How to fix Value Error with train_test_split in Python Numpy
14,960
I had that problem. Check the library "scikit-learn". sklearn have problems with the version 0.20.0+ of scikt-learn, try to do:
Windows: pip uninstall scikit-learn
Linux: sudo python36 -m pip uninstall scikit-learn
and install:
Windows: pip install scikit-learn==0.19.1
Linux: sudo python36 -m pip install scikit-learn==0.19.1
![python_beginner](https://lh3.googleusercontent.com/-M4c3ZMEj28I/AAAAAAAAAAI/AAAAAAAAAAA/ACHi3rekiCuNeAQplD29nEON6nAMS9_iDQ/mo/photo.jpg?sz=256)
Author by
python_beginner
Updated on June 04, 2022Comments
-
python_beginner about 2 years
I am using sklearn with a numpy array. I have 2 arrays (x, y) and they should be:
test_size=0.2 train_size=0.8
This is my current code:
def predict(): sample_data = pd.read_csv("includes\\csv.csv") x = np.array(sample_data["day"]) y = np.array(sample_data["balance"]) x = x.reshape(1, -1) y = y.reshape(1, -1) print(x) print(y) X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2) clf = LinearRegression() clf.fit(x_train, y_train) clf.score(x_test, y_test)
The error is:
ValueError: With n_samples=1, test_size=0.2 and train_size=None, the resulting train set will be empty. Adjust any of the aforementioned parameters.
, and it appears in the line:
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2)
Any ideas why that appears?
-
Quang Hoang about 5 yearsDid you try:
train_test_split(x, y, test_size=0.2, train_size=0.8)
? -
hpaulj about 5 yearsIt splits along the first axis, which in your samples is size 1. Review the
sklearn
docs to understand its conventions for the shapes of the inputs - number of samples versus number of features. -
python_beginner about 5 yearsyes i tried that it showed the same error
-
python_beginner about 5 yearshow can iprevent that from happening @hpaulj
-
GeorgPoe about 5 yearsyou could try:
x = sample_data["day"].values y = sample_data["balance"].values
and remove the reshape command -
python_beginner about 5 yearsits not changing anything at all still same error
-
-
osmancakirio over 3 yearsthis isn't working any more. Downgrading scikit-learn also downgrades numpy and hence you cause another problem using tensorflow.
ImportError: numpy.core.umath failed to import