shopping.py

import csv
import sys

from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier

TEST_SIZE = 0.4


def main():

    # Check command-line arguments
    if len(sys.argv) != 2:
        sys.exit("Usage: python shopping.py data")

    # Load data from spreadsheet and split into train and test sets
    evidence, labels = load_data(sys.argv[1])
    X_train, X_test, y_train, y_test = train_test_split(
        evidence, labels, test_size=TEST_SIZE
    )

    # Train model and make predictions
    model = train_model(X_train, y_train)
    predictions = model.predict(X_test)
    sensitivity, specificity = evaluate(y_test, predictions)

    # Print results
    print(f"Correct: {(y_test == predictions).sum()}")
    print(f"Incorrect: {(y_test != predictions).sum()}")
    print(f"True Positive Rate: {100 * sensitivity:.2f}%")
    print(f"True Negative Rate: {100 * specificity:.2f}%")


def load_data(filename):
    """
    Load shopping data from a CSV file `filename` and convert into a list of
    evidence lists and a list of labels. Return a tuple (evidence, labels).
    """

    evidence = []
    labels = []
    month_to_index = {
        "Jan": 0, "Feb": 1, "Mar": 2, "Apr": 3,
        "May": 4, "June": 5, "Jul": 6, "Aug": 7,
        "Sep": 8, "Oct": 9, "Nov": 10, "Dec": 11
    }

    with open(filename, mode='r', encoding='utf-8') as file:
        reader = csv.DictReader(file)
        for row in reader:
            row_evidence = [
                int(row["Administrative"]),
                float(row["Administrative_Duration"]),
                int(row["Informational"]),
                float(row["Informational_Duration"]),
                int(row["ProductRelated"]),
                float(row["ProductRelated_Duration"]),
                float(row["BounceRates"]),
                float(row["ExitRates"]),
                float(row["PageValues"]),
                float(row["SpecialDay"]),
                month_to_index[row["Month"]],
                int(row["OperatingSystems"]),
                int(row["Browser"]),
                int(row["Region"]),
                int(row["TrafficType"]),
                1 if row["VisitorType"] == "Returning_Visitor" else 0,
                1 if row["Weekend"] == "TRUE" else 0
            ]
            evidence.append(row_evidence)
            labels.append(1 if row["Revenue"] == "TRUE" else 0)

    return evidence, labels


def train_model(evidence, labels):
    """
    Given a list of evidence lists and a list of labels, return a
    fitted k-nearest neighbor model (k=1) trained on the data.
    """
    # Initialize the KNN model with k=1
    model = KNeighborsClassifier(n_neighbors=1)

    # Train the model using the provided evidence and labels
    model.fit(evidence, labels)

    # Return the trained model
    return model


def evaluate(labels, predictions):
    """
    Given a list of actual labels and a list of predicted labels,
    return a tuple (sensitivity, specificity).
    """
    # Initialize counters for true positives, false negatives, true negatives, and false positives
    tp = 0
    fn = 0
    tn = 0
    fp = 0

    # Loop through all labels and predictions to count tp, fn, tn, fp
    for actual, predicted in zip(labels, predictions):
        if actual == 1 and predicted == 1:
            tp += 1
        elif actual == 1 and predicted == 0:
            fn += 1
        elif actual == 0 and predicted == 1:
            fp += 1
        elif actual == 0 and predicted == 0:
            tn += 1

    # Calculate sensitivity and specificity
    sensitivity = tp / (tp + fn) if (tp + fn) != 0 else 0
    specificity = tn / (tn + fp) if (tn + fp) != 0 else 0

    return sensitivity, specificity


if __name__ == "__main__":
    main()