Update app.py

app.py

@@ -13,7 +13,7 @@ import os
 # =======================
 # DATA LADEN
 # =======================
-REQUIRED_COLS = {"survived","pclass","sex","age","sibsp","parch","fare","embarked"}
+REQUIRED_COLS = {"survived", "pclass", "sex", "age", "sibsp", "parch", "fare", "embarked"}
 
 def load_data(csv_path="Titanic-Dataset.csv"):
     if not os.path.exists(csv_path):
@@ -44,7 +44,9 @@ def train_model(modeltype="Random Forest"):
     for c in X.select_dtypes("object").columns:
         le = LabelEncoder()
         X[c] = le.fit_transform(X[c])
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42, stratify=y
+    )
     if modeltype == "Random Forest":
         model = RandomForestClassifier(n_estimators=300, random_state=42)
     else:
@@ -74,15 +76,20 @@ def tab_intro():
 
 # Tab 2 – Verkenning
 def tab_verkenning():
-    # Interactieve Plotly-grafieken
     fig1 = px.histogram(
-        df, x="age", color=df["survived"].map({0:"Niet overleefd",1:"Overleefd"}),
-        nbins=30, title="Leeftijdsverdeling per overlevingsstatus"
+        df,
+        x="age",
+        color=df["survived"].map({0: "Niet overleefd", 1: "Overleefd"}),
+        nbins=30,
+        title="Leeftijdsverdeling per overlevingsstatus",
     )
     fig1.update_layout(legend_title_text="Status", bargap=0.05)
     fig2 = px.box(
-        df, x="pclass", y="fare", color=df["survived"].map({0:"Niet overleefd",1:"Overleefd"}),
-        title="Ticketprijs per klasse"
+        df,
+        x="pclass",
+        y="fare",
+        color=df["survived"].map({0: "Niet overleefd", 1: "Overleefd"}),
+        title="Ticketprijs per klasse",
     )
     fig2.update_layout(legend_title_text="Status")
     return fig1, fig2
@@ -93,11 +100,10 @@ def tab_model(model_type):
         _, acc = train_model(model_type)
         return f"Het {model_type}-model behaalt een nauwkeurigheid van **{acc:.2%}**."
     except Exception as e:
-        return f"Fout bij trainen: {e}"
+        return f"⚠️ Fout bij trainen: {e}"
 
 # Tab 4 – Voorspelling
 def predict_overleven(pclass, sex, age, sibsp, parch, fare, embarked):
-    # Train snel RF op de volledige dataset (demo-doeleinden)
     X = df.drop("survived", axis=1).copy()
     y = df["survived"].astype(int).copy()
     for c in X.select_dtypes("object").columns:
@@ -105,19 +111,17 @@ def predict_overleven(pclass, sex, age, sibsp, parch, fare, embarked):
         X[c] = le.fit_transform(X[c])
     rf = RandomForestClassifier(n_estimators=300, random_state=42)
     rf.fit(X, y)
-    # encode invoer
+    # Encode invoer
     sex_enc = 1 if str(sex).lower().startswith("v") else 0  # Vrouw=1, Man=0
     embarked_enc = {"C": 0, "Q": 1, "S": 2}.get(str(embarked).strip()[0].upper(), 2)
-    row = [[int(pclass), int(sex_enc), float(age), int(sibsp), int(parch), float(fare), int(embarked_enc)]]
+    row = [[int(pclass), sex_enc, float(age), int(sibsp), int(parch), float(fare), embarked_enc]]
     p = rf.predict_proba(row)[0, 1]
     return f"🎯 Je geschatte overlevingskans is **{p:.1%}**."
 
 # =======================
 # UI – Gradio
 # =======================
-
 custom_css = """
-/* Achtergrond + leesbaarheid */
 body {
     background: url('titanic_bg.png') no-repeat center center fixed;
     background-size: cover;
@@ -126,8 +130,6 @@ body {
 .gradio-container {
     background: rgba(10, 16, 26, 0.70);
 }
-
-/* Glossy zonsondergang rechtsboven */
 .gradio-container::before {
     content: '';
     position: fixed;
@@ -137,19 +139,13 @@ body {
     pointer-events: none;
     z-index: 0;
 }
-
-/* Tekstcontrasten */
 h1, h2, h3, p, label, .gr-markdown { color: #eef5ff !important; }
 label { font-weight: 600; }
-
-/* Kaarten / secties */
 div.svelte-1ipelgc, .block.padded { 
     background: rgba(20, 28, 42, 0.70) !important; 
     border-radius: 16px; 
     border: 1px solid rgba(60, 80, 110, 0.5);
 }
-
-/* Tabs */
 button.svelte-1ipelgc, .tabitem { 
     backdrop-filter: blur(2px);
 }
@@ -163,13 +159,17 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft(primary_hue="blue", secondar
 
         with gr.Tab("Verkenning"):
             btn1 = gr.Button("Toon grafieken")
-            out1 = gr.Plotl(label="Leeftijdsverdeling")
-            out2 = gr.Plotl(label="Ticketprijs per klasse")
+            out1 = gr.Plot(label="Leeftijdsverdeling")
+            out2 = gr.Plot(label="Ticketprijs per klasse")
             btn1.click(fn=tab_verkenning, outputs=[out1, out2])
 
         with gr.Tab("Machine Learning"):
             with gr.Row():
-                model_dropdown = gr.Dropdown(["Random Forest", "Logistic Regression"], label="Kies modeltype", value="Random Forest")
+                model_dropdown = gr.Dropdown(
+                    ["Random Forest", "Logistic Regression"],
+                    label="Kies modeltype",
+                    value="Random Forest",
+                )
                 btn2 = gr.Button("Train model")
             out3 = gr.Markdown()
             btn2.click(fn=tab_model, inputs=model_dropdown, outputs=out3)
@@ -186,8 +186,10 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft(primary_hue="blue", secondar
                 embarked = gr.Radio(["C", "Q", "S"], label="Vertrekhaven", value="S")
             btn3 = gr.Button("Voorspel")
             out4 = gr.Markdown()
-            btn3.click(fn=predict_overleven, 
-                       inputs=[pclass, sex, age, sibsp, parch, fare, embarked],
-                       outputs=out4)
+            btn3.click(
+                fn=predict_overleven,
+                inputs=[pclass, sex, age, sibsp, parch, fare, embarked],
+                outputs=out4,
+            )
 
-demo.launch()
+demo.launch()