def update(self) -> bool:
new_lines = _find_new_lines(self._filename, start_from=self._lines_read)
if len(new_lines) > 0:
self._lines_read += len(new_lines)
print(f"read {len(new_lines)} new lines")
events_by_type = _lines_to_dict(new_lines)
if len(self.evaluations) == 0:
search_start = None
else:
search_start = self.evaluations.start.min()
start_n = self.evaluations.n.max()
if math.isnan(start_n):
start_n = -1
new_evaluations = _evaluations_to_dataframe(
events_by_type[TOKENS.EVALUATION_RESULT],
metric_names=self.metrics,
search_start=search_start,
start_n=start_n + 1,
)
self.evaluations = pd.concat([self.evaluations, new_evaluations])
for metric in self.metrics:
self.evaluations[f"{metric}_cummax"] = self.evaluations[metric].cummax()
new_individuals = {
id_: Individual.from_string(pipeline, pset)
for id_, pipeline in zip(new_evaluations.id, new_evaluations.pipeline)
}
self.individuals.update(new_individuals)
return len(new_lines) > 0
def pipeline_to_children(pipeline, automl):
''' Converts pipeline format of Gama log file to individual scikit-learn
components.
Parameters:
-----------
pipeline: pipeline set
Contains pipeline in Gama format.
automl: GamaClassifier or GamaRegressor
Contains either a GamaClassifier object or GamaRegressor object.
Returns:
--------
scikit-learn predictor, scikit-learn preprocessor (Optional), scikit-learn preprocessor (Optional), scikit-learn preprocessor (Optional)
Contains the GAMA individuals converted to the respective pipeline scikit-learn components.
'''
ind = Individual.from_string(pipeline, automl._pset)
inds = [p.str_nonrecursive for p in ind.primitives]
if len(inds) == 1:
return inds[0], np.nan, np.nan, np.nan
elif len(inds) == 2:
return inds[0], inds[1], np.nan, np.nan
elif len(inds) == 3:
return inds[0], inds[2], inds[1], np.nan
else:
return inds[0], inds[3], inds[2], inds[1]
def InvalidLinearSVC(pset):
individual_str = """LinearSVC(data,
LinearSVC.C=0.001,
LinearSVC.dual=True,
LinearSVC.loss='squared_hinge',
LinearSVC.penalty='l1',
LinearSVC.tol=1e-05)"""
individual_str = "".join(individual_str.split()).replace(",", ", ")
return Individual.from_string(individual_str, pset, compile_individual)
def LinearSVC(pset):
individual_str = """LinearSVC(data,
LinearSVC.C=0.001,
LinearSVC.dual=True,
LinearSVC.loss='squared_hinge',
LinearSVC.penalty='l2',
LinearSVC.tol=1e-05)"""
individual_str = ''.join(individual_str.split()).replace(',', ', ')
return Individual.from_string(individual_str, pset, None)
def update(self, force: bool = False) -> bool:
if not force and not self.incomplete:
return False
with open(os.path.join(self._log_directory, "evaluations.log"),
"r") as fh:
header = fh.readline()[:-1]
self._last_tell = max(self._last_tell, fh.tell())
fh.seek(self._last_tell)
try:
df = pd.read_csv(fh, sep=";", header=None, index_col=False)
except pd.errors.EmptyDataError:
return False
self._last_tell = fh.tell()
df.columns = header.split(";")
df["n"] = df.index
df = df.rename(
columns=dict(t_start="start", t_wallclock="duration"))
def tuple_to_metrics(tuple_str):
return pd.Series(
[float(value) for value in tuple_str[1:-1].split(",")])
df[self.metrics] = df.score.apply(tuple_to_metrics)
df.start = pd.to_datetime(df.start) # needed?
df.duration = pd.to_timedelta(df.duration, unit="s")
new_individuals = {
id_: Individual.from_string(pipeline, pset)
for id_, pipeline in zip(df.id, df.pipeline)
}
# Merge with previous records
self.individuals.update(new_individuals)
if self.evaluations.empty:
self.evaluations = df
else:
df["n"] += self.evaluations.n.max() + 1
self.evaluations = pd.concat([self.evaluations, df])
df = self.evaluations
search_start = df.start.min()
for metric in self.metrics:
df[f"{metric}_cummax"] = df[metric].cummax()
if len(df.start) > 0:
df["relative_end"] = ((df.start + df.duration) -
search_start).dt.total_seconds()
else:
df["relative_end"] = pd.Series()
return True
def ForestPipeline(pset):
individual_str = """RandomForestClassifier(
FeatureAgglomeration(
data,
FeatureAgglomeration.affinity='l2',
FeatureAgglomeration.linkage='complete'
),
RandomForestClassifier.bootstrap=True,
RandomForestClassifier.criterion='gini',
RandomForestClassifier.max_features=0.6,
RandomForestClassifier.min_samples_leaf=7,
RandomForestClassifier.min_samples_split=6,
RandomForestClassifier.n_estimators=100)"""
individual_str = "".join(individual_str.split()).replace(",", ", ")
return Individual.from_string(individual_str, pset, None)
def SS_RBS_SS_BNB(pset):
return Individual.from_string(
"BernoulliNB(StandardScaler(RobustScaler(StandardScaler(data))), alpha=0.1, fit_prior=True)", # noqa: E501
pset,
compile_individual,
)
def SS_BNB(pset):
return Individual.from_string(
"BernoulliNB(StandardScaler(data), alpha=0.1, fit_prior=True)",
pset,
compile_individual,
)
def RS_MNB(pset):
return Individual.from_string(
"MultinomialNB(RobustScaler(data), alpha=1.0, fit_prior=True)",
pset,
compile_individual,
)
def GNB(pset):
return Individual.from_string("GaussianNB(data)", pset, compile_individual)
def execute_recommendations(X, y, cat_ind, recommendations, task, n_jobs=1):
''' Executes the recommendations made by the nearest neighbor model based on
a learning task and sets the number of jobs to n_jobs for the estimators
and preprocessing algorithms.
Parameters:
-----------
X: pd.DataFrame
Contains the dataframe of a given dataset excluding its target column.
y: pd.Series
Contains the series of the target of a given dataset.
cat_ind: list
Contains boolean values to determine whether a column is categorical or
not based.
recommendations: list
Contains the list with the recommendations made by the nearest neighbor model.
task: str
Contains the learning task (i.e. "classification" or "regression")
n_jobs: int
Contains what to set the number of jobs at for the estimators and preprocessing algorithms
available in the recommended pipelines.
Returns:
--------
list
Contains scores of each pipeline run on X and y.
'''
categorical, numeric, string = category_numeric_or_string(X, cat_ind)
if task.lower() == "classification":
gama = GamaClassifier(scoring='accuracy')
elif task.lower() == "regression":
gama = GamaRegressor(scoring='r2')
else:
return "{} is not implemented, please try 'classification' or 'regression'".format(
task)
scores = []
for recommendation in recommendations:
pipeline, k, did = recommendation
ind = Individual.from_string(pipeline, gama._pset)
X_pipe = deepcopy(X)
y_pipe = deepcopy(y)
X_pipe, y_pipe = onehot_or_targ(X_pipe, y_pipe, categorical, k)
pipeline = [eval(p.str_nonrecursive) for p in ind.primitives]
pipeline.reverse()
try:
for component in pipeline:
if pipeline.index(component) == len(pipeline) - 1:
try:
setattr(component, 'n_jobs', n_jobs)
except:
pass
X_train, X_test, y_train, y_test = train_test_split(
X_pipe, y_pipe, test_size=0.30, random_state=42)
cv_scores = cross_val_score(component,
X_pipe,
y_pipe,
cv=10)
score = sum(cv_scores) / 10
#component.fit(X_train, y_train)
#score = component.score(X_test, y_test)
scores.append(score)
else:
if isinstance(component, SelectPercentile) | isinstance(
component, SelectFwe):
X_pipe = component.fit_transform(X_pipe, y_pipe)
else:
X_pipe = component.fit_transform(X_pipe)
except:
scores.append(0)
return scores
def __init__(
self,
logfile: Optional[str] = None,
log_lines: Optional[List[str]] = None,
name: Optional[str] = None,
):
""" Parse the logfile or log lines provided.
Parameters
----------
logfile: str, optional (default=None)
Path to the log file. If not specified, loglines must be provided.
log_lines: List[str], optional (default=None)
A list with each element one line from the log file.
If not specified, logfile must be provided.
name: str, optional (default=None)
Name of the report.
If set to None, defaults to `logfile` if it is not None else 'nameless'.
"""
if not ((logfile is None) ^ (log_lines is None)):
raise ValueError("Must provide exactly one of 'logfile' or 'loglines'.")
if log_lines is None:
log_lines = _find_new_lines(cast(str, logfile))
self._lines_read = len(log_lines)
self._individuals = None
self.name = (
name
if name is not None
else (logfile if logfile is not None else "nameless")
)
events_by_type = _lines_to_dict(log_lines)
if len(events_by_type[TOKENS.INIT]) == 0:
raise ValueError("The log must contain at least contain an INIT string.")
config = _find_metric_configuration(events_by_type[TOKENS.INIT])
self.metrics, self.search_method, self.postprocessing, self._filename = config
self.phases: List[Tuple[str, str, datetime, float]] = _find_phase_information(
events_by_type
)
search_start = self.phases[1][2] if len(self.phases) > 1 else None
self.evaluations: pd.DataFrame = _evaluations_to_dataframe(
events_by_type[TOKENS.EVALUATION_RESULT],
metric_names=self.metrics,
search_start=search_start,
)
# This can take a while for long logs (e.g. ~1sec for 10k individuals)
self.individuals: Dict[str, Individual] = {
id_: Individual.from_string(pipeline, pset)
for id_, pipeline in zip(self.evaluations.id, self.evaluations.pipeline)
}
parse_method_data: Dict[str, Callable[..., pd.DataFrame]] = defaultdict(
lambda: lambda *args: None,
AsynchronousSuccessiveHalving=_ASHA_data_to_dataframe,
)
# search_method is formatted like NAME(kwargs)
# where kwargs could contain additional parentheses.
method_name, _ = self.search_method.split("(", maxsplit=1)
method_token = METHOD_TOKENS.get(method_name)
self.method_data = parse_method_data[method_name](
events_by_type[method_token], self.metrics
)
self.incomplete = len(self.phases) < 3
def BernoulliNBThreeScalers(pset):
return Individual.from_string(
"BernoulliNB(StandardScaler(RobustScaler(StandardScaler(data))), alpha=0.1, fit_prior=True)",
pset, compile_individual)