Update app.py

app.py

@@ -8,7 +8,7 @@ from sklearn.tree import DecisionTreeRegressor, DecisionTreeClassifier
 from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor, RandomForestClassifier
 from sklearn.svm import SVR, SVC
 from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error, accuracy_score, precision_score, recall_score, f1_score, roc_auc_score
-from sklearn.impute import KNNImputer
+from sklearn.impute import KNNImputer, SimpleImputer
 from sklearn.preprocessing import RobustScaler, StandardScaler, OneHotEncoder
 from sklearn.compose import ColumnTransformer
 from sklearn.pipeline import Pipeline
@@ -16,6 +16,9 @@ from ydata_profiling import ProfileReport
 from streamlit_pandas_profiling import st_profile_report
 from io import StringIO
 import joblib  # For saving and loading models
+import requests
+import asyncio
+from io import BytesIO
 
 # Configuration
 st.set_page_config(page_title="Data Wizard Pro", layout="wide", page_icon="🧙")
@@ -30,12 +33,10 @@ st.markdown(
             color: #e0e0ff; /* Light text */
             font-family: 'Courier New', monospace; /* Monospace font */
         }
-
         /* Main content area */
         .stApp {
             background-color: #0a0a1a; /* Match body background */
         }
-
         /* Containers and blocks */
         .st-emotion-cache-16idsys,
         .st-emotion-cache-1v0mbdj,
@@ -51,44 +52,37 @@ st.markdown(
             box-shadow: 0 4px 8px rgba(0, 0, 0, 0.5); /* Enhanced shadow */
             color: #e0e0ff; /* Light text color */
         }
-
         /* Sidebar */
         .st-bb {
             background-color: #141422; /* Dark sidebar background */
             padding: 20px;
             border-radius: 10px;
         }
-
         /* Headers */
         h1, h2, h3, h4, h5, h6, .st-bb {
             color: #00f7ff; /* Cyan color for headers */
         }
-
         /* Selectboxes and Buttons */
         .st-cb, .st-ci, .st-cj, .st-ch {
             background-color: #141422; /* Dark selectbox background */
             color: #00f7ff !important; /* Cyan text color */
             border: 1px solid #00f7ff; /* Cyan border */
         }
-
         /* Selectbox text */
         .st-cv {
             color: #00f7ff !important; /* Cyan color for selectbox text */
         }
-
         /* Number input and text input */
         .st-cr {
             background-color: #141422 !important; /* Dark input background */
             color: #00f7ff !important; /* Cyan text color */
             border: 1px solid #00f7ff !important; /* Cyan border */
         }
-
         /* Slider */
         .st-cw {
             background-color: #141422 !important; /* Dark slider background */
             border: 1px solid #00f7ff !important; /* Cyan border */
         }
-
         /* Buttons */
         .st-bz, .st-b0 {
             background-color: #141422; /* Darker Button background */
@@ -100,7 +94,6 @@ st.markdown(
             background-color: #00f7ff; /* Hover color */
             color: #0a0a1a; /* Hover text color */
         }
-
         /* File uploader */
         .st-ae {
             background-color: #141422 !important; /* Dark file uploader background */
@@ -113,7 +106,6 @@ st.markdown(
             border-radius: 10px !important; /* Rounded corners */
             box-shadow: 0 4px 8px rgba(0, 0, 0, 0.5) !important; /* Enhanced shadow */
         }
-
         /* Dataframes and tables */
         .dataframe {
             background-color: #1e1e30 !important; /* Dark table background */
@@ -136,11 +128,100 @@ st.markdown(
             border-radius: 10px;
         }
         /* Add more styling for other elements as needed */
+        /* Style the space around the navigation menu to match the theme */
+        [data-testid="stSidebar"] {
+            background-color: #141422 !important;
+        }
+        [data-testid="stSidebarNav"] {
+            background-color: #141422 !important;
+            color: #e0e0ff !important;
+        }
+        [data-testid="stSidebarNavItems"] {
+            color: #e0e0ff !important;
+        }
+        /* Ensure all text is white or cyan (no black) */
+        .st-bb,
+        .st-cb, .st-ci, .st-cj, .st-ch,
+        .st-cv,
+        .st-cr,
+        .st-cw,
+        .st-ae,
+        .st-emotion-cache-r421ms,
+        .st-emotion-cache-10oheav,
+        .st-emotion-cache-16idsys,
+        .st-emotion-cache-1v0mbdj,
+        .st-emotion-cache-1wrcr25,
+        .st-emotion-cache-607q0z,
+        .st-emotion-cache-1v3fvcr,
+        .st-emotion-cache-10trblm {
+            color: #e0e0ff !important; /* Default to white */
+        }
+        h1, h2, h3, h4, h5, h6 {
+            color: #00f7ff !important; /* Headings to cyan */
+        }
+
+        /* Styles for loader */
+        .loader {
+            border: 5px solid #f3f3f3;
+            border-top: 5px solid #00f7ff; /* Cyan loader color */
+            border-radius: 50%;
+            width: 30px;
+            height: 30px;
+            animation: spin 2s linear infinite;
+        }
+
+        @keyframes spin {
+            0% { transform: rotate(0deg); }
+            100% { transform: rotate(360deg); }
+        }
     </style>
     """,
     unsafe_allow_html=True,
 )
 
+# --- Image Loading ---
+@st.cache_data(ttl=3600)
+async def load_image(image_url):
+    """Loads an image from a URL asynchronously."""
+    try:
+        response = requests.get(image_url, stream=True)
+        response.raise_for_status()  # Raise HTTPError for bad responses (4xx or 5xx)
+        return BytesIO(response.content)  # Return image data as a BytesIO object
+    except requests.exceptions.RequestException as e:
+        st.error(f"Error loading image: {e}")
+        return None  # Handle errors gracefully
+
+async def set_background():
+    """Sets the background image."""
+    image_url = "https://images.unsplash.com/photo-1504821618514-8c1b6e408ca8?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1949&q=80"  # Replace with actual URL
+    image_data = await load_image(image_url)
+
+    if image_data:
+        st.markdown(
+            f"""
+            <style>
+            .stApp {{
+                background-image: url(data:image/{"jpeg"};base64,{image_data.getvalue().hex()});
+                background-size: cover;
+            }}
+            </style>
+            """,
+            unsafe_allow_html=True
+        )
+asyncio.run(set_background())
+# --- Loader ----
+def show_loader(message="Loading..."):
+    """Displays an animated loader."""
+    st.markdown(
+        f"""
+        <div style="display: flex; align-items: center; justify-content: center; margin-top: 20px;">
+            <div class="loader"></div>
+            <span style="margin-left: 10px; color: #00f7ff;">{message}</span>
+        </div>
+        """,
+        unsafe_allow_html=True
+    )
+
 # Cache decorators
 @st.cache_data(ttl=3600)
 def load_data(uploaded_file):
@@ -158,7 +239,6 @@ def load_data(uploaded_file):
     else:
         return None
 
-
 @st.cache_data(ttl=3600)
 def generate_profile(df):
     """Generate automated EDA report"""
@@ -187,7 +267,18 @@ app_mode = st.sidebar.radio("Navigate", [
     "Visualization Lab"
 ])
 
-# Data Upload Section
+# --- Progress Bar ----
+def animated_progress_bar(progress_var, message="Processing..."):
+    """Displays an animated progress bar with a message."""
+    progress_bar = st.progress(0)
+    status_text = st.empty()  # Empty element to update the status message
+
+    for i in range(progress_var): #progress will increment
+        status_text.text(f"{message} ({i+1}/{progress_var})")
+        progress_bar.progress((i+1)/progress_var) #progress incrementally.
+        time.sleep(0.01) # reduced sleep timer as its getting too long
+
+# --- Main App Logic ---
 if app_mode == "Data Upload":
     st.title("📤 Data Upload & Analysis")
 
@@ -210,10 +301,10 @@ if app_mode == "Data Upload":
             # Automated EDA Report
             with st.expander("🚀 Automated Data Report"):
                 if st.button("Generate Smart Report"):
+                    show_loader("Generating EDA Report")
                     pr = generate_profile(df)
                     st_profile_report(pr)
 
-# Smart Cleaning Section
 elif app_mode == "Smart Cleaning":
     st.title("🧼 Intelligent Data Cleaning")
 
@@ -312,7 +403,6 @@ elif app_mode == "Smart Cleaning":
                                     z_scores = np.abs((df[col] - df[col].mean()) / df[col].std())
                                     df = df[z_scores <= zscore_threshold]
 
-
                     st.session_state.cleaned_data = df
                     st.success("Transformation applied!")
 
@@ -324,7 +414,6 @@ elif app_mode == "Smart Cleaning":
         with col2:
             st.write("Cleaned Data", df.head(3))
 
-# Advanced EDA Section
 elif app_mode == "Advanced EDA":
     st.title("🔍 Advanced Exploratory Analysis")
 
@@ -347,12 +436,9 @@ elif app_mode == "Advanced EDA":
         with cols[0]:
             x_col = st.selectbox("X Axis", df.columns)
         with cols[1]:
-            y_col = st.selectbox("Y Axis", df.columns) if plot_type in ["Scatter Plot", "Box Plot", "Violin Plot", "Time Series"] else None
+            y_col = st.selectbox("Y Axis", df.columns) if plot_type not in ["Correlation Heatmap"] else None
         with cols[2]:
             z_col = st.selectbox("Z Axis", df.columns) if plot_type == "3D Scatter" else None
-        if plot_type == "Time Series":
-            time_col = x_col # rename for clarity
-            value_col = y_col
 
         #Interactive filtering
         filter_col = st.selectbox("Filter Column", [None] + list(df.columns))
@@ -361,12 +447,11 @@ elif app_mode == "Advanced EDA":
             filter_options = st.multiselect("Filter Values", unique_values, default=unique_values)
             df = df[df[filter_col].isin(filter_options)]
 
-
         # Generate Plot
         if st.button("Generate Visualization"):
             try:  # add try-except block for potential errors
                 if plot_type == "Histogram":
-                    fig = px.histogram(df, x=x_col, nbins=30, template="plotly_dark")
+                    fig = px.histogram(df, x=x_col, y=y_col, nbins=30, template="plotly_dark")
                 elif plot_type == "Scatter Plot":
                     fig = px.scatter(df, x=x_col, y=y_col, color_discrete_sequence=['#00f7ff'])
                 elif plot_type == "3D Scatter":
@@ -391,7 +476,6 @@ elif app_mode == "Advanced EDA":
             except Exception as e:
                 st.error(f"Error generating plot: {e}")
 
-# Model Training Section
 elif app_mode == "Model Training":
     st.title("🤖 Model Training Studio")
 
@@ -454,11 +538,10 @@ elif app_mode == "Model Training":
                     max_depth = st.slider("Max Depth", 5, 20, None)  # None for unlimited
                     param_grid = {'max_depth': [max_depth]}
 
-
-
         with col2:
             if st.button("Train Model"):
                 try:
+                    show_loader("Training the Model")
                     X = df.drop(columns=[target])
                     y = df[target]
 
@@ -482,7 +565,6 @@ elif app_mode == "Model Training":
                     X_test = preprocessor.transform(X_test)
                     st.session_state.preprocessor = preprocessor #store for prediction later
 
-
                     # Model Training
                     if task_type == "Regression":
                         if model_type == "Linear Regression":
@@ -505,15 +587,17 @@ elif app_mode == "Model Training":
                         elif model_type == "Support Vector Machine":
                             model = SVC(probability=True) #probability=True needed for ROC AUC
 
-
                     #Hyperparameter tuning
                     if enable_hyperparameter_tuning and model_type in ["Random Forest", "Gradient Boosting", "Support Vector Machine", "Logistic Regression", "Decision Tree"]:
                         grid_search = GridSearchCV(model, param_grid, cv=3, scoring='neg_mean_squared_error' if task_type == "Regression" else 'accuracy')
+                        animated_progress_bar(50, "Performing Grid Search") #add loading for grid search
+
                         grid_search.fit(X_train, y_train)
                         model = grid_search.best_estimator_ #use best model
                         st.write("Best Parameters:", grid_search.best_params_)
 
                     else:
+                        animated_progress_bar(80, "Fitting Model")
                         model.fit(X_train, y_train)
 
                     st.session_state.model = model
@@ -553,13 +637,13 @@ elif app_mode == "Model Training":
                     st.write("Cross-Validation Scores:", scores)
                     st.write("Mean Cross-Validation Score:", scores.mean())
 
-
-
                     #Model persistence
                     if st.checkbox("Save Model"):
                         model_filename = st.text_input("Model Filename", "trained_model.joblib")
                         joblib.dump((model, preprocessor), model_filename) # save both model AND preprocessor
                         st.success(f"Model saved as {model_filename}")
+                    animated_progress_bar(100, "Model Trained Succesfully")
+
                 except Exception as e:
                     st.error(f"Error during training: {e}")
 
@@ -581,7 +665,6 @@ elif app_mode == "Predictions":
 
         if st.button("Predict"):
             try:
-
                 input_df = pd.DataFrame([input_data])
                 # Preprocess input
                 input_processed = preprocessor.transform(input_df)
@@ -602,7 +685,8 @@ elif app_mode == "Predictions":
     else:
         st.warning("Please train a model first.")
 
-elif app_mode == "Visualization Lab":
+
+    elif app_mode == "Visualization Lab":
     st.title("📊 Advanced Visualization Lab")
 
     if st.session_state.cleaned_data is not None:
@@ -610,10 +694,9 @@ elif app_mode == "Visualization Lab":
 
         # Visualization Gallery
         viz_type = st.selectbox("Choose Visualization Type", [
-            "3D Scatter Plot",
-            "Interactive Heatmap",
+            "3D Scatter Plot"Interactive Heatmap",
             "Time Series Analysis",
-            "Cluster Analysis (Coming Soon)" #Removed placeholder, keep in mind
+            "Cluster Analysis (Coming Soon)"  # Removed placeholder
         ])
 
         # Dynamic Controls
@@ -621,19 +704,24 @@ elif app_mode == "Visualization Lab":
         with cols[0]:
             x_axis = st.selectbox("X Axis", df.columns)
         with cols[1]:
-            y_axis = st.selectbox("Y Axis", df.columns)
+            y_axis = st.selectbox("Y Axis", df.columns) if viz_type not in ["Interactive Heatmap"] else None
         with cols[2]:
             z_axis = st.selectbox("Z Axis", df.columns) if viz_type == "3D Scatter Plot" else None
 
         # Generate Visualization
-        try: #Add try-except
+        try:  # Add try-except
             if viz_type == "3D Scatter Plot":
-                fig = px.scatter_3d(df, x=x_axis, y=y_axis, z=z_axis, color=x_axis)
-                st.plotly_chart(fig, use_container_width=True)
+                if y_axis is None or z_axis is None:
+                    st.error("Please select Y and Z axes for 3D Scatter Plot.")
+                else:
+                    fig = px.scatter_3d(df, x=x_axis, y=y_axis, z=z_axis, color=x_axis)
+                    fig.update_layout(plot_bgcolor="#1e1e30", paper_bgcolor="#1e1e30", font_color="#e0e0ff")
+                    st.plotly_chart(fig, use_container_width=True)
 
             elif viz_type == "Interactive Heatmap":
-                corr = df.corr(numeric_only=True) #Add numeric_only=True
+                corr = df.corr(numeric_only=True)  # Add numeric_only=True
                 fig = px.imshow(corr, text_auto=True, color_continuous_scale='RdBu')
+                fig.update_layout(plot_bgcolor="#1e1e30", paper_bgcolor="#1e1e30", font_color="#e0e0ff")
                 st.plotly_chart(fig, use_container_width=True)
 
             elif viz_type == "Time Series Analysis":
@@ -641,9 +729,11 @@ elif app_mode == "Visualization Lab":
                 time_col = st.selectbox("Time Column", df.columns)
                 value_col = st.selectbox("Value Column", df.columns)
                 fig = px.line(df, x=time_col, y=value_col)
+                fig.update_layout(plot_bgcolor="#1e1e30", paper_bgcolor="#1e1e30", font_color="#e0e0ff")
                 st.plotly_chart(fig, use_container_width=True)
 
-            elif viz_type == "Cluster Analysis (Coming Soon)": #Removed placeholder
-               st.write("Cluster Analysis Feature Coming Soon!")  # placeholder for future development
+            elif viz_type == "Cluster Analysis (Coming Soon)":  # Removed placeholder
+                st.write("Cluster Analysis Feature Coming Soon!")  # placeholder for future development
+
         except Exception as e:
-            st.error(f"Error generating visualization: {e}")
+            st.error(f"Error generating visualization: {e}")