def convergence_sensitivity_analysis():
for i in range(len(producer_names)):
starting_index = producer_starting_indicies[i]
producer = producers[i][starting_index:]
injectors_tmp = [injector[starting_index:] for injector in injectors]
X, y = production_rate_dataset(producer, *injectors_tmp)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.5,
shuffle=False)
for p0 in p0s:
crmp = CRMP(p0=deepcopy(p0))
crmp = crmp.fit(X_train, y_train)
# Fitting
y_hat = crmp.predict(X_train)
r2, mse = fit_statistics(y_hat, y_train)
fit_data['Producer'].append(i + 1)
fit_data['Model'].append(model_namer(crmp))
fit_data['tau_initial'].append(p0[0])
fit_data['tau_final'].append(crmp.tau_)
fit_data['f1_initial'].append(p0[1])
fit_data['f1_final'].append(crmp.gains_[0])
fit_data['f2_initial'].append(p0[2])
fit_data['f2_final'].append(crmp.gains_[1])
fit_data['f3_initial'].append(p0[3])
fit_data['f3_final'].append(crmp.gains_[2])
fit_data['f4_initial'].append(p0[4])
fit_data['f4_final'].append(crmp.gains_[3])
fit_data['r2'].append(r2)
fit_data['MSE'].append(mse)
# Prediction
y_hat = crmp.predict(X_test)
r2, mse = fit_statistics(y_hat, y_test)
predict_data['Producer'].append(i + 1)
predict_data['Model'].append(model_namer(crmp))
predict_data['tau_initial'].append(p0[0])
predict_data['tau_final'].append(crmp.tau_)
predict_data['f1_initial'].append(p0[1])
predict_data['f1_final'].append(crmp.gains_[0])
predict_data['f2_initial'].append(p0[2])
predict_data['f2_final'].append(crmp.gains_[1])
predict_data['f3_initial'].append(p0[3])
predict_data['f3_final'].append(crmp.gains_[2])
predict_data['f4_initial'].append(p0[4])
predict_data['f4_final'].append(crmp.gains_[3])
predict_data['r2'].append(r2)
predict_data['MSE'].append(mse)
# Fitting
fit_df = pd.DataFrame(fit_data)
fit_df.to_csv(fit_ouput_file)
# Prediction
predict_df = pd.DataFrame(predict_data)
predict_df.to_csv(predict_output_file)
from src.helpers.features import koval_dataset, production_rate_dataset
from src.helpers.models import model_namer, serialized_model_path, is_CV_model
koval_fitting_file = INPUTS['wfsim']['koval_fitting']
koval_fitting_data = {'Model': [], 't_i': [], 'Fit': []}
X, y = koval_dataset(W_t, f_w)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.8,
random_state=1,
shuffle=False)
koval = Koval().fit(X=X_train, y=y_train)
y_hat = koval.predict(X_train)
time = np.linspace(1, len(y_hat), num=len(y_hat))
for k in range(len(y_hat)):
koval_fitting_data['Model'].append(model_namer(koval))
koval_fitting_data['t_i'].append(k + 1)
koval_fitting_data['Fit'].append(y_hat[k])
pickled_model = serialized_model_path('koval', koval)
with open(pickled_model, 'wb') as f:
pickle.dump(koval, f)
X, y = production_rate_dataset(f_w, W_t)
train_split, test_split, train_test_seperation_idx = forward_walk_splitter(
X, y, 2)
X_train = X[:train_test_seperation_idx]
y_train = y[:train_test_seperation_idx]
models = [BayesianRidge(), ElasticNetCV, LassoCV, LinearRegression()]
for model in models:
if is_CV_model(model):
def convergence_sensitivity_analysis():
t = time[1:]
iterations = 0
for i in range(number_of_producers):
X, y = production_rate_dataset(producers[i], *injectors)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.5,
shuffle=False)
train_length = len(y_train)
test_length = len(y_test)
train_time = t[:train_length]
test_time = t[train_length:]
# plt.plot(train_time, y_train, c='r', label='Fit')
# plt.plot(test_time, y_test, c='g', label='Predict')
# plt.plot(t, y, c='k', label='Actual')
for p0 in param_grid['p0']:
crmp = CRMP(p0=deepcopy(p0))
crmp = crmp.fit(X_train, y_train)
# Fitting
y_hat = crmp.predict(X_train)
# plt.plot(train_time, y_hat, alpha=0.01, c='r', linewidth=2)
r2, mse = fit_statistics(y_hat, y_train)
fit_data['Producer'].append(i + 1)
fit_data['Model'].append(model_namer(crmp))
fit_data['tau_initial'].append(p0[0])
fit_data['tau_final'].append(crmp.tau_)
fit_data['f1_initial'].append(p0[1])
fit_data['f1_final'].append(crmp.gains_[0])
fit_data['f2_initial'].append(p0[2])
fit_data['f2_final'].append(crmp.gains_[1])
fit_data['r2'].append(r2)
fit_data['MSE'].append(mse)
# Prediction
y_hat = crmp.predict(X_test)
# plt.plot(test_time, y_hat, alpha=0.01, c='g', linewidth=2)
r2, mse = fit_statistics(y_hat, y_test)
predict_data['Producer'].append(i + 1)
predict_data['Model'].append(model_namer(crmp))
predict_data['tau_initial'].append(p0[0])
predict_data['tau_final'].append(crmp.tau_)
predict_data['f1_initial'].append(p0[1])
predict_data['f1_final'].append(crmp.gains_[0])
predict_data['f2_initial'].append(p0[2])
predict_data['f2_final'].append(crmp.gains_[1])
predict_data['r2'].append(r2)
predict_data['MSE'].append(mse)
iterations += 1
print(iterations)
# plt.vlines(76, 0, 1000, linewidth=1, alpha=0.8)
# plt.title(producer_names[i])
# plt.xlabel('Time')
# plt.ylabel('Production Rate')
# plt.legend()
# plt.show()
# Fitting
fit_df = pd.DataFrame(fit_data)
fit_df.to_csv(fit_ouput_file)
# Prediction
predict_df = pd.DataFrame(predict_data)
predict_df.to_csv(predict_output_file)
def test_model_namer(self):
model = BayesianRidge()
model_name = model_namer(model)
assert (model_name == 'BayesianRidge')
'Step size': [],
't_start': [],
't_end': [],
't_i': [],
'Prediction': []
}
koval_predictions_metrics = {'Model': [], 'Step size': [], 'r2': [], 'MSE': []}
# Koval Predictions
X, y = koval_dataset(W_t, f_w)
for step_size in step_sizes:
train_split, test_split, train_test_seperation_idx = forward_walk_splitter(
X, y, step_size, training_split=0.8)
r2, mse, y_hat, time_step = test_model(X, y, koval, test_split)
koval_predictions_metrics['Model'].append(model_namer(koval))
koval_predictions_metrics['Step size'].append(step_size)
koval_predictions_metrics['r2'].append(r2)
koval_predictions_metrics['MSE'].append(mse)
for i in range(len(y_hat)):
y_hat_i = y_hat[i]
time_step_i = time_step[i]
t_start = time_step_i[0] + 2
t_end = time_step_i[-1] + 2
for k in range(len(y_hat_i)):
y_i = y_hat_i[k]
t_i = time_step_i[k] + 2
koval_predictions['Model'].append(model_namer(koval))
koval_predictions['Step size'].append(step_size)
koval_predictions['t_start'].append(t_start)
def evaluate_crmp_bhp_model():
iteration = 0
for name in producer_names:
print('Producer Name: ', name)
producer = get_real_producer_data(producers_df, name, bhp=True)
injectors = injectors_df[['Name', 'Date', 'Water Vol']]
X, y = construct_real_production_rate_dataset(producer[['Date', name]],
injectors,
producer['delta_p'])
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.40,
shuffle=False)
X_train = X_train.to_numpy()
X_test = X_test.to_numpy()
y_train = y_train.to_numpy()
y_test = y_test.to_numpy()
for p0 in p0s:
iteration += 1
print('Iteration: {}'.format(iteration))
crmpbhp = CrmpBHP(p0=deepcopy(p0))
crmpbhp = crmpbhp.fit(X_train, y_train)
# Fitting
# y_hat = crmpbhp.predict(X_train)
# r2, mse = fit_statistics(y_hat, y_train, shutin=True)
# fit_data['Producer'].append(name)
# fit_data['Model'].append(model_namer(crmpbhp))
# fit_data['tau_initial'].append(p0[0])
# fit_data['tau_final'].append(crmpbhp.tau_)
# fit_data['f1_initial'].append(p0[1])
# fit_data['f1_final'].append(crmpbhp.gains_[0])
# fit_data['f2_initial'].append(p0[2])
# fit_data['f2_final'].append(crmpbhp.gains_[1])
# fit_data['f3_initial'].append(p0[3])
# fit_data['f3_final'].append(crmpbhp.gains_[2])
# fit_data['f4_initial'].append(p0[4])
# fit_data['f4_final'].append(crmpbhp.gains_[3])
# fit_data['r2'].append(r2)
# fit_data['MSE'].append(mse)
# Prediction
y_hat = crmpbhp.predict(X_test[:30, 1:])
r2, mse = fit_statistics(y_hat, y_test[:30], shutin=True)
predict_data['Producer'].append(name)
predict_data['Model'].append(model_namer(crmpbhp))
predict_data['tau_initial'].append(p0[0])
predict_data['tau_final'].append(crmpbhp.tau_)
predict_data['f1_initial'].append(p0[1])
predict_data['f1_final'].append(crmpbhp.gains_[0])
predict_data['f2_initial'].append(p0[2])
predict_data['f2_final'].append(crmpbhp.gains_[1])
predict_data['f3_initial'].append(p0[3])
predict_data['f3_final'].append(crmpbhp.gains_[2])
predict_data['f4_initial'].append(p0[4])
predict_data['f4_final'].append(crmpbhp.gains_[3])
predict_data['r2'].append(r2)
predict_data['MSE'].append(mse)
# Fitting
fit_df = pd.DataFrame(fit_data)
fit_df.to_csv(fit_output_file)
# Prediction
predict_df = pd.DataFrame(predict_data)
predict_df.to_csv(predict_output_file)