Untitled

import os
import numpy as np
import pandas as pd
import xgboost as xgb
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from tqdm import tqdm  # For progress tracking

"""
 Mr. Doo, assume this is the folder that contains only those 10 aircraft signals
 
 data/
│── aircraft_1/
│   ├── signal_1.iq
│   ├── signal_2.iq
│── aircraft_2/
│   ├── signal_3.iq
│   ├── signal_4.iq
│── aircraft_3/
│   ├── signal_5.iq
|   ...
|__ aircraft_10/
    |── signal_x.iq
...
"""

def read_iq_file(filename):
    """ Reads IQ binary file and normalizes I and Q values. """
    with open(filename, "rb") as f:
        data = np.frombuffer(f.read(), dtype=np.uint8)
    
    I = data[0::2].astype(np.float32)
    Q = data[1::2].astype(np.float32)
    
    # Normalize values (-1 to 1)
    I = (I - 128) / 128.0
    Q = (Q - 128) / 128.0

    return I, Q


def compute_featues(I, Q):
    """
        Shared previously
    """
    pass

# === Function to Process All IQ Files ===
def process_iq_folder(dataset_path):
    """ Scans a folder structure <class_name>/file.iq and extracts features. """
    data = []
    labels = []
    
    for class_name in tqdm(os.listdir(dataset_path), desc="Processing Classes"):
        class_path = os.path.join(dataset_path, class_name)
        if not os.path.isdir(class_path):
            continue  # Skip non-directory files
        
        for file_name in os.listdir(class_path):
            if file_name.endswith(".iq"):
                file_path = os.path.join(class_path, file_name)
                try:
                    I, Q = read_iq_file(file_path)
                    features = compute_features(I, Q)
                    data.append(features)
                    labels.append(class_name)
                except Exception as e:
                    print(f"Error processing {file_path}: {e}")

    return pd.DataFrame(data), labels

# === Run Feature Extraction ===
dataset_path = "data"  # Path to the dataset folder
X, y = process_iq_folder(dataset_path)

# === Encode Labels ===
label_encoder = LabelEncoder()
y_encoded = label_encoder.fit_transform(y)  # Converts class names into numbers

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

# === Train XGBoost Classifier ===
xgb_classifier = xgb.XGBClassifier(
    objective="multi:softmax",
    num_class=len(np.unique(y_encoded)),
    eval_metric="mlogloss",
    max_depth=6,
    learning_rate=0.1,
    n_estimators=100,
    use_label_encoder=False
)

xgb_classifier.fit(X_train, y_train)

# === Model Evaluation ===
y_pred = xgb_classifier.predict(X_test)
accuracy = np.mean(y_pred == y_test)
print(f"Model Accuracy: {accuracy:.4f}")