Related
I pass the predictors from an imputation pipeline,
I check the columns for NaN and inf values with
col_name = X.columns.to_series()[np.isinf(X).any()]
There are no columns with missing values or inf values.
classifier = MLPClassifier
I do: clf.fit(X,y) then get the error ValueError: Input contains NaN, infinity or a value too large for dtype('float64')
What am I missing here? Can anybody help or guide me as to what to do????
What might be the other possible explanations for this error? What else should I be checking for? Also
full traceback:
Input In [137], in <cell line: 4>()
1 #l = list(X.isin([np.inf, -np.inf]))
2 #col_name = X.columns.to_series()[np.isnan(X).any()]
3 #col_name
----> 4 clf.fit(X, y)
File ~\anaconda3\lib\site-packages\sklearn\pipeline.py:394, in Pipeline.fit(self, X, y, **fit_params)
392 if self._final_estimator != "passthrough":
393 fit_params_last_step = fit_params_steps[self.steps[-1][0]]
--> 394 self._final_estimator.fit(Xt, y, **fit_params_last_step)
396 return self
File ~\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:752, in BaseMultilayerPerceptron.fit(self, X, y)
735 def fit(self, X, y):
736 """Fit the model to data matrix X and target(s) y.
737
738 Parameters
(...)
750 Returns a trained MLP model.
751 """
--> 752 return self._fit(X, y, incremental=False)
File ~\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:393, in BaseMultilayerPerceptron._fit(self, X, y, incremental)
386 raise ValueError(
387 "hidden_layer_sizes must be > 0, got %s." % hidden_layer_sizes
388 )
389 first_pass = not hasattr(self, "coefs_") or (
390 not self.warm_start and not incremental
391 )
--> 393 X, y = self._validate_input(X, y, incremental, reset=first_pass)
395 n_samples, n_features = X.shape
397 # Ensure y is 2D
File ~\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:1100, in MLPClassifier._validate_input(self, X, y, incremental, reset)
1099 def _validate_input(self, X, y, incremental, reset):
-> 1100 X, y = self._validate_data(
1101 X,
1102 y,
1103 accept_sparse=["csr", "csc"],
1104 multi_output=True,
1105 dtype=(np.float64, np.float32),
1106 reset=reset,
1107 )
1108 if y.ndim == 2 and y.shape[1] == 1:
1109 y = column_or_1d(y, warn=True)
File ~\anaconda3\lib\site-packages\sklearn\base.py:581, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, **check_params)
579 y = check_array(y, **check_y_params)
580 else:
--> 581 X, y = check_X_y(X, y, **check_params)
582 out = X, y
584 if not no_val_X and check_params.get("ensure_2d", True):
File ~\anaconda3\lib\site-packages\sklearn\utils\validation.py:979, 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, estimator)
962 raise ValueError("y cannot be None")
964 X = check_array(
965 X,
966 accept_sparse=accept_sparse,
(...)
976 estimator=estimator,
977 )
--> 979 y = _check_y(y, multi_output=multi_output, y_numeric=y_numeric)
981 check_consistent_length(X, y)
983 return X, y
File ~\anaconda3\lib\site-packages\sklearn\utils\validation.py:989, in _check_y(y, multi_output, y_numeric)
987 """Isolated part of check_X_y dedicated to y validation"""
988 if multi_output:
--> 989 y = check_array(
990 y, accept_sparse="csr", force_all_finite=True, ensure_2d=False, dtype=None
991 )
992 else:
993 y = column_or_1d(y, warn=True)
File ~\anaconda3\lib\site-packages\sklearn\utils\validation.py:800, 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, estimator)
794 raise ValueError(
795 "Found array with dim %d. %s expected <= 2."
796 % (array.ndim, estimator_name)
797 )
799 if force_all_finite:
--> 800 _assert_all_finite(array, allow_nan=force_all_finite == "allow-nan")
802 if ensure_min_samples > 0:
803 n_samples = _num_samples(array)
File ~\anaconda3\lib\site-packages\sklearn\utils\validation.py:114, in _assert_all_finite(X, allow_nan, msg_dtype)
107 if (
108 allow_nan
109 and np.isinf(X).any()
110 or not allow_nan
111 and not np.isfinite(X).all()
112 ):
113 type_err = "infinity" if allow_nan else "NaN, infinity"
--> 114 raise ValueError(
115 msg_err.format(
116 type_err, msg_dtype if msg_dtype is not None else X.dtype
117 )
118 )
119 # for object dtype data, we only check for NaNs (GH-13254)
120 elif X.dtype == np.dtype("object") and not allow_nan:
ValueError: Input contains NaN, infinity or a value too large for dtype('float64').
You may want to check nan as well
col_name = X.columns.to_series()[np.isinf(X).any() | np.isnan(X).any()]
I am new to Python and am learning LSTM using Pandas with a sample project that I've modified from Github to use with my own data. I am running it on Kaggle.
For reference, the project is found here: https://github.com/abaranovskis-redsamurai/automation-repo/blob/master/forecast-lstm/forecast_lstm_shampoo_sales.ipynb
My data is simply a csv with dates and sales. Here's what the first few lines look like, with the date being YYYY-MM:
"date","num"
"1995-12",700
"1996-1",500
"1997-2",1300
"1996-3",2800
"1996-4",3500
The error I am getting says that "TypeError: float() argument must be a string or a number, not 'datetime.datetime'".
The code is here:
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import LSTM
from tensorflow.keras.layers import Dropout
import warnings
warnings.filterwarnings("ignore")
def parser(x):
return pd.datetime.strptime(x, '%Y-%m')
df = pd.read_csv('../input/smalltestb/smalltest1b.csv', parse_dates=[0], date_parser=parser)
df.tail()
train = df
scaler = MinMaxScaler()
scaler.fit(train)
train = scaler.transform(train)
n_input = 12
n_features = 1
generator = TimeseriesGenerator(train, train, length=n_input, batch_size=6)
model = Sequential()
model.add(LSTM(200, activation='relu', input_shape=(n_input, n_features)))
model.add(Dropout(0.15))
Finally, the error message:
TypeError Traceback (most recent call last)
/tmp/ipykernel_35/785266029.py in <module>
25
26 scaler = MinMaxScaler()
---> 27 scaler.fit(train)
28 train = scaler.transform(train)
29 n_input = 12
/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_data.py in fit(self, X, y)
334 # Reset internal state before fitting
335 self._reset()
--> 336 return self.partial_fit(X, y)
337
338 def partial_fit(self, X, y=None):
/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_data.py in partial_fit(self, X, y)
369 X = self._validate_data(X, reset=first_pass,
370 estimator=self, dtype=FLOAT_DTYPES,
--> 371 force_all_finite="allow-nan")
372
373 data_min = np.nanmin(X, axis=0)
/opt/conda/lib/python3.7/site-packages/sklearn/base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
418 f"requires y to be passed, but the target y is None."
419 )
--> 420 X = check_array(X, **check_params)
421 out = X
422 else:
/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
70 FutureWarning)
71 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 72 return f(**kwargs)
73 return inner_f
74
/opt/conda/lib/python3.7/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, estimator)
596 array = array.astype(dtype, casting="unsafe", copy=False)
597 else:
--> 598 array = np.asarray(array, order=order, dtype=dtype)
599 except ComplexWarning:
600 raise ValueError("Complex data not supported\n"
/opt/conda/lib/python3.7/site-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
81
82 """
---> 83 return array(a, dtype, copy=False, order=order)
84
85
/opt/conda/lib/python3.7/site-packages/pandas/core/generic.py in __array__(self, dtype)
1991
1992 def __array__(self, dtype: NpDtype | None = None) -> np.ndarray:
-> 1993 return np.asarray(self._values, dtype=dtype)
1994
1995 def __array_wrap__(
/opt/conda/lib/python3.7/site-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
81
82 """
---> 83 return array(a, dtype, copy=False, order=order)
84
85
TypeError: float() argument must be a string or a number, not 'datetime.datetime'
So, I decided to run just the import part and look at the head in another notebook. It didn't format correctly
date num
0 1995-12-01 00:00:00 700
1 1996-01-01 00:00:00 500
2 1996-02-01 00:00:00 1300
3 1996-03-01 00:00:00 2800
4 1997-04-01 00:00:00 3500
This is definitely not what I wanted (wanted YYYY-MM) and I know it's saved as such. I know this must be from the parser and it's not saving it to the dataframe in the way that I am expecting.
How do I address this? As a note, the guy on Github had this for is parser but it choked when I tried it:
def parser(x):
return pd.datetime.strptime('190'+x, '%Y-%m')
df = pd.read_csv('shampoo.csv', parse_dates=[0], index_col=0, date_parser=parser)
(He added '190' to the last digit of a year with a dash and a month number whereas I am using a year dash month number.)
Any suggestions? Thanks for having a look!
Thanks!
I want to create a logistic regression model to predict if the relationship is known or unknown, I've set the known values to 1 and unknown to 0 in the dataset. I have also added several features to train the data and predict the relationship.
I have run this code:
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import sklearn.datasets
from sklearn.model_selection import train_test_split
import pandas as pd
df = pd.read_csv('boo.csv')
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
y = pd.get_dummies(df.Relationship, prefix='Relationship')
X = pd.get_dummies(df, columns=['Relationship', 'Month','Year','Victim Age', 'Perpetrator
Age', 'Victim Sex', 'Victim Race', 'Perpetrator Sex', 'Crime Type', 'Perpetrator Race'], drop_first = True )
X_train, X_test, y_train, y_test = train_test_split(df[['Month','Year','Victim Age', 'Perpetrator Age', 'Victim Sex', 'Victim Race', 'Perpetrator Sex', 'Crime Type', 'Perpetrator Race']], df.Relationship, test_size=0.1)
model = LogisticRegression()
np.isnan(X)
np.where(np.isnan(X))
np.nan_to_num(X)
model.fit(X, y)
I am encountering this error:
ValueError Traceback (most recent call last)
<ipython-input-101-68355fc70ed4> in <module>
15 np.where(np.isnan(X))
16 np.nan_to_num(X)
---> 17 model.fit(X, y)
~\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py in fit(self, X, y, sample_weight)
1342 _dtype = [np.float64, np.float32]
1343
-> 1344 X, y = self._validate_data(X, y, accept_sparse='csr', dtype=_dtype,
1345 order="C",
1346 accept_large_sparse=solver != 'liblinear')
~\anaconda3\lib\site-packages\sklearn\base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
431 y = check_array(y, **check_y_params)
432 else:
--> 433 X, y = check_X_y(X, y, **check_params)
434 out = X, y
435
~\anaconda3\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
61 extra_args = len(args) - len(all_args)
62 if extra_args <= 0:
---> 63 return f(*args, **kwargs)
64
65 # extra_args > 0
~\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, estimator)
812 raise ValueError("y cannot be None")
813
--> 814 X = check_array(X, accept_sparse=accept_sparse,
815 accept_large_sparse=accept_large_sparse,
816 dtype=dtype, order=order, copy=copy,
~\anaconda3\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
61 extra_args = len(args) - len(all_args)
62 if extra_args <= 0:
---> 63 return f(*args, **kwargs)
64
65 # extra_args > 0
~\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, estimator)
661
662 if force_all_finite:
--> 663 _assert_all_finite(array,
664 allow_nan=force_all_finite == 'allow-nan')
665
~\anaconda3\lib\site-packages\sklearn\utils\validation.py in _assert_all_finite(X, allow_nan, msg_dtype)
101 not allow_nan and not np.isfinite(X).all()):
102 type_err = 'infinity' if allow_nan else 'NaN, infinity'
--> 103 raise ValueError(
104 msg_err.format
105 (type_err,
ValueError: Input contains NaN, infinity or a value too large for dtype('float64').
I viewed several stackoverflow problems and tried their solutions, but nothing seems to work. This error occurs only when I try to fit X and y in the model.
You need to fix the 'nan' values in your dataset. You are checking for the nan values but not fixing it. Below is sample data.
X = np.concatenate((np.arange(1,15),[np.NaN,np.NaN]))
print(np.isnan(X), np.where(np.isnan(X)), np.nan_to_num(X))
Output:
[False False False False False False False False False False False False
False False True True]
(array([14, 15]),)
[ 1. 2. 3. 4. 5. 6. 7. 8. 9. 10. 11. 12. 13. 14. 0. 0.]
you need to do the next step and assign it back. The code doesnt do 'inplace' assigning.if you dont assign it,there wont be changes in the original array.
X = np.nan_to_num(X) # assign it
Now if you check X again, there wont be 'nan' values, and then proceed with training the model.
This is my code/model that I'm trying to implement:
kf = KFold(n_splits=10,shuffle=True,random_state=2652124)
transf = TfidfVectorizer(analyzer='word', token_pattern=r'\w{1,}',max_features=1500, min_df=5, max_df=0.7, stop_words=stop)
scaler = MinMaxScaler(feature_range=(0, 1))
metadados = ['F13','F14','F19','F21','F22']
cls = RandomForestClassifier(n_estimators=1000,random_state=0)
features = make_column_transformer(
(transf,'textimage'),(transf,'subtitle'),
(scaler, metadata),(scaler,'F3'),remainder ='drop')
X = features.fit_transform(data)
y = data['classification']
for train_index, test_index in kf.split(X):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
cls.fit(X_train,y_train)
y_score = cls.fit(X_train, y_train).predict_proba(X_test)
roc = roc_auc_score(y_test, y_score[:,1])
pred = cls.predict(X_test)
acs = accuracy_score(y_test,pred)
clr = classification_report(y_test,pred)
The error:
TypeError Traceback (most recent call last)
TypeError: only size-1 arrays can be converted to Python scalars
The above exception was the direct cause of the following exception:
ValueError Traceback (most recent call last)
<ipython-input-13-6bdcb91ff478> in <module>
14
15 kfnum = 1
---> 16 X = features.fit_transform(data)
17 y = data['classe']
18 catr = 'timagem + metadados + legenda'
~/.local/lib/python3.8/site-packages/sklearn/compose/_column_transformer.py in fit_transform(self, X, y)
529 self._validate_remainder(X)
530
--> 531 result = self._fit_transform(X, y, _fit_transform_one)
532
533 if not result:
~/.local/lib/python3.8/site-packages/sklearn/compose/_column_transformer.py in _fit_transform(self, X, y, func, fitted)
456 self._iter(fitted=fitted, replace_strings=True))
457 try:
--> 458 return Parallel(n_jobs=self.n_jobs)(
459 delayed(func)(
460 transformer=clone(trans) if not fitted else trans,
~/.local/lib/python3.8/site-packages/joblib/parallel.py in __call__(self, iterable)
1049 self._iterating = self._original_iterator is not None
1050
-> 1051 while self.dispatch_one_batch(iterator):
1052 pass
1053
~/.local/lib/python3.8/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
864 return False
865 else:
--> 866 self._dispatch(tasks)
867 return True
868
~/.local/lib/python3.8/site-packages/joblib/parallel.py in _dispatch(self, batch)
782 with self._lock:
783 job_idx = len(self._jobs)
--> 784 job = self._backend.apply_async(batch, callback=cb)
785 # A job can complete so quickly than its callback is
786 # called before we get here, causing self._jobs to
~/.local/lib/python3.8/site-packages/joblib/_parallel_backends.py in apply_async(self, func, callback)
206 def apply_async(self, func, callback=None):
207 """Schedule a func to be run"""
--> 208 result = ImmediateResult(func)
209 if callback:
210 callback(result)
~/.local/lib/python3.8/site-packages/joblib/_parallel_backends.py in __init__(self, batch)
570 # Don't delay the application, to avoid keeping the input
571 # arguments in memory
--> 572 self.results = batch()
573
574 def get(self):
~/.local/lib/python3.8/site-packages/joblib/parallel.py in __call__(self)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/.local/lib/python3.8/site-packages/joblib/parallel.py in <listcomp>(.0)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/.local/lib/python3.8/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
738 with _print_elapsed_time(message_clsname, message):
739 if hasattr(transformer, 'fit_transform'):
--> 740 res = transformer.fit_transform(X, y, **fit_params)
741 else:
742 res = transformer.fit(X, y, **fit_params).transform(X)
~/.local/lib/python3.8/site-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
688 if y is None:
689 # fit method of arity 1 (unsupervised transformation)
--> 690 return self.fit(X, **fit_params).transform(X)
691 else:
692 # fit method of arity 2 (supervised transformation)
~/.local/lib/python3.8/site-packages/sklearn/preprocessing/_data.py in fit(self, X, y)
334 # Reset internal state before fitting
335 self._reset()
--> 336 return self.partial_fit(X, y)
337
338 def partial_fit(self, X, y=None):
~/.local/lib/python3.8/site-packages/sklearn/preprocessing/_data.py in partial_fit(self, X, y)
367
368 first_pass = not hasattr(self, 'n_samples_seen_')
--> 369 X = self._validate_data(X, reset=first_pass,
370 estimator=self, dtype=FLOAT_DTYPES,
371 force_all_finite="allow-nan")
~/.local/lib/python3.8/site-packages/sklearn/base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
418 f"requires y to be passed, but the target y is None."
419 )
--> 420 X = check_array(X, **check_params)
421 out = X
422 else:
~/.local/lib/python3.8/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
70 FutureWarning)
71 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 72 return f(**kwargs)
73 return inner_f
74
~/.local/lib/python3.8/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, estimator)
596 array = array.astype(dtype, casting="unsafe", copy=False)
597 else:
--> 598 array = np.asarray(array, order=order, dtype=dtype)
599 except ComplexWarning:
600 raise ValueError("Complex data not supported\n"
~/.local/lib/python3.8/site-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
81
82 """
---> 83 return array(a, dtype, copy=False, order=order)
84
85
~/.local/lib/python3.8/site-packages/pandas/core/series.py in __array__(self, dtype)
795 dtype='datetime64[ns]')
796 """
--> 797 return np.asarray(self.array, dtype)
798
799 # ----------------------------------------------------------------------
~/.local/lib/python3.8/site-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
81
82 """
---> 83 return array(a, dtype, copy=False, order=order)
84
85
~/.local/lib/python3.8/site-packages/pandas/core/arrays/numpy_.py in __array__(self, dtype)
209
210 def __array__(self, dtype=None) -> np.ndarray:
--> 211 return np.asarray(self._ndarray, dtype=dtype)
212
213 _HANDLED_TYPES = (np.ndarray, numbers.Number)
~/.local/lib/python3.8/site-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
81
82 """
---> 83 return array(a, dtype, copy=False, order=order)
84
85
ValueError: setting an array element with a sequence.
I have no problemas using only:
features = make_column_transformer(
(transf,'textimage'),(transf,'subtitle'),
(scaler, metadata),remainder ='drop')
So my problem is the column 'F3' in my dataframe, which is an array in each row:
0 [0.0026778684, 0.003117677, 0.00040434036, 0.0...
1 [0.061992627, 0.047432333, 0.012270351, 0.0102...
2 [0.0, 0.0, 0.0, 4.3830705e-06, 1.3149212e-05, ...
3 [0.30314153, 0.04477268, 0.01840577, 0.0319251...
4 [0.2563626, 0.03259786, 0.018686974, 0.0198365...
...
1287 [0.11471527, 0.032394826, 0.012400794, 0.01131...
1288 [0.002138354, 0.001044489, 0.0007786191, 0.001...
1289 [0.056204572, 0.026556363, 0.02082041, 0.01966...
1290 [0.051759016, 0.0058623934, 0.0054726205, 0.00...
1291 [0.0, 5.4140626e-05, 4.4114586e-05, 4.8125003e...
Name: F3, Length: 1292, dtype: object
Can anyone help me with that? How can I change a column into a list into a pipeline, or how can I concatenate the tranform with a list? Any suggestions?
I have a single independent variable X where each element is a 2-d array with shape (20, 431). The variable X itself is a 2-d numpy array of shape (200,). . How do I pass this to the sklearn.SVM object?
Edit: actual dataframe:
Category Features
0 1 [[-177.08171, -219.89174, -253.55954, -218.560...
1 0 [[-291.89288, -316.40735, -389.8398, -413.6302...
2 1 [[-355.88293, -351.0909, -364.43524, -400.7097.
Each element of Features is a 20*431 numpy array. I need to use these features to classify the category.
x = data.iloc[:, 1].values
y = data.iloc[:, 0].values
x.shape
(200, )
x[0].shape
(20, 431)
y.shape
(200, )
Fitting the model after splitting into train and test data:
classifier = SVC(kernel = 'rbf', random_state=0)
classifier.fit(x_train, y_train)
Error:
TypeError Traceback (most recent call last)
TypeError: only size-1 arrays can be converted to Python scalars
The above exception was the direct cause of the following exception:
ValueError Traceback (most recent call last)
<ipython-input-203-fdf0fc8db087> in <module>
----> 1 classifier.fit(x_train, y_train)
~\Anaconda3\envs\LangDetEnv1.0\lib\site-packages\sklearn\svm\_base.py in fit(self, X, y, sample_weight)
160 X, y = self._validate_data(X, y, dtype=np.float64,
161 order='C', accept_sparse='csr',
--> 162 accept_large_sparse=False)
163
164 y = self._validate_targets(y)
~\Anaconda3\envs\LangDetEnv1.0\lib\site-packages\sklearn\base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
430 y = check_array(y, **check_y_params)
431 else:
--> 432 X, y = check_X_y(X, y, **check_params)
433 out = X, y
434
~\Anaconda3\envs\LangDetEnv1.0\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
71 FutureWarning)
72 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73 return f(**kwargs)
74 return inner_f
75
~\Anaconda3\envs\LangDetEnv1.0\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, estimator)
801 ensure_min_samples=ensure_min_samples,
802 ensure_min_features=ensure_min_features,
--> 803 estimator=estimator)
804 if multi_output:
805 y = check_array(y, accept_sparse='csr', force_all_finite=True,
~\Anaconda3\envs\LangDetEnv1.0\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
71 FutureWarning)
72 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73 return f(**kwargs)
74 return inner_f
75
~\Anaconda3\envs\LangDetEnv1.0\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, estimator)
597 array = array.astype(dtype, casting="unsafe", copy=False)
598 else:
--> 599 array = np.asarray(array, order=order, dtype=dtype)
600 except ComplexWarning:
601 raise ValueError("Complex data not supported\n"
~\Anaconda3\envs\LangDetEnv1.0\lib\site-packages\numpy\core\_asarray.py in asarray(a, dtype, order)
81
82 """
---> 83 return array(a, dtype, copy=False, order=order)
84
85
ValueError: setting an array element with a sequence.