如何在 Flask 上的 sklearn 管道中使用自定义转换?

Question

我无法使用 sklearn 管道在 Flask 中使用自定义转换picke.dump().

假设我想在泡菜中使用以下管道来供应 Flask。它选择变量，创建假人并将进入模型的变量分开。

# Custom Transformer that extracts columns passed as argument to its constructor
class FeatureSelector(BaseEstimator, TransformerMixin):
# Class Constructor
def __init__(self, feature_names):
self._feature_names = feature_names
# Return self nothing else to do here
def fit(self, X, y=None):
return self
# Method that describes what we neeed this transformer to do
def transform(self, X, y=None):
return X[self._feature_names]
# Defining the steps in the categorical pipeline
categorical_features = ['marital', 'contact', 'job']
# Converts certain features to binary
class CategoricalBinary(TransformerMixin):
# Class Constructor
#def __init__(self):
# Return self nothing else to do here
def fit(self, X, y=None):
return self
# Faz as transformações com a função get_dummies
def transform(self, X, y=None):
X = pd.get_dummies(X, columns=X.columns.tolist())
return X
# Custom Transformer that extracts columns passed as argument to its constructor
class ModelFeatureSelector(BaseEstimator, TransformerMixin):
# Class Constructor
def __init__(self, feature_names):
self._feature_names = feature_names
# Return self nothing else to do here
def fit(self, X, y=None):
return self
# Method that describes what we neeed this transformer to do
def transform(self, X, y=None):
return X[self._feature_names]
model_features = ['marital_divorced', 'marital_married', 'marital_single',
'contact_cellular', 'job_admin.', 'job_blue-collar',
'job_entrepreneur', 'job_housemaid', 'job_management',
'job_retired', 'job_self-employed', 'job_services',
'job_student', 'job_technician', 'job_unemployed']
categorical_transform = Pipeline(steps=[('feature_selector', FeatureSelector(categorical_features)),
('categorical_dummy', CategoricalBinary()),
('model_features', ModelFeatureSelector(model_features)),
('logreg', LogisticRegression(class_weight='balanced', solver='liblinear'))])
# Fits
categorical_transform.fit(X_train, y_train)
# Save on pickle
with open('categorical_transform.pkl', 'wb') as f:
pickle.dump(categorical_transform, f)

我编程了烧瓶

# Importa as classes necessárias do pacote `flask`
from flask import Flask, request, jsonify
# Importa o pacote de interação com o sistema `os`, o pacote `pandas` para maniulação da informação
# e o pacote `pickle` para carregar nosso modelo.
import os
import pandas as pd
import pickle
from sklearn.pipeline import FeatureUnion, Pipeline
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.impute import SimpleImputer
import outros
# Cria a aplicação
app = Flask(__name__)
# Model
model = pickle.load(open('categorical_transform.pkl', 'rb'))
# TAREFA: PREENCHA O MÉTODO DE REQUISIÇÃO
@app.route('/predict', methods=['POST'])
def predictor():
# Recebe o conteúdo da postagem no formato json.
content = request.json
features = pd.DataFrame([content])
# Aplica a predição do modelo
predito = model.predict(features)
# Cria e envia uma resposta para o 'chamador' da API
return jsonify(status='completed', predict=float(predito[1][1]))
# Essa linha garante que a aplicação execute no localhost, ou seja, no IP "0.0.0.0"
# e que esteja na porta padrão do sistema ou, caso ela não exista, na porta 8080.
if __name__ == '__main__':
app.run(debug=True,host='0.0.0.0',port=os.environ.get('PORT', 8080))

引发以下异常：

AttributeError: Can't get attribute 'FeatureSelector'

Answer 1

你已经在某个 python 脚本中创建了一个自定义转换器FeatureSelector。在 Flask 脚本中，您可以导入该自定义类的父类，但不导入FeatureSelector本身。因此，在 Flask 脚本中没有自定义类的定义。因此，泡菜无法重建物体。

假设FeatureSelector是在custom_classes.py中定义的。然后，您的 Flask 脚本应包含一行：

from custom_classes import FeatureSelector