package not predicting

[andamchako]

• Lazy Predict version: lazypredict-0.2.7
• Python version: 3.8
• Operating System: Windows 10 64-bit

Description

I'm trying to make predictions but keep getting the same error both locally and on colab

What I Did

AttributeError                            Traceback (most recent call last)
<ipython-input-22-cb325c4d69cb> in <module>
      1 from lazypredict.Supervised import LazyClassifier
      2 clf = LazyClassifier(verbose=0,ignore_warnings=True, custom_metric=None)
----> 3 models,predictions = clf.fit(X_train, X_test, y_train, y_test)
      4 models

~\AppData\Local\Continuum\anaconda3\lib\site-packages\lazypredict\Supervised.py in fit(self, X_train, X_test, y_train, y_test)
    203             X_test = pd.DataFrame(X_test)
    204 
--> 205         numeric_features = X_train.select_dtypes(
    206             include=['int64', 'float64', 'int32', 'float32']).columns
    207         categorical_features = X_train.select_dtypes(

~\AppData\Local\Continuum\anaconda3\lib\site-packages\scipy\sparse\base.py in __getattr__(self, attr)
    689             return self.getnnz()
    690         else:
--> 691             raise AttributeError(attr + " not found")
    692 
    693     def transpose(self, axes=None, copy=False):

AttributeError: select_dtypes not found.

[shankarpandala]

@andamchako What are the datatypes of you input ?

[Tarrannum]

I am facing the same issue, the dtypes selected are int64 and float64

[shankarpandala]

I am facing the same issue, the dtypes selected are int64 and float64

Can you show any reproducible example ?

[AbhiPawar5]

Hi @shankarpandala, Thanks for creating such an amazing package!
I have encountered the same issue mentioned above - AttributeError: select_dtypes not found

Environment : Google Colab

• Python - 3.7.11
• lazypredict==0.2.9

Objective : Text classification using CountVectorizer and Tfidf, target label - 0 or 1

Sample code :

sentences = df[['cleaned_text']].values
y = df['label'].values


sentences_train, sentences_test, y_train, y_test = train_test_split(sentences, y, 
                                                                    test_size=0.25, random_state=1000)

#BOW
count_vect = CountVectorizer(ngram_range=(1, 1))
count_vect.fit(sentences_train.ravel())

X_train = count_vect.fit_transform(sentences_train.ravel())
X_test  = count_vect.transform(sentences_test.ravel())

import lazypredict
from lazypredict.Supervised import LazyClassifier
clf = LazyClassifier(verbose=0, ignore_warnings=True, custom_metric=None)
models,predictions = clf.fit(X_train, X_test, y_train, y_test)

[jdvala]

Hi @AbhiPawar5 I have created a package inspired by lazypredict for text classification. Please check it out, comments and suggestions are welcome
https://github.com/jdvala/lazytext