predicted = model.predict(testData.toarray())
print "Predicted : " + str(predicted)
# summarize the fit of the model
test_preds = [1 if elem > 0.5 else 0 for elem in predicted]
print metrics.confusion_matrix(testModY, test_preds)
recall = metrics.recall_score(testModY, test_preds)
precision = metrics.precision_score(testModY, test_preds)
sbuf = str(recall) + "\n"
sbuf += str(precision) + "\n"
print sbuf
print "=====" + str(model.get_params().keys())
param = {
'alpha_1': [1e-06],
'alpha_2': [1e-06],
'compute_score': [False],
'copy_X': [True],
'fit_intercept': [True],
'lambda_1': [1e-06],
'lambda_2': [1e-06],
'n_iter': [300, 400, 500],
'normalize': [False],
'tol': [0.001],
'verbose': [False]
}
grid = GridSearchCV(estimator=model, param_grid=param)
grid.fit(trainData.toarray(), trainModY)
X_test = X_test[features]
print (y_train)
y_train = y_train[['Target']]
print (y_train)
y_test = y_test[['Target']]
# corr = data.corr()
# param_grid = {'C': [4.7, 4.8, 4.9, 5.0], 'gamma': [ 0.000009, 0.000010, 0.000011, 0.000012]}
print(X_train)
print(y_train)
# regressor = LinearRegression()
regressor = BayesianRidge()
#regressor.fit(X_train, y_train.squeeze().tolist())
regressor.fit(X_train, y_train.squeeze().tolist())
print(regressor.score(X_test, y_test.squeeze().tolist()))
print(regressor.get_params())
y_predict = regressor.predict(X_test)
print(y_predict)
plt.plot(y_test.squeeze().tolist(), y_predict, 'o');
plt.show()
tY = test[:, column_count - 1]
# Setting up algorithm
rf = BayesianRidge()
# Train model
rf.fit(X=x, y=y)
# Get prediction results
result = rf.predict(tX)
print("Result")
print("------")
print(result)
# Analyze performance
print("Performance")
print("-----------")
print(("Mean Absolute Error", mean_absolute_error(tY, np.array(result))))
# Dump pickle files
print((df_mapper.features))
print((rf.get_params()))
joblib.dump(df_mapper, mapper_pkl, compress=3)
joblib.dump(rf, estimator_pkl, compress=3)
# Build pmml
command = "java -jar converter-executable-1.1-SNAPSHOT.jar --pkl-mapper-input mapper.pkl --pkl-estimator-input estimator.pkl --pmml-output mapper-estimator.pmml"
os.system(command)
#-----------------------------------------------------------------------------------
# Posterior Density estimate:
count, bins, ignored = plt.hist(sigmas, 40, density=True, color='black')
plt.xlabel(r"$\sigma$")
plt.ylabel(r"value")
plt.title(r"Trace plot of $\sigma$ posterior draws")
plt.show()
# #############################################################################
# Fit the Bayesian Ridge Regression and an OLS for comparison
clf = BayesianRidge(n_iter=500, compute_score=True)
clf.fit(X, y)
beta_hat = clf.coef_
X[:10, :p]
n, k = X.shape
clf.get_params()
pred = clf.predict([[1, 0.56, 0.88]], return_std=True)
pred # yhat
yhat = pred[0]
se_yhat = pred[1]
R2 = clf.score(X, y)
R2
ols = LinearRegression()
ols.fit(X, y)
rf = BayesianRidge() # Train model rf.fit(X=x, y=y) # Get prediction results result = rf.predict(tX) print "Result" print "------" print result # Analyze performance print "Performance" print "-----------" print "Root Mean Squared Error", mean_squared_error(tY, np.array(result)) ** 0.5 print "Mean Absolute Error", mean_absolute_error(tY, np.array(result)) # Dump pickle files print df_mapper.features print rf.get_params() joblib.dump(df_mapper, mapper_pkl, compress = 3) joblib.dump(rf, estimator_pkl, compress = 3) # Build pmml command = "java -jar converter-executable-1.1-SNAPSHOT.jar --pkl-mapper-input mapper.pkl --pkl-estimator-input estimator.pkl --pmml-output mapper-estimator.pmml" os.system(command)
