我在Azure ML Studio上部署了一个ML模型，我使用推理架构对其进行了更新，以允许与Power BI兼容，如本文所述。
当通过RESTapi将数据发送到模型时(在添加这个推理模式之前(，一切都很好，我得到了返回的结果。然而，一旦添加了上面链接的指令中描述的模式并对我的数据进行了个性化处理，通过RESTapi发送的相同数据只返回错误"；列表索引超出范围"；。部署进行得很好，并且被指定为"；健康的"；没有错误消息。
如有任何帮助，我们将不胜感激。谢谢
编辑：
输入脚本：
import numpy as np
import pandas as pd
import joblib
from azureml.core.model import Model
from inference_schema.schema_decorators import input_schema, output_schema
from inference_schema.parameter_types.standard_py_parameter_type import StandardPythonParameterType
from inference_schema.parameter_types.numpy_parameter_type import NumpyParameterType
from inference_schema.parameter_types.pandas_parameter_type import PandasParameterType
def init():
global model
#Model name is the name of the model registered under the workspace
model_path = Model.get_model_path(model_name = 'databricksmodelpowerbi2')
model = joblib.load(model_path)
#Provide 3 sample inputs for schema generation for 2 rows of data
numpy_sample_input = NumpyParameterType(np.array([[2400.0, 78.26086956521739, 11100.0, 3.612565445026178, 3.0, 0.0], [368.55, 96.88311688311687, 709681.1600000012, 73.88059701492537, 44.0, 0.0]], dtype = 'float64'))
pandas_sample_input = PandasParameterType(pd.DataFrame({'1': [2400.0, 368.55], '2': [78.26086956521739, 96.88311688311687], '3': [11100.0, 709681.1600000012], '4': [3.612565445026178, 73.88059701492537], '5': [3.0, 44.0], '6': [0.0, 0.0]}))
standard_sample_input = StandardPythonParameterType(0.0)
# This is a nested input sample, any item wrapped by `ParameterType` will be described by schema
sample_input = StandardPythonParameterType({'input1': numpy_sample_input,
'input2': pandas_sample_input,
'input3': standard_sample_input})
sample_global_parameters = StandardPythonParameterType(1.0) #this is optional
sample_output = StandardPythonParameterType([1.0, 1.0])
@input_schema('inputs', sample_input)
@input_schema('global_parameters', sample_global_parameters) #this is optional
@output_schema(sample_output)
def run(inputs, global_parameters):
try:
data = inputs['input1']
# data will be convert to target format
assert isinstance(data, np.ndarray)
result = model.predict(data)
return result.tolist()
except Exception as e:
error = str(e)
return error
预测脚本：
import requests
import json
from ast import literal_eval
# URL for the web service
scoring_uri = ''
## If the service is authenticated, set the key or token
#key = '<your key or token>'
# Two sets of data to score, so we get two results back
data = {"data": [[2400.0, 78.26086956521739, 11100.0, 3.612565445026178, 3.0, 0.0], [368.55, 96.88311688311687, 709681.1600000012, 73.88059701492537, 44.0, 0.0]]}
# Convert to JSON string
input_data = json.dumps(data)
# Set the content type
headers = {'Content-Type': 'application/json'}
## If authentication is enabled, set the authorization header
#headers['Authorization'] = f'Bearer {key}'
# Make the request and display the response
resp = requests.post(scoring_uri, input_data, headers=headers)
print(resp.text)
result = literal_eval(resp.text)
微软文档说："为了为自动化web服务消费生成符合要求的swagger，评分脚本run((函数必须具有以下形式的API：
类型为"的第一个参数；StandardPythonParameterType"；，命名的输入和嵌套。
一个可选的第二参数类型"；StandardPythonParameterType"；，名为GlobalParameters。
返回类型为"的字典；StandardPythonParameterType；命名的结果并嵌套">
我已经测试过了，它区分大小写所以它将是这样的：
import numpy as np
import pandas as pd
import joblib
from azureml.core.model import Model
from inference_schema.schema_decorators import input_schema, output_schema
from inference_schema.parameter_types.standard_py_parameter_type import
StandardPythonParameterType
from inference_schema.parameter_types.numpy_parameter_type import NumpyParameterType
from inference_schema.parameter_types.pandas_parameter_type import PandasParameterType
def init():
global model
# Model name is the name of the model registered under the workspace
model_path = Model.get_model_path(model_name = 'databricksmodelpowerbi2')
model = joblib.load(model_path)
# Provide 3 sample inputs for schema generation for 2 rows of data
numpy_sample_input = NumpyParameterType(np.array([[2400.0, 78.26086956521739, 11100.0,
3.612565445026178, 3.0, 0.0], [368.55, 96.88311688311687, 709681.1600000012,
73.88059701492537, 44.0, 0.0]], dtype = 'float64'))
pandas_sample_input = PandasParameterType(pd.DataFrame({'value': [2400.0, 368.55],
'delayed_percent': [78.26086956521739, 96.88311688311687], 'total_value_delayed':
[11100.0, 709681.1600000012], 'num_invoices_per30_dealing_days': [3.612565445026178,
73.88059701492537], 'delayed_streak': [3.0, 44.0], 'prompt_streak': [0.0, 0.0]}))
standard_sample_input = StandardPythonParameterType(0.0)
# This is a nested input sample, any item wrapped by `ParameterType` will be described
by schema
sample_input = StandardPythonParameterType({'input1': numpy_sample_input,
'input2': pandas_sample_input,
'input3': standard_sample_input})
sample_global_parameters = StandardPythonParameterType(1.0) #this is optional
numpy_sample_output = NumpyParameterType(np.array([1.0, 2.0]))
# 'Results' is case sensitive
sample_output = StandardPythonParameterType({'Results': numpy_sample_output})
# 'Inputs' is case sensitive
@input_schema('Inputs', sample_input)
@input_schema('global_parameters', sample_global_parameters) #this is optional
@output_schema(sample_output)
def run(Inputs, global_parameters):
try:
data = inputs['input1']
# data will be convert to target format
assert isinstance(data, np.ndarray)
result = model.predict(data)
return result.tolist()
except Exception as e:
error = str(e)
return error
`
我不确定你是否已经弄清楚了，但我也遇到了类似的问题，我无法让Power BI查看我的ML模型。最后，我使用以下模式专门为PowerBI(pandas-df类型(创建了一个服务：
import json
import pandas as pd
import numpy as np
import os
import joblib
from sklearn.ensemble import RandomForestClassifier
from inference_schema.schema_decorators import input_schema, output_schema
from inference_schema.parameter_types.standard_py_parameter_type import StandardPythonParameterType
from inference_schema.parameter_types.numpy_parameter_type import NumpyParameterType
from inference_schema.parameter_types.pandas_parameter_type import PandasParameterType
import pickle
import azureml.train.automl
# Called when the service is loaded
def init():
# AZUREML_MODEL_DIR is an environment variable created during deployment. Join this path with the filename of the model file.
# It holds the path to the directory that contains the deployed model (./azureml-models/$MODEL_NAME/$VERSION).
# If there are multiple models, this value is the path to the directory containing all deployed models (./azureml-models).
global model
model_path = os.path.join(os.getenv('AZUREML_MODEL_DIR'), 'model.pkl')
# Get the path to the deployed model file and load it
# Deserialize the model file back into a sklearn model
model = joblib.load(model_path)
input_sample = PandasParameterType(pd.DataFrame({
'input1': [0.0, 20.0],
'input2': [0.0, 20.0],
'input2': [0.0, 20.0]
}))
output_sample = PandasParameterType(pd.DataFrame([0.8, 0.2]))
# Called when a request is received
@input_schema('data', input_sample)
@output_schema(output_sample)
def run(data):
try:
result = model.predict(data)
# You can return any data type, as long as it is JSON serializable.
return result.tolist()
except Exception as e:
error = str(e)
return error