ValueError: could not convert string to float in panda

Question

My code is :

 import pandas as pd
data = pd.read_table('train.tsv')

X=data.Phrase
Y=data.Sentiment
from sklearn import cross_validation
X_train,X_test,Y_train,Y_test=cross_validation.train_test_split(X,Y,test_size=0.2,random_state=0)
from sklearn.naive_bayes import MultinomialNB
clf = MultinomialNB()
clf.fit(X,Y)

I get the error :ValueError: could not convert string to float:

What changes can I make that my code works?

no it consists of strings too. X.phrase has string data. Y.Sentiment has numeric data. — Animesh Sharma
– Animesh Sharma, Commented May 25, 2017 at 9:33

Jay Patel · Accepted Answer · 2017-05-25 10:08:22Z

3

You can't pass in text data into MultinomialNB of scikit-learn as stated in its documentation.

None of the algorithms in scikit-learn works directly with text data. You need to do some preprocessing to get desired output. You'll need to first extract the features from text data using techniques like bagging or tokenizing. Have a look at this link for better understanding.

You also might want to look at using NLTK for such use cases as yours.

answered May 25, 2017 at 10:08

Jay Patel

5701 gold badge3 silver badges14 bronze badges

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

Comments

DCzo · Accepted Answer · 2017-05-25 09:51:40Z

0

ValueError when using Multinomial Naive Bayes classifier

You probably should preprocess your data as shown in the answer above.

answered May 25, 2017 at 9:51

DCzo

1413 silver badges14 bronze badges

Collectives™ on Stack Overflow

ValueError: could not convert string to float in panda

2 Answers 2

Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related