def pca_prostate(ip, port):
h2o.init(ip, port)
print "Importing prostate.csv data...\n"
prostate = h2o.upload_file(h2o.locate("smalldata/logreg/prostate.csv"))
print "Converting CAPSULE, RACE, DPROS and DCAPS columns to factors"
prostate["CAPSULE"] = prostate["CAPSULE"].asfactor()
prostate["RACE"] = prostate["RACE"].asfactor()
prostate["DPROS"] = prostate["DPROS"].asfactor()
prostate["DCAPS"] = prostate["DCAPS"].asfactor()
prostate.describe()
print "PCA on columns 3 to 9 with k = 3, retx = FALSE, transform = 'STANDARDIZE'"
fitPCA = h2o.prcomp(x=prostate[2:9], k=3, transform="NONE", pca_method="Power")
pred1 = fitPCA.predict(prostate)
pred2 = h2o.get_frame(fitPCA._model_json['output']['loading_key']['name'])
print "Compare dimensions of projection and loading matrix"
print "Projection matrix:\n"
print pred1.head()
print "Loading matrix:\n"
print pred2.head()
assert pred1.nrow() == pred2.nrow(), "Expected same number of rows, but got {0} and {1}".format(pred1.nrow(),
pred2.nrow())
assert pred1.ncol() == pred2.ncol(), "Expected same number of rows, but got {0} and {1}".format(pred1.ncol(),
pred2.ncol())
def screeplot_test():
kwargs = {}
kwargs['server'] = True
australia = h2o.upload_file(pyunit_utils.locate("smalldata/pca_test/AustraliaCoast.csv"))
australia_pca = h2o.prcomp(x=australia[0:8], k = 4, transform = "STANDARDIZE")
australia_pca.screeplot(type="barplot", **kwargs)
australia_pca.screeplot(type="lines", **kwargs)
def screeplot_test(ip,port):
# Connect to h2o
h2o.init(ip,port)
kwargs = {}
kwargs['server'] = True
australia = h2o.upload_file(h2o.locate("smalldata/pca_test/AustraliaCoast.csv"))
australia_pca = h2o.prcomp(x=australia[0:8], k = 4, transform = "STANDARDIZE")
australia_pca.screeplot(type="barplot", **kwargs)
australia_pca.screeplot(type="lines", **kwargs)
def screeplot_test(ip, port):
kwargs = {}
kwargs['server'] = True
australia = h2o.upload_file(
h2o.locate("smalldata/pca_test/AustraliaCoast.csv"))
australia_pca = h2o.prcomp(x=australia[0:8], k=4, transform="STANDARDIZE")
australia_pca.screeplot(type="barplot", **kwargs)
australia_pca.screeplot(type="lines", **kwargs)
def pca_arrests(ip, port):
print "Importing USArrests.csv data..."
arrestsH2O = h2o.upload_file(h2o.locate("smalldata/pca_test/USArrests.csv"))
arrestsH2O.describe()
for i in range(4):
print "H2O PCA with " + str(i) + " dimensions:\n"
print "Using these columns: {0}".format(arrestsH2O.names)
pca_h2o = h2o.prcomp(x=arrestsH2O[0:4], k = i+1)
def pca_arrests(ip, port):
print "Importing USArrests.csv data..."
arrestsH2O = h2o.upload_file(
h2o.locate("smalldata/pca_test/USArrests.csv"))
arrestsH2O.describe()
for i in range(4):
print "H2O PCA with " + str(i) + " dimensions:\n"
print "Using these columns: {0}".format(arrestsH2O.names())
pca_h2o = h2o.prcomp(x=arrestsH2O[0:4], k=i + 1)
def pca_scoring():
print "Importing arrests.csv data..."
arrestsH2O = h2o.upload_file(h2o.locate("smalldata/pca_test/USArrests.csv"))
print "Run PCA with transform = 'DEMEAN'"
fitH2O = h2o.prcomp(x=arrestsH2O[0:4], k=4, transform="DEMEAN")
# TODO: fitH2O.show()
print "Project training data into eigenvector subspace"
predH2O = fitH2O.predict(arrestsH2O)
print "H2O Projection:"
print predH2O.head()
def pca_scoring():
print "Importing arrests.csv data..."
arrestsH2O = h2o.upload_file(
pyunit_utils.locate("smalldata/pca_test/USArrests.csv"))
print "Run PCA with transform = 'DEMEAN'"
fitH2O = h2o.prcomp(x=arrestsH2O[0:4], k=4, transform="DEMEAN")
# TODO: fitH2O.show()
print "Project training data into eigenvector subspace"
predH2O = fitH2O.predict(arrestsH2O)
print "H2O Projection:"
predH2O.head()
def pca_prostate():
print "Importing prostate.csv data...\n"
prostate = h2o.upload_file(tests.locate("smalldata/logreg/prostate.csv"))
print "Converting CAPSULE, RACE, DPROS and DCAPS columns to factors"
prostate["CAPSULE"] = prostate["CAPSULE"].asfactor()
prostate["RACE"] = prostate["RACE"].asfactor()
prostate["DPROS"] = prostate["DPROS"].asfactor()
prostate["DCAPS"] = prostate["DCAPS"].asfactor()
prostate.describe()
print "PCA on columns 3 to 9 with k = 3, retx = FALSE, transform = 'STANDARDIZE'"
fitPCA = h2o.prcomp(x=prostate[2:9], k=3, transform="NONE", pca_method="Power")
pred = fitPCA.predict(prostate)
print "Projection matrix:\n"
print pred.head()
def pca_prostate(ip, port):
print "Importing prostate.csv data...\n"
prostate = h2o.upload_file(h2o.locate("smalldata/logreg/prostate.csv"))
print "Converting CAPSULE, RACE, DPROS and DCAPS columns to factors"
prostate["CAPSULE"] = prostate["CAPSULE"].asfactor()
prostate["RACE"] = prostate["RACE"].asfactor()
prostate["DPROS"] = prostate["DPROS"].asfactor()
prostate["DCAPS"] = prostate["DCAPS"].asfactor()
prostate.describe()
print "PCA on columns 3 to 9 with k = 3, retx = FALSE, transform = 'STANDARDIZE'"
fitPCA = h2o.prcomp(x=prostate[2:9], k=3, transform="NONE", pca_method="Power")
pred = fitPCA.predict(prostate)
print "Projection matrix:\n"
print pred.head()