python - 尝试使用 sk learn 绘制线性回归模型时遇到模糊的 RuntimeWarning

Question

import pandas
import math
from csv import reader
import sys
import numpy as np
from pandas.plotting import scatter_matrix
import matplotlib.pyplot as plt
import scipy.optimize as opt
import warnings
from sklearn import model_selection
from sklearn import linear_model  


def fxn():
    warnings.warn("Runtime Warning",RuntimeWarning)

with warnings.catch_warnings():
    warnings.simplefilter("ignore")
    fxn()
def costcomp(X,y,theta):
    inner=np.power(((X*theta.T)-y),2)
    return np.sum(inner)/(2*len(X))


def gradient(theta,X,y,lr,itr):
    temp=np.matrix(np.zeros(theta.shape))
    parameters=int(theta.ravel().shape[1])
    cost=np.zeros(itr)
    for i in range(itr):
        err=(X*theta.T)-y
        for j in range(parameters):
            tem=np.multiply(err,X[:,j])
            temp[0,j]=theta[0,j]-((lr/len(X))*np.sum(tem))
        theta=temp
        cost[i]=costcomp(X,y,theta)

    return theta,cost


dataset = pandas.read_csv("PYTHONFINAL.csv",names=['Month','Year','Day','Time','SpeedLimit','Age','Accidents'])
dataset = (dataset- dataset.mean()) / dataset.std()  
dataset.insert(0, 'Ones', 1)

cols=dataset.shape[1]
X=dataset.iloc[:,0:cols-1]
y=dataset.iloc[:,cols-1:cols]
X = np.matrix(X.values)  
y = np.matrix(y.values)
theta = np.matrix(np.array([0,0,0,0,0,0,0]))
X_train, X_validation, y_train, y_validation = model_selection.train_test_split(X, y, test_size=0.20, random_state=7)
print(costcomp(X_train,y_train,theta))
learningrate=0.01
iterations=2000
grad,costf=gradient(theta,X_train,y_train,learningrate,iterations)
print(grad)
print(costcomp(X_train,y_train,grad))
fig, ax = plt.subplots(figsize=(12,8))  
ax.plot(np.arange(iterations),costf, 'r')  
ax.set_xlabel('Iterations')  
ax.set_ylabel('Cost')  
ax.set_title('Error vs. Training Epoch')

#           **PROBLEM STARTS HERE**

model = linear_model.LinearRegression()
model.fit(X, y)
x = np.array(X[:, 1].A1)  
f = model.predict(X).flatten()

plt.show()


x = np.linspace(dataset.Month.min(), dataset.Month.max(), 100)  
f = grad[0, 0] + (grad[0, 1] * x)

fig, ax = plt.subplots(figsize=(12,8))  
ax.plot(x, f, 'r', label='Prediction')  
ax.scatter(dataset.Month, dataset.Accidents, label='Traning Data')  
ax.legend(loc=2)  
ax.set_xlabel('Month')  
ax.set_ylabel('Accidents')  
ax.set_title('Predicted Accidents vs. Month')  

错误:

Warning (from warnings module):
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/scipy/linalg/basic.py", line 1226
    warnings.warn(mesg, RuntimeWarning)
RuntimeWarning: internal gelsd driver lwork query error, required iwork dimension not returned. This is likely the result of LAPACK bug 0038, fixed in LAPACK 3.2.2 (released July 21, 2010). Falling back to 'gelss' driver.

问题:

我一直想绘制一个图表来看看线性回归模型构建是否有效。因此，我想要一个我构建的模型和用于该程序的原始数据集的回归线图。head(20 )我使用的数据集的值在所附图像中提供。

Dataset for the problem

Answer 1

您可以使用此代码来抑制这些特殊警告。

import warnings
warnings.filterwarnings(action="ignore", module="scipy", message="^internal gelsd")