inference_example.py

"""
Example inference script for TikTok Bot Detection Model
"""

import joblib
import pandas as pd
from sklearn.preprocessing import MinMaxScaler


def load_model(model_path="TIKTOK_BOT_Detection_Model_v1.pkl"):
    """Load the trained bot detection model"""
    return joblib.load(model_path)


def prepare_features(account_data):
    """
    Prepare account features for prediction

    Args:
        account_data (dict): Dictionary containing account features

    Returns:
        numpy.ndarray: Scaled features ready for prediction
    """
    features = [
        "IsPrivate",
        "IsVerified",
        "HasProfilePic",
        "FollowingCount",
        "FollowerCount",
        "HasInstagram",
        "HasYoutube",
        "HasBio",
        "HasLinkInBio",
        "HasPosts",
        "PostsCount",
        "FollowToFollowerRatio",
    ]

    df = pd.DataFrame([account_data])

    # Scale features
    scaler = MinMaxScaler()
    df_scaled = scaler.fit_transform(df[features])

    return df_scaled


def predict_single_account(model, account_data):
    """
    Predict if a single account is a bot

    Args:
        model: Trained sklearn model
        account_data (dict): Account features

    Returns:
        dict: Prediction results with probabilities
    """
    features_scaled = prepare_features(account_data)

    prediction = model.predict(features_scaled)[0]
    probability = model.predict_proba(features_scaled)[0]

    return {
        "is_bot": bool(prediction),
        "bot_probability": float(probability[1]),
        "human_probability": float(probability[0]),
        "confidence": float(max(probability)),
    }


def predict_batch(model, accounts_df):
    """
    Predict for multiple accounts at once

    Args:
        model: Trained sklearn model
        accounts_df (pd.DataFrame): DataFrame with account features

    Returns:
        pd.DataFrame: Original data with predictions added
    """
    features = [
        "IsPrivate",
        "IsVerified",
        "HasProfilePic",
        "FollowingCount",
        "FollowerCount",
        "HasInstagram",
        "HasYoutube",
        "HasBio",
        "HasLinkInBio",
        "HasPosts",
        "PostsCount",
        "FollowToFollowerRatio",
    ]

    scaler = MinMaxScaler()
    features_scaled = scaler.fit_transform(accounts_df[features])

    predictions = model.predict(features_scaled)
    probabilities = model.predict_proba(features_scaled)

    accounts_df["is_bot"] = predictions
    accounts_df["bot_probability"] = probabilities[:, 1]
    accounts_df["human_probability"] = probabilities[:, 0]

    return accounts_df


# Example usage
if __name__ == "__main__":
    # Load model
    print("Loading TikTok bot detection model...")
    model = load_model()
    print("✓ Model loaded successfully!\n")

    # Example 1: Single account prediction
    print("=" * 60)
    print("Example 1: Single Account Prediction")
    print("=" * 60)

    suspicious_account = {
        "IsPrivate": 0,
        "IsVerified": 0,
        "HasProfilePic": 1,
        "FollowingCount": 5000,
        "FollowerCount": 100,
        "HasInstagram": 0,
        "HasYoutube": 0,
        "HasBio": 0,
        "HasLinkInBio": 1,
        "HasPosts": 1,
        "PostsCount": 50,
        "FollowToFollowerRatio": 50.0,
    }

    result = predict_single_account(model, suspicious_account)

    print(f"Account Analysis:")
    print(f"  Following: {suspicious_account['FollowingCount']}")
    print(f"  Followers: {suspicious_account['FollowerCount']}")
    print(f"  Posts: {suspicious_account['PostsCount']}")
    print(f"\nPrediction:")
    print(f"  Is Bot: {result['is_bot']}")
    print(f"  Bot Probability: {result['bot_probability']:.2%}")
    print(f"  Confidence: {result['confidence']:.2%}")

    # Example 2: Batch prediction
    print(f"\n{'='*60}")
    print("Example 2: Batch Prediction")
    print("=" * 60)

    accounts = pd.DataFrame(
        [
            {
                "IsPrivate": 0,
                "IsVerified": 1,
                "HasProfilePic": 1,
                "FollowingCount": 500,
                "FollowerCount": 10000,
                "HasInstagram": 1,
                "HasYoutube": 1,
                "HasBio": 1,
                "HasLinkInBio": 1,
                "HasPosts": 1,
                "PostsCount": 200,
                "FollowToFollowerRatio": 0.05,
            },
            {
                "IsPrivate": 0,
                "IsVerified": 0,
                "HasProfilePic": 0,
                "FollowingCount": 8000,
                "FollowerCount": 50,
                "HasInstagram": 0,
                "HasYoutube": 0,
                "HasBio": 0,
                "HasLinkInBio": 1,
                "HasPosts": 1,
                "PostsCount": 10,
                "FollowToFollowerRatio": 160.0,
            },
        ]
    )

    results = predict_batch(model, accounts.copy())

    print("\nResults:")
    for idx, row in results.iterrows():
        print(f"\nAccount {idx + 1}:")
        print(f"  Followers: {row['FollowerCount']}")
        print(f"  Is Bot: {bool(row['is_bot'])}")
        print(f"  Bot Probability: {row['bot_probability']:.2%}")