Expected 2D array, got 1D array instead when trying to make predictions

Question

m = np.array([[1,5,3,6,10,20]])
c = np.array([[100,500,300,600,1000,2000]])

model = LinearRegression()
model.fit(m,c)

I get the error when trying to make the prediction.

model.predict([5])

If I add double brackets, it forces me to pass 6 inputs, but the idea is that it receives only one or as many as I want.

Why do you train a model, bit you predict from modelo? Is it a typo just here, or in your code, too? Please edit your post to clarify and remedy this. — desertnaut
– desertnaut, Commented Sep 23, 2022 at 12:13
Are you trying to predict c from m, or are you trying to make a linear model like y = mx + c? — Matt Hall
– Matt Hall, Commented Sep 23, 2022 at 17:17

Matt Hall · Accepted Answer · 2022-09-23 17:15:27Z

1

You trained the wrong model. You train 6 models, each with 6 features (and your dataset is only 1-point).

# should be this
m = np.array([[1,5,3,6,10,20]]).T
c = np.array([100,500,300,600,1000,2000])

model = LinearRegression()
model.fit(m,c)

modelo.predict([[5]])
# array([500])

edited Sep 23, 2022 at 17:15

Matt Hall

8,1691 gold badge28 silver badges38 bronze badges

answered Sep 22, 2022 at 21:51

Quang Hoang

151k11 gold badges64 silver badges86 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

mauricio Over a year ago

thanks a lot,it didn't work this way modelo.predict([5]) I had to add double brackets.

mauricio Over a year ago

I have seen a lot of theory, and the truth is that I have not understood your solution. Could you recommend a reading that will clarify these doubts? <3

Collectives™ on Stack Overflow

Expected 2D array, got 1D array instead when trying to make predictions

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related