# read training info
digit_train_set = pd.read_csv(csv_filename)
image_info = DisplayImage(csv_filename)
digit_train_set = image_info.get_all_info()
# separate training info into samples and target
samples_v1 = digit_train_set[:, 1]
target = digit_train_set[:, 0]
target = target.astype(int)
# print(type(target[0]))
# print(target)
# exit(0)
samples_v2 = list(map(lambda v: np.reshape(v, (-1)), samples_v1))
samples_v3 = image_info.circle_info_arr(samples_v2, samples_v1)
x_train, x_test_before, y_train, y_test = train_test_split(samples_v3,
target,
test_size=0.2,
random_state=10)
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
x_train = scaler.fit_transform(x_train)
x_test = scaler.transform(x_test_before)
from sklearn.decomposition import PCA
model_pca = PCA(0.80)
x_train = model_pca.fit_transform(x_train)
x_test = model_pca.transform(x_test)
# read testing info digit_test_set = pd.read_csv(test_csv_filename) test_samples_v1 = digit_test_set.values # separate training info into samples and target train_samples_v1 = digit_train_set[:, 1] target = digit_train_set[:, 0] target = target.astype(int) train_samples_v2 = list(map(lambda v: np.reshape(v, (-1)), train_samples_v1)) train_samples_v3 = image_info.circle_info_arr(train_samples_v2, train_samples_v1) test_samples_v2 = list(map(lambda v: np.reshape(v, (28, -1, 1)), test_samples_v1)) test_samples_v2 = list(map(lambda v: v.astype(np.uint8), test_samples_v2)) test_samples_v3 = image_info.circle_info_arr(test_samples_v1, test_samples_v2) from sklearn.preprocessing import StandardScaler scaler = StandardScaler() x_train = scaler.fit_transform(train_samples_v3) x_test = scaler.transform(test_samples_v3)
