注意這一種形式和之前時間序列不一樣，
這個響應值爲分類變量，我們只對輸入x進行標準化，而之前時間序列是x和y標準化，所以最後y還要inverse.
對於不需要inverse的有個更簡單的方法
1.分類問題結合sklearn
import numpy
import pandas
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.cross_validation import cross_val_score
from sklearn.preprocessing import LabelEncoder
from sklearn.cross_validation import StratifiedKFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load dataset
dataframe = pandas.read_csv("../data/sonar.csv", header=None)
dataset = dataframe.values
# split into input (X) and output (Y) variables
X = dataset[:,0:60].astype(float)
Y = dataset[:,60]
# encode class values as integers
encoder = LabelEncoder()
encoder.fit(Y)
encoded_Y = encoder.transform(Y)
# baseline model
def create_baseline():
# create model
model = Sequential()
model.add(Dense(60, input_dim=60, init='normal', activation='relu'))
model.add(Dense(1, init='normal', activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
# evaluate baseline model
estimator = KerasClassifier(build_fn=create_baseline, nb_epoch=100, batch_size=5, verbose=0)
kfold = StratifiedKFold(y=encoded_Y, n_folds=10, shuffle=True, random_state=seed)
results = cross_val_score(estimator, X, encoded_Y, cv=kfold)
print("Baseline: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))
# Baseline: 81.68% (5.67%)
# evaluate baseline model with standardized dataset
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasClassifier(build_fn=create_baseline, nb_epoch=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = StratifiedKFold(y=encoded_Y, n_folds=10, shuffle=True, random_state=seed)
results = cross_val_score(pipeline, X, encoded_Y, cv=kfold)
print("Standardized: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))
# Standardized: 84.07% (6.23%)
# smaller model
def create_smaller():
# create model
model = Sequential()
model.add(Dense(30, input_dim=60, init='normal', activation='relu'))
model.add(Dense(1, init='normal', activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasClassifier(build_fn=create_smaller, nb_epoch=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = StratifiedKFold(y=encoded_Y, n_folds=10, shuffle=True, random_state=seed)
results = cross_val_score(pipeline, X, encoded_Y, cv=kfold)
print("Smaller: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))
# Smaller: 84.61% (4.65%)
# larger model
def create_larger():
# create model
model = Sequential()
model.add(Dense(60, input_dim=60, init='normal', activation='relu'))
model.add(Dense(30, init='normal', activation='relu'))
model.add(Dense(1, init='normal', activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasClassifier(build_fn=create_larger, nb_epoch=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = StratifiedKFold(y=encoded_Y, n_folds=10, shuffle=True, random_state=seed)
results = cross_val_score(pipeline, X, encoded_Y, cv=kfold)
print("Larger: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))
# Larger: 86.47% (3.82%)
標準化體現在：
# evaluate baseline model with standardized dataset
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasClassifier(build_fn=create_baseline, nb_epoch=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = StratifiedKFold(y=encoded_Y, n_folds=10, shuffle=True, random_state=seed)
results = cross_val_score(pipeline, X, encoded_Y, cv=kfold)
print("Standardized: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))
# Standardized: 84.07% (6.23%)
來自jb的書page68
2.迴歸問題借和sklearn
import numpy
import pandas
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.cross_validation import cross_val_score
from sklearn.cross_validation import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
# load dataset
dataframe = pandas.read_csv("../data/housing.csv", delim_whitespace=True, header=None)
dataset = dataframe.values
# split into input (X) and output (Y) variables
X = dataset[:,0:13]
Y = dataset[:,13]
# define base mode
def baseline_model():
# create model
model = Sequential()
model.add(Dense(13, input_dim=13, init='normal', activation='relu'))
model.add(Dense(1, init='normal'))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# evaluate model with standardized dataset
estimator = KerasRegressor(build_fn=baseline_model, nb_epoch=100, batch_size=5, verbose=0)
kfold = KFold(n=len(X), n_folds=10, random_state=seed)
results = cross_val_score(estimator, X, Y, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))
# Results: 38.04 (28.15) MSE
# evaluate model with standardized dataset
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=baseline_model, nb_epoch=50, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n=len(X), n_folds=10, random_state=seed)
results = cross_val_score(pipeline, X, Y, cv=kfold)
print("Standardized: %.2f (%.2f) MSE" % (results.mean(), results.std()))
# Standardized: 28.24 (26.25) MSE
# Smaller model
def smaller_model():
# create model
model = Sequential()
model.add(Dense(6, input_dim=13, init='normal', activation='relu'))
model.add(Dense(1, init='normal'))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=smaller_model, nb_epoch=50, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n=len(X), n_folds=10, random_state=seed)
results = cross_val_score(pipeline, X, Y, cv=kfold)
print("Smaller: %.2f (%.2f) MSE" % (results.mean(), results.std()))
# Smaller: 35.06 (32.06) MSE
# larger model
def larger_model():
# create model
model = Sequential()
model.add(Dense(13, input_dim=13, init='normal', activation='relu'))
model.add(Dense(6, init='normal', activation='relu'))
model.add(Dense(1, init='normal'))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=larger_model, nb_epoch=50, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n=len(X), n_folds=10, random_state=seed)
results = cross_val_score(pipeline, X, Y, cv=kfold)
print("Larger: %.2f (%.2f) MSE" % (results.mean(), results.std()))
# Larger: 24.60 (25.65) MSE
# deeper model
def deeper_model():
# create model
model = Sequential()
model.add(Dense(13, input_dim=13, init='normal', activation='relu'))
model.add(Dense(6, init='normal', activation='relu'))
model.add(Dense(3, init='normal', activation='relu'))
model.add(Dense(1, init='normal'))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=deeper_model, nb_epoch=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n=len(X), n_folds=10, random_state=seed)
results = cross_val_score(pipeline, X, Y, cv=kfold)
print("Deeper: %.2f (%.2f) MSE" % (results.mean(), results.std()))
# Deeper: 32.36 (39.52) MSE
# wider model
def wider_model():
# create model
model = Sequential()
model.add(Dense(20, input_dim=13, init='normal', activation='relu'))
model.add(Dense(1, init='normal'))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=wider_model, nb_epoch=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n=len(X), n_folds=10, random_state=seed)
results = cross_val_score(pipeline, X, Y, cv=kfold)
print("Wider: %.2f (%.2f) MSE" % (results.mean(), results.std()))
# Wider: 21.64 (23.75) MSE
# wider and deeper model
def wider_and_deeper_model():
# create model
model = Sequential()
model.add(Dense(20, input_dim=13, init='normal', activation='relu'))
model.add(Dense(10, init='normal', activation='relu'))
model.add(Dense(1, init='normal'))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
numpy.random.seed(seed)
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=wider_and_deeper_model, nb_epoch=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n=len(X), n_folds=10, random_state=seed)
results = cross_val_score(pipeline, X, Y, cv=kfold)
print("Wider and Deeper: %.2f (%.2f) MSE" % (results.mean(), results.std()))
# Wider and Deeper: 22.30 (25.85) MSE
注意：
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=wider_model, nb_epoch=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n=len(X), n_folds=10, random_state=seed)
results = cross_val_score(pipeline, X, Y, cv=kfold)
這裏說明pipline兩個隊X,Y操作，但你要知道StandardScaler(X,y)其中只轉換X，對Y視而不見，
所以最後我們比較Y也是不用Inverse,這裏有個弊端，就是Y沒有標準化也會影響一些效果，想標準化的話那就去看時間序列那裏怎麼做的