first push

src/streamlit_app.py

@@ -6,23 +6,24 @@ 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
+from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
 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"])
 
-BASE_DIR = "/tmp"
+# Writable directories for Hugging Face / Streamlit Cloud
+BASE_DIR = "/tmp"  # only /tmp is writable in HF Spaces
 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(UPLOAD_DIR, exist_ok=True)
-os.makedirs(PROCESSED_DIR, exist_ok=True)
-os.makedirs(PKL_DIR, exist_ok=True)
-os.makedirs(ENCODER_DIR, exist_ok=True)
+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"])
@@ -34,13 +35,15 @@ if page == "Upload File":
         st.success(f"File saved to {save_path}")
 
         if uploaded_file.name.endswith(".csv"):
-            df = pd.read_csv(save_path)
+            uploaded_file.seek(0)
+            df = pd.read_csv(uploaded_file)
             st.dataframe(df)
         elif uploaded_file.name.endswith(".sql"):
-            with open(save_path, "r", encoding="utf-8") as f:
-                sql_content = f.read()
+            uploaded_file.seek(0)
+            sql_content = uploaded_file.read().decode("utf-8", errors="ignore")
             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")]
@@ -66,9 +69,6 @@ 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)
@@ -97,6 +97,7 @@ 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")
 
@@ -142,7 +143,7 @@ elif page == "Train & Select Model":
             else:
                 models = {
                     "Linear Regression": LinearRegression(),
-                    "Decision Tree": DecisionTreeClassifier()
+                    "Decision Tree Regressor": DecisionTreeRegressor()
                 }
                 for name, model in models.items():
                     model.fit(X_train, y_train)
@@ -164,6 +165,7 @@ 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")