class TestLinearDeploy(unittest.TestCase):
    def setUp(self):
        df = pd.read_csv(fixture('HCPyDiabetesClinical.csv'),
                         na_values=['None'])
        df.drop('PatientID', axis=1, inplace=True)  # drop uninformative column

        np.random.seed(42)
        self.o = DeploySupervisedModel(modeltype='classification',
                                       df=df,
                                       graincol='PatientEncounterID',
                                       windowcol='InTestWindowFLG',
                                       predictedcol='ThirtyDayReadmitFLG',
                                       impute=True)
        self.o.deploy(
            method='linear',
            cores=1,
            server='localhost',
            dest_db_schema_table='[SAM].[dbo].[HCPyDeployClassificationBASE]',
            use_saved_model=False)

    def runTest(self):

        self.assertAlmostEqual(np.round(self.o.y_pred[5], 5), 0.18087)

    def tearDown(self):
        del self.o
Beispiel #2
0
def main():

    t0 = time.time()

    # Load in data
    # CSV snippet for reading data into dataframe
    df = pd.read_csv('healthcareai/tests/fixtures/HCPyDiabetesClinical.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', axis=1, inplace=True)

    p = DeploySupervisedModel(modeltype='regression',
                              df=df,
                              graincol='PatientEncounterID',
                              windowcol='InTestWindowFLG',
                              predictedcol='LDLNBR',
                              impute=True,
                              debug=False)

    p.deploy(method='rf',
             cores=2,
             server='localhost',
             dest_db_schema_table='[SAM].[dbo].[HCPyDeployRegressionBASE]',
             use_saved_model=False,
             trees=200,
             debug=False)

    print('\nTime:\n', time.time() - t0)
Beispiel #3
0
    def setUp(self):
        df = pd.read_csv(fixture('DiabetesClinicalSampleData.csv'),
                         na_values=['None'])
        df.drop('PatientID', axis=1, inplace=True)  # drop uninformative column

        np.random.seed(42)
        self.o = DeploySupervisedModel(modeltype='classification',
                                       df=df,
                                       graincol='PatientEncounterID',
                                       windowcol='InTestWindowFLG',
                                       predictedcol='ThirtyDayReadmitFLG',
                                       impute=True)
        self.o.deploy(
            method='linear',
            cores=1,
            server='localhost',
            dest_db_schema_table='[SAM].[dbo].[HCPyDeployClassificationBASE]',
            use_saved_model=False)