File size: 5,323 Bytes
fdb0c97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
import numpy as np
import plotly.graph_objs as go
import plotly.figure_factory as ff
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix, roc_curve, auc

def generate_data(dataset_name, noise, random_state=42):
    if dataset_name == "moons":
        X, y = make_moons(n_samples=300, noise=noise, random_state=random_state)
    elif dataset_name == "circles":
        X, y = make_circles(n_samples=300, noise=noise, factor=0.5, random_state=random_state)
    else:
        X, y = make_classification(
            n_samples=300, n_features=2, n_redundant=0, n_informative=2,
            random_state=random_state, n_clusters_per_class=1, flip_y=noise/10.0
        )
    return X, y

def serve_prediction_plot(dataset_name, noise, n_neighbors, weights, metric, p_value, test_size=0.3):
    # 1. Fetch and Preprocess Data
    X, y = generate_data(dataset_name, noise)
    X = StandardScaler().fit_transform(X)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=42)

    # 2. Fit KNN Model
    clf = KNeighborsClassifier(n_neighbors=n_neighbors, weights=weights, metric=metric, p=p_value)
    clf.fit(X_train, y_train)
    
    train_score = clf.score(X_train, y_train)
    test_score = clf.score(X_test, y_test)

    # 3. Create a Fine Mesh Grid for Contours
    x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5
    y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5
    h = 0.05
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))

    grid_points = np.c_[xx.ravel(), yy.ravel()]
    if hasattr(clf, "predict_proba"):
        Z = clf.predict_proba(grid_points)[:, 1]
    else:
        Z = clf.predict(grid_points)
    Z = Z.reshape(xx.shape)

    # 4. Construct the Main Boundary Plot
    fig_boundary = go.Figure()
    fig_boundary.add_trace(go.Contour(
        x=np.arange(x_min, x_max, h), y=np.arange(y_min, y_max, h), z=Z,
        colorscale='RdBu', opacity=0.35, showscale=False, hoverinfo='skip'
    ))

    for label, color, name in [(0, '#FF4136', 'Train Class 0'), (1, '#0074D9', 'Train Class 1')]:
        mask = (y_train == label)
        fig_boundary.add_trace(go.Scatter(
            x=X_train[mask, 0], y=X_train[mask, 1], mode='markers',
            marker=dict(color=color, size=8, line=dict(width=1, color='black')), name=name
        ))

    for label, color, name in [(0, '#FF4136', 'Test Class 0'), (1, '#0074D9', 'Test Class 1')]:
        mask = (y_test == label)
        fig_boundary.add_trace(go.Scatter(
            x=X_test[mask, 0], y=X_test[mask, 1], mode='markers',
            marker=dict(color=color, size=10, symbol='diamond', line=dict(width=1.5, color='white')), name=name
        ))

    fig_boundary.update_layout(
        title="KNN Decision Space Map",
        xaxis=dict(title="Feature 1", showgrid=False),
        yaxis=dict(title="Feature 2", showgrid=False),
        legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1),
        margin=dict(l=40, r=40, t=80, b=40),
        plot_bgcolor='white', paper_bgcolor='white'
    )

    # 5. Construct the Confusion Matrix Heatmap
    y_pred = clf.predict(X_test)
    cm = confusion_matrix(y_test, y_pred)
    
    x_labels = ['Predicted 0', 'Predicted 1']
    y_labels = ['Actual 1', 'Actual 0']
    cm_text = [[str(y) for y in x] for x in cm]

    fig_cm = ff.create_annotated_heatmap(
        z=cm[::-1], x=x_labels, y=y_labels, annotation_text=cm_text[::-1], colorscale='Blues'
    )
    fig_cm.update_layout(
        title="Confusion Matrix (Test Data)",
        margin=dict(l=60, r=20, t=80, b=40),
        height=280
    )

    # 6. Construct the ROC Curve with AUC Calculation
    # Get predicted probabilities for class 1
    y_probs = clf.predict_proba(X_test)[:, 1] if hasattr(clf, "predict_proba") else y_pred
    fpr, tpr, thresholds = roc_curve(y_test, y_probs)
    roc_auc = auc(fpr, tpr)

    fig_roc = go.Figure()
    
    # Add Baseline Random Guess Line
    fig_roc.add_trace(go.Scatter(
        x=[0, 1], y=[0, 1], mode='lines', 
        line=dict(color='gray', width=1.5, dash='dash'), 
        name='Random Guess (AUC = 0.50)', hoverinfo='skip'
    ))
    
    # Add ROC Curve Line
    fig_roc.add_trace(go.Scatter(
        x=fpr, y=tpr, mode='lines+markers', 
        line=dict(color='#e11d48', width=3), 
        name=f'KNN Model (AUC = {roc_auc:.2f})',
        hovertext=[f"Threshold: {t:.2f}" for t in thresholds],
        hoverinfo='text+x+y'
    ))

    fig_roc.update_layout(
        title=f"ROC Curve (AUC: {roc_auc:.2f})",
        xaxis=dict(title="False Positive Rate (1 - Specificity)", range=[-0.02, 1.02], gridcolor='#f1f5f9'),
        yaxis=dict(title="True Positive Rate (Sensitivity / Recall)", range=[-0.02, 1.02], gridcolor='#f1f5f9'),
        margin=dict(l=50, r=20, t=80, b=50),
        plot_bgcolor='white', paper_bgcolor='white',
        height=280, showlegend=False
    )

    return fig_boundary, fig_cm, fig_roc, train_score, test_score