face Spaces (repo root), 2) Colab, 3) Local
+HF_CSV_DOG = "cmt_dog_sound_analysis.csv"
+HF_CSV_HUMAN = "cmt_human_speech_analysis.csv"
+COLAB_CSV_DOG = "/content/cmt_dog_sound_analysis.csv"
+COLAB_CSV_HUMAN = "/content/cmt_human_speech_analysis.csv"
+
+# Determine which environment we're in and set paths accordingly
+if os.path.exists(HF_CSV_DOG) and os.path.exists(HF_CSV_HUMAN):
+    # Hugging Face Spaces - files in repo root
+    CSV_DOG = HF_CSV_DOG
+    CSV_HUMAN = HF_CSV_HUMAN
+    print("Using Hugging Face Spaces paths")
+elif os.path.exists(COLAB_CSV_DOG) and os.path.exists(COLAB_CSV_HUMAN):
+    # Google Colab environment
+    CSV_DOG = COLAB_CSV_DOG
+    CSV_HUMAN = COLAB_CSV_HUMAN
+    print("Using Google Colab paths")
+else:
+    # Fallback to local or will trigger dummy data
+    CSV_DOG = HF_CSV_DOG  # Try repo root first
+    CSV_HUMAN = HF_CSV_HUMAN
+    print("Falling back to local/dummy data paths")
 
 # These are for creating dummy audio files if needed
 os.makedirs(DOG_DIR, exist_ok=True)
 os.makedirs(os.path.join(HUMAN_DIR, "Actor_01"), exist_ok=True)
 
-# --- Audio Data Configuration (Must match your data source locations) ---
-DOG_AUDIO_BASE_PATH = '/content/drive/MyDrive/combined'
-HUMAN_AUDIO_BASE_PATH = '/content/drive/MyDrive/human'
+# --- Audio Data Configuration (Platform-aware paths) ---
+# For Hugging Face Spaces, audio files might be in the repo or need different handling
+# For Colab, they're in Google Drive
+if os.path.exists("/content/drive/MyDrive/combined"):
+    # Google Colab with mounted Drive
+    DOG_AUDIO_BASE_PATH = '/content/drive/MyDrive/combined'
+    HUMAN_AUDIO_BASE_PATH = '/content/drive/MyDrive/human'
+    print("Using Google Drive audio paths")
+elif os.path.exists("audio/combined"):
+    # Hugging Face Spaces with audio in repo
+    DOG_AUDIO_BASE_PATH = 'audio/combined'
+    HUMAN_AUDIO_BASE_PATH = 'audio/human'
+    print("Using Hugging Face Spaces audio paths")
+else:
+    # Fallback to local dummy paths
+    DOG_AUDIO_BASE_PATH = DOG_DIR
+    HUMAN_AUDIO_BASE_PATH = HUMAN_DIR
+    print("Using local dummy audio paths")
 
 
 # ---------------------------------------------------------------
@@ -105,13 +140,20 @@ def find_nearest_cross_species_neighbor(selected_row, df_combined, n_neighbors=5
 # ---------------------------------------------------------------
 # Load datasets (Colab-first paths)
 # ---------------------------------------------------------------
+# Debug: Show what files we're looking for and what exists
+print(f"Looking for CSV files:")
+print(f"- Dog CSV: {CSV_DOG} (exists: {os.path.exists(CSV_DOG)})")
+print(f"- Human CSV: {CSV_HUMAN} (exists: {os.path.exists(CSV_HUMAN)})")
+print(f"Current working directory: {os.getcwd()}")
+print(f"Files in current directory: {os.listdir('.')}")
+
 if os.path.exists(CSV_DOG) and os.path.exists(CSV_HUMAN):
-    print(f"Found existing data files. Loading from:\n- {CSV_DOG}\n- {CSV_HUMAN}")
+    print(f"✅ Found existing data files. Loading from:\n- {CSV_DOG}\n- {CSV_HUMAN}")
     df_dog = pd.read_csv(CSV_DOG)
     df_human = pd.read_csv(CSV_HUMAN)
-    print("Successfully loaded data from specified paths.")
+    print(f"Successfully loaded data: {len(df_dog)} dog rows, {len(df_human)} human rows")
 else:
-    print("Could not find one or both CSV files. Generating and using in-memory dummy data.")
+    print("❌ Could not find one or both CSV files. Generating and using in-memory dummy data.")
     
     # This section is for DUMMY DATA GENERATION ONLY.
     # It runs if the primary CSVs are not found and does NOT write files.