regularisation_old.py

# import the necessary packages
from sklearn.linear_model import SGDClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from pyimagesearch.preprocessing import SimplePreprocessor
from pyimagesearch.datasets import SimpleDatasetLoader
from imutils import paths
import argparse

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-d","--dataset", required=True,
    help="path to input dataset")

# grab the list of image paths
print("[INFO] loading images...")
args = vars(ap.parse_args())
imagePaths = list(paths.list_images(args["dataset"]))


# init image preprocessor, load the data set from disk
# and reshape the matrix
sp = SimplePreprocessor(32,32)
sdl = SimpleDatasetLoader(preprocessors=[sp])
(data, labels) = sdl.load(imagePaths, verbose=500)
data = data.reshape((data.shape[0],3072))

# encode the labels as integers
le = LabelEncoder()
labels = le.fit_transform(labels)

# partition the data to training , testing splits using 75% of data
# for training and balance 25% for testing
(trainX,testX,trainY,testY) = train_test_split(data, labels,
    test_size=0.25, random_state=42)

# loop over out set of regularisers
for r in (None, "l1", "l2"):
    # train a SGD classifier using softmax loss function and the
    # specified regularisation function for 10 epochs
    print("[INFO] training model with '{}' penaly".format(r))
    model = SGDClassifier(loss ="log", penalty=r, max_iter=10,
        learning_rate="constant", eta0=0.01, random_state=42)
    model.fit(trainX,trainY)

    # evaluate classifier
    acc = model.score(testX,testY)
    print("[INFO] '{}' penalty accuracy: {:.2f}%".format(r,acc*100))