使用Flask框架将机器学习模型部署上线

使用Flask框架将机器学习模型部署上线

1.flask基础

• 下面是基础代码

  from flask import Flask

  app = Flask(__name__)

  @app.route('/users/')
  def hello_world(username=None):

      return("Hello {}!".format(username))

2.创建一个机器学习模型

import os 
import json
import numpy as np
import pandas as pd
from sklearn.externals import joblib
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import make_pipeline
import warnings
warnings.filterwarnings("ignore")

• 数据处理过程

from sklearn.base import BaseEstimator, TransformerMixin

class PreProcessing(BaseEstimator, TransformerMixin):
    """Custom Pre-Processing estimator for our use-case
    """

    def __init__(self):
        pass

    def transform(self, df):
        """Regular transform() that is a help for training, validation & testing datasets
           (NOTE: The operations performed here are the ones that we did prior to this cell)
        """
        pred_var = ['Gender','Married','Dependents','Education','Self_Employed','ApplicantIncome',\
                    'CoapplicantIncome','LoanAmount','Loan_Amount_Term','Credit_History','Property_Area']
        
        df = df[pred_var]
        
        df['Dependents'] = df['Dependents'].fillna(0)
        df['Self_Employed'] = df['Self_Employed'].fillna('No')
        df['Loan_Amount_Term'] = df['Loan_Amount_Term'].fillna(self.term_mean_)
        df['Credit_History'] = df['Credit_History'].fillna(1)
        df['Married'] = df['Married'].fillna('No')
        df['Gender'] = df['Gender'].fillna('Male')
        df['LoanAmount'] = df['LoanAmount'].fillna(self.amt_mean_)
        
        gender_values = {'Female' : 0, 'Male' : 1} 
        married_values = {'No' : 0, 'Yes' : 1}
        education_values = {'Graduate' : 0, 'Not Graduate' : 1}
        employed_values = {'No' : 0, 'Yes' : 1}
        property_values = {'Rural' : 0, 'Urban' : 1, 'Semiurban' : 2}
        dependent_values = {'3+': 3, '0': 0, '2': 2, '1': 1}
        df.replace({'Gender': gender_values, 'Married': married_values, 'Education': education_values, \
                    'Self_Employed': employed_values, 'Property_Area': property_values, \
                    'Dependents': dependent_values}, inplace=True)
        
        return df.as_matrix()

    def fit(self, df, y=None, **fit_params):
        """Fitting the Training dataset & calculating the required values from train
           e.g: We will need the mean of X_train['Loan_Amount_Term'] that will be used in
                transformation of X_test
        """
        
        self.term_mean_ = df['Loan_Amount_Term'].mean()
        self.amt_mean_ = df['LoanAmount'].mean()
        return self

• 读取数据,并查找缺失值

data = pd.read_csv(path)
for i in data.columns:
		print(data[i].isnull())

• 使用管道

from sklearn.pipeline import make_pipeline
from sklearn.ensemble import RandomForestClassifier

pipe = make_pipeline(PreProcessing(),RandomForestClassifier())

• 使用网格搜索法选择参数

X_train,X_test,y_train,y_test = train_text_split(data[pred_var],data['loan_status'],test_size=0.25,random_state=42)
grid,fit(X_train,y_train)

• 验证模型

print('test set sorce:{:.2f}').format(grid.score(X_test,y_test))

3.模型序列化与反序列化

• 序列化

list_to_pickle = [1,'here',123,'walker']
import pickle
list_pickle = pickle.dumps(list_to_pickle)

• 反序列化

load_pickle = pickle.loads(list_pickle)