import numpy as np
import json

def get_data_from_json() -> np.ndarray:
    with open('cattle_log.json', 'r') as file:
        log_content = json.load(file)['logs']

    X = []

    # Iterate over each log entry in the log_content
    for log_entry in log_content:
        # Extract and convert the necessary attributes
        total_today_str = log_entry['distanceTraveled']['totalToday'].rstrip('m')
        heart_rate = int(log_entry['healthData']['heartRate'])  # Assuming heart rate is always an integer
        weight_str = log_entry['healthData']['weight'].rstrip('kg')
        
        # Convert the distance and weight to floating-point values
        total_today = float(total_today_str)  # Convert distance to float
        weight = float(weight_str)  # Convert weight to float
        
        # Create a 3D vector for the current log entry and append it to the list of vectors
        vector_3d = [total_today, heart_rate, weight]
        X.append(vector_3d)

    # Convert X into a NumPy array for easier slicing
    X = np.array(X)
    return X


def generate_random_data(num_dimensions, rng) -> np.ndarray:
    # Generating a dataset with 100 points. 95 points are generated from a Gaussian distribution,
    # and 5 points are anomalies added manually.
    X = 0.3 * rng.randn(95, num_dimensions)
    X = np.r_[X + 2, X - 2]
    X_outliers = rng.uniform(low=-4, high=4, size=(5, num_dimensions))
    X = np.r_[X, X_outliers]
    return X