def run(self):
encoding_dim = 32
svm=SVM(Input(shape=(encoding_dim,)))
svm.train(self.trainingData,self.trainLabel,self.testData)
ans = svm.test(self.testData)
print("Classification report for classifier %s:n%sn" % (svm.clf, metrics.classification_report(self.testLabel, ans)))
self.printaccuracy(self.testLabel,ans)
def main():
svm = SVM(C=100000, fraction_split=0.7)
fraction_train = float(sys.argv[2])
svm.load_dataset(fraction_train)
svm.train()
accuracy, f1 = svm.test()
return accuracy, f1
def train_and_test(svm,datasets):
testset = datasets['testset']
finaltrainset = datasets['finaltrainset']
svm.train(finaltrainset)
outputs, costs = svm.test(testset)
id_to_class = {}
for label, id in testset.class_to_id.iteritems():
id_to_class[id] = label
# Ground truth
lbl = datasets['ground_truth']
auto_lbl = np.array([int(id_to_class[output[0]]) for output in outputs]) # Predicted labels
len_bg = testset.metadata['len_bg']
lbl = np.append(lbl, [0]*len_bg)
auto_lbl = np.append(auto_lbl, [0]*len_bg)
(dice, jaccard, precision, recall) = compute_statistics.compute_eval_multilabel_metrics(auto_lbl, lbl)
dice = dice[~np.isnan(dice)]
return dice.mean()
def main():
svm = SVM(C=100000, fraction_split=0.7)
svm.load_dataset()
accuracies = []
f1s = []
num_splits = int(sys.argv[2])
kf = KFold(n_splits=num_splits)
split_num = 1
for training_indices, testing_indices in kf.split(svm.dataset):
print("Split {}/{}".format(split_num, num_splits))
svm.update_train_and_test_sets(training_indices, testing_indices)
svm.train()
accuracy, f1 = svm.test()
accuracies.append(accuracy)
f1s.append(f1)
split_num += 1
return stats.mean(accuracies), stats.mean(f1s)
# 读取训练文件
print('load TrainData')
X_train, y_train = loadData('./mnist/mnist_train.csv')
# 读取测试文件
print('load TestData')
X_test, y_test = loadData('./mnist/mnist_test.csv')
print('Init SVM classifier')
svm=SVM(X_train[0:6000],y_train[0:6000])
print('start to train')
svm.train()
print('start to test')
svm.test(X_test[0:400], y_test[0:400])
# clf = svm.SVC()
# clf.fit(X_train[0:6000],y_train[0:6000])
# print(clf.score(X_test[0:400], y_test[0:400]))
# 获取结束时间
end = time.time()
print('run time:', end - start)
def main():
# 入力データのファイルパス
LOAD_INPUT_DATA_PATH = "/Users/panzer5/github/sample/python/scikit/svm/ex4_data/train.csv"
# 学習済みモデルデータの出力先パス
SAVE_TRAINED_DATA_PATH = '/Users/panzer5/github/sample/python/scikit/svm/ex4_data/train.learn'
# テストデータのファイルパス
LOAD_TEST_DATA_PATH = "/Users/panzer5/github/sample/python/scikit/svm/ex4_data/test.csv"
# グラフ出力先パス
SAVE_GRAPH_IMG_PATH = '/Users/panzer5/github/sample/python/scikit/svm/ex4_data/graph.png'
# 説明変数の列名
NAME_X = ["x1", "x2"]
# 目的変数の列名
NAME_Y = "x3"
# SVMのパラメータ
GAMMA = 0.1
C = 1
KERNEL = "rbf"
# クラスのデータとプロット時に割り当てる色
CLASS_DATAS = [0, 1, 2]
CLASS_COLORS = ["blue", "red", "green"]
svm = SVM()
# 学習済みモデルの作成
svm.train(load_input_data_path=LOAD_INPUT_DATA_PATH,
save_trained_data_path=SAVE_TRAINED_DATA_PATH,
name_x=NAME_X,
name_y=NAME_Y,
gamma=GAMMA,
C=C,
kernel=KERNEL)
# 学習済みモデルの検証
svm.test(load_trained_data_path=SAVE_TRAINED_DATA_PATH,
load_test_data_path=LOAD_TEST_DATA_PATH,
name_x=NAME_X,
name_y=NAME_Y)
# 未知データを入力して予測
"""
svm.test(
load_trained_data_path = SAVE_TRAINED_DATA_PATH,
load_input_data_path = LOAD_INPUT_DATA_PATH,
name_x = NAME_X,
name_y = NAME_Y)
"""
# グラフにプロットして決定境界を可視化
svm.plot2d(
load_input_data_path=LOAD_INPUT_DATA_PATH,
load_trained_data_path=SAVE_TRAINED_DATA_PATH,
save_graph_img_path=SAVE_GRAPH_IMG_PATH,
class_datas=CLASS_DATAS,
class_colors=CLASS_COLORS,
name_x=NAME_X,
name_y=NAME_Y,
x1_name="x1",
x2_name="x2",
fig_size_x=10,
fig_size_y=10,
lim_font_size=25,
)
def main():
# 学習済みモデルデータの出力先パス
SAVE_TRAINED_DATA_PATH = 'C:/github/sample/python/scikit/svm/ex6_data/train.learn'
# テスト用の画像データ（ペイントソフトで2と書いて保存したもの）
LOAD_TEST_IMG_PATH = 'C:/github/sample/python/scikit/svm/ex6_data/test_2.png'
# SVMのパラメータ
GAMMA = 0.1
C = 1
KERNEL = "linear" # 手書き数字画像の場合はrbfだと学習結果が悪い
svm = SVM()
# 学習用のデータを読み込み(Digitsデータセットを利用)
digits_dataset = datasets.load_digits()
# 説明変数（学習データ：手書き数字の画像データ8*8, 2次元配列）を抽出
X = digits_dataset.images
print("X1:", X[1])
# 目的変数：数字（0～9）
y = digits_dataset.target
# xの二次元配列を１次元に変換(-1で変換元の要素数に合わせて自動で値が決定：変換前要素数=変換後要素数となる）
X = X.reshape((-1, 64))
# 説明変数のデータを、学習用データと検証用データに分割(学習用90%、検証用10％、シャッフルする)
train_X, test_X, train_y, test_y = train_test_split(X,
y,
test_size=0.2,
shuffle=True)
print("train_X size:", train_X.shape)
print("train_y size:", train_y.shape)
print("test_X size:", test_X.shape)
print("test_y size:", test_y.shape)
# 学習済みモデルの作成
svm.train(save_trained_data_path=SAVE_TRAINED_DATA_PATH,
train_X=train_X,
train_y=train_y,
gamma=GAMMA,
C=C,
kernel=KERNEL)
# 学習済みモデルの検証
svm.test(load_trained_data_path=SAVE_TRAINED_DATA_PATH,
test_X=test_X,
test_y=test_y)
# 学習済みモデルを使って予測
# OpenCVで任意の手書き数字画像をロードし,
# グレースケール変換, 、白黒反転
# 8*8にリサイズ, 1次元配列に変換,
# 値を0～16に収めてモデルに入力
test_img = cv2.imread(LOAD_TEST_IMG_PATH)
test_gray = cv2.cvtColor(test_img, cv2.COLOR_BGR2GRAY)
test_gray = cv2.bitwise_not(test_gray)
test_gray = cv2.resize(test_gray, (8, 8))
test_gray = test_gray.reshape(-1, 64)
test_gray = np.clip(test_gray, 0, 16)
predict_y = svm.predict(load_trained_data_path=SAVE_TRAINED_DATA_PATH,
test_X=test_gray)
print("test_X:", test_gray)
print("predict_y:", predict_y)
"""
self.X_test = []
self.Y_test = []
self.X_test, self.Y_test = get_x_y(self.test_data)
#print(self.X_test)
self.svm = svm.SVR()
def train(self):
self.svm = self.svm.fit(self.X_train, self.Y_train)
def test(self):
RMSE = 0
N = len(self.Y_test)
for i in range(N):
y = self.svm.predict([self.X_test[i]])
y_hat = self.Y_test[i]
RMSE += ((float(y[0]) - y_hat) ** 2)
RMSE = (RMSE / N) ** 0.5
print(RMSE)
return RMSE
svm = SVM('train.csv', 'test.csv')
svm.train()
svm.test()
def main():
# 学習済みモデルデータの出力先パス
SAVE_TRAINED_DATA_PATH = '/Users/panzer5/github/sample/python/scikit/svm/ex5_data/train.learn'
# グラフ出力先パス
SAVE_GRAPH_IMG_PATH = '/Users/panzer5/github/sample/python/scikit/svm/ex5_data/graph_x2_x3.png'
# SVMのパラメータ
GAMMA = 0.1
C = 1
KERNEL = "rbf"
# クラスのデータとプロット時に割り当てる色
CLASS_DATAS = [0, 1, 2]
CLASS_COLORS = ["blue", "red", "green"]
svm = SVM()
# 学習用のデータを読み込み(Irisデータセットを利用)
iris_dataset = load_iris()
# 説明変数（学習データ）を抽出
X = iris_dataset.data
# 目的変数：アヤメの品種（'setosa'=0 'versicolor'=1 'virginica'=2）
y = iris_dataset.target
X1 = np.vstack((X[:, :1])) #sepal length(ガクの長さ)を取得
X2 = np.vstack((X[:, 1:2])) #sepal width(ガクの幅)を取得
X3 = np.vstack((X[:, 2:3])) #petal length(花弁の長さ)を取得
X4 = np.vstack((X[:, 3:4])) #petal width(花弁の幅)を取得
# 学習に使用する説明変数を選択
X = np.hstack((X1, X2, X3, X4))
#X = np.hstack((X1, X2))
#X = np.hstack((X2, X3))
#X = np.hstack((X3, X4))
# 説明変数のデータを、学習用データと検証用データに分割(学習用90%、検証用10％、シャッフルする)
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.1, shuffle=True)
print("train_X size:", train_X.shape)
print("train_y size:", train_y.shape)
print("test_X size:", test_X.shape)
print("test_y size:", test_y.shape)
# 学習済みモデルの作成
svm.train(save_trained_data_path = SAVE_TRAINED_DATA_PATH,
train_X=train_X,
train_y=train_y,
gamma = GAMMA,
C = C,
kernel = KERNEL)
# 学習済みモデルの検証
svm.test(
load_trained_data_path = SAVE_TRAINED_DATA_PATH,
test_X=test_X,
test_y=test_y)
# 学習済みモデルを使って予測
predict_y = svm.predict(
load_trained_data_path = SAVE_TRAINED_DATA_PATH,
test_X=test_X)
print("test_X:", test_X)
print("predict_y:", predict_y)
"""
# グラフにプロットして決定境界を可視化(説明変数２つで学習したときのみ利用可能)
svm.plot2d(load_trained_data_path = SAVE_TRAINED_DATA_PATH,
save_graph_img_path = SAVE_GRAPH_IMG_PATH,
train_X=train_X,
train_y=train_y,
class_datas = CLASS_DATAS,
class_colors = CLASS_COLORS,
x1_name = "x2",
x2_name = "x3",
fig_size_x = 10,
fig_size_y = 10,
lim_font_size = 25,
)
"""
"""