def __init__(self, connector_contract: ConnectorContract):
""" initialise the Handler passing the connector_contract dictionary
Extra Parameters in the ConnectorContract kwargs:
- region_name (optional) session region name
- profile_name (optional) session shared credentials file profile name
"""
self.botocore = HandlerFactory.get_module('botocore.exceptions')
self.boto3 = HandlerFactory.get_module('boto3')
super().__init__(connector_contract)
cc_params = connector_contract.kwargs
cc_params.update(connector_contract.query
) # Update kwargs with those in the uri query
region_name = cc_params.pop('region_name', 'us-east-2')
aws_access_key_id = cc_params.pop('aws_access_key_id',
os.environ.get('AWS_ACCESS_KEY_ID'))
aws_secret_access_key = cc_params.pop(
'aws_secret_access_key', os.environ.get('AWS_SECRET_ACCESS_KEY'))
aws_session_token = cc_params.pop('aws_session_token',
os.environ.get('AWS_SESSION_TOKEN'))
profile_name = cc_params.pop('profile_name', None)
self._session = self.boto3.Session(
region_name=region_name,
aws_access_key_id=aws_access_key_id,
aws_secret_access_key=aws_secret_access_key,
profile_name=profile_name,
aws_session_token=aws_session_token)
self._file_state = 0
self._changed_flag = True
def __init__(self, connector_contract: ConnectorContract):
""" initialise the Hander passing the source_contract dictionary """
# required module import
self.psycopg2 = HandlerFactory.get_module('psycopg2')
super().__init__(connector_contract)
self._file_state = 0
self._changed_flag = True
def _yaml_dump(self, data, path_file, **kwargs) -> None:
""" dump YAML file
:param data: the data to persist
:param path_file: the name and path of the file
:param default_flow_style: (optional) if to include the default YAML flow style
"""
module_name = 'yaml'
if HandlerFactory.check_module(module_name=module_name):
module = HandlerFactory.get_module(module_name=module_name)
else:
raise ModuleNotFoundError(
f"The required module {module_name} has not been installed. "
f"Please pip install the appropriate package in order to complete this action"
)
encoding = kwargs.pop('encoding', 'utf-8')
default_flow_style = kwargs.pop('default_flow_style', False)
with self._lock:
# make sure the dump is clean
try:
with closing(open(path_file, mode='w',
encoding=encoding)) as ymlfile:
module.safe_dump(data=data,
stream=ymlfile,
default_flow_style=default_flow_style,
**kwargs)
except IOError as e:
raise IOError(
f"The yaml file {path_file} failed to open with: {e}")
# check the file was created
return
def _yaml_load(path_file, **kwargs) -> dict:
""" loads the YAML file
:param path_file: the name and path of the file
:return: a dictionary
"""
module_name = 'yaml'
if HandlerFactory.check_module(module_name=module_name):
module = HandlerFactory.get_module(module_name=module_name)
else:
raise ModuleNotFoundError(
f"The required module {module_name} has not been installed. "
f"Please pip install the appropriate package in order to complete this action"
)
encoding = kwargs.pop('encoding', 'utf-8')
try:
with closing(open(path_file, mode='r',
encoding=encoding)) as ymlfile:
rtn_dict = module.safe_load(ymlfile)
except IOError as e:
raise IOError(
f"The yaml file {path_file} failed to open with: {e}")
if not isinstance(rtn_dict, dict) or not rtn_dict:
raise TypeError(
f"The yaml file {path_file} could not be loaded as a dict type"
)
return rtn_dict
def has_changed(self) -> bool:
""" returns the status of the change_flag indicating if the file has changed since last load or reset"""
if not self.exists():
return False
# maintain the change flag
_cc = self.connector_contract
if _cc.schema.startswith('http') or _cc.schema.startswith('git'):
if not isinstance(self.connector_contract, ConnectorContract):
raise ValueError(
"The Pandas Connector Contract has not been set")
module_name = 'requests'
_address = _cc.address.replace("git://", "https://")
if HandlerFactory.check_module(module_name=module_name):
module = HandlerFactory.get_module(module_name=module_name)
state = module.head(_address).headers.get('last-modified', 0)
else:
raise ModuleNotFoundError(
f"The required module {module_name} has not been installed. Please pip "
f"install the appropriate package in order to complete this action"
)
else:
state = os.stat(_cc.address).st_mtime_ns
if state != self._file_state:
self._changed_flag = True
self._file_state = state
return self._changed_flag
def register_estimator(self,
canonical: pd.DataFrame,
target: str,
headers: list,
class_name: str,
module_name: str,
hyper_param: dict = None,
test_size: float = None,
random_state: int = None,
save_intent: bool = None,
model_name: str = None,
intent_order: int = None,
replace_intent: bool = None,
remove_duplicates: bool = None):
""" registers and fits an estimator model returning the model fit
:param canonical: the model canonical
:param class_name: the name of the model class
:param target: the model target
:param headers: the model features header names
:param hyper_param: (optional) hyper parameters for the model instance
:param test_size: (optional) the size of the test sample (default tp 0.33)
:param random_state: (optional) a random state value for the test sample
:param module_name: (optional) the name of the module
:param save_intent: (optional) if the intent contract should be saved to the property manager
:param model_name: (optional) the name of the model
:param intent_order: (optional) the order in which each intent should run.
If None: default's to -1
if -1: added to a level above any current instance of the intent section, level 0 if not found
if int: added to the level specified, overwriting any that already exist
:param replace_intent: (optional) if the intent method exists at the level, or default level
True - replaces the current intent method with the new
False - leaves it untouched, disregarding the new intent
:param remove_duplicates: (optional) removes any duplicate intent in any level that is identical
:return: CatBoostClassifier.
"""
# resolve intent persist options
_method = inspect.currentframe().f_code.co_name
self._set_intend_signature(self._intent_builder(method=_method,
params=locals()),
model_name=model_name,
intent_order=intent_order,
replace_intent=replace_intent,
remove_duplicates=remove_duplicates,
save_intent=save_intent)
# Code block for intent
local_intent = {}
if model_name and self._pm.has_intent(model_name):
local_intent = self._pm.get_intent(level=model_name,
intent=_method)
module_name = module_name if isinstance(
module_name, str) else local_intent.get('module_name', None)
X = Commons.filter_columns(canonical, headers=headers)
y = Commons.filter_columns(canonical, headers=target)
module = HandlerFactory.get_module(module_name='ds_behavioral')
def __init__(self, connector_contract: ConnectorContract):
""" Initialise the handler passing the source_contract dictionary """
super().__init__(connector_contract)
self.cortex_content = HandlerFactory.get_module('cortex.content')
self.token = self._load_token()
self.api_endpoint = self._load_api_endpoint()
self.project = self._load_project_name()
self.cortex_mc_client = self.cortex_content.ManagedContentClient(
url=self.api_endpoint, token=self.token)
self._etag = 0
self._changed_flag = True
def __init__(self, connector_contract: ConnectorContract):
""" initialise the Hander passing the source_contract dictionary """
# required module import
self.mongo = HandlerFactory.get_module('pymongo')
super().__init__(connector_contract)
database = self.connector_contract.kwargs.get("database")
self._mongo_database = self.mongo.MongoClient(
self.connector_contract.uri)[database]
self._mongo_collection = self._mongo_database[
self.connector_contract.kwargs.get("collection")]
self._file_state = 0
self._changed_flag = True
def _get_canonical(self,
data: [pd.DataFrame, pd.Series, list, str, dict],
header: str = None) -> pd.DataFrame:
if isinstance(data, pd.DataFrame):
return deepcopy(data)
if isinstance(data, dict):
method = data.pop('method', None)
if method is None:
raise ValueError(f"The data dictionary has no 'method' key.")
if str(method).startswith('@generate'):
task_name = data.pop('task_name', None)
if task_name is None:
raise ValueError(
f"The data method '@generate' requires a 'task_name' key."
)
repo_uri = data.pop('repo_uri', None)
module = HandlerFactory.get_module(module_name='ds_behavioral')
inst = module.SyntheticBuilder.from_env(task_name=task_name,
uri_pm_repo=repo_uri,
default_save=False)
size = data.pop('size', None)
seed = data.get('seed', None)
run_book = data.pop('run_book', None)
result = inst.tools.run_intent_pipeline(size=size,
columns=run_book,
seed=seed)
return inst.tools.frame_selection(canonical=result,
save_intent=False,
**data)
else:
raise ValueError(
f"The data 'method' key {method} is not a recognised intent method"
)
elif isinstance(data, (list, pd.Series)):
header = header if isinstance(header, str) else 'default'
return pd.DataFrame(data=deepcopy(data), columns=[header])
elif isinstance(data, str):
if data == '@empty':
return pd.DataFrame()
if not self._pm.has_connector(connector_name=data):
raise ValueError(
f"The data connector name '{data}' is not in the connectors catalog"
)
handler = self._pm.get_connector_handler(data)
canonical = handler.load_canonical()
if isinstance(canonical, dict):
canonical = pd.DataFrame.from_dict(data=canonical,
orient='columns')
return canonical
raise ValueError(
f"The canonical format is not recognised, pd.DataFrame, pd.Series"
f"str, list or dict expected, {type(data)} passed")
def _json_load(path_file: str, **kwargs) -> [dict, pd.DataFrame]:
""" loads a pickle file """
if path_file.startswith('http'):
module_name = 'requests'
if HandlerFactory.check_module(module_name=module_name):
module = HandlerFactory.get_module(module_name=module_name)
username = kwargs.get('username', None)
password = kwargs.get('password', None)
auth = (username, password) if username and password else None
r = module.get(path_file, auth=auth)
return r.json()
with closing(open(path_file, mode='r')) as f:
return json.load(f, **kwargs)
def exists(self) -> bool:
""" Returns True is the file exists """
if not isinstance(self.connector_contract, ConnectorContract):
raise ValueError("The Pandas Connector Contract has not been set")
_cc = self.connector_contract
if _cc.schema.startswith('http') or _cc.schema.startswith('git'):
module_name = 'requests'
_address = _cc.address.replace("git://", "https://")
if HandlerFactory.check_module(module_name=module_name):
module = HandlerFactory.get_module(module_name=module_name)
return module.get(_address).status_code == 200
raise ModuleNotFoundError(
f"The required module {module_name} has not been installed. "
f"Please pip install the appropriate package in order to complete this action"
)
if os.path.exists(_cc.address):
return True
return False
def _pickle_load(path_file: str, **kwargs) -> [dict, pd.DataFrame]:
""" loads a pickle file """
fix_imports = kwargs.pop('fix_imports', True)
encoding = kwargs.pop('encoding', 'ASCII')
errors = kwargs.pop('errors', 'strict')
if path_file.startswith('http'):
module_name = 'requests'
if HandlerFactory.check_module(module_name=module_name):
module = HandlerFactory.get_module(module_name=module_name)
username = kwargs.get('username', None)
password = kwargs.get('password', None)
auth = (username, password) if username and password else None
r = module.get(path_file, auth=auth)
return r.content
with closing(open(path_file, mode='rb')) as f:
return pickle.load(f,
fix_imports=fix_imports,
encoding=encoding,
errors=errors)
def _get_constant(reference: str,
size: int = None,
shuffle: bool = True,
seed: int = None) -> [pd.DataFrame, list]:
"""private method to retrieve data constant"""
module = HandlerFactory.get_module(
module_name=f"ds_behavioral.sample.{reference}")
if reference.startswith("lookup_"):
return AbstractSample._select_list(selection=module.data,
size=size,
seed=seed,
shuffle=shuffle)
df = pd.DataFrame.from_dict(module.data, orient='columns')
idx = df.index.to_list()
selection = AbstractSample._select_list(selection=idx,
size=size,
seed=seed,
shuffle=shuffle)
rtn_df: pd.DataFrame = df.iloc[selection].reset_index(drop=True)
return rtn_df
def __init__(self, connector_contract: ConnectorContract):
""" initialise the Handler passing the source_contract dictionary """
self.pyhive = HandlerFactory.get_module('pyhive.hive')
super().__init__(connector_contract)
self._file_state = 0
self._changed_flag = True
def _get_canonical(self, data: [pd.DataFrame, pd.Series, list, str, dict, int], header: str=None, size: int=None,
deep_copy: bool=None) -> pd.DataFrame:
""" Used to return or generate a pandas Dataframe from a number of different methods.
The following can be passed and their returns
- pd.Dataframe -> a deep copy of the pd.DataFrame
- pd.Series or list -> creates a pd.DataFrame of one column with the 'header' name or 'default' if not given
- str -> instantiates a connector handler with the connector_name and loads the DataFrame from the connection
- int -> generates an empty pd.Dataframe with an index size of the int passed.
- dict -> use the canonical2dict(...) method to construct a dict with a method and related parameters
methods:
- model_*(...) -> one of the builder model methods and paramters
- *_selection(...) -> one of the builder selection methods (get_, correlate_, frame_) and paramters
- @empty -> generates an empty pd.DataFrame where size and headers can be passed
:size sets the index size of the dataframe
:headers any initial headers for the dataframe
- @generate -> generate a synthetic file from a remote Domain Contract
:task_name the name of the SyntheticBuilder task to run
:repo_uri the location of the Domain Product
:size (optional) a size to generate
:seed (optional) if a seed should be applied
:run_book (optional) if specific intent should be run only
:param data: a dataframe or action event to generate a dataframe
:param header: (optional) header for pd.Series or list
:param size: (optional) a size parameter for @empty of @generate
:param header: (optional) used in conjunction with lists or pd.Series to give a header reference
:return: a pd.Dataframe
"""
deep_copy = deep_copy if isinstance(deep_copy, bool) else True
if isinstance(data, pd.DataFrame):
if deep_copy:
return deepcopy(data)
return data
if isinstance(data, dict):
data = data.copy()
method = data.pop('method', None)
if method is None:
try:
return pd.DataFrame.from_dict(data=data)
except ValueError:
raise ValueError("The canonical data passed was of type 'dict' but did not contain a 'method' key "
"or was not convertible to Dataframe")
if method in self.__dir__():
if str(method).startswith('model_') or method == 'frame_selection':
data.update({'save_intent': False})
return eval(f"self.{method}(**data)", globals(), locals())
if str(method).endswith('_selection'):
if not isinstance(header, str):
raise ValueError(f"The canonical type 'dict' method '{method}' must have a header parameter.")
data.update({'save_intent': False})
if method == 'get_selection':
if not isinstance(size, int):
raise ValueError(f"The canonical type 'dict' method '{method}' must have a size parameter.")
data.update({'size': size})
return pd.DataFrame(data=eval(f"self.{method}(**data)", globals(), locals()), columns=[header])
elif str(method).startswith('@generate'):
task_name = data.pop('task_name', None)
if task_name is None:
raise ValueError(f"The data method '@generate' requires a 'task_name' key.")
uri_pm_repo = data.pop('repo_uri', None)
module = HandlerFactory.get_module(module_name='ds_discovery')
inst = module.SyntheticBuilder.from_env(task_name=task_name, uri_pm_repo=uri_pm_repo,
default_save=False)
size = size if isinstance(size, int) and 'size' not in data.keys() else data.pop('size', None)
seed = data.get('seed', None)
run_book = data.pop('run_book', None)
result = inst.tools.run_intent_pipeline(canonical=size, columns=run_book, seed=seed)
return inst.tools.frame_selection(canonical=result, save_intent=False, **data)
elif str(method).startswith('@empty'):
size = size if isinstance(size, int) and 'size' not in data.keys() else data.pop('size', None)
headers = data.pop('headers', None)
size = range(size) if size else None
return pd.DataFrame(index=size, columns=headers)
else:
raise ValueError(f"The data 'method' key {method} is not a recognised intent method")
elif isinstance(data, (list, pd.Series)):
header = header if isinstance(header, str) else 'default'
if deep_copy:
data = deepcopy(data)
return pd.DataFrame(data=data, columns=[header])
elif isinstance(data, str):
if not self._pm.has_connector(connector_name=data):
if isinstance(size, int):
return pd.DataFrame(index=range(size))
raise ValueError(f"The data connector name '{data}' is not in the connectors catalog")
handler = self._pm.get_connector_handler(data)
canonical = handler.load_canonical()
if isinstance(canonical, dict):
canonical = pd.DataFrame.from_dict(data=canonical)
return canonical
elif isinstance(data, int):
return pd.DataFrame(index=range(data)) if data > 0 else pd.DataFrame()
elif not data:
return pd.DataFrame()
raise ValueError(f"The canonical format is not recognised, pd.DataFrame, pd.Series, "
f"str, list or dict expected, {type(data)} passed")