ValueError could not convert string to float in Machine learning

Question

Hi Guys,

I am trying to filter my dataset using constant variable method, but it shows me the bellow error.

ValueError                                Traceback (most recent call last)
<ipython-input-10-d28793719248> in <module>
----> 1 model.fit(dataset)
~\anaconda3\lib\site-packages\sklearn\feature_selection\_variance_threshold.py in fit(self, X, y)
     67         """
     68         X = check_array(X, ('csr', 'csc'), dtype=np.float64,
---> 69                         force_all_finite='allow-nan')
     70 
     71         if hasattr(X, "toarray"):   # sparse matrix
~\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    529                     array = array.astype(dtype, casting="unsafe", copy=False)
    530                 else:
--> 531                     array = np.asarray(array, order=order, dtype=dtype)
    532             except ComplexWarning:
    533                 raise ValueError("Complex data not supported\n"
~\anaconda3\lib\site-packages\numpy\core\_asarray.py in asarray(a, dtype, order)
     83 
     84     """
---> 85     return array(a, dtype, copy=False, order=order)
     86 
     87 
ValueError: could not convert string to float: '208 Michael Ferry Apt. 674\nLaurabury, NE 37010-5101'

How can I solve this error?

Answer 1

Hi@akhtar,

You are trying to use constant variable method for filtering your dataset. But your dataset may contain string as shown in the error. We know constant or quasi-constant method is used to filter out the columns which contains only numeric value.

To avoid this error you can use co-relation method to filter out your string data.

Hope this will help.

If you need to know more, Its recommended to go for Machine Learning with Python course today.

Thank you!

Comments

logmodel.fit(X_train,y_train)

ValueError                                Traceback (most recent call last)
<ipython-input-39-0b508b2e1562> in <module>
----> 1 logmodel.fit(X_train,y_train)

~\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py in fit(self, X, y, sample_weight)
   1525 
   1526         X, y = check_X_y(X, y, accept_sparse='csr', dtype=_dtype, order="C",
-> 1527                          accept_large_sparse=solver != 'liblinear')
   1528         check_classification_targets(y)
   1529         self.classes_ = np.unique(y)

~\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)
    753                     ensure_min_features=ensure_min_features,
    754                     warn_on_dtype=warn_on_dtype,
--> 755                     estimator=estimator)
    756     if multi_output:
    757         y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False,

~\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    529                     array = array.astype(dtype, casting="unsafe", copy=False)
    530                 else:
--> 531                     array = np.asarray(array, order=order, dtype=dtype)
    532             except ComplexWarning:
    533                 raise ValueError("Complex data not supported\n"

~\anaconda3\lib\site-packages\numpy\core\_asarray.py in asarray(a, dtype, order)
     83 
     84     """
---> 85     return array(a, dtype, copy=False, order=order)
     86 
     87 

ValueError: could not convert string to float: 'SOTON/O.Q. 3101307'

---

As mentioned above you have to convert your string data to float. For that you can use the concept of categorical variable. Just remove your string column and pass that column in dummy variable function.

$ pd.get_dummies(string column)