tests.test_packages.test_catboost() - Code Metrics - Inspection of "rm opt-dev from dev-branch" - SimonBlanke/Hyperactive - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 61a8e6...a7d091 )

by Simon

created 2019-10-27 13:44 UTC

tests.test_packages.test_catboost() A

↳ Parent: tests.test_packages

Complexity

Conditions

Size

Total Lines	23
Code Lines	16

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	16
dl	0
loc	23
rs	9.6
c	0
b	0
f	0
cc	1
nop	0

# Author: Simon Blanke
# Email: [email protected]
# License: MIT License

from sklearn.datasets import load_breast_cancer

from sklearn.model_selection import cross_val_score
from hyperactive import Hyperactive

data = load_breast_cancer()
X, y = data.data, data.target


def test_meta_learn():

    from sklearn.tree import DecisionTreeClassifier

    def model(para, X_train, y_train):
        model = DecisionTreeClassifier(
            criterion=para["criterion"],
            max_depth=para["max_depth"],
            min_samples_split=para["min_samples_split"],
            min_samples_leaf=para["min_samples_leaf"],
        )
        scores = cross_val_score(model, X_train, y_train, cv=3)

        return scores.mean()

    search_config = {
        model: {
            "criterion": ["gini", "entropy"],
            "max_depth": range(1, 21),
            "min_samples_split": range(2, 21),
            "min_samples_leaf": range(1, 21),
        }
    }

    opt = Hyperactive(search_config, meta_learn=True)
    opt.search(X, y)


def test_sklearn():

    from sklearn.tree import DecisionTreeClassifier

    def model(para, X_train, y_train):
        model = DecisionTreeClassifier(
            criterion=para["criterion"],
            max_depth=para["max_depth"],
            min_samples_split=para["min_samples_split"],
            min_samples_leaf=para["min_samples_leaf"],
        )
        scores = cross_val_score(model, X_train, y_train, cv=3)

        return scores.mean()

    search_config = {
        model: {
            "criterion": ["gini", "entropy"],
            "max_depth": range(1, 21),
            "min_samples_split": range(2, 21),
            "min_samples_leaf": range(1, 21),
        }
    }

    opt = Hyperactive(search_config)
    opt.search(X, y)
    # opt.predict(X)
    # opt.score(X, y)


def test_xgboost():
    from xgboost import XGBClassifier

    def model(para, X_train, y_train):
        model = XGBClassifier(
            n_estimators=para["n_estimators"], max_depth=para["max_depth"]
        )
        scores = cross_val_score(model, X_train, y_train, cv=3)

        return scores.mean()

    search_config = {model: {"n_estimators": range(2, 20), "max_depth": range(1, 11)}}

    opt = Hyperactive(search_config)
    opt.search(X, y)
    # opt.predict(X)
    # opt.score(X, y)


def test_lightgbm():
    from lightgbm import LGBMClassifier

    def model(para, X_train, y_train):
        model = LGBMClassifier(
            num_leaves=para["num_leaves"], learning_rate=para["learning_rate"]
        )
        scores = cross_val_score(model, X_train, y_train, cv=3)

        return scores.mean()

    search_config = {
        model: {
            "num_leaves": range(2, 20),
            "learning_rate": [0.001, 0.005, 00.01, 0.05, 0.1, 0.5, 1],
        }
    }

    opt = Hyperactive(search_config)
    opt.search(X, y)
    # opt.predict(X)
    # opt.score(X, y)


def test_catboost():
    from catboost import CatBoostClassifier

    def model(para, X_train, y_train):
        model = CatBoostClassifier(
            iterations=para["iterations"],
            depth=para["depth"],
            learning_rate=para["learning_rate"],
        )
        scores = cross_val_score(model, X_train, y_train, cv=3)

        return scores.mean()

    search_config = {
        model: {
            "iterations": [1],
            "depth": range(2, 10),
            "learning_rate": [0.001, 0.005, 00.01, 0.05, 0.1, 0.5, 1],
        }
    }

    opt = Hyperactive(search_config)
    opt.search(X, y)
    # opt.predict(X)
    # opt.score(X, y)


def test_keras():
    from keras.models import Sequential
    from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten
    from keras.datasets import cifar10
    from keras.utils import to_categorical

    (X_train, y_train), (X_test, y_test) = cifar10.load_data()

    X_train = X_train[0:1000]
    y_train = y_train[0:1000]

    X_test = X_train[0:1000]
    y_test = y_train[0:1000]

    y_train = to_categorical(y_train, 10)
    y_test = to_categorical(y_test, 10)

    def cnn(para, X_train, y_train):
        model = Sequential()

        model.add(
            Conv2D(
                filters=para["filters.0"],
                kernel_size=para["kernel_size.0"],
                activation="relu",
            )
        )
        model.add(MaxPooling2D(pool_size=(2, 2)))

        model.add(Flatten())
        model.add(Dense(10, activation="softmax"))

        model.compile(
            optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"]
        )
        model.fit(X_train, y_train, epochs=1)

        loss, score = model.evaluate(x=X_test, y=y_test)

        return score

    search_config = {cnn: {"filters.0": [32, 64], "kernel_size.0": [3, 4]}}

    opt = Hyperactive(search_config)
    opt.search(X_train, y_train)
    # opt.predict(X)
    # opt.score(X, y)


"""
def test_pytorch():
    import torch
    import torchvision
    import torchvision.transforms as transforms
    import torch.nn as nn
    import torch.nn.functional as F
    import torch.optim as optim

    transform = transforms.Compose(
        [transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
    )

    trainset = torchvision.datasets.CIFAR10(
        root="./data", train=True, download=True, transform=transform
    )

    def cnn(para, X_train, y_train):
        class Net(nn.Module):
            def __init__(self):
                super(Net, self).__init__()
                self.conv1 = nn.Conv2d(3, 6, 5)
                self.pool = nn.MaxPool2d(2, 2)
                self.conv2 = nn.Conv2d(6, 16, 5)
                self.fc1 = nn.Linear(16 * 5 * 5, 120)
                self.fc2 = nn.Linear(120, 84)
                self.fc3 = nn.Linear(84, 10)

            def forward(self, x):
                x = self.pool(F.relu(self.conv1(x)))
                x = self.pool(F.relu(self.conv2(x)))
                x = x.view(-1, 16 * 5 * 5)
                x = F.relu(self.fc1(x))
                x = F.relu(self.fc2(x))
                x = self.fc3(x)
                return x

        trainloader = torch.utils.data.DataLoader(
            trainset, batch_size=4, shuffle=True, num_workers=2
        )

        net = Net()

        criterion = nn.CrossEntropyLoss()
        optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

        for epoch in range(1):  # loop over the dataset multiple times

            running_loss = 0.0
            for i, data in enumerate(trainloader, 0):
                # get the inputs; data is a list of [inputs, labels]
                inputs, labels = data

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward + backward + optimize
                outputs = net(inputs)
                loss = criterion(outputs, labels)
                loss.backward()
                optimizer.step()

                # print statistics
                running_loss += loss.item()
                if i % 2000 == 1999:  # print every 2000 mini-batches
                    print(
                        "[%d, %5d] loss: %.3f" % (epoch + 1, i + 1, running_loss / 2000)
                    )
                    running_loss = 0.0

        return running_loss

    search_config = {cnn: {"filters.0": [32, 64], "kernel_size.0": [3, 4]}}

    opt = Hyperactive(search_config)
    opt.search(None, None)
    # opt.predict(X)
    # opt.score(X, y)



def test_chainer():
    def cnn(para, X_train, y_train):
        pass

    search_config = {cnn: {"filters.0": [32, 64], "kernel_size.0": [3, 4]}}
    opt = Hyperactive(search_config)
    opt.search(None, None)
    # opt.predict(X)
    # opt.score(X, y)
"""


1		# Author: Simon Blanke
2		# Email: [email protected]
3		# License: MIT License
4
5		from sklearn.datasets import load_breast_cancer
6
7		from sklearn.model_selection import cross_val_score
8		from hyperactive import Hyperactive
9
10		data = load_breast_cancer()
11		X, y = data.data, data.target
12
13
14	View Code Duplication	def test_meta_learn():
		0 ignored issues – show Duplication introduced 2019-10-27 13:47 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
15		from sklearn.tree import DecisionTreeClassifier
16
17		def model(para, X_train, y_train):
18		model = DecisionTreeClassifier(
19		criterion=para["criterion"],
20		max_depth=para["max_depth"],
21		min_samples_split=para["min_samples_split"],
22		min_samples_leaf=para["min_samples_leaf"],
23		)
24		scores = cross_val_score(model, X_train, y_train, cv=3)
25
26		return scores.mean()
27
28		search_config = {
29		model: {
30		"criterion": ["gini", "entropy"],
31		"max_depth": range(1, 21),
32		"min_samples_split": range(2, 21),
33		"min_samples_leaf": range(1, 21),
34		}
35		}
36
37		opt = Hyperactive(search_config, meta_learn=True)
38		opt.search(X, y)
39
40
41	View Code Duplication	def test_sklearn():
		0 ignored issues – show Duplication introduced 2019-10-27 13:47 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
42		from sklearn.tree import DecisionTreeClassifier
43
44		def model(para, X_train, y_train):
45		model = DecisionTreeClassifier(
46		criterion=para["criterion"],
47		max_depth=para["max_depth"],
48		min_samples_split=para["min_samples_split"],
49		min_samples_leaf=para["min_samples_leaf"],
50		)
51		scores = cross_val_score(model, X_train, y_train, cv=3)
52
53		return scores.mean()
54
55		search_config = {
56		model: {
57		"criterion": ["gini", "entropy"],
58		"max_depth": range(1, 21),
59		"min_samples_split": range(2, 21),
60		"min_samples_leaf": range(1, 21),
61		}
62		}
63
64		opt = Hyperactive(search_config)
65		opt.search(X, y)
66		# opt.predict(X)
67		# opt.score(X, y)
68
69
70		def test_xgboost():
71		from xgboost import XGBClassifier
72
73		def model(para, X_train, y_train):
74		model = XGBClassifier(
75		n_estimators=para["n_estimators"], max_depth=para["max_depth"]
76		)
77		scores = cross_val_score(model, X_train, y_train, cv=3)
78
79		return scores.mean()
80
81		search_config = {model: {"n_estimators": range(2, 20), "max_depth": range(1, 11)}}
82
83		opt = Hyperactive(search_config)
84		opt.search(X, y)
85		# opt.predict(X)
86		# opt.score(X, y)
87
88
89		def test_lightgbm():
90		from lightgbm import LGBMClassifier
91
92		def model(para, X_train, y_train):
93		model = LGBMClassifier(
94		num_leaves=para["num_leaves"], learning_rate=para["learning_rate"]
95		)
96		scores = cross_val_score(model, X_train, y_train, cv=3)
97
98		return scores.mean()
99
100		search_config = {
101		model: {
102		"num_leaves": range(2, 20),
103		"learning_rate": [0.001, 0.005, 00.01, 0.05, 0.1, 0.5, 1],
104		}
105		}
106
107		opt = Hyperactive(search_config)
108		opt.search(X, y)
109		# opt.predict(X)
110		# opt.score(X, y)
111
112
113		def test_catboost():
114		from catboost import CatBoostClassifier
115
116		def model(para, X_train, y_train):
117		model = CatBoostClassifier(
118		iterations=para["iterations"],
119		depth=para["depth"],
120		learning_rate=para["learning_rate"],
121		)
122		scores = cross_val_score(model, X_train, y_train, cv=3)
123
124		return scores.mean()
125
126		search_config = {
127		model: {
128		"iterations": [1],
129		"depth": range(2, 10),
130		"learning_rate": [0.001, 0.005, 00.01, 0.05, 0.1, 0.5, 1],
131		}
132		}
133
134		opt = Hyperactive(search_config)
135		opt.search(X, y)
136		# opt.predict(X)
137		# opt.score(X, y)
138
139
140		def test_keras():
141		from keras.models import Sequential
142		from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten
143		from keras.datasets import cifar10
144		from keras.utils import to_categorical
145
146		(X_train, y_train), (X_test, y_test) = cifar10.load_data()
147
148		X_train = X_train[0:1000]
149		y_train = y_train[0:1000]
150
151		X_test = X_train[0:1000]
152		y_test = y_train[0:1000]
153
154		y_train = to_categorical(y_train, 10)
155		y_test = to_categorical(y_test, 10)
156
157		def cnn(para, X_train, y_train):
158		model = Sequential()
159
160		model.add(
161		Conv2D(
162		filters=para["filters.0"],
163		kernel_size=para["kernel_size.0"],
164		activation="relu",
165		)
166		)
167		model.add(MaxPooling2D(pool_size=(2, 2)))
168
169		model.add(Flatten())
170		model.add(Dense(10, activation="softmax"))
171
172		model.compile(
173		optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"]
174		)
175		model.fit(X_train, y_train, epochs=1)
176
177		loss, score = model.evaluate(x=X_test, y=y_test)
178
179		return score
180
181		search_config = {cnn: {"filters.0": [32, 64], "kernel_size.0": [3, 4]}}
182
183		opt = Hyperactive(search_config)
184		opt.search(X_train, y_train)
185		# opt.predict(X)
186		# opt.score(X, y)
187
188
189		"""
190		def test_pytorch():
191		import torch
192		import torchvision
193		import torchvision.transforms as transforms
194		import torch.nn as nn
195		import torch.nn.functional as F
196		import torch.optim as optim
197
198		transform = transforms.Compose(
199		[transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
200		)
201
202		trainset = torchvision.datasets.CIFAR10(
203		root="./data", train=True, download=True, transform=transform
204		)
205
206		def cnn(para, X_train, y_train):
207		class Net(nn.Module):
208		def __init__(self):
209		super(Net, self).__init__()
210		self.conv1 = nn.Conv2d(3, 6, 5)
211		self.pool = nn.MaxPool2d(2, 2)
212		self.conv2 = nn.Conv2d(6, 16, 5)
213		self.fc1 = nn.Linear(16 * 5 * 5, 120)
214		self.fc2 = nn.Linear(120, 84)
215		self.fc3 = nn.Linear(84, 10)
216
217		def forward(self, x):
218		x = self.pool(F.relu(self.conv1(x)))
219		x = self.pool(F.relu(self.conv2(x)))
220		x = x.view(-1, 16 * 5 * 5)
221		x = F.relu(self.fc1(x))
222		x = F.relu(self.fc2(x))
223		x = self.fc3(x)
224		return x
225
226		trainloader = torch.utils.data.DataLoader(
227		trainset, batch_size=4, shuffle=True, num_workers=2
228		)
229
230		net = Net()
231
232		criterion = nn.CrossEntropyLoss()
233		optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
234
235		for epoch in range(1): # loop over the dataset multiple times
236
237		running_loss = 0.0
238		for i, data in enumerate(trainloader, 0):
239		# get the inputs; data is a list of [inputs, labels]
240		inputs, labels = data
241
242		# zero the parameter gradients
243		optimizer.zero_grad()
244
245		# forward + backward + optimize
246		outputs = net(inputs)
247		loss = criterion(outputs, labels)
248		loss.backward()
249		optimizer.step()
250
251		# print statistics
252		running_loss += loss.item()
253		if i % 2000 == 1999: # print every 2000 mini-batches
254		print(
255		"[%d, %5d] loss: %.3f" % (epoch + 1, i + 1, running_loss / 2000)
256		)
257		running_loss = 0.0
258
259		return running_loss
260
261		search_config = {cnn: {"filters.0": [32, 64], "kernel_size.0": [3, 4]}}
262
263		opt = Hyperactive(search_config)
264		opt.search(None, None)
265		# opt.predict(X)
266		# opt.score(X, y)
267
268
269
270		def test_chainer():
271		def cnn(para, X_train, y_train):
272		pass
273
274		search_config = {cnn: {"filters.0": [32, 64], "kernel_size.0": [3, 4]}}
275		opt = Hyperactive(search_config)
276		opt.search(None, None)
277		# opt.predict(X)
278		# opt.score(X, y)
279		"""
280

SimonBlanke / Hyperactive

Push — master ( 61a8e6...a7d091 )

tests.test_packages.test_catboost() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like