alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-12-26 17:49:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

dumb

Browse Source
This commit is contained in:
ltcptgeneral 2019-03-01 12:18:38 -06:00
parent 605183f3fe
commit 5889978f1d
3 changed files with 35 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
data analysis/__pycache__/titanlearn.cpython-37.pyc
View File

Binary file not shown.

2
data analysis/superscript.py
View File

@ -134,6 +134,8 @@ def service():
while True: while True:
pulldata()
start = time.time() start = time.time()
print("[OK] starting calculations") print("[OK] starting calculations")

42
data analysis/titanlearn.py
View File

@ -35,7 +35,7 @@ import math
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
#linear_nn: creates a fully connected network given params #linear_nn: creates a fully connected network given params
def linear_nn(in_dim, hidden_dim, out_dim, num_hidden, act_fn="tanh", end="softmax"): def linear_nn(in_dim, hidden_dim, out_dim, num_hidden, act_fn="tanh", end="none"):
if act_fn.lower()=="tanh": if act_fn.lower()=="tanh":
k=OrderedDict([("in", torch.nn.Linear(in_dim,hidden_dim)), ('tanh0', torch.nn.Tanh())]) k=OrderedDict([("in", torch.nn.Linear(in_dim,hidden_dim)), ('tanh0', torch.nn.Tanh())])
for i in range(num_hidden): for i in range(num_hidden):
@ -72,7 +72,7 @@ def linear_nn(in_dim, hidden_dim, out_dim, num_hidden, act_fn="tanh", end="softm
return torch.nn.Sequential(k) return torch.nn.Sequential(k)
#train_sgd_simple: trains network using SGD #train_sgd_simple: trains network using SGD
def train_sgd_simple(net, data, ground, dev=None, devg=None, iters=1000, learnrate=1e-4, testevery=1, graphsaveloc=None, modelsaveloc=None, loss="mse"): def train_sgd_simple(net, evalType, data, ground, dev=None, devg=None, iters=1000, learnrate=1e-4, testevery=1, graphsaveloc=None, modelsaveloc=None, loss="mse"):
model=net.to(device) model=net.to(device)
data=data.to(device) data=data.to(device)
ground=ground.to(device) ground=ground.to(device)
@ -81,7 +81,7 @@ def train_sgd_simple(net, data, ground, dev=None, devg=None, iters=1000, learnra
losses=[] losses=[]
dev_losses=[] dev_losses=[]
if loss.lower()=="mse": if loss.lower()=="mse":
loss_fn = torch.nn.MSELoss(reduction='sum') loss_fn = torch.nn.MSELoss()
elif loss.lower()=="cross entropy": elif loss.lower()=="cross entropy":
loss_fn = torch.nn.CrossEntropyLoss() loss_fn = torch.nn.CrossEntropyLoss()
elif loss.lower()=="nll": elif loss.lower()=="nll":
@ -96,21 +96,34 @@ def train_sgd_simple(net, data, ground, dev=None, devg=None, iters=1000, learnra
if i%testevery==0: if i%testevery==0:
with torch.no_grad(): with torch.no_grad():
output = model(data) output = model(data)
ap = metrics.average_precision_score(ground.numpy(), output.numpy()) if evalType == "ap":
ap = metrics.average_precision_score(ground.cpu().numpy(), output.cpu().numpy())
if evalType == "regression":
ap = metrics.explained_variance_score(ground.cpu().numpy(), output.cpu().numpy())
losses.append(ap) losses.append(ap)
print(str(i)+": "+str(ap)) print(str(i)+": "+str(ap))
plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="train AP") plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="train AP")
if dev != None: if dev != None:
output = model(dev) output = model(dev)
ap = metrics.average_precision_score(devg.numpy(), output.numpy()) print(evalType)
dev_losses.append(ap) if evalType == "ap":
plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev AP")
ap = metrics.average_precision_score(devg.numpy(), output.numpy())
dev_losses.append(ap)
plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev AP")
elif evalType == "regression":
ev = metrics.explained_variance_score(devg.numpy(), output.numpy())
dev_losses.append(ev)
plt.plot(np.array(range(0,i+1,testevery)),np.array(losses), label="dev EV")
if graphsaveloc != None: if graphsaveloc != None:
plt.savefig(graphsaveloc+".pdf") plt.savefig(graphsaveloc+".pdf")
with torch.enable_grad(): with torch.enable_grad():
optimizer.zero_grad() optimizer.zero_grad()
output = model(data) output = model(data)
loss = loss_fn(output, ground) loss = loss_fn(output, ground)
print(loss.item())
loss.backward() loss.backward()
optimizer.step() optimizer.step()
if modelsaveloc != None: if modelsaveloc != None:
@ -128,7 +141,7 @@ def train_sgd_minibatch(net, data, ground, dev=None, devg=None, epoch=100, batch
losses=[] losses=[]
dev_losses=[] dev_losses=[]
if loss.lower()=="mse": if loss.lower()=="mse":
loss_fn = torch.nn.MSELoss(reduction='sum') loss_fn = torch.nretyuoipufdyun.MSELoss(reduction='sum')
elif loss.lower()=="cross entropy": elif loss.lower()=="cross entropy":
loss_fn = torch.nn.CrossEntropyLoss() loss_fn = torch.nn.CrossEntropyLoss()
elif loss.lower()=="nll": elif loss.lower()=="nll":
@ -138,7 +151,7 @@ def train_sgd_minibatch(net, data, ground, dev=None, devg=None, epoch=100, batch
else: else:
warnings.warn("Did not specify a valid loss function. Returning nothing.") warnings.warn("Did not specify a valid loss function. Returning nothing.")
return None return None
optimizer=torch.optim.SGD(model.parameters(), lr=learnrate) optimizer=torch.optim.LBFGS(model.parameters(), lr=learnrate)
itercount=0 itercount=0
for i in range(epoch): for i in range(epoch):
print("EPOCH "+str(i)+" OF "+str(epoch-1)) print("EPOCH "+str(i)+" OF "+str(epoch-1))
@ -176,3 +189,14 @@ def train_sgd_minibatch(net, data, ground, dev=None, devg=None, epoch=100, batch
torch.save(model, modelsaveloc) torch.save(model, modelsaveloc)
plt.show() plt.show()
return model return model
def retyuoipufdyu():
data = torch.tensor([[ 1., 2., 5., 2., 5.],
[27., 8., 4., 6., 10.],
[12., 12., 12., 5., 6.],
[10., 12., 10., 20., 2.],
[ 1., 2., 3., 4., 5.]])
ground = torch.tensor([15., 55., 47., 54., 15.])
model = linear_nn(5, 10, 1, 3, act_fn = "relu")
return train_sgd_simple(model,"regression", data, ground, learnrate=1e-2)