import sys
from collections import OrderedDict
sys.path.append("../..")
import ktensor
import tensorTools
def loadJSON(fn):
with open(fn, 'rb') as outfile:
jsonDict = json.load(outfile)
outfile.close()
return jsonDict
MBias = ktensor.loadTensor(
"../results/pred-raw-bias-marble-{0}.dat".format(run))
M = ktensor.loadTensor("../results/pred-raw-marble-{0}.dat".format(run))
MCP = ktensor.loadTensor("../results/pred-raw-cpapr-{0}.dat".format(run))
X, axisDict, classDict = tensorTools.loadSingleTensor(
"../data/cms-tensor-{0}.dat")
cptLevel = loadJSON("../data/cpt-level2.json")
icdLevel = loadJSON("../data/icd-level2.json")
## lookup values
def lookupDict(idx, n, axisDict, levelDict):
ivAxis = {v: k for k, v in axisDict[n].items()}
modeCat = [levelDict[str(ivAxis[k])] for k in idx]
return modeCat
import json
import sys
from collections import OrderedDict
sys.path.append("../..")
import ktensor
import tensorTools
def loadJSON(fn):
with open(fn, 'rb') as outfile:
jsonDict = json.load(outfile)
outfile.close()
return jsonDict
MBias = ktensor.loadTensor("../results/pred-raw-bias-marble-{0}.dat".format(run))
M = ktensor.loadTensor("../results/pred-raw-marble-{0}.dat".format(run))
MCP = ktensor.loadTensor("../results/pred-raw-cpapr-{0}.dat".format(run))
X, axisDict, classDict = tensorTools.loadSingleTensor("../data/cms-tensor-{0}.dat")
cptLevel = loadJSON("../data/cpt-level2.json")
icdLevel = loadJSON("../data/icd-level2.json")
## lookup values
def lookupDict(idx, n, axisDict, levelDict):
ivAxis = {v: k for k, v in axisDict[n].items()}
modeCat = [levelDict[str(ivAxis[k])] for k in idx]
return modeCat
## get the top k from MBias
import ktensor
import numpy
import decompTools
caseX = ktensor.loadTensor("results/apr-raw-1.dat")
controlX = ktensor.loadTensor("results/apr-raw-2.dat")
allX = ktensor.loadTensor("results/apr-raw-200.dat")
## since they don't share the same axis, remove one of the factors
caseX.U = [caseX.U[1], caseX.U[2]]
caseX = decompTools.zeroSmallFactors(caseX, 1e-2)
controlX.U = [controlX.U[1], controlX.U[2]]
controlX = decompTools.zeroSmallFactors(controlX, 1e-2)
allX.U = [allX.U[1], allX.U[2]]
allX = decompTools.zeroSmallFactors(allX, 1e-2)
fms = caseX.greedy_fms(controlX)
numpy.savetxt("plots/case-control.csv", fms, delimiter=",")
allFMS = caseX.greedy_fms(allX)
numpy.savetxt("plots/case-all.csv", allFMS, delimiter=",")
import ktensor
import numpy;
import decompTools
caseX = ktensor.loadTensor("results/apr-raw-1.dat")
controlX = ktensor.loadTensor("results/apr-raw-2.dat")
allX = ktensor.loadTensor("results/apr-raw-200.dat")
## since they don't share the same axis, remove one of the factors
caseX.U = [caseX.U[1], caseX.U[2]]
caseX = decompTools.zeroSmallFactors(caseX, 1e-2)
controlX.U = [controlX.U[1], controlX.U[2]]
controlX = decompTools.zeroSmallFactors(controlX, 1e-2)
allX.U = [allX.U[1], allX.U[2]]
allX = decompTools.zeroSmallFactors(allX, 1e-2)
fms = caseX.greedy_fms(controlX)
numpy.savetxt("plots/case-control.csv", fms, delimiter=",")
allFMS = caseX.greedy_fms(allX)
numpy.savetxt("plots/case-all.csv", allFMS, delimiter=",")
import numpy as np
import json
import sys
sys.path.append("../..")
import ktensor
import tensorTools
dataOut = []
bins = [None, None, None]
for run in range(400, 409):
M = ktensor.loadTensor("../results/pred-raw-cpapr-{0}.dat".format(run))
for n in range(M.ndims()):
factVals = M.U[n].flatten()
nnzIdx = np.nonzero(factVals)
factVals = factVals[nnzIdx]
if bins[n] == None:
factHist = np.histogram(factVals, bins=10)
bins[n] = factHist[1]
else:
factHist = np.histogram(factVals, bins=bins[n])
dataOut.append({"expt": run, "mode": n, "count": factHist[0].tolist(), "bins": factHist[1].tolist()})
with open("cpapr-hist.json", "w") as outfile:
json.dump(dataOut, outfile)
import numpy as np
import json
import sys
sys.path.append("../..")
import ktensor
import tensorTools
dataOut = []
bins = [None, None, None]
for run in range(400, 409):
M = ktensor.loadTensor("../results/pred-raw-cpapr-{0}.dat".format(run))
for n in range(M.ndims()):
factVals = M.U[n].flatten()
nnzIdx = np.nonzero(factVals)
factVals = factVals[nnzIdx]
if bins[n] == None:
factHist = np.histogram(factVals, bins=10)
bins[n] = factHist[1]
else:
factHist = np.histogram(factVals, bins=bins[n])
dataOut.append({
"expt": run,
"mode": n,
"count": factHist[0].tolist(),
"bins": factHist[1].tolist()
})
with open("cpapr-hist.json", 'w') as outfile:
json.dump(dataOut, outfile)