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)
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)