[Python] reg.predict is telling me I am not providing an array

I am new to Linear Regression in sklearn. It seems I have an issue with an array that I thought I coded correctly. When I ask for reg.score or reg.coef_ the code works great, but when I try to predict it throws an error that is saying it is not 2 dimensional or an array. Can somebody tell me what I did wrong on this one?

Code is below.

Thanks, Hoot

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()

from sklearn.linear_model import LinearRegression

data =pd.read_csv('1.01. Simple linear regression.csv')

x = data['SAT']
y = data['GPA']

x_matrix = x.values.reshape(-1,1) #creating a matrix for sklearn
x_matrix.shape

reg = LinearRegression()

reg.fit(x_matrix,y)

reg.score(x_matrix,y)

reg.coef_

reg.intercept_

reg.predict(1740)

*# Everything worked up till this point. This code is throwing the error saying that it is not 2 dimensional. I thought I fixed it in the x_matrix code.*

Continue reading...