def getdataset(datasetname, onehot_encode_strings=True):
# load
dataset = fetch_mldata(datasetname)
# get X and y
X = dshape(dataset.data)
try:
target = dshape(dataset.target)
except:
print("WARNING: No target found. Taking last column of data matrix as target")
target = X[:, -1]
X = X[:, :-1]
if len(target.shape) > 1 and target.shape[1] > X.shape[1]: # some mldata sets are mixed up...
X = target
target = dshape(dataset.data)
if len(X.shape) == 1 or X.shape[1] <= 1:
for k in dataset.keys():
if k != 'data' and k != 'target' and len(dataset[k]) == X.shape[1]:
X = np.hstack((X, dshape(dataset[k])))
# one-hot for categorical values
if onehot_encode_strings:
cat_ft = [i for i in range(X.shape[1]) if 'str' in str(
type(unpack(X[0, i]))) or 'unicode' in str(type(unpack(X[0, i])))]
if len(cat_ft):
for i in cat_ft:
X[:, i] = tonumeric(X[:, i])
X = OneHotEncoder(categorical_features=cat_ft).fit_transform(X)
# if sparse, make dense
try:
X = X.toarray()
except:
pass
# convert y to monotonically increasing ints
y = tonumeric(target).astype(int)
return np.nan_to_num(X.astype(float)), y
def single_output_multiclass_one_hot():
y = np.random.randint(low=0, high=3, size=(1000,))
X = y.reshape(-1, 1)
# For compatibility with Keras, accept one-hot-encoded inputs
# with categorical_crossentropy loss
y = OneHotEncoder(sparse=False).fit_transform(y.reshape(-1, 1))
sklearn_est = MLPClassifier(**mlp_kwargs)
scikeras_est = KerasClassifier(
create_model("softmax", [3]), **scikeras_kwargs, loss="categorical_crossentropy"
)
for dtype in ("float32", "float64", "int64", "int32", "uint8", "uint16"):
y_ = y.astype(dtype)
yield TestParams(
sklearn_est=sklearn_est,
scikeras_est=scikeras_est,
X=X,
y=y_,
X_expected_dtype_keras=X.dtype,
y_expected_dtype_keras=tf.keras.backend.floatx(),
min_score=0.95,
scorer=accuracy_score,
)
# one-hot encoding of the dependent variable
y_eval = OneHotEncoder().fit_transform(y_eval.reshape(-1,1)) # it's a scipy.sparse.csr.csr_mat
y_eval = y_eval.toarray() # converting to ndarray
# accuracy on eval dataset
with tf.Session() as sess:
# as 46th step gives the best result
saver = tf.train.import_meta_graph('./model_ae_fc_1_2/ae_99.8_fc-46.meta')
saver.restore(sess,'./model_ae_fc_1_2/ae_99.8_fc-46')
graph = tf.get_default_graph()
y_ph = graph.get_tensor_by_name('Placeholders/Y_ph:0')
x_ph = graph.get_tensor_by_name('Placeholders/X_ph:0')
logits = graph.get_tensor_by_name('output_layer/Add:0')
correct_pred = tf.equal(tf.math.argmax(logits,axis=1),tf.math.argmax(y_ph,axis=1))
acc = tf.reduce_mean(tf.cast(correct_pred,'float'))
feed_eval = {}
X_eval_scaled = sc.transform(x_eval) #scaling the eval set
feed_eval[x_ph] = X_eval_scaled.astype(np.float32)
feed_eval[y_ph] = y_eval.astype(np.float32)
print("Accuracy for the 40% unseen data is : ", acc.eval(feed_eval))
# In[1]: import numpy as np from sklearn.datasets import load_iris iris = load_iris() X = iris.data.astype(np.float32) y_true = iris.target.astype(np.int32) # In[2]: from sklearn.preprocessing import OneHotEncoder y_onehot = OneHotEncoder().fit_transform(y_true.reshape(-1, 1)) y_onehot = y_onehot.astype(np.int64).todense() # In[4]: # divide data into test set and training set from sklearn.cross_validation import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y_onehot, random_state=14) # In[5]: input_layer_size, hidden_layer_size, output_layer_size = 4, 6, 3 # In[7]:
import os
import numpy as np
batches = []
for i in range(1, 6):
batch_filename = os.path.join(data_folder,
'data_batch_{}'.format(i)) #导入 1-6
batches.append(unpickle(batch_filename))
X = np.vstack([batch['data'] for batch in batches])
X = np.array(X) / X.max()
X = X.astype(np.float32)
from sklearn.preprocessing import OneHotEncoder
y = np.hstack(batch['labels'] for batch in batches).flatten()
y = OneHotEncoder().fit_transform(y.reshape(y.shape[0], 1)).todense()
y = y.astype(np.float32)
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
X_train = X_train.reshape(-1, 3, 32, 32)
X_test = X_test.reshape(-1, 3, 32, 32) #reshape(-1,...) 计算完后面维度后自动生成 -1
#bulid
from lasagne import layers
layers = [
('input', layers.InputLayer),
('conv1', layers.Conv2DLayer),
('pool1', layers.MaxPool2DLayer),
('conv2', layers.Conv2DLayer),
('pool2', layers.MaxPool2DLayer),