Update app.py

app.py

@@ -30,12 +30,8 @@ def grade_to_gpa(grade):
         return 0.0
 
 gpas = SPD.apply(grade_to_gpa, 'GradeClass')
-
 SPD = SPD.with_column('GPA', gpas)
 
-def gpa_to_label(gpa):
-    return "PASS" if gpa >= 2.0 else "FAIL"
-
 effectiveness_array = np.array(SPD.column('StudyEffectiveness'))
 gpa_array = np.array(SPD.column('GPA'))
 
@@ -53,15 +49,11 @@ slope = (
 intercept = np.mean(gpa_array) - (slope * np.mean(effectiveness_array))
 
 def linear_regression_gpa(effectiveness):
-
     gpa = intercept + (slope * effectiveness)
-
     if gpa < 0:
         gpa = 0
-
     if gpa > 4:
         gpa = 4
-
     return round(gpa, 2)
 
 def predict_tree_gpa(
@@ -75,16 +67,13 @@ def predict_tree_gpa(
     volunteering,
     effectiveness
 ):
-
     if effectiveness >= 18:
         gpa = 3.6 + (study_time * 0.02) - (absences * 0.01)
-
     elif effectiveness >= 14:
         if absences <= 18:
             gpa = 2.8 + (study_time * 0.03) - (absences * 0.015)
         else:
             gpa = 1.7 - (absences * 0.02)
-
     elif effectiveness >= 10:
         if study_time >= 10 and absences <= 12:
             gpa = 2.4 + (study_time * 0.03)
@@ -92,7 +81,6 @@ def predict_tree_gpa(
             gpa = 2.2 + (parental_support * 0.08)
         else:
             gpa = 1.5 - (absences * 0.02)
-
     elif effectiveness >= 6:
         if study_time >= 12 and absences < 8:
             gpa = 2.1 + (study_time * 0.025)
@@ -103,16 +91,13 @@ def predict_tree_gpa(
                 gpa = 1.3
         else:
             gpa = 1.0
-
     else:
         gpa = 0.6
 
     if gpa < 0:
         gpa = 0
-
     if gpa > 4:
         gpa = 4
-
     return round(gpa, 2)
 
 data = SPD.select(
@@ -133,18 +118,12 @@ data = SPD.select(
 )
 
 np.random.seed(1)
-
 shuffled = data.sample(with_replacement=False)
-
 size = int(data.num_rows * 0.8)
-
 train = shuffled.take(np.arange(size))
-test = shuffled.take(np.arange(size, data.num_rows))
 
 def distance(r1, r2):
-
     total = 0
-
     total += (r1.item('Age') - r2.item('Age'))**2
     total += (r1.item('Gender') - r2.item('Gender'))**2
     total += (r1.item('Ethnicity') - r2.item('Ethnicity'))**2
@@ -158,100 +137,29 @@ def distance(r1, r2):
     total += (r1.item('Music') - r2.item('Music'))**2
     total += (r1.item('Volunteering') - r2.item('Volunteering'))**2
     total += (r1.item('StudyEffectiveness') - r2.item('StudyEffectiveness'))**2
-
     return np.sqrt(total)
 
 def knn_neighbors(test_row, k):
-
     dists = make_array()
-
     for i in np.arange(train.num_rows):
-
         row = train.row(i)
-
         d = distance(test_row, row)
-
         dists = np.append(dists, d)
-
     temp = train.with_column('Distance', dists)
-
     nearest = temp.sort('Distance').take(np.arange(k))
-
     return nearest
 
 def knn_gpa(test_row, k):
-
     nearest = knn_neighbors(test_row, k)
-
     gpa = np.mean(nearest.column('GPA'))
-
     if gpa < 0:
         gpa = 0
-
     if gpa > 4:
         gpa = 4
-
     return round(gpa, 2)
 
 k = 5
 
-correct = 0
-
-for i in np.arange(test.num_rows):
-
-    row = test.row(i)
-
-    study_time = row.item('StudyTimeWeekly')
-    absences = row.item('Absences')
-    parental_support = row.item('ParentalSupport')
-    tutoring = row.item('Tutoring')
-    extracurricular = row.item('Extracurricular')
-    sports = row.item('Sports')
-    music = row.item('Music')
-    volunteering = row.item('Volunteering')
-    effectiveness = row.item('StudyEffectiveness')
-
-    tree_gpa = predict_tree_gpa(
-        study_time,
-        absences,
-        parental_support,
-        tutoring,
-        extracurricular,
-        sports,
-        music,
-        volunteering,
-        effectiveness
-    )
-
-    linear_gpa = linear_regression_gpa(effectiveness)
-
-    knn_prediction = knn_gpa(row, k)
-
-    predictions = [
-        gpa_to_label(tree_gpa),
-        gpa_to_label(linear_gpa),
-        gpa_to_label(knn_prediction)
-    ]
-
-    final_prediction = max(set(predictions), key=predictions.count)
-
-    actual = gpa_to_label(row.item('GPA'))
-
-    if final_prediction == actual:
-        correct += 1
-
-ensemble_accuracy = round(correct / test.num_rows, 4)
-
-def majority_vote(predictions):
-
-    passes = predictions.count("PASS")
-    fails = predictions.count("FAIL")
-
-    if passes > fails:
-        return "PASS"
-
-    return "FAIL"
-
 def predict_models(
     outside_study_time,
     in_class_learning_time,
@@ -264,12 +172,9 @@ def predict_models(
     music,
     volunteering
 ):
-
     attention_multiplier = attentiveness / 10
 
-    study_time = outside_study_time + (
-        in_class_learning_time * attention_multiplier
-    )
+    study_time = outside_study_time + (in_class_learning_time * attention_multiplier)
 
     study_effect = (
         (study_time * 1.5)
@@ -290,9 +195,7 @@ def predict_models(
         study_effect
     )
 
-    linear_gpa = linear_regression_gpa(
-        study_effect
-    )
+    linear_gpa = linear_regression_gpa(study_effect)
 
     test_row = Table().with_columns(
         'Age', [17],
@@ -313,25 +216,10 @@ def predict_models(
 
     knn_prediction = knn_gpa(test_row, k)
 
-    tree_label = gpa_to_label(tree_gpa)
-    linear_label = gpa_to_label(linear_gpa)
-    knn_label = gpa_to_label(knn_prediction)
+    avg_gpa = (tree_gpa + linear_gpa + knn_prediction) / 3
 
-    final_prediction = majority_vote([
-        tree_label,
-        linear_label,
-        knn_label
-    ])
-
-    accuracy_output = f"Combined Model Accuracy: {ensemble_accuracy}"
-
-    return (
-        tree_label,
-        linear_label,
-        knn_label,
-        final_prediction,
-        accuracy_output
-    )
+    result = "PASS" if avg_gpa >= 2.0 else "FAIL"
+    return result
 
 theme = gr.themes.Soft(
     primary_hue="blue",
@@ -341,15 +229,13 @@ theme = gr.themes.Soft(
     text_size="lg"
 )
 
-with gr.Blocks(
-    fill_height=True
-) as app:
+with gr.Blocks(theme=theme, fill_height=True) as app:
 
     gr.Markdown(
         """
 # Student Performance Predictor
 
-### Predict pass/fail results using multiple machine learning models
+### Predict Pass or Fail using machine learning models
 """
     )
 
@@ -359,106 +245,35 @@ with gr.Blocks(
 
             with gr.Group():
 
-                outside_study_time = gr.Slider(
-                    0,
-                    20,
-                    value=8,
-                    label="Study Time Outside Class Weekly"
-                )
-
-                in_class_learning_time = gr.Slider(
-                    0,
-                    25,
-                    value=15,
-                    label="Learning Time In Class Weekly"
-                )
-
-                attentiveness = gr.Slider(
-                    1,
-                    10,
-                    value=5,
-                    step=1,
-                    label="Attentiveness In Class"
-                )
-
-                absences = gr.Slider(
-                    0,
-                    30,
-                    value=5,
-                    label="Absences"
-                )
-
-                parental_support = gr.Slider(
-                    0,
-                    4,
-                    value=2,
-                    step=1,
-                    label="Parental Support"
-                )
-
-                tutoring = gr.Checkbox(
-                    label="Tutoring"
-                )
-
-                extracurricular = gr.Checkbox(
-                    label="Extracurricular Activities"
-                )
-
-                sports = gr.Checkbox(
-                    label="Sports"
-                )
-
-                music = gr.Checkbox(
-                    label="Music"
-                )
-
-                volunteering = gr.Checkbox(
-                    label="Volunteering"
-                )
-
-                btn = gr.Button(
-                    "Predict Performance",
-                    variant="primary",
-                    size="lg"
-                )
+                outside_study_time = gr.Slider(0, 20, value=8, label="Study Time Outside Class Weekly")
 
-        with gr.Column(scale=1):
+                in_class_learning_time = gr.Slider(0, 25, value=15, label="Learning Time In Class Weekly")
 
-            with gr.Row(equal_height=True):
+                attentiveness = gr.Slider(1, 10, value=5, step=1, label="Attentiveness In Class")
 
-                tree_output = gr.Textbox(
-                    label="Decision Tree",
-                    lines=1,
-                    interactive=False
-                )
+                absences = gr.Slider(0, 30, value=5, label="Absences")
 
-                linear_output = gr.Textbox(
-                    label="Linear Regression",
-                    lines=1,
-                    interactive=False
-                )
+                parental_support = gr.Slider(0, 4, value=2, step=1, label="Parental Support")
 
-            with gr.Row(equal_height=True):
+                tutoring = gr.Checkbox(label="Tutoring")
 
-                knn_output = gr.Textbox(
-                    label="KNN",
-                    lines=1,
-                    interactive=False
-                )
+                extracurricular = gr.Checkbox(label="Extracurricular Activities")
 
-                final_output = gr.Textbox(
-                    label="Final Majority Vote",
-                    lines=1,
-                    interactive=False
-                )
+                sports = gr.Checkbox(label="Sports")
 
-    with gr.Row():
+                music = gr.Checkbox(label="Music")
+
+                volunteering = gr.Checkbox(label="Volunteering")
+
+                btn = gr.Button("Predict Performance", variant="primary", size="lg")
+
+        with gr.Column(scale=1):
 
-        accuracy_box = gr.Textbox(
-            label="Combined Model Accuracy",
-            lines=1,
-            interactive=False
-        )
+            result_output = gr.Textbox(
+                label="Result",
+                lines=3,
+                interactive=False
+            )
 
     btn.click(
         predict_models,
@@ -474,13 +289,7 @@ with gr.Blocks(
             music,
             volunteering
         ],
-        outputs=[
-            tree_output,
-            linear_output,
-            knn_output,
-            final_output,
-            
-        ]
+        outputs=[result_output]
     )
 
 app.launch()