def setUp(self):
cols = ['ThirtyDayReadmitFLG', 'SystolicBPNBR', 'LDLNBR']
df = pd.read_csv(fixture('HCPyDiabetesClinical.csv'),
na_values=['None'],
usecols=cols)
np.random.seed(42)
self.o = DevelopSupervisedModel(modeltype='classification',
df=df,
predictedcol='ThirtyDayReadmitFLG',
impute=True)
def main():
t0 = time.time()
# CSV snippet for reading data into dataframe
df = pd.read_csv(
'healthcareai/tests/fixtures/DiabetesClinicalSampleData.csv',
na_values=['None'])
# SQL snippet for reading data into dataframe
# import pyodbc
# cnxn = pyodbc.connect("""SERVER=localhost;
# DRIVER={SQL Server Native Client 11.0};
# Trusted_Connection=yes;
# autocommit=True""")
#
# df = pd.read_sql(
# sql="""SELECT
# *
# FROM [SAM].[dbo].[HCPyDiabetesClinical]""",
# con=cnxn)
#
# # Set None string to be None type
# df.replace(['None'],[None],inplace=True)
# Look at data that's been pulled in
print(df.head())
print(df.dtypes)
# Drop columns that won't help machine learning
df.drop(['PatientID', 'InTestWindowFLG'], axis=1, inplace=True)
# Step 1: compare two models
o = DevelopSupervisedModel(
modeltype='classification',
df=df,
predictedcol='ThirtyDayReadmitFLG',
graincol='PatientEncounterID', #OPTIONAL
impute=True,
debug=False)
# Run the linear model
o.linear(cores=1)
# Run the random forest model
o.random_forest(cores=1, tune=True)
# Look at the RF feature importance rankings
o.plot_rffeature_importance(save=False)
# Create ROC plot to compare the two models
o.plot_roc(debug=False, save=False)
print('\nTime:\n', time.time() - t0)
def setUp(self):
df = pd.read_csv(fixture('HCPyDiabetesClinical.csv'),
na_values=['None'])
# Drop uninformative columns
df.drop(['PatientID', 'InTestWindowFLG'], axis=1, inplace=True)
np.random.seed(42)
self.o = DevelopSupervisedModel(modeltype='classification',
df=df,
predictedcol='ThirtyDayReadmitFLG',
impute=True)
self.o.linear(cores=1)
def setUp(self):
df = pd.read_csv(fixture('DiabetesClinicalSampleData.csv'),
na_values=['None'])
# Drop uninformative columns
df.drop(['PatientID', 'InTestWindowFLG'], axis=1, inplace=True)
# Convert numeric columns to factor/category columns
np.random.seed(42)
self.o = DevelopSupervisedModel(modeltype='classification',
df=df,
predictedcol='ThirtyDayReadmitFLG',
impute=True)
self.o.random_forest(cores=1)
class TestLinearDevTuneFalse(unittest.TestCase):
def setUp(self):
df = pd.read_csv(fixture('HCPyDiabetesClinical.csv'),
na_values=['None'])
# Drop uninformative columns
df.drop(['PatientID', 'InTestWindowFLG'], axis=1, inplace=True)
np.random.seed(42)
self.o = DevelopSupervisedModel(modeltype='classification',
df=df,
predictedcol='ThirtyDayReadmitFLG',
impute=True)
self.o.linear(cores=1)
def runTest(self):
self.assertAlmostEqual(np.round(self.o.au_roc, 6), 0.672075)
def tearDown(self):
del self.o
class TestRFDevTuneFalse(unittest.TestCase):
def setUp(self):
df = pd.read_csv(fixture('DiabetesClinicalSampleData.csv'),
na_values=['None'])
# Drop uninformative columns
df.drop(['PatientID', 'InTestWindowFLG'], axis=1, inplace=True)
# Convert numeric columns to factor/category columns
np.random.seed(42)
self.o = DevelopSupervisedModel(modeltype='classification',
df=df,
predictedcol='ThirtyDayReadmitFLG',
impute=True)
self.o.random_forest(cores=1)
def runTest(self):
self.assertAlmostEqual(np.round(self.o.au_roc, 6), 0.965070)
def tearDown(self):
del self.o
class TestRFDevTuneTrue2ColError(unittest.TestCase):
def setUp(self):
cols = ['ThirtyDayReadmitFLG', 'SystolicBPNBR', 'LDLNBR']
df = pd.read_csv(fixture('HCPyDiabetesClinical.csv'),
na_values=['None'],
usecols=cols)
np.random.seed(42)
self.o = DevelopSupervisedModel(modeltype='classification',
df=df,
predictedcol='ThirtyDayReadmitFLG',
impute=True)
def runTest(self):
self.assertRaises(ValueError,
lambda: self.o.random_forest(cores=1, tune=True))
def tearDown(self):
del self.o