BDA-Lab-3

The Da Vinci Code, written by Dan Brown, follows Harvard symbologist Robert Langdon as he becomes entangled in a mysterious murder at the Louvre Museum. Alongside cryptologist Sophie Neveu, Langdon unravels a complex web of codes, symbols, and historical secrets tied to a hidden truth about the Holy Grail and the controversial legacy of Mary Magdalene. The story presents a fictional European secret society, the Priory of Sion, supposedly founded in 1099 and involving famous figures such as Leonardo da Vinci. Another Catholic organization, Opus Dei, emerges in the narrative as a shadowy force, sparking further intrigue. 

The plot unfolds through a series of cryptic messages and objects, including a keystone believed to lead to the Grail’s hidden location. Langdon and Sophie encounter numerous obstacles, including Silas, a devout albino monk, and Leigh Teabing, a Grail historian with his own hidden motives. As they decode symbols like the pentacle and the number PHI, they chase leads through significant historical sites like Westminster Abbey and Rosslyn Chapel. The story weaves themes of faith, power, and historical mystery, ultimately suggesting a hidden lineage of Jesus and Mary Magdalene that could challenge traditional Christian beliefs.

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, roc_auc_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, roc_auc_score, roc_curve
import matplotlib.pyplot as plt
import xgboost as xgb
from sklearn.ensemble import GradientBoostingClassifier


def ctr_prediction_RandomForest(data):
    """
    Function to predict Click-Through Rate (CTR) using a machine learning model.
    
    Parameters:
    - data: pandas DataFrame, where the last column is 'CTR' (target variable).
    
    Returns:
    - model: trained model.
    - accuracy: model's accuracy score.
    - auc: ROC-AUC score.
    - y_pred: Predicted CTR values.
    """
    # Preprocessing steps (same as before)
    if data.isnull().sum().any():
        data = data.dropna()

    categorical_cols = ['user_location', 'ad_type']  # Example categorical columns
    data = pd.get_dummies(data, columns=categorical_cols, drop_first=True)

    X = data.drop(columns=['CTR'])  # Features
    y = data['CTR']  # Target variable: CTR (0 = No Click, 1 = Click)

    # Train-Test Split
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # Initialize and train the model (e.g., Random Forest, Logistic Regression, etc.)
    model = RandomForestClassifier(random_state=42)
    model.fit(X_train, y_train)

    # Make predictions
    y_pred = model.predict(X_test)

    # Evaluate performance
    accuracy = accuracy_score(y_test, y_pred)
    auc = roc_auc_score(y_test, model.predict_proba(X_test)[:, 1])

    # Step 9: Plotting Model Performance (Optional)
    # Plot ROC curve
    fpr, tpr, thresholds = roc_curve(y_test, model.predict_proba(X_test)[:, 1])
    plt.figure(figsize=(8, 6))
    plt.plot(fpr, tpr, color='blue', label='ROC Curve')
    plt.plot([0, 1], [0, 1], color='gray', linestyle='--')
    plt.xlabel('False Positive Rate')
    plt.ylabel('True Positive Rate')
    plt.title('ROC Curve')
    plt.legend(loc='lower right')
    plt.show()

    return model, accuracy, auc, y_pred


def ctr_prediction_xgboost(data):
    """
    Function to predict Click-Through Rate (CTR) using XGBoost Classifier.
    
    Parameters:
    - data: pandas DataFrame, where the last column is 'CTR' (target variable).
    
    Returns:
    - model: trained XGBoost model.
    - accuracy: model's accuracy score.
    - auc: ROC-AUC score.
    - y_pred: Predicted CTR values.
    """
    # Preprocessing steps (same as before)
    if data.isnull().sum().any():
        data = data.dropna()

    categorical_cols = ['user_location', 'ad_type']
    data = pd.get_dummies(data, columns=categorical_cols, drop_first=True)

    X = data.drop(columns=['CTR'])  # Features
    y = data['CTR']  # Target variable: CTR (0 = No Click, 1 = Click)

    # Train-Test Split
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # Initialize and train the XGBoost Classifier
    model = xgb.XGBClassifier(use_label_encoder=False, random_state=42)
    model.fit(X_train, y_train)

    # Make predictions
    y_pred = model.predict(X_test)

    # Evaluate performance
    accuracy = accuracy_score(y_test, y_pred)
    auc = roc_auc_score(y_test, y_pred)

    return model, accuracy, auc, y_pred


def ctr_prediction_gradient_boosting(data):
    """
    Function to predict Click-Through Rate (CTR) using Gradient Boosting Classifier.
    
    Parameters:
    - data: pandas DataFrame, where the last column is 'CTR' (target variable).
    
    Returns:
    - model: trained Gradient Boosting model.
    - accuracy: model's accuracy score.
    - auc: ROC-AUC score.
    - y_pred: Predicted CTR values.
    """
    # Preprocessing steps (same as before)
    if data.isnull().sum().any():
        data = data.dropna()

    categorical_cols = ['user_location', 'ad_type']
    data = pd.get_dummies(data, columns=categorical_cols, drop_first=True)

    X = data.drop(columns=['CTR'])  # Features
    y = data['CTR']  # Target variable: CTR (0 = No Click, 1 = Click)

    # Train-Test Split
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # Initialize and train the Gradient Boosting Classifier
    model = GradientBoostingClassifier(random_state=42)
    model.fit(X_train, y_train)

    # Make predictions
    y_pred = model.predict(X_test)

    # Evaluate performance
    accuracy = accuracy_score(y_test, y_pred)
    auc = roc_auc_score(y_test, y_pred)

    return model, accuracy, auc, y_pred