import pandas as pd
import numpy as np
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from sklearn.metrics import roc_curve, auc
import plotly.graph_objects as go

# Create synthetic binary classification data
X, y = make_classification(n_samples=1000, n_features=20, random_state=42)

# Scale the data using StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Split the data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)

# Initialize the models
knn = KNeighborsClassifier()
rf = RandomForestClassifier()
dt = DecisionTreeClassifier()
svm = SVC(probability=True)

# Fit the models on the train set
knn.fit(X_train, y_train)
rf.fit(X_train, y_train)
dt.fit(X_train, y_train)
svm.fit(X_train, y_train)

# Predict probabilities on the test set
knn_probs = knn.predict_proba(X_test)[:, 1]
rf_probs = rf.predict_proba(X_test)[:, 1]
dt_probs = dt.predict_proba(X_test)[:, 1]
svm_probs = svm.predict_proba(X_test)[:, 1]

# Calculate the false positive rate (FPR) and true positive rate (TPR) for ROC curve
knn_fpr, knn_tpr, _ = roc_curve(y_test, knn_probs)
rf_fpr, rf_tpr, _ = roc_curve(y_test, rf_probs)
dt_fpr, dt_tpr, _ = roc_curve(y_test, dt_probs)
svm_fpr, svm_tpr, _ = roc_curve(y_test, svm_probs)

# Calculate the AUC (Area Under the Curve) for ROC curve
knn_auc = auc(knn_fpr, knn_tpr)
rf_auc = auc(rf_fpr, rf_tpr)
dt_auc = auc(dt_fpr, dt_tpr)
svm_auc = auc(svm_fpr, svm_tpr)

# Create an interactive AUC/ROC curve using Plotly
fig = go.Figure()
fig.add_trace(go.Scatter(x=knn_fpr, y=knn_tpr, name='KNN (AUC = {:.2f})'.format(knn_auc)))
fig.add_trace(go.Scatter(x=rf_fpr, y=rf_tpr, name='Random Forest (AUC = {:.2f})'.format(rf_auc)))
fig.add_trace(go.Scatter(x=dt_fpr, y=dt_tpr, name='Decision Tree (AUC = {:.2f})'.format(dt_auc)))
fig.add_trace(go.Scatter(x=svm_fpr, y=svm_tpr, name='SVM (AUC = {:.2f})'.format(svm_auc)))
fig.update_layout(title='AUC/ROC Curve',
                  xaxis=dict(title='False Positive Rate'),
                  yaxis=dict(title='True Positive Rate'),
                  legend=dict(x=0.7, y=0.2))
# Show plot
fig.show()