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')
def SVR_ST(trainFileName, testFileName):
trainData = ld.LoadData_DATA_ST(trainFileName)
testData = ld.LoadData_DATA_ST(testFileName)
store = ['1', '2', '3', '4', '5']
res = []
for i in store:
train_X = []
train_y = []
context = trainData[i]
for array in context:
array = [float(x) for x in array[2:]]
train_X.append((array[2:-1]))
train_y.append(array[-1])
test_X = []
items = []
context = testData[i]
for array in context:
items.append((array[0], array[1]))
array = [float(x) for x in array[2:]]
test_X.append((array[2:]))
train_X = np.matrix(train_X)
test_X = np.matrix(test_X)
svr = SVR(kernel='linear', epsilon=0.5, C=1)
pred_y = svr.fit(train_X[:, -8:-3], train_y).predict(test_X[:, -7:-2])
for i in range(len(test_X)):
res.append([
items[i][0], items[i][1],
'%.4f' % max(pred_y[i], 0),
'%.4f' % test_X[i, -4],
'%.4f' % (float(test_X[i, -5]) * 2)
])
return res
def SVR_ST(trainFileName,testFileName):
trainData = ld.LoadData_DATA_ST(trainFileName)
testData = ld.LoadData_DATA_ST(testFileName)
store = ['1','2','3','4','5']
res = []
for i in store:
train_X = [];train_y = []
context = trainData[i]
for array in context:
array = [float(x) for x in array[2:] ]
train_X.append((array[2:-1]))
train_y.append(array[-1])
test_X = [];items = []
context = testData[i]
for array in context:
items.append((array[0],array[1]))
array = [float(x) for x in array[2:] ]
test_X.append((array[2:]))
train_X=np.matrix(train_X)
test_X = np.matrix(test_X)
svr= SVR(kernel='linear',epsilon=0.5,C=1)
pred_y=svr.fit(train_X[:,-8:-3], train_y).predict(test_X[:,-7:-2])
for i in range(len(test_X)):
res.append([items[i][0],items[i][1],'%.4f'%max(pred_y[i],0),'%.4f'%test_X[i,-4],'%.4f'%(float(test_X[i,-5])*2)])
return res
def SVR_ST_train():
trainData = ld.loadData_ST('./data/EVAL_DataSetST1.csv')
testData = ld.loadData_ST('./data/VALIDATION_DataSetST1.csv')
store = ['1','2','3','4','5']
res = []
for i in store:
train_X = [];train_y = []
context = trainData[i]
for array in context:
array = [float(x) for x in array[2:] ]
train_X.append((array[2:-1]))
train_y.append(array[-1])
test_X = [];test_y = [];items = []
context = testData[i]
for array in context:
items.append((array[0],array[1]))
array = [float(x) for x in array[2:] ]
test_X.append((array[2:-1]))
test_y.append(array[-1])
train_X=np.matrix(train_X)
test_X = np.matrix(test_X)
svr= SVR(kernel='linear',epsilon=0.5,C=1)
pred_y=svr.fit(train_X[:,-8:-1], train_y).predict(test_X[:,-8:-1])
for i in range(len(test_X)):
res.append([items[i][0],items[i][1],'%.2f'%max(pred_y[i],0),'%.2f'%max(test_X[i,-4],0),'%.2f'%max(2*test_X[i,-5],0)])
return res
def SVR_ALL(trainFileName,testFileName):
train_X,train_y,_= ld.LoadData_DATA_LABEL_ITEM(trainFileName)
test_X,items= ld.LoadData_DATA_ITEM(testFileName)
train_X=np.matrix(train_X)
test_X = np.matrix(test_X)
svr= SVR(kernel='linear',epsilon=0.5,C=1)
pred_y=svr.fit(train_X[:,-8:-3], train_y).predict(test_X[:,-7:-2])
res =[]
for i in range(len(test_X)):
res.append([items[i],'all','%.4f'%max(pred_y[i],0),'%.4f'%test_X[i,-4],'%.4f'%(float(test_X[i,-5])*2)])
return res
def SVR_ALL_train():
train_X,train_y,_= ld.loadData_all('./data/EVAL_DataSet1.csv')
test_X,test_y,items = ld.loadData_all('./data/VALIDATION_DataSet1.csv')
train_X=np.matrix(train_X)
test_X = np.matrix(test_X)
svr= SVR(kernel='linear',epsilon=0.5,C=1)
pred_y=svr.fit(train_X[:,-8:-1], train_y).predict(test_X[:,-8:-1])
res =[]
for i in range(len(test_X)):
res.append([items[i],'all','%.2f'%max(pred_y[i],0),'%.2f'%test_X[i,-4],'%.2f'%(float(test_X[i,-5])*2)])
return res
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)
def SVR_ALL(trainFileName, testFileName):
train_X, train_y, _ = ld.LoadData_DATA_LABEL_ITEM(trainFileName)
test_X, items = ld.LoadData_DATA_ITEM(testFileName)
train_X = np.matrix(train_X)
test_X = np.matrix(test_X)
svr = SVR(kernel='linear', epsilon=0.5, C=1)
pred_y = svr.fit(train_X[:, -8:-3], train_y).predict(test_X[:, -7:-2])
res = []
for i in range(len(test_X)):
res.append([
items[i], 'all',
'%.4f' % max(pred_y[i], 0),
'%.4f' % test_X[i, -4],
'%.4f' % (float(test_X[i, -5]) * 2)
])
return res
def SVR_ALL_train():
train_X, train_y, _ = ld.loadData_all('./data/EVAL_DataSet1.csv')
test_X, test_y, items = ld.loadData_all('./data/VALIDATION_DataSet1.csv')
train_X = np.matrix(train_X)
test_X = np.matrix(test_X)
svr = SVR(kernel='linear', epsilon=0.5, C=1)
pred_y = svr.fit(train_X[:, -8:-1], train_y).predict(test_X[:, -8:-1])
res = []
for i in range(len(test_X)):
res.append([
items[i], 'all',
'%.2f' % max(pred_y[i], 0),
'%.2f' % test_X[i, -4],
'%.2f' % (float(test_X[i, -5]) * 2)
])
return res
def SVR_ST_train():
trainData = ld.loadData_ST('./data/EVAL_DataSetST1.csv')
testData = ld.loadData_ST('./data/VALIDATION_DataSetST1.csv')
store = ['1', '2', '3', '4', '5']
res = []
for i in store:
train_X = []
train_y = []
context = trainData[i]
for array in context:
array = [float(x) for x in array[2:]]
train_X.append((array[2:-1]))
train_y.append(array[-1])
test_X = []
test_y = []
items = []
context = testData[i]
for array in context:
items.append((array[0], array[1]))
array = [float(x) for x in array[2:]]
test_X.append((array[2:-1]))
test_y.append(array[-1])
train_X = np.matrix(train_X)
test_X = np.matrix(test_X)
svr = SVR(kernel='linear', epsilon=0.5, C=1)
pred_y = svr.fit(train_X[:, -8:-1], train_y).predict(test_X[:, -8:-1])
for i in range(len(test_X)):
res.append([
items[i][0], items[i][1],
'%.2f' % max(pred_y[i], 0),
'%.2f' % max(test_X[i, -4], 0),
'%.2f' % max(2 * test_X[i, -5], 0)
])
return res
def train(driverSpeed, sectionSpeed, newData, firstTime, n, minLon, lonLen,
minLat, latLen, defaultVel):
'''返回SVR,由[路段平均速度，个人平均速度，载客信息]->瞬时速度训练得到'''
X = []
Y = []
for file in newData:
df = pandas.read_csv(
file,
header=None,
names=["taxiId", "lat", "lon", "busy", "time", "vel", "sec"],
dtype={
"taxiId": numpy.int16,
"lat": numpy.float32,
"lon": numpy.float32,
"busy": numpy.int8,
"time": numpy.str,
"vel": numpy.float32,
"sec": numpy.int16
})
taxiId1 = -1
sectionId1 = 0
busy1 = 0
time1 = firstTime
for row in df.itertuples(index=False):
taxiId2 = row[0]
busy2 = row[3]
time2 = datetime.datetime.strptime(row[4], "%Y/%m/%d %H:%M:%S")
v = row[5]
sectionId2 = row[6]
if taxiId1 == taxiId2 and time1.hour == time2.hour and not numpy.isnan(
v):
#前一个点额瞬时速度
Y.append(v)
x = []
#路段平均速度
v = sectionSpeed[sectionId1][time1.hour - firstTime.hour]
if numpy.isnan(v):
x.append(defaultVel)
else:
x.append(v)
#个人平均速度
v = driverSpeed[taxiId1 - 1][time1.hour - firstTime.hour]
if numpy.isnan(v):
x.append(defaultVel)
else:
x.append(v)
#是否载客
x.append(busy1)
X.append(x)
taxiId1 = taxiId2
busy1 = busy2
time1 = time2
sectionId1 = sectionId2
clf = SVR(C=1.0,
cache_size=200,
coef0=0.0,
degree=3,
epsilon=0.2,
gamma='auto',
kernel='rbf',
max_iter=-1,
shrinking=True,
tol=0.001,
verbose=False)
clf.fit(X, Y)
return clf
def __sv_regressor__(self, data, target):
from sklearn.svm.classes import SVR
svr_rbf = SVR(kernel='rbf', C=1e3, gamma=0.1)
svr_rbf.fit(data, target)
self.ensemble = svr_rbf
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")