('cat', Pipeline(steps=[('b', OrdinalEncoder())]),
categorical_features)]).fit_transform(data)
encoded = pd.DataFrame(encoded, columns=reorder_features)
return encoded
data = pd.read_csv(
'../../results/pipeline/features_rebalance/meta_learner/ts_all.csv')
columns = data.columns
data = SimpleImputer(strategy="constant", fill_value=0.0).fit_transform(data)
data = pd.DataFrame(data=data, columns=columns)
data = encode_data(data)
X, y = data.drop(columns=['class']), data['class']
print(data)
estimator = autosklearn.classification.AutoSklearnClassifier()
# scores = cross_validate(estimator,
# X,
# encode_data(pd.DataFrame(y)),
# scoring=["accuracy", "balanced_accuracy", "precision_macro", "recall_macro", "f1_macro"],
# cv = 10,
# return_train_score=True,
# return_estimator=True)
# results = {'train': {
# 'accuracy': (scores['train_accuracy'].mean(), scores['train_accuracy'].std() * 2),
# 'balanced_accuracy': (scores['train_balanced_accuracy'].mean(), scores['train_balanced_accuracy'].std() * 2),
# 'precision_macro': (scores['train_precision_macro'].mean(), scores['train_precision_macro'].std() * 2),
def transform(self, X, y=None):
#Feature Engeneering
X = self.add_features(X)
#Feature Selection
if self.X_features != 'all':
X = X[self.X_features]
#Used to rename X data
X_columns = X.columns
#Imputing Missing Values/Dropping Missing Values
Xrows_with_nan = [
index for index, row in X.iterrows() if row.isnull().any()
]
if self.X_imputer_strat == 'drop':
X = X.drop(Xrows_with_nan).reset_index(drop=True)
else:
X = SimpleImputer(strategy=self.X_imputer_strat,
fill_value=self.X_fill_value).fit_transform(X)
#Reshaping/Renaming X
X = pd.DataFrame(X, columns=X_columns)
#Handles case when only X needs to be transformed; i.e. Predictions;
if type(y) == type(None):
return X
#Drops Y-Values so that if X-NaN values were dropped, the data still
# matches with the target data
if self.X_imputer_strat == 'drop':
y = y.drop(Xrows_with_nan).reset_index(drop=True)
#Reshaping y
y = pd.DataFrame(y, columns=["Half Life (Seconds)"
]).reset_index(drop=True)
#Creating Target Vectors
y = self.add_magnitude_and_value_features(y)
isStable = self.get_isStable_feature(y, self.magnitude_threshold,
self.seconds_threshold)
y_columns = y.columns
#Imputing Missing Values/Dropping Missing Values
Yrows_with_nan = [
index for index, row in pd.DataFrame(y).iterrows()
if row.isnull().any()
]
if self.y_imputer_strat == 'drop':
y = y.drop(Yrows_with_nan).reset_index(drop=True)
X = X.drop(Yrows_with_nan).reset_index(drop=True)
isStable = isStable.drop(Yrows_with_nan).reset_index(drop=True)
else:
y = SimpleImputer(strategy=self.y_imputer_strat,
fill_value=self.y_fill_value).fit_transform(y)
#Reshaping/Renaming y
y = pd.DataFrame(y, columns=y_columns)
#Choosing Target Vector
if self.target_vector == 'Seconds':
y = y['Half Life (Seconds)']
elif self.target_vector == 'Magnitude':
y = y['Magnitude of Value']
if self.prediction_type == 'Binary':
y = isStable
#Returns X, y
return X, y
