Learn by Coding Examples in Applied Machine Learning

Regression with the Keras in Python

In [4]:
# ignore warnings
import warnings
warnings.filterwarnings("ignore")

Baseline Neural Network Model

In [6]:
# Regression Example With Boston Dataset: Baseline
from pandas import read_csv
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold

# load dataset
dataframe = read_csv("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 model
def baseline_model():
    # create model
    model = Sequential()
    model.add(Dense(13, input_dim=13, kernel_initializer='normal', activation='relu'))
    model.add(Dense(1, kernel_initializer='normal'))
    
    # Compile model
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model

# evaluate model
estimator = KerasRegressor(build_fn=baseline_model, epochs=100, batch_size=5, verbose=0)
kfold = KFold(n_splits=10)
results = cross_val_score(estimator, X, Y, cv=kfold)

print(); print("Results for regression: ")
print("Baseline: %.2f (%.2f) MSE" % (results.mean(), results.std()))

Results for regression: 
Baseline: -35.90 (30.09) MSE

Modeling The Standardized Dataset

In [7]:
from pandas import read_csv
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

# load dataset
dataframe = read_csv("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 model
def baseline_model():
    # create model
    model = Sequential()
    model.add(Dense(13, input_dim=13, kernel_initializer='normal', activation='relu'))
    model.add(Dense(1, kernel_initializer='normal'))
    
    # Compile model
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model

# evaluate model with standardized dataset
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=baseline_model, epochs=50, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n_splits=10)
results = cross_val_score(pipeline, X, Y, cv=kfold)

print(); print("Results for regression: ")
print("Standardized: %.2f (%.2f) MSE" % (results.mean(), results.std()))

Results for regression: 
Standardized: -30.88 (31.76) MSE

Regression Example With Boston Dataset: Standardized data and Larger Model

In [8]:
from pandas import read_csv
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

# load dataset
dataframe = read_csv("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 the model
def larger_model():
    # create model
    model = Sequential()
    model.add(Dense(10, input_dim=13, kernel_initializer='normal', activation='relu'))
    model.add(Dense(6, kernel_initializer='normal', activation='relu'))
    model.add(Dense(1, kernel_initializer='normal'))
    
    # Compile model
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model

# evaluate model with standardized dataset
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=larger_model, epochs=50, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n_splits=10)
results = cross_val_score(pipeline, X, Y, cv=kfold)

print(); print("Results for regression: ")
print("Larger: %.2f (%.2f) MSE" % (results.mean(), results.std()))

Results for regression: 
Larger: -24.77 (27.62) MSE

Regression Example With Boston Dataset: Standardized data and Wider model

In [9]:
from pandas import read_csv
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

# load dataset
dataframe = read_csv("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 wider model
def wider_model():
    # create model
    model = Sequential()
    model.add(Dense(30, input_dim=13, kernel_initializer='normal', activation='relu'))
    model.add(Dense(15, kernel_initializer='normal', activation='relu'))
    model.add(Dense(1, kernel_initializer='normal'))
    
    # Compile model
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model

# evaluate model with standardized dataset
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=wider_model, epochs=100, batch_size=5, verbose=0)))
pipeline = Pipeline(estimators)
kfold = KFold(n_splits=10)
results = cross_val_score(pipeline, X, Y, cv=kfold)

print(); print("Results for regression: ")
print("Wider: %.2f (%.2f) MSE" % (results.mean(), results.std()))

Results for regression: 
Wider: -22.20 (24.90) MSE
In [ ]: