"""
model = reg_cnn((X_train.shape[1], X_train.shape[2], X_train.shape[3]))
model.fit(X_train,
y_train,
epochs=800,
batch_size=64,
verbose=1,
validation_split=0.1)
score = model.evaluate(X_test, y_test, batch_size=50)
print score
pred_y_test = model.predict(X_test)
# means of val
my_rmse = rmse(pred_y_test, y_test)
print "rmse = ", my_rmse
plt.figure(1)
#plt.ylim(-1.5,3)
plt.plot(dates[len(dates) - len(y_test):len(dates)], y_test, color='g')
plt.plot(dates[len(dates) - len(pred_y_test):len(dates)],
pred_y_test,
color='r')
plt.show()
pred_y_train = model.predict(X_train)
plt.figure(1)
plt.plot(dates[0:len(y_train)], y_train, color='g')
plt.plot(dates[0:len(pred_y_train)], pred_y_train, color='r')
plt.show()
def main():
# ---------- Directories & User inputs --------------
# Location of data folder
data_dir = './data/'
FLAG_train = (len(sys.argv) > 1 and sys.argv[1] == '--train')
##########################################
######## Load and preprocess data ########
##########################################
# Read and preprocess data from CSV
data = dataset.read_and_preprocess_data(data_dir=data_dir,
file_name='training.csv')
print data.head(), '\n', data.tail(), '\n', data.info()
plt.figure()
data.groupby(['serieNames'])['sales'].plot()
plt.legend(loc="best")
# Split data/labels into train/test set
X_train, y_train, X_test, y_test = dataset.split_data(df=data,
test_ratio=0.1)
y_train_serieNames, y_test_serieNames = X_train['serieNames'], X_test[
'serieNames']
# Data normalization
sc = MinMaxScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
##########################################
######## Train regressor #################
##########################################
if FLAG_train:
models.train_regressor_models(X_train, y_train, n_splits=3)
else:
# Load the pre-trained regressor with tuned parameters
# Linear Ridge Regression
regressor_ridge = models.load_regressor_Ridge(X_train, y_train)
# Random ForestRegression
regressor_rf = models.load_regressor_RF(X_train, y_train)
# Support Vector Regression
regressor_svr = models.load_regressor_SVR(X_train, y_train)
# Dummy regressor
dummy = DummyRegressor(strategy='mean')
dummy.fit(X_train, y_train)
y_hat_dummy = pd.DataFrame({
'y_hat_dummy': y_test,
'serieNames': y_test_serieNames
})
y_hat_dummy = y_hat_dummy.groupby(['serieNames'
])['y_hat_dummy'].shift()
y_hat_dummy = y_hat_dummy.fillna(method='bfill')
print 'RMSE dummy mean %.5f' % (models.rmse(y_test, y_hat_dummy))
##########################################
######## Compare model performance #######
##########################################
regressor_models = {
'Baseline Previous Mean': dummy,
'Ridge Regression': regressor_ridge,
'Support Vector Regression': regressor_svr,
'Random Forest Regression': regressor_rf
}
# Test errors: test the model with tuned parameters
for i, regressor_model in sorted(regressor_models.items()):
y_hat_regressor = regressor_model.predict(X_test)
RMSE_regressor = models.rmse(y_test, y_hat_regressor)
print 'RMSE %s : %.5f' % (i, RMSE_regressor)
plt.figure()
plt.ylabel("RMSE")
plt.title('RMSE %s : %.5f' % (i, RMSE_regressor))
plot_prediction_perSerie(y_true=y_test,
y_pred=y_hat_regressor,
y_serieNames=y_test_serieNames)
plt.figure()
plt.ylabel("RMSE")
plt.title('RMSE dummy last observation %.5f' %
(models.rmse(y_test, y_hat_dummy)))
plot_prediction_perSerie(y_true=y_test,
y_pred=y_hat_dummy,
y_serieNames=y_test_serieNames)
# Generization errors: cross_validate_score
plt.figure()
plt.title('Generalization errors (RMSE)')
n_splits = 10
scoring = 'neg_mean_squared_error'
for i, regressor_model in sorted(regressor_models.items()):
test_error = models.get_regressor_cross_validate_score(
regressor_model,
X_test,
y_test,
scoring=scoring,
n_splits=n_splits)
test_rmse = np.array([np.sqrt(-e) for e in test_error])
plt.plot(test_rmse,
'o-',
label=i + ' : %0.2f (+/- %0.2f)' %
(test_rmse.mean(), test_rmse.std() / 2))
plt.xlabel("Fold number")
plt.ylabel("RMSE")
plt.legend(loc="best")
##########################################
######## Make predictions ################
##########################################
file_name = 'test.csv'
new_samples = dataset.read_and_preprocess_data(data_dir=data_dir,
file_name=file_name)
X_new = new_samples.values
X_new = sc.transform(X_new)
# Directly predict
y_new_hat = regressor_rf.predict(X_new)
# Fit all data available and make prediction
X_all = np.concatenate((X_train, X_test), axis=0)
y_all = np.concatenate((y_train, y_test), axis=0)
regressor_rf.fit(X_all, y_all)
y_new_hat_all = regressor_rf.predict(X_new)
# Plot the prediction results
plt.figure()
df_new = pd.DataFrame({
'sales_pred_90': y_new_hat,
'sales_pred_100': y_new_hat_all,
'serieNames': new_samples['serieNames']
})
df_new.groupby(['serieNames'
])['sales_pred_90'].plot(label='sales_pred_90%')
df_new.groupby(['serieNames'
])['sales_pred_100'].plot(style='o--',
label='sales_pred_100%')
plt.ylabel("sales")
plt.legend(loc="best")
##########################################
######## Save prediction results #########
##########################################
# Save the prediction results
df_new.reset_index()
df_new.to_csv('./results/prediction.csv', index=False)
# Write to the test.csv format
df_test = pd.read_csv(data_dir + 'test.csv')
df_test['sales'] = y_new_hat_all
df_test.to_csv('./results/test_prediction.csv', index=False)
plt.figure()
df_test = df_test.set_index(['TSDate'])
df_test.groupby(['serieNames'])['sales'].plot(style='*-')
plt.ylabel("sales")
plt.legend(loc="best")
# Visualize the prediction
Visualize_prediction(data_dir)
plt.legend(loc="best")
plt.show()
print(X_test[-2])
print(Y_test[-2])
print(predicted_Y_test[-2])
tmp = X_test[-2]
tmp = tmp.reshape(1, 1, 10)
print(model.predict(tmp))
print(X_test[-1])
print(Y_test[-1])
print(predicted_Y_test[-1])
tmp = X_test[-1]
tmp = tmp.reshape(1, 1, 10)
print(model.predict(tmp))
# means of val
my_rmse = rmse(predicted_Y_test, Y_test)
print "rmse = ", my_rmse
plt.figure(1)
#plt.ylim(-1.5,3)
plt.plot(dates[len(dates) - len(Y_test):len(dates)], Y_test, color='g')
plt.plot(dates[len(dates) - len(predicted_Y_test):len(dates)],
predicted_Y_test,
color='r')
plt.show()
predicted_Y_train = model.predict(X_train)
plt.figure(1)
plt.plot(dates[0:len(Y_train)], Y_train, color='g')
plt.plot(dates[0:len(predicted_Y_train)], predicted_Y_train, color='r')
plt.show()
def ensemble_rmse(weights):
final_prediction = 0
for weight, prediction in zip(weights, predictions):
final_prediction += weight * prediction
return rmse(target[split:], final_prediction)