def test_ml_pipeline():
'load a test data set, run SVM on it, and plot the predictions vs the actual values'
data, targets = ReactivityDataLoader().load_mopac_learning()
regressor = SVR(C=1000)
trainData, testData, trainTargets, testTargets = train_test_split(data, targets)
regressor.fit(trainData, trainTargets)
os.chdir(str(Path.home() / 'Desktop'))
main.plotScatterPlot(testTargets, regressor.predict(testData), 'predictedVsActual')
class SVRImpl():
def __init__(self,
kernel='rbf',
degree=3,
gamma='auto_deprecated',
coef0=0.0,
tol=0.001,
C=1.0,
epsilon=0.1,
shrinking=True,
cache_size=200,
verbose=False,
max_iter=(-1)):
self._hyperparams = {
'kernel': kernel,
'degree': degree,
'gamma': gamma,
'coef0': coef0,
'tol': tol,
'C': C,
'epsilon': epsilon,
'shrinking': shrinking,
'cache_size': cache_size,
'verbose': verbose,
'max_iter': max_iter
}
self._wrapped_model = SKLModel(**self._hyperparams)
def fit(self, X, y=None):
if (y is not None):
self._wrapped_model.fit(X, y)
else:
self._wrapped_model.fit(X)
return self
def predict(self, X):
return self._wrapped_model.predict(X)
from ex30.ex30_lib_graph import plot2
from sklearn.svm.classes import SVR
OUTPUT_PNG_FILE = '/experiments/ex30/ex30_svr.png'
X = [[float(x)] for x in range(0, 24)]
Y = [
12.0, 13.0, 13.0, 13.0, 28.0, 31.0, 38.0, 60.0, 85.0, 80.0, 64.0, 60.0,
59.0, 58.0, 65.0, 70.0, 80.0, 90.0, 110.0, 100.0, 85.0, 65.0, 45.0, 20.0
]
X2 = [[float(x) / 10.0] for x in range(0, 231)]
model = SVR(kernel='rbf', C=10)
model.fit(X, Y)
Y_pred = model.predict(X2)
print(str(Y_pred))
plot2(Y, Y_pred, OUTPUT_PNG_FILE, "Observed pollution concentration levels",
"Predicted pollution concentration levels by SVR")
