first push

src/streamlit_app.py

@@ -9,17 +9,16 @@ from sklearn.neighbors import KNeighborsClassifier
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.metrics import accuracy_score, r2_score
 
-# Define writable directories in /tmp
-UPLOAD_DIR = "/tmp/uploads"
-PROCESSED_DIR = "/tmp/processed"
-PKL_DIR = "/tmp/pkl"
-ENCODERS_DIR = "/tmp/encoders"
-
-# Ensure directories exist
-os.makedirs(UPLOAD_DIR, exist_ok=True)
-os.makedirs(PROCESSED_DIR, exist_ok=True)
-os.makedirs(PKL_DIR, exist_ok=True)
-os.makedirs(ENCODERS_DIR, exist_ok=True)
+# Define existing directories (must already be present in environment)
+UPLOAD_DIR = "uploads"
+PROCESSED_DIR = "processed"
+PKL_DIR = "pkl"
+ENCODERS_DIR = "encoders"
+
+# Warn if directories don't exist
+for folder in [UPLOAD_DIR, PROCESSED_DIR, PKL_DIR, ENCODERS_DIR]:
+    if not os.path.exists(folder):
+        st.warning(f"Directory not found: {folder}. Please create it before using this app.")
 
 st.sidebar.title("Navigation")
 page = st.sidebar.selectbox("Go to", ["Upload File", "Preprocess Data", "Train & Select Model", "Create App"])
@@ -50,7 +49,10 @@ if page == "Upload File":
 # ========================
 elif page == "Preprocess Data":
     st.title("Preprocess Uploaded CSV")
-    files = [f for f in os.listdir(UPLOAD_DIR) if f.endswith(".csv")]
+    if os.path.exists(UPLOAD_DIR):
+        files = [f for f in os.listdir(UPLOAD_DIR) if f.endswith(".csv")]
+    else:
+        files = []
 
     if files:
         selected_file = st.selectbox("Select a CSV file to preprocess", files)
@@ -90,7 +92,6 @@ elif page == "Preprocess Data":
                 st.session_state.df[col] = le.fit_transform(st.session_state.df[col].astype(str))
                 label_encoders[col] = le
 
-            # Save each encoder as pickle
             for col, le in label_encoders.items():
                 with open(f"{ENCODERS_DIR}/{selected_file}_{col}_encoder.pkl", "wb") as f:
                     pickle.dump(le, f)
@@ -111,7 +112,10 @@ elif page == "Preprocess Data":
 elif page == "Train & Select Model":
     st.title("Train Models and Select the Best One")
 
-    processed_files = [f for f in os.listdir(PROCESSED_DIR) if f.endswith(".csv")]
+    if os.path.exists(PROCESSED_DIR):
+        processed_files = [f for f in os.listdir(PROCESSED_DIR) if f.endswith(".csv")]
+    else:
+        processed_files = []
 
     if processed_files:
         selected_file = st.selectbox("Select a processed CSV", processed_files)
@@ -181,7 +185,11 @@ elif page == "Train & Select Model":
 elif page == "Create App":
     st.title("Use Model for Prediction")
 
-    processed_files = [f for f in os.listdir(PROCESSED_DIR) if f.endswith(".csv")]
+    if os.path.exists(PROCESSED_DIR):
+        processed_files = [f for f in os.listdir(PROCESSED_DIR) if f.endswith(".csv")]
+    else:
+        processed_files = []
+
     if processed_files:
         selected_csv = st.selectbox("Select a processed CSV file", processed_files)
         df = pd.read_csv(os.path.join(PROCESSED_DIR, selected_csv))
@@ -200,7 +208,6 @@ elif page == "Create App":
 
             model.fit(X, y)
 
-            # Load encoders for features if available
             encoders = {}
             for col in X.columns:
                 encoder_path = f"{ENCODERS_DIR}/{selected_csv}_{col}_encoder.pkl"
@@ -208,7 +215,6 @@ elif page == "Create App":
                     with open(encoder_path, "rb") as f:
                         encoders[col] = pickle.load(f)
 
-            # Load encoder for target if available
             target_encoder = None
             target_encoder_path = f"{ENCODERS_DIR}/{selected_csv}_{target_col}_encoder.pkl"
             if os.path.exists(target_encoder_path):