def objective_function():
X, y = production_rate_dataset(producers[0], *injectors)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.5,
shuffle=False)
crmp = CRMP().fit(X_train, y_train)
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,
test_size=0.5,
shuffle=False)
for p0 in param_grid['p0']:
crmp.tau_ = p0[0]
crmp.gains_ = p0[1:]
y_hat = crmp.predict(X_test)
r2, mse = fit_statistics(y_hat, y_test)
objective_function_data['Producer'].append(i + 1)
objective_function_data['tau'].append(p0[0])
objective_function_data['f1'].append(p0[1])
objective_function_data['f2'].append(p0[2])
objective_function_data['r2'].append(r2)
objective_function_data['MSE'].append(mse)
objective_function_df = pd.DataFrame(objective_function_data)
objective_function_df.to_csv(objective_function_file)
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)
def fit_all_producers():
for i in range(number_of_producers):
producer = producers[i]
X, y = production_rate_dataset(producer, *injectors)
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=0.5, shuffle=False
)
crmp = CRMP(q0=producer[0])
crmp = crmp.fit(X_train, y_train)
print('Producer {}'.format(i + 1))
print('Tau: {}'.format(crmp.tau_))
print('Gains: {}'.format(crmp.gains_))
print()
def fit_individual_initial_guesses():
producer = producers[2]
X, y = production_rate_dataset(producer, *injectors)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.5,
shuffle=False)
crmp = CRMP(p0=[1e-03, 0.4, 0.6])
crmp = crmp.fit(X_train, y_train)
y_hat = crmp.predict(X_train)
r2, mse = fit_statistics(y_hat, y_train)
print(crmp.tau_)
print(crmp.gains_)
print(mse)
def minimum_train_size():
data_sizes = np.linspace(1, 148, 148).astype(int)
for data_size in data_sizes:
X, y = production_rate_dataset(producers[3], *injectors)
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=data_size, shuffle=False)
crmp = CRMP(p0=[5, 0.5, 0.5])
crmp = crmp.fit(X_train, y_train)
y_hat = crmp.predict(X_test)
r2, mse = fit_statistics(y_hat, y_test)
if np.log(mse) < 11.0581424463:
print(data_size)
print(mse)
return
def plot_production_history_with_fit_and_predict():
df = pd.read_csv(predict_file)
starting_index = producer_starting_indicies[1]
producer = producers[1][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)
crmp = CRMP().fit(X_train, y_train)
for i in range(len(producer_names)):
producer_df = producer_rows_from_df(df, i + 1)
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)
producer_length = len(producer)
t = np.linspace(1, producer_length, producer_length)
train_length = len(y_train)
train_time = t[:train_length]
test_time = t[train_length:][1:]
empty = []
plt.plot(empty, empty, c='r', label='Fit')
plt.plot(empty, empty, c='g', label='Predict')
plt.plot(t, producer, c='k')
for index, row in producer_df.iterrows():
tau = row['tau_final']
f1 = row['f1_final']
f2 = row['f2_final']
f3 = row['f3_final']
f4 = row['f4_final']
crmp.tau_ = tau
crmp.gains_ = [f1, f2, f3, f4]
# Fitting
y_hat = crmp.predict(X_train)
plt.plot(train_time, y_hat, '--', alpha=0.02, c='r', linewidth=2)
# Prediction
y_hat = crmp.predict(X_test)
plt.plot(test_time, y_hat, ':', alpha=0.02, c='g', linewidth=2)
plt.vlines(test_time[0],
0,
1.1 * max(producer),
linewidth=2,
alpha=0.8)
plot_helper(FIG_DIR,
title=producer_names[i],
xlabel='Time [days]',
ylabel='Production Rate [bbls/day]',
legend=True,
save=True)
batch_size=batch,
validation_split=0.1,
verbose=0)
y_hat_lstm = []
for j in range(30):
y_hat_j = model.predict(X_test_scaled[j:(j + 1)])[0][0]
X_test_scaled[j + 1] = y_hat_j
y_hat_lstm.append(y_hat_j)
y_hat_lstm = np.array(y_hat_lstm).reshape(-1, 1)
y_hat_lstm = scaler.inverse_transform(y_hat_lstm)
r2, mse = fit_statistics(y_hat_lstm, y_test[:30])
print(mse)
crmp = CRMP().fit(X_train, y_train)
y_hat_crmp = crmp.predict(X_test[:30, 1:])
r2, mse = fit_statistics(y_hat_crmp, y_test[:30])
print(mse)
t = np.linspace(76, 105, 30)
plt.plot(t, y_test[:30], color='k', label='True Value', linewidth=2)
plt.plot(t, y_hat_crmp, alpha=0.5, label='CRMP', linewidth=2)
plt.plot(t, y_hat_lstm, alpha=0.5, label='LSTM Neural Network', linewidth=2)
plt.tight_layout()
plot_helper(
FIG_DIR,
title='{}: 30 Days Prediction for CRMP and LSTM Neural Network'.format(
name),
xlabel='Days',
ylabel='Production Rate [bbls/day]',
from sklearn.linear_model import (BayesianRidge, HuberRegressor,
LinearRegression)
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPRegressor
from crmp import CRMP, MBBaggingRegressor
from src.config import INPUTS
from src.data.read_crmp import injectors, producers, producer_names
from src.helpers.analysis import fit_statistics
from src.helpers.cross_validation import goodness_score
from src.helpers.features import production_rate_dataset
from src.simulations import injector_names, number_of_producers
estimators = [CRMP()]
estimators = [
LinearRegression(),
BayesianRidge(),
HuberRegressor(),
MLPRegressor()
]
def log_transformation(column):
return np.log(column + 1)
std = 25
for estimator in estimators:
print(estimator)
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)