Error in classifying text with a tree

Question

I’m trying to sort, but it’s giving the error. Follow the code, then the error.

#coding=UTF-8  

import io  
import os  
import pandas as pd 
from sklearn.feature_extraction.text import CountVectorizer  
from sklearn import tree  

pasta="c:/users/usuario/dados"  
os.chdir(pasta)  

def main():  
    df=pd.read_csv('twits_classificados.csv', encoding='ISO-8859-1', sep=";")  
    exemploArvore(df)  

def exemploArvore(df):  
    textos=df['texto'].values  
    sentimento=df['sentimento'].values  

    #a linha abaixo traz a frequencia de palavras
    vectorizer = CountVectorizer(analyzer="word")  

    freqWords = vectorizer.fit_transform(textos)


    modelo = tree.DecisionTreeClassifier()

    modelo.fit(freqWords, sentimento)

    texto=["estou com medo da violência"]
    fwTexto=vectorizer.fit_transform(texto)

    print(modelo.predict(fwTexto))


main()

The mistake:

Traceback (most recent call last):
  File "C:\Users\USUARIO\workspacePython\testes\arvore.py", line 39, in <module>
    main()
  File "C:\Users\USUARIO\workspacePython\testes\arvore.py", line 14, in main
    exemploArvore(df)
  File "C:\Users\USUARIO\workspacePython\testes\arvore.py", line 36, in exemploArvore
    print(modelo.predict(fwTexto))
  File "C:\ProgramData\Anaconda3\lib\site-packages\sklearn\tree\tree.py",
line 404, in predict
    X = self._validate_X_predict(X, check_input)
  File "C:\ProgramData\Anaconda3\lib\site-packages\sklearn\tree\tree.py",
line 376, in _validate_X_predict
    % (self.n_features_, n_features))
ValueError: Number of features of the model must match the input. Model n_features is 2765 and input n_features is 5

Answer 1

You should only call the method fit_transform during training, in the test you should call only the method transform of your vectorizer.

In your test, change the line:

fwTexto = vectorizer.fit_transform(texto)

For

fwTexto = vectorizer.transform(texto)