Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

【PPSCI Doc No.2-7】ppsci.data.process.transform #688

Merged
merged 6 commits into from
Dec 22, 2023
Merged

【PPSCI Doc No.2-7】ppsci.data.process.transform #688

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e13677c
add discribe
Liyulingyue Dec 10, 2023
787d483
add discribe
Liyulingyue Dec 10, 2023
6a05561
add discribe
Liyulingyue Dec 10, 2023
3a53729
add discribe
Liyulingyue Dec 10, 2023
208842b
Update preprocess.py
Liyulingyue Dec 21, 2023
fc5b05b
Update preprocess.py
Liyulingyue Dec 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
76 changes: 62 additions & 14 deletions ppsci/data/process/transform/preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,19 @@ class Translate:

Examples:
>>> import ppsci
>>> import numpy as np
>>> translate = ppsci.data.transform.Translate({"x": 1.0, "y": -1.0})
>>> input_data = np.array([[[1.0, 2.0], [3.0, 4.0]], [[5.0, 6.0], [7.0, 8.0]]])
>>> input_dict = {"x": input_data[:,:,0], "y": input_data[:,:,1]}
>>> label_dict = {"x": np.array([1.0, 2.0]), "y": np.array([3.0, 4.0])}
>>> weight_dict = {"x": np.array([10.0, 20.0]), "y": np.array([30.0, 40.0])}
>>> translated_input_dict, translated_label_dict, translated_weight_dict = translate(input_dict, label_dict, weight_dict)
>>> print(translated_input_dict)
{"x": array([[2., 3.], [4., 5.]]), "y": array([[0., 1.], [2., 3.]])}
>>> print(translated_label_dict)
{"x": array([2., 3.]), "y": array([3., 4.])}
>>> print(translated_weight_dict)
{"x": array([10., 20.]), "y": array([30., 40.])}
"""

def __init__(self, offset: Dict[str, float]):
Expand All @@ -46,7 +58,7 @@ def __call__(self, input_dict, label_dict, weight_dict):


class Scale:
"""Scale class.
"""Scale class for data transformation.

Args:
scale (Dict[str, float]): Scale the input data according to the variable name
Expand All @@ -55,6 +67,16 @@ class Scale:
Examples:
>>> import ppsci
>>> translate = ppsci.data.transform.Scale({"x": 1.5, "y": 2.0})
>>> input_dict = {"x": 10, "y": 20}
>>> label_dict = {"x": 100, "y": 200}
>>> weight_dict = {"x": 1000, "y": 2000}
>>> input_dict_scaled, label_dict_scaled, weight_dict_scaled = translate(input_dict, label_dict, weight_dict)
Liyulingyue marked this conversation as resolved.
Show resolved Hide resolved
>>> print(input_dict_scaled)
{'x': 15.0, 'y': 40.0}
>>> print(label_dict_scaled)
{'x': 100, 'y': 200}
>>> print(weight_dict_scaled)
{'x': 1000, 'y': 2000}
"""

def __init__(self, scale: Dict[str, float]):
Expand All @@ -79,6 +101,12 @@ class Normalize:
Examples:
>>> import ppsci
>>> normalize = ppsci.data.transform.Normalize((0.0, 0.0, 0.0), (1.0, 1.0, 1.0))
>>> input_item = {"data": np.array([1.0, 2.0, 3.0])}
>>> label_item = {"data": np.array([4.0, 5.0, 6.0])}
>>> weight_item = np.array([0.1, 0.2, 0.3])
>>> normalized_item = normalize(input_item, label_item, weight_item)
>>> print(normalized_item)
({'data': array([1., 2., 3.])}, {'data': array([4., 5., 6.])}, array([0.1, 0.2, 0.3]))
"""

def __init__(
Expand Down Expand Up @@ -117,6 +145,16 @@ class Log1p:
Examples:
>>> import ppsci
>>> log1p = ppsci.data.transform.Log1p(1e-5)
>>> input_item = {"data": np.array([1.0, 2.0, 3.0])}
>>> label_item = {"data": np.array([4.0, 5.0, 6.0])}
>>> weight_item = np.array([0.1, 0.2, 0.3])
>>> input_item_transformed, label_item_transformed, weight_item_transformed = log1p(input_item, label_item, weight_item)
Liyulingyue marked this conversation as resolved.
Show resolved Hide resolved
>>> print(input_item_transformed)
{'data': array([11.51293546, 12.20607765, 12.61154109])}
>>> print(label_item_transformed)
{'data': array([12.89922233, 13.12236538, 13.3046866 ])}
>>> print(weight_item_transformed)
[0.1 0.2 0.3]
"""

def __init__(
Expand Down Expand Up @@ -194,7 +232,12 @@ class SqueezeData:

Examples:
>>> import ppsci
>>> import numpy as np
>>> squeeze_data = ppsci.data.transform.SqueezeData()
>>> input_data = {"input": np.random.rand(10, 224, 224)}
>>> label_data = {"label": np.random.rand(10, 224, 224)}
>>> weight_data = {"weight": np.random.rand(10, 224, 224)}
>>> input_data_squeezed, label_data_squeezed, weight_data_squeezed = squeeze_data(input_data, label_data, weight_data)
"""

def __init__(self, apply_keys: Tuple[str, ...] = ("input", "label")):
Expand Down Expand Up @@ -235,22 +278,27 @@ class FunctionalTransform:
transform_func (Callable): Function of data transform.

Examples:
>>> import ppsci
>>> import numpy as np
>>> # This is the transform_func function. It takes three dictionaries as input: data_dict, label_dict, and weight_dict.
>>> # The function will perform some transformations on the data in data_dict, convert all labels in label_dict to uppercase,
>>> # and modify the weights in weight_dict by dividing each weight by 10.
>>> # Finally, it returns the transformed data, labels, and weights as a tuple.
>>> def transform_func(data_dict, label_dict, weight_dict):
... rand_ratio = np.random.rand()
... for key in data_dict:
... data_dict[key] = data_dict[key] * rand_ratio
... data_dict[key] = data_dict[key] * 2
... for key in label_dict:
... label_dict[key] = label_dict[key].upper()
... for key in weight_dict:
... weight_dict[key] = weight_dict[key] / 10
... return data_dict, label_dict, weight_dict
>>> transform_cfg = {
... "transforms": (
... {
... "FunctionalTransform": {
... "transform_func": transform_func,
... },
... },
... ),
... }
>>> transform = ppsci.data.transform.FunctionalTransform(transform_func)
>>> # Define some sample data, labels, and weights
>>> data = {'feature1': np.array([1, 2, 3]), 'feature2': np.array([4, 5, 6])}
>>> label = {'class': 'class1', 'instance': 'instance1'}
>>> weight = {'weight1': 0.5, 'weight2': 0.5}
>>> # Apply the transform function to the data, labels, and weights using the FunctionalTransform instance
>>> transformed_data = transform(data, label, weight)
>>> print(transformed_data)
({'feature1': [2, 4, 6], 'feature2': [8, 10, 12]}, {'class': 'CLASS1', 'instance': 'INSTANCE1'}, {'weight1': 0.5, 'weight2': 0.5})
"""

def __init__(
Expand Down