max/model-training
1
0
Fork 0
mirror of https://git.gfz-potsdam.de/naaice/model-training.git synced 2025-12-16 08:08:22 +01:00
Code Issues Packages Projects Releases Wiki Activity

correction of scaling error in mass balance loss

Browse Source
This commit is contained in:
Hannes Signer 2025-02-25 18:06:56 +01:00
parent 8051eb3c3d
commit 0f7ee78a8a
1 changed files with 50 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
src/preprocessing.py
View File

@ -93,10 +93,10 @@ def custom_loss(preprocess, column_dict, h1, h2, h3, scaler_type="minmax", loss_
# extract the scaling parameters # extract the scaling parameters
if scaler_type == "minmax": if scaler_type == "minmax":
scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32) scale_X = tf.convert_to_tensor(preprocess.scaler_X.data_range_, dtype=tf.float32)
min_X = tf.convert_to_tensor(preprocess.scaler_X.min_, dtype=tf.float32) min_X = tf.convert_to_tensor(preprocess.scaler_X.data_min_, dtype=tf.float32)
scale_y = tf.convert_to_tensor(preprocess.scaler_y.scale_, dtype=tf.float32) scale_y = tf.convert_to_tensor(preprocess.scaler_y.data_range_, dtype=tf.float32)
min_y = tf.convert_to_tensor(preprocess.scaler_y.min_, dtype=tf.float32) min_y = tf.convert_to_tensor(preprocess.scaler_y.data_min_, dtype=tf.float32)
elif scaler_type == "standard": elif scaler_type == "standard":
scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32) scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32)
@ -117,11 +117,11 @@ def custom_loss(preprocess, column_dict, h1, h2, h3, scaler_type="minmax", loss_
results_inverse = results * scale_X + mean_X results_inverse = results * scale_X + mean_X
# apply exp1m on the columns of predicted_inverse and results_inverse # apply exp1m on the columns of predicted_inverse and results_inverse if log transformation was applied
predicted_inverse = tf.math.expm1(predicted_inverse) if preprocess.func_dict_out is not None:
results_inverse = tf.math.expm1(results_inverse) predicted_inverse = tf.math.expm1(predicted_inverse)
print(predicted_inverse) results_inverse = tf.math.expm1(results_inverse)
# mass balance # mass balance
dBa = tf.keras.backend.abs( dBa = tf.keras.backend.abs(
(predicted_inverse[:, column_dict["Ba"]] + predicted_inverse[:, column_dict["Barite"]]) - (predicted_inverse[:, column_dict["Ba"]] + predicted_inverse[:, column_dict["Barite"]]) -
@ -148,10 +148,10 @@ def custom_loss(preprocess, column_dict, h1, h2, h3, scaler_type="minmax", loss_
def mass_balance_metric(preprocess, column_dict, scaler_type="minmax"): def mass_balance_metric(preprocess, column_dict, scaler_type="minmax"):
if scaler_type == "minmax": if scaler_type == "minmax":
scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32) scale_X = tf.convert_to_tensor(preprocess.scaler_X.data_range_, dtype=tf.float32)
min_X = tf.convert_to_tensor(preprocess.scaler_X.min_, dtype=tf.float32) min_X = tf.convert_to_tensor(preprocess.scaler_X.data_min_, dtype=tf.float32)
scale_y = tf.convert_to_tensor(preprocess.scaler_y.scale_, dtype=tf.float32) scale_y = tf.convert_to_tensor(preprocess.scaler_y.data_range_, dtype=tf.float32)
min_y = tf.convert_to_tensor(preprocess.scaler_y.min_, dtype=tf.float32) min_y = tf.convert_to_tensor(preprocess.scaler_y.data_min_, dtype=tf.float32)
elif scaler_type == "standard": elif scaler_type == "standard":
scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32) scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32)
@ -169,6 +169,10 @@ def mass_balance_metric(preprocess, column_dict, scaler_type="minmax"):
elif scaler_type == "standard": elif scaler_type == "standard":
predicted_inverse = predicted * scale_y + mean_y predicted_inverse = predicted * scale_y + mean_y
results_inverse = results * scale_X + mean_X results_inverse = results * scale_X + mean_X
if preprocess.func_dict_out is not None:
predicted_inverse = tf.math.expm1(predicted_inverse)
results_inverse = tf.math.expm1(results_inverse)
# mass balance # mass balance
dBa = tf.keras.backend.abs( dBa = tf.keras.backend.abs(
@ -201,6 +205,10 @@ def mass_balance_evaluation(model, X, preprocess):
# backtransform min/max or standard scaler # backtransform min/max or standard scaler
X = pd.DataFrame(preprocess.scaler_X.inverse_transform(X.iloc[:, X.columns != "Class"]), columns=columns) X = pd.DataFrame(preprocess.scaler_X.inverse_transform(X.iloc[:, X.columns != "Class"]), columns=columns)
prediction = pd.DataFrame(preprocess.scaler_y.inverse_transform(prediction), columns=columns) prediction = pd.DataFrame(preprocess.scaler_y.inverse_transform(prediction), columns=columns)
# apply exp1m on the columns of predicted_inverse and results_inverse if log transformation was applied
if preprocess.func_dict_out is not None:
X = preprocess.funcInverse(X)
# calculate mass balance # calculate mass balance
dBa = np.abs((prediction["Ba"] + prediction["Barite"]) - (X["Ba"] + X["Barite"])) dBa = np.abs((prediction["Ba"] + prediction["Barite"]) - (X["Ba"] + X["Barite"]))
@ -216,28 +224,27 @@ class preprocessing:
self.random_state = random_state self.random_state = random_state
self.scaler_X = None self.scaler_X = None
self.scaler_y = None self.scaler_y = None
self.func_dict_in = None
self.func_dict_in = func_dict_in if func_dict_in is not None else None self.func_dict_in = func_dict_in if func_dict_in is not None else None
self.func_dict_out = func_dict_out if func_dict_out is not None else None self.func_dict_out = func_dict_out if func_dict_out is not None else None
self.state = {"cluster": False, "log": False, "balance": False, "scale": False} self.state = {"cluster": False, "log": False, "balance": False, "scale": False}
def funcTranform(self, X, y): def funcTranform(self, *args):
for key in X.keys():
if "Class" not in key: for i in args:
X[key] = X[key].apply(self.func_dict_in) for key in i.keys():
y[key] = y[key].apply(self.func_dict_in) if "Class" not in key:
i[key] = i[key].apply(self.func_dict_in)
self.state["log"] = True self.state["log"] = True
return args
return X, y def funcInverse(self, *args):
def funcInverse(self, X, y):
for key in X.keys(): for i in args:
if "Class" not in key: for key in i.keys():
X[key] = X[key].apply(self.func_dict_out) if "Class" not in key:
y[key] = y[key].apply(self.func_dict_out) i[key] = i[key].apply(self.func_dict_out)
self.state["log"] = False self.state["log"] = False
return X, y return args
def cluster(self, X, y, species='Barite', n_clusters=2, x_length=50, y_length=50): def cluster(self, X, y, species='Barite', n_clusters=2, x_length=50, y_length=50):
@ -339,26 +346,29 @@ class preprocessing:
return X_train, X_test, y_train, y_test return X_train, X_test, y_train, y_test
def scale_inverse(self, X): def scale_inverse(self, *args):
result = []
if("Class" in X.columns): for i in args:
print("Class column found") if "Class" in i.columns:
X = pd.concat([pd.DataFrame(self.scaler_X.inverse_transform(X.loc[:, X.columns != "Class"]), columns=X.columns[:-1]), X.loc[:, "Class"]], axis=1) inversed = pd.DataFrame(self.scaler_X.inverse_transform(i.loc[:, i.columns != "Class"]), columns=i.columns[:-1])
else: class_column = i.loc[:, "Class"].reset_index(drop=True)
X = self.scaler_X.inverse_transform(X) i = pd.concat([inversed, class_column], axis=1)
else:
return X i = pd.DataFrame(self.scaler_X.inverse_transform(i), columns=i.columns)
result.append(i)
return result
def split(self, X, y, ratio=0.8): def split(self, X, y, ratio=0.8):
X_train, y_train, X_test, y_test = sk.train_test_split(X, y, test_size = ratio, random_state=self.random_state) X_train, y_train, X_test, y_test = sk.train_test_split(X, y, test_size = ratio, random_state=self.random_state)
return X_train, y_train, X_test, y_test return X_train, y_train, X_test, y_test
def class_selection(self, X, y, class_label): def class_selection(self, *args, class_label=0):
X = X[X['Class'] == class_label]
y = y[y['Class'] == class_label]
return X, y for i in args:
i = i[i['Class'] == class_label]
return args