first push

src/streamlit_app.py

@@ -8,69 +8,82 @@ from sklearn.neighbors import KNeighborsClassifier
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.metrics import accuracy_score, r2_score
 
-# Initialize session state variables
-if "uploaded_file_name" not in st.session_state:
-    st.session_state.uploaded_file_name = None
-if "df" not in st.session_state:
-    st.session_state.df = None
-if "processed_df" not in st.session_state:
-    st.session_state.processed_df = None
-if "encoders" not in st.session_state:
-    st.session_state.encoders = {}
-if "models" not in st.session_state:
-    st.session_state.models = {}
-if "final_model" not in st.session_state:
-    st.session_state.final_model = None
-if "problem_type" not in st.session_state:
-    st.session_state.problem_type = None
-if "target_encoder" not in st.session_state:
-    st.session_state.target_encoder = None
-
+# -------------------
+# Session State Setup
+# -------------------
+defaults = {
+    "uploaded_file_name": None,
+    "df": None,
+    "processed_df": None,
+    "encoders": {},
+    "models": {},
+    "final_model": None,
+    "problem_type": None,
+    "target_encoder": None
+}
+for key, value in defaults.items():
+    if key not in st.session_state:
+        st.session_state[key] = value
+
+# -------------------
+# Sidebar Navigation
+# -------------------
 st.sidebar.title("Navigation")
-page = st.sidebar.selectbox("Go to", ["Upload File", "Preprocess Data", "Train & Select Model", "Create App"])
-
-# ========================
+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"])
 
     if uploaded_file is not None:
         st.session_state.uploaded_file_name = uploaded_file.name
+
         if uploaded_file.name.endswith(".csv"):
             st.session_state.df = pd.read_csv(uploaded_file)
             st.dataframe(st.session_state.df)
+
         elif uploaded_file.name.endswith(".sql"):
             sql_content = uploaded_file.read().decode("utf-8")
             st.text_area("SQL Content", sql_content, height=300)
+
         st.success("File loaded into memory!")
 
-# ========================
+# -------------------
 # Preprocess Data Page
-# ========================
+# -------------------
 elif page == "Preprocess Data":
     st.title("Preprocess Uploaded CSV")
     if st.session_state.df is not None:
         st.write("Current Data:")
         st.dataframe(st.session_state.df)
 
+        # Drop missing
         missing_placeholders = [
             "?", "NA", "N/A", "na", "null", "NULL", "none", "None",
             "missing", "Missing", "not available", "Not Available",
             "--", "---", "-", "_", ""
         ]
-
         if st.button("Drop Missing / Placeholder Values"):
-            st.session_state.df = st.session_state.df.replace(missing_placeholders, pd.NA)
-            st.session_state.df = st.session_state.df.dropna()
+            df = st.session_state.df.replace(missing_placeholders, pd.NA)
+            df = df.dropna()
+            st.session_state.df = df
             st.success("Missing values dropped!")
 
+        # Drop selected columns
         col_to_drop = st.multiselect("Select columns to drop", st.session_state.df.columns)
         if st.button("Drop Selected Columns"):
             st.session_state.df = st.session_state.df.drop(columns=col_to_drop)
             st.success(f"Dropped columns: {col_to_drop}")
 
+        # Label encode
         if st.button("Label Encode Object Columns"):
             st.session_state.encoders = {}
             for col in st.session_state.df.select_dtypes(include=['object']).columns:
@@ -79,15 +92,16 @@ elif page == "Preprocess Data":
                 st.session_state.encoders[col] = le
             st.success("Object columns label-encoded!")
 
+        # Save processed
         if st.button("Save Preprocessed Data"):
             st.session_state.processed_df = st.session_state.df.copy()
             st.success("Preprocessed data saved in memory!")
     else:
         st.warning("Please upload a CSV first.")
 
-# ========================
+# -------------------
 # Train & Select Model Page
-# ========================
+# -------------------
 elif page == "Train & Select Model":
     st.title("Train Models and Select the Best One")
 
@@ -99,13 +113,17 @@ elif page == "Train & Select Model":
             X = df.drop(columns=[target_col])
             y = df[target_col]
 
+            # Detect problem type
             if y.dtype == "object" or len(y.unique()) <= 20:
                 st.session_state.problem_type = "classification"
             else:
                 st.session_state.problem_type = "regression"
 
+            # Train/test split
             test_size = st.slider("Test size (%)", 20, 50, 30, step=5)
-            X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size/100, random_state=42)
+            X_train, X_test, y_train, y_test = train_test_split(
+                X, y, test_size=test_size/100, random_state=42
+            )
 
             results = {}
             st.session_state.models = {}
@@ -134,6 +152,7 @@ elif page == "Train & Select Model":
                     results[name] = score
                     st.session_state.models[name] = model
 
+            # Show results
             st.subheader("Model Scores")
             for name, score in results.items():
                 st.write(f"{name}: {score:.4f}")
@@ -145,9 +164,9 @@ elif page == "Train & Select Model":
     else:
         st.warning("Please preprocess a file first.")
 
-# ========================
+# -------------------
 # Create App Page
-# ========================
+# -------------------
 elif page == "Create App":
     st.title("Use Model for Prediction")