使用 matplotlib 绘制 scikit learn 线性回归结果

Posted 2023-03-12

【中文标题】使用 matplotlib 绘制 scikit learn 线性回归结果

【英文标题】：Use matplotlib to plot scikit learn linear regression results

【发布时间】：2019-03-08 17:28:06

【问题描述】：

如何在分析后绘制来自scikit learn 的线性回归结果，以在程序结束时查看“测试”数据（实际值与预测值）？下面的代码很接近，但我认为它缺少比例因子。

输入：

import pandas as pd
import numpy as np
import datetime

pd.core.common.is_list_like = pd.api.types.is_list_like # temp fix
import fix_yahoo_finance as yf
from pandas_datareader import data, wb
from datetime import date
from sklearn.linear_model import LinearRegression
from sklearn import preprocessing, cross_validation, svm
import matplotlib.pyplot as plt

df = yf.download('MMM', start = date (2012, 1, 1), end = date (2018, 1, 1) , progress = False)
df_low = df[['Low']] # create a new df with only the low column
forecast_out = int(5) # predicting some days into future
df_low['low_prediction'] = df_low[['Low']].shift(-forecast_out) # create a new column based on the existing col but shifted some days

X_low = np.array(df_low.drop(['low_prediction'], 1))
X_low = preprocessing.scale(X_low) # scaling the input values

X_low_forecast = X_low[-forecast_out:] # set X_forecast equal to last 5 days
X_low = X_low[:-forecast_out] # remove last 5 days from X

y_low = np.array(df_low['low_prediction'])
y_low = y_low[:-forecast_out]

X_low_train, X_low_test, y_low_train, y_low_test = cross_validation.train_test_split(X_low, y_low, test_size = 0.2)

clf_low = LinearRegression() # classifier
clf_low.fit(X_low_train, y_low_train) # training

confidence_low = clf_low.score(X_low_test, y_low_test) # testing

print("confidence for lows: ", confidence_low)
forecast_prediction_low = clf_low.predict(X_low_forecast)
print(forecast_prediction_low)

plt.figure(figsize = (17,9))
plt.grid(True)
plt.plot(X_low_test, color = "red")
plt.plot(y_low_test, color = "green")
plt.show()

图片：

【问题讨论】：

我认为您刚刚分别绘制了测试数据 x (X_low_test) 和 y (y_low_test)。您要做的是根据y_low_test 预测新的 y 值，例如：X_low_predicted = clf_low.predict(y_low_test)。之后，在plt.plot(X_low_test, y_low_test, label='real'); plt.plot(X_low_predicted, y_low_test, label='predicted'); plt.legend()测试集的预测值上绘制测试集

【参考方案1】：

如果你想比较目标和预测，你应该绘制y_test和X_test，而你应该绘制y_test和clf_low.predict(X_test)。

顺便说一句，您的代码中的clf_low 不是分类器，而是回归器。最好使用别名model 而不是clf。