_test_packages.test_sklearn() - Code Metrics - Inspection of "add best_scores to attributes" - SimonBlanke/Hyperactive - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 4bbf89...a67571 )

by Simon

created 2020-01-25 10:37 UTC

_test_packages.test_sklearn() A

↳ Parent: _test_packages

Complexity

Conditions

Size

Total Lines	25
Code Lines	18

Duplication

Lines	10
Ratio	40 %

Importance

Changes

Metric	Value
cc	1
eloc	18
nop	0
dl	10
loc	25
rs	9.5
c	0
b	0
f	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
memory = False


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


"""
def test_tensorflow():
    import tensorflow as tf

    mnist = tf.keras.datasets.mnist

    (X_train, y_train), (X_test, y_test) = mnist.load_data()
    X_train, X_test = X_train / 255.0, X_test / 255.0

    def cnn(para, X_train, y_train):

        model = tf.keras.models.Sequential(
            [
                tf.keras.layers.Flatten(input_shape=(28, 28)),
                tf.keras.layers.Dense(128, activation="relu"),
                tf.keras.layers.Dropout(0.2),
                tf.keras.layers.Dense(10, activation="softmax"),
            ]
        )

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

        _, score = model.evaluate(X_test, y_test, verbose=2)
        print("score", score, type(score))
        return score

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

    opt = Hyperactive(X_train, y_train, memory=memory)
    opt.search(search_config)
"""

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

        _, 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(X_train, y_train)
    opt.search(search_config)
"""


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		memory = False
13
14
15		def test_sklearn():
16		from sklearn.tree import DecisionTreeClassifier
17
18	View Code Duplication	def model(para, X_train, y_train):
		0 ignored issues – show Duplication introduced 2019-09-14 14:59 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
19		model = DecisionTreeClassifier(
20		criterion=para["criterion"],
21		max_depth=para["max_depth"],
22		min_samples_split=para["min_samples_split"],
23		min_samples_leaf=para["min_samples_leaf"],
24		)
25		scores = cross_val_score(model, X_train, y_train, cv=3)
26
27		return scores.mean()
28
29		search_config = {
30		model: {
31		"criterion": ["gini", "entropy"],
32		"max_depth": range(1, 21),
33		"min_samples_split": range(2, 21),
34		"min_samples_leaf": range(1, 21),
35		}
36		}
37
38		opt = Hyperactive(X, y)
39		opt.search(search_config)
40		# opt.predict(X)
41		# opt.score(X, y)
42
43
44		def test_xgboost():
45		from xgboost import XGBClassifier
46
47		def model(para, X_train, y_train):
48		model = XGBClassifier(
49		n_estimators=para["n_estimators"], max_depth=para["max_depth"]
50		)
51		scores = cross_val_score(model, X_train, y_train, cv=3)
52
53		return scores.mean()
54
55		search_config = {model: {"n_estimators": range(2, 20), "max_depth": range(1, 11)}}
56
57		opt = Hyperactive(X, y, memory=memory)
58		opt.search(search_config)
59		# opt.predict(X)
60		# opt.score(X, y)
61
62
63		def test_lightgbm():
64		from lightgbm import LGBMClassifier
65
66		def model(para, X_train, y_train):
67		model = LGBMClassifier(
68		num_leaves=para["num_leaves"], learning_rate=para["learning_rate"]
69		)
70		scores = cross_val_score(model, X_train, y_train, cv=3)
71
72		return scores.mean()
73
74		search_config = {
75		model: {
76		"num_leaves": range(2, 20),
77		"learning_rate": [0.001, 0.005, 00.01, 0.05, 0.1, 0.5, 1],
78		}
79		}
80
81		opt = Hyperactive(X, y, memory=memory)
82		opt.search(search_config)
83		# opt.predict(X)
84		# opt.score(X, y)
85
86
87		def test_catboost():
88		from catboost import CatBoostClassifier
89
90		def model(para, X_train, y_train):
91		model = CatBoostClassifier(
92		iterations=para["iterations"],
93		depth=para["depth"],
94		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		"iterations": [1],
103		"depth": range(2, 10),
104		"learning_rate": [0.001, 0.005, 00.01, 0.05, 0.1, 0.5, 1],
105		}
106		}
107
108		opt = Hyperactive(X, y, memory=memory)
109		opt.search(search_config)
110		# opt.predict(X)
111		# opt.score(X, y)
112
113
114		"""
115		def test_tensorflow():
116		import tensorflow as tf
117
118		mnist = tf.keras.datasets.mnist
119
120		(X_train, y_train), (X_test, y_test) = mnist.load_data()
121		X_train, X_test = X_train / 255.0, X_test / 255.0
122
123		def cnn(para, X_train, y_train):
124
125		model = tf.keras.models.Sequential(
126		[
127		tf.keras.layers.Flatten(input_shape=(28, 28)),
128		tf.keras.layers.Dense(128, activation="relu"),
129		tf.keras.layers.Dropout(0.2),
130		tf.keras.layers.Dense(10, activation="softmax"),
131		]
132		)
133
134		model.compile(
135		optimizer="adam",
136		loss="sparse_categorical_crossentropy",
137		metrics=["accuracy"],
138		)
139		model.fit(X_train, y_train, epochs=1)
140
141		_, score = model.evaluate(X_test, y_test, verbose=2)
142		print("score", score, type(score))
143		return score
144
145		search_config = {cnn: {"filters.0": [32, 64], "kernel_size.0": [3, 4]}}
146
147		opt = Hyperactive(X_train, y_train, memory=memory)
148		opt.search(search_config)
149		"""
150
151		"""
152		def test_keras():
153		from tensorflow.keras.models import Sequential
154		from tensorflow.keras.layers import Dense, Conv2D, MaxPooling2D, Flatten
155		from tensorflow.keras.datasets import cifar10
156		from tensorflow.keras.utils import to_categorical
157
158		(X_train, y_train), (X_test, y_test) = cifar10.load_data()
159
160		X_train = X_train[0:1000]
161		y_train = y_train[0:1000]
162
163		X_test = X_train[0:1000]
164		y_test = y_train[0:1000]
165
166		y_train = to_categorical(y_train, 10)
167		y_test = to_categorical(y_test, 10)
168
169		def cnn(para, X_train, y_train):
170		model = Sequential()
171
172		model.add(
173		Conv2D(
174		filters=para["filters.0"],
175		kernel_size=para["kernel_size.0"],
176		activation="relu",
177		)
178		)
179		model.add(MaxPooling2D(pool_size=(2, 2)))
180
181		model.add(Flatten())
182		model.add(Dense(10, activation="softmax"))
183
184		model.compile(
185		optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"]
186		)
187		model.fit(X_train, y_train, epochs=1)
188
189		_, score = model.evaluate(x=X_test, y=y_test)
190
191		return score
192
193		search_config = {cnn: {"filters.0": [32, 64], "kernel_size.0": [3, 4]}}
194
195		opt = Hyperactive(X_train, y_train)
196		opt.search(search_config)
197		"""
198

SimonBlanke / Hyperactive

Push — master ( 4bbf89...a67571 )

_test_packages.test_sklearn() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like