alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-12-27 01:59:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

analysis.py v 1,1,5,001

Browse Source
This commit is contained in:
art 2019-10-25 09:19:18 -05:00
parent ff2f0787ae
commit 56b575a753
3 changed files with 24 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

Binary file not shown.

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

Binary file not shown.

54
data analysis/analysis/analysis.py
View File

@ -7,10 +7,12 @@
# current benchmark of optimization: 1.33 times faster # current benchmark of optimization: 1.33 times faster
# setup: # setup:
__version__ = "1.1.5.000" __version__ = "1.1.5.001"
# changelog should be viewed using print(analysis.__changelog__) # changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog: __changelog__ = """changelog:
1.1.5.001:
- simplified regression by using .to(device)
1.1.5.000: 1.1.5.000:
- added polynomial regression to regression(); untested - added polynomial regression to regression(); untested
1.1.4.000: 1.1.4.000:
@ -256,29 +258,26 @@ def histo_analysis(hist_data):
def regression(device, inputs, outputs, args, loss = torch.nn.MSELoss(), _iterations = 10000, lr = 0.01, _iterations_ply = 10000, lr_ply = 0.01, power_limit = None): # inputs, outputs expects N-D array def regression(device, inputs, outputs, args, loss = torch.nn.MSELoss(), _iterations = 10000, lr = 0.01, _iterations_ply = 10000, lr_ply = 0.01, power_limit = None): # inputs, outputs expects N-D array
if power_limit == None: if power_limit == None:
power_limit = len(outputs[0]) power_limit = len(outputs)
else: else:
power_limit += 1 power_limit += 1
regressions = [] regressions = []
if 'cuda' in device:
Regression.set_device(device) Regression.set_device(device)
if 'lin' in args: if 'lin' in args:
model = Regression.SGDTrain(Regression.LinearRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float).cuda(), torch.tensor([outputs]).to(torch.float).cuda(), iterations=_iterations, learning_rate=lr, return_losses=True) model = Regression.SGDTrain(Regression.LinearRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float).to(device), torch.tensor([outputs]).to(torch.float).to(device), iterations=_iterations, learning_rate=lr, return_losses=True)
regressions.append((model[0].parameters, model[1][::-1][0])) regressions.append((model[0].parameters, model[1][::-1][0]))
if 'log' in args: if 'log' in args:
model = Regression.SGDTrain(Regression.LogRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float).cuda(), torch.tensor(outputs).to(torch.float).cuda(), iterations=_iterations, learning_rate=lr, return_losses=True) model = Regression.SGDTrain(Regression.LogRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float).to(device), torch.tensor(outputs).to(torch.float).to(device), iterations=_iterations, learning_rate=lr, return_losses=True)
regressions.append((model[0].parameters, model[1][::-1][0])) regressions.append((model[0].parameters, model[1][::-1][0]))
if 'exp' in args: if 'exp' in args:
model = Regression.SGDTrain(Regression.ExpRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float).cuda(), torch.tensor(outputs).to(torch.float).cuda(), iterations=_iterations, learning_rate=lr, return_losses=True) model = Regression.SGDTrain(Regression.ExpRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float).to(device), torch.tensor(outputs).to(torch.float).to(device), iterations=_iterations, learning_rate=lr, return_losses=True)
regressions.append((model[0].parameters, model[1][::-1][0])) regressions.append((model[0].parameters, model[1][::-1][0]))
if 'ply' in args: if 'ply' in args:
@ -287,49 +286,14 @@ def regression(device, inputs, outputs, args, loss = torch.nn.MSELoss(), _iterat
for i in range(2, power_limit): for i in range(2, power_limit):
model = Regression.SGDTrain(Regression.PolyRegKernel(len(inputs),i), torch.tensor(inputs).to(torch.float).cuda(), torch.tensor(outputs).to(torch.float).cuda(), iterations=_iterations_ply * 10 ** i, learning_rate=lr_ply * 10 ** -i, return_losses=True) model = Regression.SGDTrain(Regression.PolyRegKernel(len(inputs),i), torch.tensor(inputs).to(torch.float).to(device), torch.tensor(outputs).to(torch.float).to(device), iterations=_iterations_ply * 10 ** i, learning_rate=lr_ply * 10 ** -i, return_losses=True)
plys.append((model[0].parameters, model[1][::-1][0])) plys.append((model[0].parameters, model[1][::-1][0]))
regressions.append(plys) regressions.append(plys)
if 'sig' in args: if 'sig' in args:
model = Regression.SGDTrain(Regression.SigmoidalRegKernelArthur(len(inputs)), torch.tensor(inputs).to(torch.float).cuda(), torch.tensor(outputs).to(torch.float).cuda(), iterations=_iterations, learning_rate=lr, return_losses=True) model = Regression.SGDTrain(Regression.SigmoidalRegKernelArthur(len(inputs)), torch.tensor(inputs).to(torch.float).to(device), torch.tensor(outputs).to(torch.float).to(device), iterations=_iterations, learning_rate=lr, return_losses=True)
regressions.append((model[0].parameters, model[1][::-1][0]))
else:
Regression.set_device(device)
if 'linear' in args:
model = Regression.SGDTrain(Regression.LinearRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float), torch.tensor(outputs).to(torch.float), iterations=_iterations, learning_rate=lr, return_losses=True)
regressions.append((model[0].parameters, model[1][::-1][0]))
if 'log' in args:
model = Regression.SGDTrain(Regression.LogRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float), torch.tensor(outputs).to(torch.float), iterations=_iterations, learning_rate=lr, return_losses=True)
regressions.append((model[0].parameters, model[1][::-1][0]))
if 'exp' in args:
model = Regression.SGDTrain(Regression.ExpRegKernel(len(inputs)), torch.tensor(inputs).to(torch.float), torch.tensor(outputs).to(torch.float), iterations=_iterations, learning_rate=lr, return_losses=True)
regressions.append((model[0].parameters, model[1][::-1][0]))
if 'ply' in args:
plys = []
for i in range(2, power_limit):
model = Regression.SGDTrain(Regression.PolyRegKernel(len(inputs),i), torch.tensor(inputs).to(torch.float), torch.tensor(outputs).to(torch.float), iterations=_iterations_ply * 10 ** i, learning_rate=lr_ply * 10 ** -i, return_losses=True)
plys.append((model[0].parameters, model[1][::-1][0]))
regressions.append(plys)
if 'sig' in args:
model = Regression.SGDTrain(Regression.SigmoidalRegKernelArthur(len(inputs)), torch.tensor(inputs).to(torch.float), torch.tensor(outputs).to(torch.float), iterations=_iterations, learning_rate=lr, return_losses=True)
regressions.append((model[0].parameters, model[1][::-1][0])) regressions.append((model[0].parameters, model[1][::-1][0]))
return regressions return regressions