first push

src/streamlit_app.py

@@ -9,20 +9,24 @@ from sklearn.neighbors import KNeighborsClassifier
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.metrics import accuracy_score, r2_score
 
-# Writable folders inside /tmp
-BASE_DIR = "/tmp/ml_app"
-UPLOAD_DIR = os.path.join(BASE_DIR, "uploads")
-PROCESSED_DIR = os.path.join(BASE_DIR, "processed")
-PKL_DIR = os.path.join(BASE_DIR, "pkl")
-ENCODERS_DIR = os.path.join(BASE_DIR, "encoders")
-
-# Create them at runtime
-for d in [UPLOAD_DIR, PROCESSED_DIR, PKL_DIR, ENCODERS_DIR]:
-    os.makedirs(d, exist_ok=True)
+# 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)
 
 st.sidebar.title("Navigation")
 page = st.sidebar.selectbox("Go to", ["Upload File", "Preprocess Data", "Train & Select Model", "Create App"])
 
+# ========================
+# Upload File Page
+# ========================
 if page == "Upload File":
     st.title("Upload CSV or SQL File")
     uploaded_file = st.file_uploader("Upload a CSV or SQL file", type=["csv", "sql"])
@@ -41,6 +45,9 @@ if page == "Upload File":
                 sql_content = f.read()
             st.text_area("SQL Content", sql_content, height=300)
 
+# ========================
+# Preprocess Data Page
+# ========================
 elif page == "Preprocess Data":
     st.title("Preprocess Uploaded CSV")
     files = [f for f in os.listdir(UPLOAD_DIR) if f.endswith(".csv")]
@@ -83,8 +90,9 @@ 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(os.path.join(ENCODERS_DIR, f"{selected_file}_{col}_encoder.pkl"), "wb") as f:
+                with open(f"{ENCODERS_DIR}/{selected_file}_{col}_encoder.pkl", "wb") as f:
                     pickle.dump(le, f)
 
             st.success("All object columns label-encoded and encoders saved!")
@@ -97,6 +105,9 @@ elif page == "Preprocess Data":
     else:
         st.warning("No CSV files available. Please upload a CSV first.")
 
+# ========================
+# Train & Select Model Page
+# ========================
 elif page == "Train & Select Model":
     st.title("Train Models and Select the Best One")
 
@@ -164,6 +175,9 @@ elif page == "Train & Select Model":
     else:
         st.warning("No processed files found. Please preprocess a file first.")
 
+# ========================
+# Create App Page
+# ========================
 elif page == "Create App":
     st.title("Use Model for Prediction")
 
@@ -186,15 +200,17 @@ elif page == "Create App":
 
             model.fit(X, y)
 
+            # Load encoders for features if available
             encoders = {}
             for col in X.columns:
-                encoder_path = os.path.join(ENCODERS_DIR, f"{selected_csv}_{col}_encoder.pkl")
+                encoder_path = f"{ENCODERS_DIR}/{selected_csv}_{col}_encoder.pkl"
                 if os.path.exists(encoder_path):
                     with open(encoder_path, "rb") as f:
                         encoders[col] = pickle.load(f)
 
+            # Load encoder for target if available
             target_encoder = None
-            target_encoder_path = os.path.join(ENCODERS_DIR, f"{selected_csv}_{target_col}_encoder.pkl")
+            target_encoder_path = f"{ENCODERS_DIR}/{selected_csv}_{target_col}_encoder.pkl"
             if os.path.exists(target_encoder_path):
                 with open(target_encoder_path, "rb") as f:
                     target_encoder = pickle.load(f)