PANDAS ERROR:' With n_samples=1, test_size=0.25 and train_size=None,(...) Adjust any of the afo-CodePudding

I am using the following code and please see the error below. the code:

import pandas as pd
df=pd.read_csv('Ecommerce Customers')
df.head()

X=[['Avg. Session Length', 'Time on App','Time on Website']]

y=['Yearly Amount Spent']

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.25, random_state=101)

output:

ValueError: With n_samples=1, test_size=0.25 and train_size=None, the resulting train set will be empty. Adjust any of the aforementioned parameters.

I've read in the forum to extend the data in this case but I have no idea how to do it.

CodePudding user response：

You need to add 'df' when creating X and y:

X=df[['Avg. Session Length', 'Time on App','Time on Website']]

y=df['Yearly Amount Spent']

This way X and y are Dataframes/Series. Otherwise they are just lists with column names in it.

CodePudding user response：

To fix this error, you should select the columns you want as features from the dataframe, and then assign them to X.

For example:

X = df[['Avg. Session Length', 'Time on App','Time on Website']]
y = df['Yearly Amount Spent']

This should give you the correct format for the inputs to train_test_split.