def main():
print('Test: Default')
api.set_port_callback(inports[0]['name'], call_on_input)
print('Test: config')
config = api.config
config.columns = 'All'
config.info_only = True
df = pd.DataFrame({
'icol': [1, 1, 1, 1, 1],
'xcol2': ['A', 'A', 'B', 'B', 'C'],
'xcol3': ['A', 'A', 'C', 'D', 'E'],
'xcol4': ['A', 'A', 'b', 'a', 'c'],
'xcol5': ['A', 'A', 'A', 'A', 'A']
})
test_msg = api.Message(attributes={'name': 'test1'}, body=df)
log, data, trans = api.call(config, test_msg)
print('Attributes: ', data.attributes)
print('Body: ', str(data.body))
print('Attributes: ', trans.attributes)
print('Body: ', str(trans.body))
print('Logging: ')
print(log)
gs.gensolution(os.path.realpath(__file__),
config,
inports,
outports,
override_readme=True)
def main():
print('Test: Default')
api.set_port_callback(inports[0]['name'], call_on_input)
print('Test: config')
config = api.config
config.label = 'icol'
config.split = 0.2
config.to_category = True
df = pd.DataFrame({
'icol': [1, 1, 3, 3, 3],
'col2': [1, 2, None, 4, 5],
'col3': [2, 3, 4, 5, 6],
'col4': [5, 6.5, 7.5, 8, 9],
'col5': [6, 6.7, 8.2, None, 10.1],
'col6': ['A', 'A', 'B', 'B', 'C']
})
attributes = {'format': 'csv', 'name': 'DF_name'}
input_msg = api.Message(attributes=attributes, body=df)
log, train_msg, test_msg = api.call(config, input_msg)
print('Input')
print(input_msg.body)
print('Train')
print(train_msg.body)
print('Test')
print(test_msg.body)
print('Logging: ')
print(log)
gs.gensolution(os.path.realpath(__file__),
config,
inports,
outports,
override_readme=True)
def main():
print('Test: Default')
api.set_port_callback(inports[0]['name'], call_on_input)
print('Test: config')
config = api.config
config.to_nan = '0'
config.anonymize_cols = 'col3,col4,col5'
config.anonymize_to_int_cols = 'icol, col2'
config.enumerate_cols = 'col3, col4, col5'
config.prefix_cols = 'Att'
df = pd.DataFrame(
{'icol': [1, 2, 3, 4, 5], 'col2': ['Cydia', 'Cydia', None, 'Dani', 'Liza'], \
'col3': ['Frank', 'Stephen', 'Hubert', 'Hubert', 'Sue'],
'col4': [5, 6.5, 7.5, 8, 9], 'col5': [6, 7, 8, 9, 10]})
attributes = {'format': 'csv', 'name': 'DF_name', 'process_list': []}
print(df.dtypes)
test_msg = api.Message(attributes=attributes, body=df)
log, new_msg = api.call(config, test_msg)
print('Attributes: ', new_msg.attributes)
print('Body: ', str(new_msg.body))
print('Logging: ')
print(log)
gs.gensolution(os.path.realpath(__file__),
config,
inports,
outports,
override_readme=True)
def main():
print('Test: Default')
#api.set_port_callback(inports[0]['name'], call_on_input)
print('Test: config')
config = api.config
config.train_cols = 'icol, col2, col3, col4'
config.label_col = 'col5'
df = pd.DataFrame({
'icol': [1, 1, 3, 3, 3],
'col2': [1, 2, 3, 4, 5],
'col3': [2, 3, 4, 5, 6],
'col4': [5, 6.5, 7.5, 8, 9],
'col5': [6, 6.7, 8.2, 9, 10.1]
})
attributes = {'format': 'csv', 'name': 'DF_name'}
train_msg = api.Message(attributes=attributes, body=df)
log, new_msg = api.call(config, train_msg)
print('Attributes: ', new_msg.attributes)
print('Body: ', str(new_msg.body))
print('Logging: ')
print(log)
gs.gensolution(os.path.realpath(__file__),
config,
inports,
outports,
override_readme=True)
def main() :
print('Test: Default')
api.set_port_callback(inports[0]['name'], call_on_input)
print('Test: config')
config = api.config
config.var1 = 'own foo'
config.var12 = 'own bar'
test_msg = api.Message(attributes={'name':'test1'},body =4)
new_msg, log = api.call(config,test_msg)
print('Attributes: ', new_msg.attributes)
print('Body: ', str(new_msg.body))
print('Logging: ')
print(log)
gs.gensolution(os.path.realpath(__file__), config, inports, outports,override_readme=True)
outports = [{'name': 'log', 'type': 'string', "description": "Logging data"}, \
{'name': 'data', 'type': 'message', "description": "sql statement"}]
#api.add_generator(process)
def test_operator():
api.config.columns = '"ID", "TEXT_AS_NVARCHAR" as "TEXT"'
api.config.debug_mode = True
api.config.table_name = '"${schema}"."bpanceditor.db::news.V_editorInbox_TextAs_nvarchar" where "ARTIFACT_TYPE" not in (\'NEWSTICKER\')'
process()
if __name__ == '__main__':
test_operator()
if True:
subprocess.run([
"rm", '-r',
'/Users/d051079/OneDrive - SAP SE/GitHub/di_textanalysis/solution/operators/textanalysis_'
+ api.config.version
])
gs.gensolution(os.path.realpath(__file__), api.config, None, outports)
solution_name = api.config.operator_name + '_' + api.config.version
subprocess.run(["vctl", "solution", "bundle", '/Users/d051079/OneDrive - SAP SE/GitHub/di_textanalysis/solution/operators/textanalysis_'+ api.config.version,\
"-t", solution_name])
subprocess.run(
["mv", solution_name + '.zip', '../../../solution/operators'])