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

[Jyothif]

Word vec Feature

train_w2v = wordvec_df.iloc[:31962,:] test_w2v = wordvec_df.iloc[31962:,:] xtrain_w2v = train_w2v.iloc[ytrain.index,:] xvalid_w2v = train_w2v.iloc[yvalid.index,:]

lreg.fit(xtrain_w2v, ytrain) prediction = lreg.predict_proba(xvalid_w2v) prediction_int = prediction[:,1] >= 0.3 prediction_int = prediction_int.astype(np.int) f1_score(yvalid, prediction_int)

ValueError Traceback (most recent call last)

in 5 xvalid_w2v = train_w2v.iloc[yvalid.index,:] 6 ----> 7 lreg.fit(xtrain_w2v, ytrain) 8 prediction = lreg.predict_proba(xvalid_w2v) 9 prediction_int = prediction[:,1] >= 0.3 ~\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py in fit(self, X, y, sample_weight) 1530 1531 X, y = check_X_y(X, y, accept_sparse='csr', dtype=_dtype, order="C", -> 1532 accept_large_sparse=solver != 'liblinear') 1533 check_classification_targets(y) 1534 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) 717 ensure_min_features=ensure_min_features, 718 warn_on_dtype=warn_on_dtype, --> 719 estimator=estimator) 720 if multi_output: 721 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) 540 if force_all_finite: 541 _assert_all_finite(array, --> 542 allow_nan=force_all_finite == 'allow-nan') 543 544 if ensure_min_samples > 0: ~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in _assert_all_finite(X, allow_nan) 54 not allow_nan and not np.isfinite(X).all()): 55 type_err = 'infinity' if allow_nan else 'NaN, infinity' ---> 56 raise ValueError(msg_err.format(type_err, X.dtype)) 57 # for object dtype data, we only check for NaNs (GH-13254) 58 elif X.dtype == np.dtype('object') and not allow_nan: ValueError: Input contains NaN, infinity or a value too large for dtype('float64'). #