def compare_functions(r_func_name, pd_func_name):
r_func = r_functions.get_r_function(r_source_file, r_func_name)
pd_func = pd_functions.get_pd_functions(pd_source_file,
as_dict=True)[pd_func_name]
generated_args = get_generated_args(r_func, 100)
r_results = r_functions.execute_R_function_on_args(r_func, generated_args)
r_executed = {
"name": r_func_name,
"body": r_functions.get_function_body(r_func),
"inputKey": "DF-KEY",
"outputs": r_results
}
pd_results = pd_functions.execute_pd_function_on_args(
pd_func, generated_args)
pd_executed = {
"name": pd_func_name,
"body": helper.get_func_body(pd_func),
"inputKey": "DF-KEY",
"outputs": pd_results
}
r_func = Function(name=r_func_name,
input_key=r_executed["inputKey"],
outputs=Outputs(r_executed["outputs"]),
body=test_clustering.get_body(r_executed),
source=r_source_file)
pd_func = Function(name=pd_func_name,
input_key=pd_executed["inputKey"],
outputs=Outputs(pd_executed["outputs"]),
body=test_clustering.get_body(pd_executed),
source=pd_source_file)
print(test_clustering.execution_similarity(r_func, pd_func))
def create_temp_function(variable, body):
headers = "\n".join(['library("%s")' % header for header in R_SUPPORTED_LIBRARIES])
func_name = helper.generate_function_name()
func_source = """
%s <- function (%s) {
%s
}
""" % (func_name, variable, body)
file_source = "\n\n".join([headers, func_source, ""])
cache.write_file(TEMP_FUNC_PATH, file_source.encode('utf-8'))
r_func = functions.get_r_function(TEMP_FUNC_PATH, func_name)
return r_func
def delta(r_func_name, pd_func_name):
r_func = r_functions.get_r_function(r_source_file, r_func_name)
pd_func = pd_functions.get_pd_functions(pd_source_file,
as_dict=True)[pd_func_name]
generated_args = get_generated_args(r_func, 1)
print(generated_args[0])
r_result = r_functions.execute_R_function_on_args(r_func,
generated_args)[0]
pd_result = pd_functions.execute_pd_function_on_args(
pd_func, generated_args)[0]
difference = dataframer.difference(r_result['return'], pd_result['return'])
print(difference)
def get_find_assign():
global _FIND_ASSIGN
if not _FIND_ASSIGN:
_FIND_ASSIGN = functions.get_r_function(R_PARSER_PATH, "find_assign")
return _FIND_ASSIGN
def get_find_var_func():
global _FIND_VAR_FUNC
if not _FIND_VAR_FUNC:
_FIND_VAR_FUNC = functions.get_r_function(R_PARSER_PATH, "find_vars")
return _FIND_VAR_FUNC