【发布时间】：2020-07-31 06:12:35
【问题描述】：
我在spyder开发了3个ML模型，分别是线性回归、多项式回归和随机森林回归。在sypder 中，它们都运行良好。但是，当我在 Django 上部署以创建 Web 应用程序时，Random Forest 出现“ValueError: Buffer type mismatch, expected 'SIZE_t' but got 'long long'”。 （我尝试删除 randomforest 并且其他两个模型运行良好）。
先检查一下：-
在 Sypder 中开发的模型
"""****************** Import Lib ******************"""
import numpy as np
import pandas as pd
import seaborn as sns
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
"""****************** Loading dataset ******************"""
boston = load_boston()
dataset = pd.DataFrame(boston.data, columns=boston.feature_names)
dataset['target'] = boston.target
"""****************** Data Preprocessing ******************"""
""" Data Analysis """
# Check Null
dataset.isnull().sum()
# Calculate X and y
X = dataset.iloc[:,:-1].values
y = dataset.iloc[:,-1].values.reshape(-1,1)
# train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=25)
""" Visualizing Data """
corr = dataset.corr()
sns.heatmap(corr, annot=True, cmap='Blues')
sns.pairplot(dataset)
"""****************** Regression Models ******************"""
""" Linear Regression """
from sklearn.linear_model import LinearRegression
regressor_linear = LinearRegression()
regressor_linear.fit(X_train, y_train)
cv_linear = cross_val_score(estimator = regressor_linear, X=X_train, y=y_train, cv=10)
""" Polynomial Regression """
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree = 2)
X_poly = poly_reg.fit_transform(X_train)
regressor_poly2 = LinearRegression()
regressor_poly2.fit(X_poly, y_train)
cv_poly2 = cross_val_score(estimator=regressor_poly2, X=X_poly, y=y_train, cv=10)
""" Random Forest Regression """
from sklearn.ensemble import RandomForestRegressor
regressor_rf = RandomForestRegressor(n_estimators=500, random_state=0, n_jobs=-1)
regressor_rf.fit(X_train, y_train.ravel())
cv_rf = cross_val_score(estimator=regressor_rf, X=X_train, y=y_train.ravel(), cv=10)
"""****************** Measuring the Error ******************"""
models=[
('Linear Regression', cv_linear.mean()),
('Polynomial Regression (2)', cv_poly2.mean()),
('Random Forest Regression', cv_rf.mean())
]
cv_scores = pd.DataFrame(data=models, columns=['Model','CV Score'])
"""****************** Dump ******************"""
from sklearn.externals import joblib
joblib.dump(regressor_linear,'regressor_linear_jb')
joblib.dump(regressor_poly2,'regressor_poly2_jb')
joblib.dump(regressor_rf,'regressor_rf_jb')
Django 实现代码
from django.shortcuts import render
from django.http import HttpResponse
import json
from django.http import JsonResponse
import pandas as pd
import numpy as np
from sklearn.externals import joblib
from sklearn.preprocessing import PolynomialFeatures
# Create your views here.
# ML Code
regressor_linear = joblib.load('./models/regressor_linear_jb')
regressor_poly2 = joblib.load('./models/regressor_poly2_jb')
regressor_rf = joblib.load('./models/regressor_rf_jb')
# ML Code End
def predict(request):
temp_data = [
0.16902,
0,
25.65,
0,
0.581,
5.986,
88.4,
1.9929,
2,
188,
19.1,
385.02,
14.81,
]
temp_df = pd.DataFrame(temp_data).transpose()
predict = {}
# Linear Regression
predict['Linear Regressor'] = round(regressor_linear.predict(temp_df)[0, 0], 2)
# Polynomial Regression.
regressor_poly = PolynomialFeatures(degree=2)
temp_df_poly = regressor_poly.fit_transform(temp_df)
predict['Polynomial Regressor'] = round(regressor_poly2.predict(temp_df_poly)[0, 0], 2)
# Random Forest Regression
predict['Random Forest Regressor'] = round(regressor_rf.predict(temp_df)[0],2)
return JsonResponse(predict)
【问题讨论】：
标签： python django python-3.x machine-learning