# -*- coding: utf-8 -*-
# This code is part of Qiskit.
#
# (C) Copyright IBM 2018, 2020.
#
# This code is licensed under the Apache License, Version 2.0. You may
# obtain a copy of this license in the LICENSE.txt file in the root directory
# of this source tree or at http://www.apache.org/licenses/LICENSE-2.0.
#
# Any modifications or derivative works of this code must retain this
# copyright notice, and modified files need to carry a notice indicating
# that they have been altered from the originals.
"""
digits dataset
"""
import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, MinMaxScaler
from sklearn.decomposition import PCA
[docs]def digits(training_size, test_size, n, plot_data=False):
""" returns digits dataset """
class_labels = [r'A', r'B', r'C', r'D', r'E', r'F', r'G', r'H', r'I', r'J']
data = datasets.load_digits()
# pylint: disable=no-member
sample_train, sample_test, label_train, label_test = train_test_split(
data.data, data.target, test_size=0.3, random_state=22)
# Now we standardize for gaussian around 0 with unit variance
std_scale = StandardScaler().fit(sample_train)
sample_train = std_scale.transform(sample_train)
sample_test = std_scale.transform(sample_test)
# Now reduce number of features to number of qubits
pca = PCA(n_components=n).fit(sample_train)
sample_train = pca.transform(sample_train)
sample_test = pca.transform(sample_test)
# Scale to the range (-1,+1)
samples = np.append(sample_train, sample_test, axis=0)
minmax_scale = MinMaxScaler((-1, 1)).fit(samples)
sample_train = minmax_scale.transform(sample_train)
sample_test = minmax_scale.transform(sample_test)
# Pick training size number of samples from each distro
training_input = {key: (sample_train[label_train == k, :])[:training_size]
for k, key in enumerate(class_labels)}
test_input = {key: (sample_test[label_test == k, :])[:test_size]
for k, key in enumerate(class_labels)}
if plot_data:
try:
import matplotlib.pyplot as plt
except ImportError:
raise NameError('Matplotlib not installed. Please install it before plotting')
for k in range(0, 9):
plt.scatter(sample_train[label_train == k, 0][:training_size],
sample_train[label_train == k, 1][:training_size])
plt.title("PCA dim. reduced Digits dataset")
plt.show()
return sample_train, training_input, test_input, class_labels