Home/ Questions/''valueerror: input contains nan, infinity or a value too large for dtype('float64').'' - How to solve it?
Next
Answered
pete
  • 3
Asked: 2022-06-30T04:57:26+00:00 In:

”valueerror: input contains nan, infinity or a value too large for dtype(‘float64’).” – How to solve it?

  • 3

. Advertisement .

..3..

. Advertisement .

..4..

I want to train data with the panda’s data frame.

I encounter this error ”valueerror: input contains nan, infinity or a value too large for dtype(‘float64’).” when standardizing data using scikit-learn’s StandardScaler .

from sklearn.preprocessing import StandardScaler

#Training data (pandas.DataFrame type)
X = training_data()

# Standardization
sc = StandardScaler()
sc.fit(X)

Then I get this error message:

ValueError: Input contains NaN, infinity or a value too large for dtype('float64').

What can I do about the ”valueerror: input contains nan, infinity or a value too large for dtype(‘float64’).” issue? Is there a better approach?

Share

1 Answer

  1. Best Answer
    Expert

    The cause: This error happens because you didn’t remove NaN and infinity from the input data.

    Solution: To avoid this error, NaN and infinity must be eliminated from the input data.
    For instance, you can eliminate a column from X if it has at least one NaN with the code below.

    # Remove columns containing NaN from X
X.drop(X.columns[np.isnan(X).any()], axis=1)

    Each function’s description:

    • np.isnan(X): Get True for NaN elements, False matrix for other elements
    • np.isnan(X).any(): Get a list of True for columns containing NaN and False for other columns
    • X.columns[np.isnan(X).any()]: Get column names containing NaN
    • X.drop('col', axis = 1): Remove a column with column name col from X
    • 3

Leave an answer

You must login to add an answer.

Need An Account,