Delete src/data_preperation.py

src/data_preperation.py

@@ -1,57 +0,0 @@
-from src import utils
-import numpy as np
-import os
-
-
-def main(in_dir: str, out_dir: str, size: tuple, stride: tuple, classes: list):
-    # Read all files in the in_dir
-    files = os.listdir(in_dir)
-
-    # Create the out_dir if it does not exist
-    if not os.path.exists(out_dir):
-        os.makedirs(out_dir)
-
-    dataset = []
-    # Loop through all files in the in_dir
-    for file in files:
-        # apply the sliding window method to each file
-        imgs = os.listdir(in_dir + file)
-        for img in imgs:
-            path = in_dir + file + "/" + img
-            data, _ = utils.sliding_window(path, window_size=size, stride=stride)
-
-            for x in data:
-                dataset.append((np.array(x[0]), classes.index(file)))
-
-    # Split the dataset into training, validation, and test sets
-    train, val, test = utils.split_data(dataset, 0.7, 0.1, 0.2)
-    utils.plot_distribution(
-        train, val, test, classes, title="Data Distribution Before Balancing"
-    )
-
-    # Balance the dataset
-    train, excess_data = utils.balance_data(train)
-    test += excess_data
-    utils.plot_distribution(
-        train, val, test, classes, title="Data Distribution After Balancing"
-    )
-
-    # Shuffle the data
-    train = utils.shuffle_data(train)
-    val = utils.shuffle_data(val)
-    test = utils.shuffle_data(test)
-
-    # Pickle the data
-    utils.save_to_pickle(train, out_dir + "/train.pkl")
-    utils.save_to_pickle(val, out_dir + "/val.pkl")
-    utils.save_to_pickle(test, out_dir + "/test.pkl")
-
-
-if __name__ == "__main__":
-    main(
-        in_dir="raw_data/high_res/",
-        out_dir="data/high_res/",
-        size=(224, 224),
-        stride=(224, 224),
-        classes=["formal", "informal"],
-    )