first push

src/streamlit_app.py

@@ -6,52 +6,42 @@ from sklearn.preprocessing import LabelEncoder
 from sklearn.model_selection import train_test_split
 from sklearn.linear_model import LinearRegression, LogisticRegression
 from sklearn.neighbors import KNeighborsClassifier
-from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
+from sklearn.tree import DecisionTreeClassifier
 from sklearn.metrics import accuracy_score, r2_score
 
-# Sidebar navigation
 st.sidebar.title("Navigation")
 page = st.sidebar.selectbox("Go to", ["Upload File", "Preprocess Data", "Train & Select Model", "Create App"])
 
-# Writable directories for Hugging Face / Streamlit Cloud
-BASE_DIR = "/tmp"
-UPLOAD_DIR = os.path.join(BASE_DIR, "uploads")
-PROCESSED_DIR = os.path.join(BASE_DIR, "processed")
-PKL_DIR = os.path.join(BASE_DIR, "pkl")
-ENCODER_DIR = os.path.join(BASE_DIR, "encoders")
+os.makedirs("uploads", exist_ok=True)
+os.makedirs("processed", exist_ok=True)
+os.makedirs("pkl", exist_ok=True)
+os.makedirs("encoders", exist_ok=True)  # Folder to save encoders
 
-# Create all necessary writable directories
-for d in [UPLOAD_DIR, PROCESSED_DIR, PKL_DIR, ENCODER_DIR]:
-    os.makedirs(d, exist_ok=True)
-
-# -------------------- 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:
-        save_path = os.path.join(UPLOAD_DIR, uploaded_file.name)
+        save_path = os.path.join("uploads", uploaded_file.name)
         with open(save_path, "wb") as f:
             f.write(uploaded_file.getbuffer())
         st.success(f"File saved to {save_path}")
 
         if uploaded_file.name.endswith(".csv"):
-            uploaded_file.seek(0)
-            df = pd.read_csv(uploaded_file)
+            df = pd.read_csv(save_path)
             st.dataframe(df)
         elif uploaded_file.name.endswith(".sql"):
-            uploaded_file.seek(0)
-            sql_content = uploaded_file.read().decode("utf-8", errors="ignore")
+            with open(save_path, "r", encoding="utf-8") as f:
+                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")]
+    files = [f for f in os.listdir("uploads") if f.endswith(".csv")]
 
     if files:
         selected_file = st.selectbox("Select a CSV file to preprocess", files)
-        file_path = os.path.join(UPLOAD_DIR, selected_file)
+        file_path = os.path.join("uploads", selected_file)
 
         if "df" not in st.session_state or st.session_state.file_path != file_path:
             st.session_state.df = pd.read_csv(file_path)
@@ -70,6 +60,9 @@ elif page == "Preprocess Data":
             st.session_state.df = st.session_state.df.replace(missing_placeholders, pd.NA)
             st.session_state.df = st.session_state.df.dropna()
             st.success("All placeholder and missing values dropped!")
+            missing_after = st.session_state.df.isnull().sum()
+            st.write("Missing values per column AFTER drop:")
+            st.dataframe(missing_after.rename("Missing Count"))
             st.dataframe(st.session_state.df)
 
         col_to_drop = st.multiselect("Select columns to drop", st.session_state.df.columns)
@@ -84,29 +77,29 @@ 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(ENCODER_DIR, f"{selected_file}_{col}_encoder.pkl"), "wb") as f:
+                with open(f"encoders/{selected_file}_{col}_encoder.pkl", "wb") as f:
                     pickle.dump(le, f)
 
             st.success("All object columns label-encoded and encoders saved!")
             st.dataframe(st.session_state.df)
 
         if st.button("Save Preprocessed File"):
-            processed_path = os.path.join(PROCESSED_DIR, selected_file)
+            processed_path = os.path.join("processed", selected_file)
             st.session_state.df.to_csv(processed_path, index=False)
             st.success(f"Preprocessed file saved to: {processed_path}")
     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")
 
-    processed_files = [f for f in os.listdir(PROCESSED_DIR) if f.endswith(".csv")]
+    processed_files = [f for f in os.listdir("processed") if f.endswith(".csv")]
 
     if processed_files:
         selected_file = st.selectbox("Select a processed CSV", processed_files)
-        file_path = os.path.join(PROCESSED_DIR, selected_file)
+        file_path = os.path.join("processed", selected_file)
 
         df = pd.read_csv(file_path)
         st.dataframe(df.head())
@@ -144,7 +137,7 @@ elif page == "Train & Select Model":
             else:
                 models = {
                     "Linear Regression": LinearRegression(),
-                    "Decision Tree Regressor": DecisionTreeRegressor()
+                    "Decision Tree": DecisionTreeClassifier()
                 }
                 for name, model in models.items():
                     model.fit(X_train, y_train)
@@ -159,21 +152,20 @@ elif page == "Train & Select Model":
             selected_model_name = st.selectbox("Select model to save", list(results.keys()))
             if st.button("Save Selected Model"):
                 final_model = models[selected_model_name]
-                pkl_path = os.path.join(PKL_DIR, f"{selected_model_name}.pkl")
+                pkl_path = os.path.join("pkl", f"{selected_model_name}.pkl")
                 with open(pkl_path, "wb") as f:
                     pickle.dump(final_model, f)
                 st.success(f"Model saved as {pkl_path}")
     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")
 
-    processed_files = [f for f in os.listdir(PROCESSED_DIR) if f.endswith(".csv")]
+    processed_files = [f for f in os.listdir("processed") if f.endswith(".csv")]
     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))
+        df = pd.read_csv(os.path.join("processed", selected_csv))
         target_col = st.selectbox("Select target column", df.columns)
 
         if target_col:
@@ -189,15 +181,17 @@ 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(ENCODER_DIR, f"{selected_csv}_{col}_encoder.pkl")
+                encoder_path = f"encoders/{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 (for inverse transform of prediction)
             target_encoder = None
-            target_encoder_path = os.path.join(ENCODER_DIR, f"{selected_csv}_{target_col}_encoder.pkl")
+            target_encoder_path = f"encoders/{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)
@@ -226,4 +220,4 @@ elif page == "Create App":
                 else:
                     st.text(prediction[0])
     else:
-        st.warning("No processed CSV files found. Please preprocess a file first.")
+        st.warning("No processed CSV files found. Please preprocess a file first.")