import numpy
import pandas
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasClassifier
from keras.utils import np_utils
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import LabelEncoder
from sklearn.pipeline import Pipeline
S:\Users\RezyapkinV\AppData\Local\Continuum\anaconda3\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. from ._conv import register_converters as _register_converters Using TensorFlow backend.
Будем работать с датасетом The Iris Dataset.
from sklearn.datasets import load_iris
data = load_iris()
X, y = data['data'], data['target']
# encode class values as integers
encoder = LabelEncoder()
encoder.fit(y)
encoded_y = encoder.transform(y)
# convert integers to dummy variables (i.e. one hot encoded)
dummy_y = np_utils.to_categorical(encoded_y)
X[:, :5]
array([[5.1, 3.5, 1.4, 0.2], [4.9, 3. , 1.4, 0.2], [4.7, 3.2, 1.3, 0.2], [4.6, 3.1, 1.5, 0.2], [5. , 3.6, 1.4, 0.2], [5.4, 3.9, 1.7, 0.4], [4.6, 3.4, 1.4, 0.3], [5. , 3.4, 1.5, 0.2], [4.4, 2.9, 1.4, 0.2], [4.9, 3.1, 1.5, 0.1], [5.4, 3.7, 1.5, 0.2], [4.8, 3.4, 1.6, 0.2], [4.8, 3. , 1.4, 0.1], [4.3, 3. , 1.1, 0.1], [5.8, 4. , 1.2, 0.2], [5.7, 4.4, 1.5, 0.4], [5.4, 3.9, 1.3, 0.4], [5.1, 3.5, 1.4, 0.3], [5.7, 3.8, 1.7, 0.3], [5.1, 3.8, 1.5, 0.3], [5.4, 3.4, 1.7, 0.2], [5.1, 3.7, 1.5, 0.4], [4.6, 3.6, 1. , 0.2], [5.1, 3.3, 1.7, 0.5], [4.8, 3.4, 1.9, 0.2], [5. , 3. , 1.6, 0.2], [5. , 3.4, 1.6, 0.4], [5.2, 3.5, 1.5, 0.2], [5.2, 3.4, 1.4, 0.2], [4.7, 3.2, 1.6, 0.2], [4.8, 3.1, 1.6, 0.2], [5.4, 3.4, 1.5, 0.4], [5.2, 4.1, 1.5, 0.1], [5.5, 4.2, 1.4, 0.2], [4.9, 3.1, 1.5, 0.1], [5. , 3.2, 1.2, 0.2], [5.5, 3.5, 1.3, 0.2], [4.9, 3.1, 1.5, 0.1], [4.4, 3. , 1.3, 0.2], [5.1, 3.4, 1.5, 0.2], [5. , 3.5, 1.3, 0.3], [4.5, 2.3, 1.3, 0.3], [4.4, 3.2, 1.3, 0.2], [5. , 3.5, 1.6, 0.6], [5.1, 3.8, 1.9, 0.4], [4.8, 3. , 1.4, 0.3], [5.1, 3.8, 1.6, 0.2], [4.6, 3.2, 1.4, 0.2], [5.3, 3.7, 1.5, 0.2], [5. , 3.3, 1.4, 0.2], [7. , 3.2, 4.7, 1.4], [6.4, 3.2, 4.5, 1.5], [6.9, 3.1, 4.9, 1.5], [5.5, 2.3, 4. , 1.3], [6.5, 2.8, 4.6, 1.5], [5.7, 2.8, 4.5, 1.3], [6.3, 3.3, 4.7, 1.6], [4.9, 2.4, 3.3, 1. ], [6.6, 2.9, 4.6, 1.3], [5.2, 2.7, 3.9, 1.4], [5. , 2. , 3.5, 1. ], [5.9, 3. , 4.2, 1.5], [6. , 2.2, 4. , 1. ], [6.1, 2.9, 4.7, 1.4], [5.6, 2.9, 3.6, 1.3], [6.7, 3.1, 4.4, 1.4], [5.6, 3. , 4.5, 1.5], [5.8, 2.7, 4.1, 1. ], [6.2, 2.2, 4.5, 1.5], [5.6, 2.5, 3.9, 1.1], [5.9, 3.2, 4.8, 1.8], [6.1, 2.8, 4. , 1.3], [6.3, 2.5, 4.9, 1.5], [6.1, 2.8, 4.7, 1.2], [6.4, 2.9, 4.3, 1.3], [6.6, 3. , 4.4, 1.4], [6.8, 2.8, 4.8, 1.4], [6.7, 3. , 5. , 1.7], [6. , 2.9, 4.5, 1.5], [5.7, 2.6, 3.5, 1. ], [5.5, 2.4, 3.8, 1.1], [5.5, 2.4, 3.7, 1. ], [5.8, 2.7, 3.9, 1.2], [6. , 2.7, 5.1, 1.6], [5.4, 3. , 4.5, 1.5], [6. , 3.4, 4.5, 1.6], [6.7, 3.1, 4.7, 1.5], [6.3, 2.3, 4.4, 1.3], [5.6, 3. , 4.1, 1.3], [5.5, 2.5, 4. , 1.3], [5.5, 2.6, 4.4, 1.2], [6.1, 3. , 4.6, 1.4], [5.8, 2.6, 4. , 1.2], [5. , 2.3, 3.3, 1. ], [5.6, 2.7, 4.2, 1.3], [5.7, 3. , 4.2, 1.2], [5.7, 2.9, 4.2, 1.3], [6.2, 2.9, 4.3, 1.3], [5.1, 2.5, 3. , 1.1], [5.7, 2.8, 4.1, 1.3], [6.3, 3.3, 6. , 2.5], [5.8, 2.7, 5.1, 1.9], [7.1, 3. , 5.9, 2.1], [6.3, 2.9, 5.6, 1.8], [6.5, 3. , 5.8, 2.2], [7.6, 3. , 6.6, 2.1], [4.9, 2.5, 4.5, 1.7], [7.3, 2.9, 6.3, 1.8], [6.7, 2.5, 5.8, 1.8], [7.2, 3.6, 6.1, 2.5], [6.5, 3.2, 5.1, 2. ], [6.4, 2.7, 5.3, 1.9], [6.8, 3. , 5.5, 2.1], [5.7, 2.5, 5. , 2. ], [5.8, 2.8, 5.1, 2.4], [6.4, 3.2, 5.3, 2.3], [6.5, 3. , 5.5, 1.8], [7.7, 3.8, 6.7, 2.2], [7.7, 2.6, 6.9, 2.3], [6. , 2.2, 5. , 1.5], [6.9, 3.2, 5.7, 2.3], [5.6, 2.8, 4.9, 2. ], [7.7, 2.8, 6.7, 2. ], [6.3, 2.7, 4.9, 1.8], [6.7, 3.3, 5.7, 2.1], [7.2, 3.2, 6. , 1.8], [6.2, 2.8, 4.8, 1.8], [6.1, 3. , 4.9, 1.8], [6.4, 2.8, 5.6, 2.1], [7.2, 3. , 5.8, 1.6], [7.4, 2.8, 6.1, 1.9], [7.9, 3.8, 6.4, 2. ], [6.4, 2.8, 5.6, 2.2], [6.3, 2.8, 5.1, 1.5], [6.1, 2.6, 5.6, 1.4], [7.7, 3. , 6.1, 2.3], [6.3, 3.4, 5.6, 2.4], [6.4, 3.1, 5.5, 1.8], [6. , 3. , 4.8, 1.8], [6.9, 3.1, 5.4, 2.1], [6.7, 3.1, 5.6, 2.4], [6.9, 3.1, 5.1, 2.3], [5.8, 2.7, 5.1, 1.9], [6.8, 3.2, 5.9, 2.3], [6.7, 3.3, 5.7, 2.5], [6.7, 3. , 5.2, 2.3], [6.3, 2.5, 5. , 1.9], [6.5, 3. , 5.2, 2. ], [6.2, 3.4, 5.4, 2.3], [5.9, 3. , 5.1, 1.8]])
Будем решать задачу классификации на 3 класса. В качестве модели используется нейронная сеть с одним скрытым слоем. Ваша задача оценить качество решенения задачи классификации по метрике accuracy
в зависимости от числа нейронов скрытого слоя. Также оцените дисперсию функции качества в зависимости от числа главных компонент.
Нарисуйте график зависимости функции качества и ее дисперсии от числа нейронов скрытого слоя.
def baseline_model(hidden_input, dim):
# create model
model = Sequential()
model.add(Dense(hidden_input, input_dim=dim, activation='relu'))
model.add(Dense(3, activation='softmax'))
# Compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
%%time
hidden_inputs = range(1, 5)
means = []
stds = []
for i in hidden_inputs:
#model = baseline_model(hidden_input=i)
estimator = KerasClassifier(build_fn=baseline_model, hidden_input=i, dim = 4, epochs=20, batch_size=5, verbose=0)
result = cross_val_score(estimator, X, dummy_y, cv=kfold)
means.append(result.mean()*100)
stds.append(result.std()*100)
print("Model with %d neurons in hidden layer: ac = %.2f%% (std = %.2f%%)" % (i, result.mean()*100, result.std()*100))
Model with 1 neurons in hidden layer: ac = 38.67% (std = 21.46%) Model with 2 neurons in hidden layer: ac = 38.67% (std = 24.00%) Model with 3 neurons in hidden layer: ac = 60.67% (std = 16.45%) Model with 4 neurons in hidden layer: ac = 42.67% (std = 23.13%) Wall time: 12min
import matplotlib.pyplot as plt
plt.plot(hidden_inputs, means, label='Accuracy')
plt.plot(hidden_inputs, stds, label="STD")
plt.xlabel("Number of neurons in hidden layer")
plt.ylabel("Percentage")
plt.legend()
plt.show()
%%time
hidden_input = 3
dims = range(1, 5)
means = []
stds = []
for i in dims:
#model = baseline_model(hidden_input=i)
estimator = KerasClassifier(build_fn=baseline_model, hidden_input=hidden_input, dim = i, epochs=20, batch_size=5, verbose=0)
result = cross_val_score(estimator, X[:, :i], dummy_y, cv=kfold)
means.append(result.mean()*100)
stds.append(result.std()*100)
print("Model with dim = %d: ac = %.2f%% (std = %.2f%%)" % (i, result.mean()*100, result.std()*100))
Model with dim = 1: ac = 27.33% (std = 14.13%) Model with dim = 2: ac = 35.33% (std = 16.34%) Model with dim = 3: ac = 41.33% (std = 26.13%) Model with dim = 4: ac = 47.33% (std = 23.37%) Wall time: 15min 46s
plt.plot(hidden_inputs, means, label='Accuracy')
plt.plot(hidden_inputs, stds, label="STD")
plt.xlabel("Dim")
plt.ylabel("Percentage")
plt.legend()
plt.show()