I made an basic multiple linear regression model and ı wanted predict some values but ı took this warning
array=np.array([[26,1.5],[27,3]])
multiple_linear_regression.predict(array)
/Users/mali/anaconda3/lib/python3.11/site-packages/sklearn/base.py:464: UserWarning: X does not have valid feature names, but LinearRegression was fitted with feature names
warnings.warn(
array([31926.2169 , 35070.62783243])
but code is worked but ı wondered what is that warning and how can ı fixed it?
You don't show it in your code but I'm guessing you have something like:
multiple_linear_regression = sklearn.linear_model.LinearRegression()
multiple_linear_regression.fit(df[["A"]], df[["B"]])
array=np.array([[26,1.5],[27,3]])
multiple_linear_regression.predict(array)
In which case, you are fitting the model in a way that keeps the DataFrame features. However, when you try to use the .predict() call, you are passing you are doing so with a structure that does not have the features present.
My suggestion is to not include the features in the original fit. You can do so by using the .values property
multiple_linear_regression = sklearn.linear_model.LinearRegression()
multiple_linear_regression.fit(df[["A"]].values, df[["B"]].values)
array=np.array([[26,1.5],[27,3]])
multiple_linear_regression.predict(array)
