MLflow 模型签名沙盒笔记本
下载此笔记本 欢迎来到 MLflow 模型签名沙盒!这个交互式 Jupyter 笔记本旨在引导您了解 MLflow 生态系统中模型签名的基础概念。在学习笔记本的过程中,您将获得在定义、强制执行和使用模型签名方面的实践经验——这是模型管理的一个关键方面,可提高可重复性、可靠性和易用性。
模型签名为何重要
在机器学习领域,精确定义模型的输入和输出是确保顺畅运行的关键。模型签名充当模型期望和生成的数据的模式定义,作为模型开发人员和用户的蓝图。这不仅可以明确期望,还便于自动验证检查,从而简化了从模型训练到部署的过程。
签名强制执行实况
通过探索此笔记本中的代码单元格,您将亲眼目睹模型签名如何强制执行数据完整性、防止常见错误,并在出现差异时提供描述性反馈。这对于维护模型输入的质量和一致性非常有价值,尤其是在生产环境中提供模型时。
深入理解的实践示例
该笔记本包含一系列示例,展示了不同的数据类型和结构,从简单的标量到复杂的嵌套字典。这些示例演示了签名是如何推断、记录和更新的,从而为您提供对签名生命周期的全面理解。在与提供的 PythonModel 实例交互并调用其 predict 方法时,您将学会如何处理各种输入场景——包括必需和可选的数据字段——以及如何更新现有模型以包含详细签名。无论您是希望改进模型管理实践的数据科学家,还是将 MLflow 集成到工作流程中的开发人员,该笔记本都是您掌握模型签名的沙盒。让我们深入探索 MLflow 签名的强大功能!
注意:此笔记本中显示的许多功能仅在 MLflow 2.10.0 及更高版本中可用。特别是,在 2.10.0 版本之前不支持
Array和Object类型。
import numpy as np
import pandas as pd
import mlflow
from mlflow.models.signature import infer_signature, set_signature
def report_signature_info(input_data, output_data=None, params=None):
inferred_signature = infer_signature(input_data, output_data, params)
report = f"""
The input data:
{input_data}.
The data is of type: {type(input_data)}.
The inferred signature is:
{inferred_signature}
"""
print(report)
MLflow 签名中的标量支持
在本教程的这一部分,我们探讨了标量数据类型在 MLflow 模型签名中的关键作用。标量类型,如字符串、整数、浮点数、双精度数、布尔值和日期时间,是定义模型输入和输出模式的基础。准确表示这些类型对于确保模型正确处理数据至关重要,这直接影响预测的可靠性和准确性。
通过检查各种标量类型的示例,本节演示了 MLflow 如何推断和记录数据的结构和性质。我们将看到 MLflow 签名如何处理不同的标量类型,确保输入模型的数据与预期格式匹配。这种理解对于任何机器学习从业者都至关重要,因为它有助于准备和验证数据输入,从而实现更顺畅的模型操作和更可靠的结果。
通过实际示例,包括字符串、浮点数和其他类型的列表,我们说明了 MLflow 的 infer_signature 函数如何准确推断数据格式。此功能是 MLflow 处理各种数据输入能力的基础,也是机器学习模型中更复杂数据结构的基础。在本节结束时,您将清晰地了解标量数据在 MLflow 签名中的表示方式,以及这对于您的 ML 项目的重要性。
# List of strings
report_signature_info(["a", "list", "of", "strings"])
The input data: ['a', 'list', 'of', 'strings']. The data is of type: <class 'list'>. The inferred signature is: inputs: [string (required)] outputs: None params: None
# List of floats
report_signature_info([np.float32(0.117), np.float32(1.99)])
The input data: [0.117, 1.99]. The data is of type: <class 'list'>. The inferred signature is: inputs: [float (required)] outputs: None params: None
# Adding a column header to a list of doubles
my_data = pd.DataFrame({"input_data": [np.float64(0.117), np.float64(1.99)]})
report_signature_info(my_data)
The input data: input_data 0 0.117 1 1.990. The data is of type: <class 'pandas.core.frame.DataFrame'>. The inferred signature is: inputs: ['input_data': double (required)] outputs: None params: None
# List of Dictionaries
report_signature_info([{"a": "a1", "b": "b1"}, {"a": "a2", "b": "b2"}])
The input data:
[{'a': 'a1', 'b': 'b1'}, {'a': 'a2', 'b': 'b2'}].
The data is of type: <class 'list'>.
The inferred signature is:
inputs:
['a': string (required), 'b': string (required)]
outputs:
None
params:
None
# List of Arrays of strings
report_signature_info([["a", "b", "c"], ["d", "e", "f"]])
The input data: [['a', 'b', 'c'], ['d', 'e', 'f']]. The data is of type: <class 'list'>. The inferred signature is: inputs: [Array(string) (required)] outputs: None params: None
# List of Arrays of Dictionaries
report_signature_info(
[[{"a": "a", "b": "b"}, {"a": "a", "b": "b"}], [{"a": "a", "b": "b"}, {"a": "a", "b": "b"}]]
)
The input data:
[[{'a': 'a', 'b': 'b'}, {'a': 'a', 'b': 'b'}], [{'a': 'a', 'b': 'b'}, {'a': 'a', 'b': 'b'}]].
The data is of type: <class 'list'>.
The inferred signature is:
inputs:
[Array({a: string (required), b: string (required)}) (required)]
outputs:
None
params:
None
理解类型转换:int 到 long
在本教程的这一部分,我们观察了 MLflow 模式推断中一个有趣的类型转换方面。在报告整数列表的签名信息时,您可能会注意到推断的数据类型是 long 而不是 int。这种从 int 到 long 的转换不是错误或 bug,而是 MLflow 模式推断机制中有效且有意的类型转换。
为何将整数推断为 long
- 更广泛的兼容性: 转换为
long可确保跨各种平台和系统的兼容性。由于整数 (int) 的大小可能因系统架构而异,使用long(具有更一致的大小规范)可以避免潜在的差异和数据溢出问题。 - 数据完整性: 通过将整数推断为 long,MLflow 可确保超出 int 通常容量的较大整数值能够准确表示和处理,而不会丢失数据或发生溢出。
- 机器学习模型中的一致性: 在许多机器学习框架中,尤其是在涉及大型数据集或计算的框架中,长整数通常是数值运算的标准数据类型。推断模式中的这种标准化与机器学习社区中的常见做法一致。
# List of integers
report_signature_info([1, 2, 3])
The input data: [1, 2, 3]. The data is of type: <class 'list'>. The inferred signature is: inputs: [long (required)] outputs: None params: None
/Users/benjamin.wilson/repos/mlflow-fork/mlflow/mlflow/types/utils.py:378: UserWarning: Hint: Inferred schema contains integer column(s). Integer columns in Python cannot represent missing values. If your input data contains missing values at inference time, it will be encoded as floats and will cause a schema enforcement error. The best way to avoid this problem is to infer the model schema based on a realistic data sample (training dataset) that includes missing values. Alternatively, you can declare integer columns as doubles (float64) whenever these columns may have missing values. See `Handling Integers With Missing Values <https://www.mlflow.org/docs/latest/models.html#handling-integers-with-missing-values>`_ for more details. warnings.warn(
# List of Booleans
report_signature_info([True, False, False, False, True])
The input data: [True, False, False, False, True]. The data is of type: <class 'list'>. The inferred signature is: inputs: [boolean (required)] outputs: None params: None
# List of Datetimes
report_signature_info([np.datetime64("2023-12-24 11:59:59"), np.datetime64("2023-12-25 00:00:00")])
The input data:
[numpy.datetime64('2023-12-24T11:59:59'), numpy.datetime64('2023-12-25T00:00:00')].
The data is of type: <class 'list'>.
The inferred signature is:
inputs:
[datetime (required)]
outputs:
None
params:
None
# Complex list of Dictionaries
report_signature_info([{"a": "b", "b": [1, 2, 3], "c": {"d": [4, 5, 6]}}])
The input data:
[{'a': 'b', 'b': [1, 2, 3], 'c': {'d': [4, 5, 6]}}].
The data is of type: <class 'list'>.
The inferred signature is:
inputs:
['a': string (required), 'b': Array(long) (required), 'c': {d: Array(long) (required)} (required)]
outputs:
None
params:
None
# Pandas DF input
data = [
{"a": "a", "b": ["a", "b", "c"], "c": {"d": 1, "e": 0.1}, "f": [{"g": "g"}, {"h": 1}]},
{"b": ["a", "b"], "c": {"d": 2, "f": "f"}, "f": [{"g": "g"}]},
]
data = pd.DataFrame(data)
report_signature_info(data)
The input data:
a b c f
0 a [a, b, c] {'d': 1, 'e': 0.1} [{'g': 'g'}, {'h': 1}]
1 NaN [a, b] {'d': 2, 'f': 'f'} [{'g': 'g'}].
The data is of type: <class 'pandas.core.frame.DataFrame'>.
The inferred signature is:
inputs:
['a': string (optional), 'b': Array(string) (required), 'c': {d: long (required), e: double (optional), f: string (optional)} (required), 'f': Array({g: string (optional), h: long (optional)}) (required)]
outputs:
None
params:
None
签名强制执行
在本教程的这一部分,我们重点关注 MLflow 中签名强制执行的实际应用。签名强制执行是一项强大的功能,可确保提供给模型的數據符合定义的输入模式。此步骤对于防止因数据不匹配或格式错误而可能出现的错误和不一致至关重要。
通过实践示例,我们将观察 MLflow 如何在运行时强制数据符合预期签名。我们将使用 MyModel 类(一个简单的 Python 模型)来演示 MLflow 如何根据模型的签名检查输入数据的兼容性。此过程有助于保护模型免受不兼容或错误输入的侵害,从而提高模型预测的鲁棒性和可靠性。
本节还强调了 MLflow 中精确数据表示的重要性及其对模型性能的影响。通过测试不同类型的数据(包括不符合预期模式的数据),我们将看到 MLflow 如何验证数据并提供信息反馈。签名强制执行的这一方面对于调试数据问题和完善模型输入非常有价值,使其成为部署机器学习模型的任何人的关键技能。
class MyModel(mlflow.pyfunc.PythonModel):
def predict(self, context, model_input, params=None):
return model_input
data = [{"a": ["a", "b", "c"], "b": "b", "c": {"d": "d"}}, {"a": ["a"], "c": {"d": "d", "e": "e"}}]
report_signature_info(data)
The input data:
[{'a': ['a', 'b', 'c'], 'b': 'b', 'c': {'d': 'd'}}, {'a': ['a'], 'c': {'d': 'd', 'e': 'e'}}].
The data is of type: <class 'list'>.
The inferred signature is:
inputs:
['a': Array(string) (required), 'b': string (optional), 'c': {d: string (required), e: string (optional)} (required)]
outputs:
None
params:
None
# Generate a prediction that will serve as the model output example for signature inference
model_output = MyModel().predict(context=None, model_input=data)
with mlflow.start_run():
model_info = mlflow.pyfunc.log_model(
python_model=MyModel(),
name="test_model",
signature=infer_signature(model_input=data, model_output=model_output),
)
loaded_model = mlflow.pyfunc.load_model(model_info.model_uri)
prediction = loaded_model.predict(data)
prediction
/Users/benjamin.wilson/miniconda3/envs/mlflow-dev-env/lib/python3.8/site-packages/_distutils_hack/__init__.py:30: UserWarning: Setuptools is replacing distutils.
warnings.warn("Setuptools is replacing distutils.")
| a | b | c | |
|---|---|---|---|
| 0 | [a, b, c] | b | {'d': 'd'} |
| 1 | [a] | NaN | {'d': 'd', 'e': 'e'} |
我们可以直接从调用 log_model() 返回的记录模型信息中检查推断的签名。
model_info.signature
inputs:
['a': Array(string) (required), 'b': string (optional), 'c': {d: string (required), e: string (optional)} (required)]
outputs:
['a': Array(string) (required), 'b': string (optional), 'c': {d: string (required), e: string (optional)} (required)]
params:
None
我们还可以快速验证记录的输入签名是否与签名推断匹配。同时,我们也可以生成输出签名。
注意:建议使用模型记录输入和输出签名。
report_signature_info(data, prediction)
The input data:
[{'a': ['a', 'b', 'c'], 'b': 'b', 'c': {'d': 'd'}}, {'a': ['a'], 'c': {'d': 'd', 'e': 'e'}}].
The data is of type: <class 'list'>.
The inferred signature is:
inputs:
['a': Array(string) (required), 'b': string (optional), 'c': {d: string (required), e: string (optional)} (required)]
outputs:
['a': Array(string) (required), 'b': string (optional), 'c': {d: string (required), e: string (optional)} (required)]
params:
None
# Using the model while not providing an optional input (note the output return structure and the non existent optional columns)
loaded_model.predict([{"a": ["a", "b", "c"], "c": {"d": "d"}}])
| a | c | |
|---|---|---|
| 0 | [a, b, c] | {'d': 'd'} |
# Using the model while omitting the input of required fields (this will raise an Exception from schema enforcement,
# stating that the required fields "a" and "c" are missing)
loaded_model.predict([{"b": "b"}])
---------------------------------------------------------------------------
MlflowException Traceback (most recent call last)
~/repos/mlflow-fork/mlflow/mlflow/pyfunc/__init__.py in predict(self, data, params) 469 try: --> 470 data = _enforce_schema(data, input_schema) 471 except Exception as e:
~/repos/mlflow-fork/mlflow/mlflow/models/utils.py in _enforce_schema(pf_input, input_schema)
939 message += f" Note that there were extra inputs: {extra_cols}"
--> 940 raise MlflowException(message)
941 elif not input_schema.is_tensor_spec():
MlflowException: Model is missing inputs ['a', 'c'].
During handling of the above exception, another exception occurred:
MlflowException Traceback (most recent call last)
/var/folders/cd/n8n0rm2x53l_s0xv_j_xklb00000gp/T/ipykernel_97464/1628231496.py in <cell line: 4>()
2 # stating that the required fields "a" and "c" are missing)
3
----> 4 loaded_model.predict([{"b": "b"}])
~/repos/mlflow-fork/mlflow/mlflow/pyfunc/__init__.py in predict(self, data, params)
471 except Exception as e:
472 # Include error in message for backwards compatibility
--> 473 raise MlflowException.invalid_parameter_value(
474 f"Failed to enforce schema of data '{data}' "
475 f"with schema '{input_schema}'. "
MlflowException: Failed to enforce schema of data '[{'b': 'b'}]' with schema '['a': Array(string) (required), 'b': string (optional), 'c': {d: string (required), e: string (optional)} (required)]'. Error: Model is missing inputs ['a', 'c'].
更新签名
本教程的这一部分讨论了数据和模型的动态特性,重点介绍了更新 MLflow 模型签名这一关键任务。随着数据集的演变和需求的改变,有必要修改模型的签名以匹配新的数据结构或输入。这种更新签名能力是随着时间的推移保持模型准确性和相关性的关键。
我们将演示如何识别何时需要更新签名,并逐步介绍为现有模型创建和应用新签名的过程。本节强调了 MLflow 在适应数据格式和结构变化方面的灵活性,而无需重新保存整个模型。但是,对于 MLflow 中的注册模型,更新签名需要重新注册模型才能反映注册版本中的更改。
通过探索更新模型签名的步骤,您将了解在手动定义了无效签名的情况下,或者在记录时未定义签名但需要使用有效签名更新模型的情况下,如何更新模型签名。
# Updating an existing model that wasn't saved with a signature
class MyTypeCheckerModel(mlflow.pyfunc.PythonModel):
def predict(self, context, model_input, params=None):
print(type(model_input))
print(model_input)
if not isinstance(model_input, (pd.DataFrame, list)):
raise ValueError("The input must be a list.")
return "Input is valid."
with mlflow.start_run():
model_info = mlflow.pyfunc.log_model(
python_model=MyTypeCheckerModel(),
name="test_model",
)
loaded_model = mlflow.pyfunc.load_model(model_info.model_uri)
loaded_model.metadata.signature
test_data = [{"a": "we are expecting strings", "b": "and only strings"}, [1, 2, 3]]
loaded_model.predict(test_data)
<class 'list'>
[{'a': 'we are expecting strings', 'b': 'and only strings'}, [1, 2, 3]]
'Input is valid.'
MLflow 中模式强制执行的必要性
在本教程的这一部分,我们讨论了机器学习模型部署中的一个常见挑战:错误消息的清晰度和可解释性。如果没有模式强制执行,模型通常会返回晦涩难懂或具有误导性的错误消息。这是因为,在没有明确定义的模式的情况下,模型会尝试处理可能与其预期不符的输入,从而导致模糊或难以诊断的错误。
模式强制执行为何重要
模式强制执行充当守门员,确保输入到模型中的数据精确匹配预期的格式。这不仅降低了运行时错误的发生几率,而且使任何发生的错误都更容易理解和纠正。如果没有这种强制执行,诊断问题将成为一项耗时且复杂的工作,通常需要深入研究模型的内部逻辑。
更新模型签名以获得更清晰的错误消息
为了说明模式强制执行的价值,我们将更新已保存模型的签名,使其与预期的数据结构匹配。此过程包括定义预期数据结构,使用 infer_signature 函数生成适当的签名,然后使用 set_signature 将此签名应用于模型。通过这样做,我们确保任何未来的错误都更具信息量,并与我们预期的数据结构保持一致,从而简化故障排除并提高模型可靠性。
expected_data_structure = [{"a": "string", "b": "another string"}, {"a": "string"}]
signature = infer_signature(expected_data_structure, loaded_model.predict(expected_data_structure))
set_signature(model_info.model_uri, signature)
<class 'list'>
[{'a': 'string', 'b': 'another string'}, {'a': 'string'}]
loaded_with_signature = mlflow.pyfunc.load_model(model_info.model_uri)
loaded_with_signature.metadata.signature
inputs: ['a': string (required), 'b': string (optional)] outputs: [string (required)] params: None
loaded_with_signature.predict(expected_data_structure)
<class 'pandas.core.frame.DataFrame'>
a b
0 string another string
1 string NaN
'Input is valid.'
验证模式强制执行不会允许有缺陷的输入
既然我们已经正确设置了签名并更新了模型定义,让我们确保之前的有缺陷的输入类型将引发有用的错误消息!
loaded_with_signature.predict(test_data)
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
~/repos/mlflow-fork/mlflow/mlflow/pyfunc/__init__.py in predict(self, data, params) 469 try: --> 470 data = _enforce_schema(data, input_schema) 471 except Exception as e:
~/repos/mlflow-fork/mlflow/mlflow/models/utils.py in _enforce_schema(pf_input, input_schema) 907 elif isinstance(pf_input, (list, np.ndarray, pd.Series)): --> 908 pf_input = pd.DataFrame(pf_input) 909
~/miniconda3/envs/mlflow-dev-env/lib/python3.8/site-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy) 781 columns = ensure_index(columns) --> 782 arrays, columns, index = nested_data_to_arrays( 783 # error: Argument 3 to "nested_data_to_arrays" has incompatible
~/miniconda3/envs/mlflow-dev-env/lib/python3.8/site-packages/pandas/core/internals/construction.py in nested_data_to_arrays(data, columns, index, dtype) 497 --> 498 arrays, columns = to_arrays(data, columns, dtype=dtype) 499 columns = ensure_index(columns)
~/miniconda3/envs/mlflow-dev-env/lib/python3.8/site-packages/pandas/core/internals/construction.py in to_arrays(data, columns, dtype) 831 elif isinstance(data[0], abc.Mapping): --> 832 arr, columns = _list_of_dict_to_arrays(data, columns) 833 elif isinstance(data[0], ABCSeries):
~/miniconda3/envs/mlflow-dev-env/lib/python3.8/site-packages/pandas/core/internals/construction.py in _list_of_dict_to_arrays(data, columns) 911 sort = not any(isinstance(d, dict) for d in data) --> 912 pre_cols = lib.fast_unique_multiple_list_gen(gen, sort=sort) 913 columns = ensure_index(pre_cols)
~/miniconda3/envs/mlflow-dev-env/lib/python3.8/site-packages/pandas/_libs/lib.pyx in pandas._libs.lib.fast_unique_multiple_list_gen()
~/miniconda3/envs/mlflow-dev-env/lib/python3.8/site-packages/pandas/core/internals/construction.py in <genexpr>(.0) 909 if columns is None: --> 910 gen = (list(x.keys()) for x in data) 911 sort = not any(isinstance(d, dict) for d in data)
AttributeError: 'list' object has no attribute 'keys'
During handling of the above exception, another exception occurred:
MlflowException Traceback (most recent call last)
/var/folders/cd/n8n0rm2x53l_s0xv_j_xklb00000gp/T/ipykernel_97464/2586525788.py in <cell line: 1>() ----> 1 loaded_with_signature.predict(test_data)
~/repos/mlflow-fork/mlflow/mlflow/pyfunc/__init__.py in predict(self, data, params)
471 except Exception as e:
472 # Include error in message for backwards compatibility
--> 473 raise MlflowException.invalid_parameter_value(
474 f"Failed to enforce schema of data '{data}' "
475 f"with schema '{input_schema}'. "
MlflowException: Failed to enforce schema of data '[{'a': 'we are expecting strings', 'b': 'and only strings'}, [1, 2, 3]]' with schema '['a': string (required), 'b': string (optional)]'. Error: 'list' object has no attribute 'keys'
总结:MLflow 模型签名沙盒的见解和最佳实践
随着我们完成 MLflow 模型签名沙盒笔记本之旅,我们对 MLflow 生态系统中的模型签名细节获得了宝贵的见解。本教程为您提供了有效管理和利用模型签名所需的知识和实践技能,确保您的机器学习模型的鲁棒性和准确性。
关键要点包括准确定义标量类型的重要性、强制执行和遵守模型签名对数据完整性的意义,以及 MLflow 在更新无效模型签名方面提供的灵活性。这些概念不仅仅是理论上的,而且是成功部署和管理现实世界模型场景的基础。
无论您是完善模型的 数据科学家,还是将机器学习集成到应用程序中的开发人员,理解和利用模型签名都至关重要。我们希望本教程为您提供了 MLflow 签名方面的坚实基础,使您能够在未来的 ML 项目中实施这些最佳实践。