Does anybody can see what I'm doing wrong?
Input:
from sklearn.ensemble import ExtraTreesClassifier
modelo = ExtraTreesClassifier()
modelo.fit(x_treino,y_treino)
resultado = modelo.score(x_teste, y_teste)
print("Acurácia", resultado)
Output: i'm having this errors
D:\Anaconda\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
D:\Anaconda\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)
869 raise ValueError("y cannot be None")
870
--> 871 X = check_array(X, accept_sparse=accept_sparse,
872 accept_large_sparse=accept_large_sparse,
873 dtype=dtype, order=order, copy=copy,
D:\Anaconda\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
D:\Anaconda\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)
671 array = array.astype(dtype, casting="unsafe", copy=False)
672 else:
--> 673 array = np.asarray(array, order=order, dtype=dtype)
674 except ComplexWarning as complex_warning:
675 raise ValueError("Complex data not supported\n"
D:\Anaconda\lib\site-packages\numpy\core\_asarray.py in asarray(a, dtype, order, like)
100 return _asarray_with_like(a, dtype=dtype, order=order, like=like)
101
--> 102 return array(a, dtype, copy=False, order=order)
103
104
D:\Anaconda\lib\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__(
D:\Anaconda\lib\site-packages\numpy\core\_asarray.py in asarray(a, dtype, order, like)
100 return _asarray_with_like(a, dtype=dtype, order=order, like=like)
101
--> 102 return array(a, dtype, copy=False, order=order)
103
104
ValueError: could not convert string to float: 'M'
MACHINE LEARNING MODEL USIN PYTHON WITH THE FUNCTION ExtraTreesClassifier now I don't have anything else to share but sof is making me write more to post this so ignore this texte here pls.
Ok so from your comment I can see that the data has only two numerical variables (Age, Na to K), while the rest are categorical (Sex, Blood Pressure, Cholesterol, Drug). ExtraTreesClassifier can only work with numerical variables hence the ValueError. To combat this you should first preprocess the data so that they are transformed to numeric and especially float so that they are able to be handled by the classifier.
Some preprocessing algorithms for your case would be LabelEncoder, OrdinalEncoder or maybe OneHotEncoder, depending on the data and your methods.
Here's the full documentation page (you're looking for categorical to numeric transformations):
https://scikit-learn.org/stable/modules/classes.html#module-sklearn.preprocessing
If your question was answered please consider marking it as solved.
Related
I wrote this code: df['Liquid Milk'] = df['Liquid Milk'].replace("", np.nan).astype('float64')
I got an error below, not sure where is an error, have tried many different way, but still same error. Any help, appreciated.
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-52-607dcacd5a1a> in <module>
----> 1 m['Liquid Milk(Mil Litres)']=m['Liquid Milk(Mil Litres)'].replace("", np.nan).astype('float64')
2
3
4
/usr/local/lib/python3.6/dist-packages/pandas/core/generic.py in astype(self, dtype, copy, errors, **kwargs)
5679 # else, only a single dtype is given
5680 new_data = self._data.astype(dtype=dtype, copy=copy, errors=errors,
-> 5681 **kwargs)
5682 return self._constructor(new_data).__finalize__(self)
5683
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/managers.py in astype(self, dtype, **kwargs)
529
530 def astype(self, dtype, **kwargs):
--> 531 return self.apply('astype', dtype=dtype, **kwargs)
532
533 def convert(self, **kwargs):
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/managers.py in apply(self, f, axes, filter, do_integrity_check, consolidate, **kwargs)
393 copy=align_copy)
394
--> 395 applied = getattr(b, f)(**kwargs)
396 result_blocks = _extend_blocks(applied, result_blocks)
397
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/blocks.py in astype(self, dtype, copy, errors, values, **kwargs)
532 def astype(self, dtype, copy=False, errors='raise', values=None, **kwargs):
533 return self._astype(dtype, copy=copy, errors=errors, values=values,
--> 534 **kwargs)
535
536 def _astype(self, dtype, copy=False, errors='raise', values=None,
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/blocks.py in _astype(self, dtype, copy, errors, values, **kwargs)
631
632 # _astype_nansafe works fine with 1-d only
--> 633 values = astype_nansafe(values.ravel(), dtype, copy=True)
634
635 # TODO(extension)
/usr/local/lib/python3.6/dist-packages/pandas/core/dtypes/cast.py in astype_nansafe(arr, dtype, copy, skipna)
700 if copy or is_object_dtype(arr) or is_object_dtype(dtype):
701 # Explicit copy, or required since NumPy can't view from / to object.
--> 702 return arr.astype(dtype, copy=True)
703
704 return arr.view(dtype)
ValueError: could not convert string to float: '571,2'
A float number's integer and fraction part must be separated by a . not a ,. Replace all ,s with .s.
float("571.2")
would work
float("571,2")
would fail.
I'm getting a value error on my python code, because part of the data has a string and float. Im using Kaggle Imdb data, which has both floats and strings. I need help with changing the code so the string is allowed.
Not sure how to change the string to float in order to resolve the error.
enter code here
f
rom sklearn.tree import DecisionTreeRegressor
#setting the imdb features import in the data
imdb_features=['original_title','genre','director','actors','avg_vote','reviews_from_users','reviews_from_critics']
X= imdb_moviedata[imdb_features]
#Building Model
imdb_moviedata_model = DecisionTreeRegressor(random_state=1)
#Fit the model
imdb_moviedata_model.fit(X,y)
Receiving the following Error code:
------------------------------------------------------------------------`enter code here`
ValueError Traceback (most recent call last)
<ipython-input-21-61e73a0f75b7> in <module>
3 imdb_moviedata_model = DecisionTreeRegressor(random_state=1)
4 #Fit the model
----> 5 float(imdb_moviedata_model.fit(X,y))
/opt/anaconda3/lib/python3.8/site-packages/sklearn/tree/_classes.py in fit(self, X, y, sample_weight, check_input, X_idx_sorted)
1240 """
1241
-> 1242 super().fit(
1243 X, y,
1244 sample_weight=sample_weight,
/opt/anaconda3/lib/python3.8/site-packages/sklearn/tree/_classes.py in fit(self, X, y, sample_weight, check_input, X_idx_sorted)
154 check_X_params = dict(dtype=DTYPE, accept_sparse="csc")
155 check_y_params = dict(ensure_2d=False, dtype=None)
--> 156 X, y = self._validate_data(X, y,
157 validate_separately=(check_X_params,
158 check_y_params))
/opt/anaconda3/lib/python3.8/site-packages/sklearn/base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
427 # :(
428 check_X_params, check_y_params = validate_separately
--> 429 X = check_array(X, **check_X_params)
430 y = check_array(y, **check_y_params)
431 else:
/opt/anaconda3/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
/opt/anaconda3/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"
/opt/anaconda3/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
/opt/anaconda3/lib/python3.8/site-packages/pandas/core/generic.py in __array__(self, dtype)
1779
1780 def __array__(self, dtype=None) -> np.ndarray:
-> 1781 return np.asarray(self._values, dtype=dtype)
1782
1783 def __array_wrap__(self, result, context=None):
/opt/anaconda3/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: could not convert string to float: 'Miss Jerry'
Getting the following error while using the summary_data_from_transaction_data utility function included within the Lifestyles python package. Using pandas version 0.2 on Google Colab.
TypeError: float() argument must be a string or a number, not 'Day'
Any help will be much appreciated.
Code:
data_summary = summary_data_from_transaction_data(data_final, customer_id_col = "CustomerID", datetime_col = "InvoiceDate", monetary_value_col = "Sales", observation_period_end = "2011-12-09", freq = "D")
Stacktrace:
/usr/local/lib/python3.6/dist-packages/lifetimes/utils.py in summary_data_from_transaction_data(transactions, customer_id_col, datetime_col, monetary_value_col, datetime_format, observation_period_end, freq)
194 summary_columns.append('monetary_value')
195
--> 196 return customers[summary_columns].astype("float64")
197
198
/usr/local/lib/python3.6/dist-packages/pandas/core/generic.py in astype(self, dtype, copy, errors, **kwargs)
5880 # else, only a single dtype is given
5881 new_data = self._data.astype(
-> 5882 dtype=dtype, copy=copy, errors=errors, **kwargs
5883 )
5884 return self._constructor(new_data).__finalize__(self)
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/managers.py in astype(self, dtype, **kwargs)
579
580 def astype(self, dtype, **kwargs):
--> 581 return self.apply("astype", dtype=dtype, **kwargs)
582
583 def convert(self, **kwargs):
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/managers.py in apply(self, f, axes, filter, do_integrity_check, consolidate, **kwargs)
436 kwargs[k] = obj.reindex(b_items, axis=axis, copy=align_copy)
437
--> 438 applied = getattr(b, f)(**kwargs)
439 result_blocks = _extend_blocks(applied, result_blocks)
440
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/blocks.py in astype(self, dtype, copy, errors, values, **kwargs)
557
558 def astype(self, dtype, copy=False, errors="raise", values=None, **kwargs):
--> 559 return self._astype(dtype, copy=copy, errors=errors, values=values, **kwargs)
560
561 def _astype(self, dtype, copy=False, errors="raise", values=None, **kwargs):
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/blocks.py in _astype(self, dtype, copy, errors, values, **kwargs)
641 # _astype_nansafe works fine with 1-d only
642 vals1d = values.ravel()
--> 643 values = astype_nansafe(vals1d, dtype, copy=True, **kwargs)
644
645 # TODO(extension)
/usr/local/lib/python3.6/dist-packages/pandas/core/dtypes/cast.py in astype_nansafe(arr, dtype, copy, skipna)
727 if copy or is_object_dtype(arr) or is_object_dtype(dtype):
728 # Explicit copy, or required since NumPy can't view from / to object.
--> 729 return arr.astype(dtype, copy=True)
730
731 return arr.view(dtype)
TypeError: float() argument must be a string or a number, not 'Day'
Sample data in the data_final df and associated dtypes are as per the attachments.
sample data
dtypes
Thanks for any help.
Apologies folks - I was able to resolve my issue after updating the Lifetimes package to the latest 0.11.1 version in Colab!
so Im trying to transforming this values in a float to be able to sum(). The problem is there is something weird that wont let me accomplish it
Data:
cw= pd.DataFrame({ "campaign": "151515151515" ,
"Media_Cost": "$ 14,52" })
cw.dtypes
Media_Cost object
My attempts,
I tried all lines of code bellow, one at the time, neither works mysteriously..
cw["Media_Cost"] = cw["Media_Cost"].str.replace('$','')
# Attempt 1
cw.Media_Cost = cw.Media_Cost.astype(float)
# Attempt 3
cw.Media_Cost = len(float(cw.Media_Cost))
# Attempt 4
cw.Media_Cost = cw.Media_Cost.apply(lambda x: float(cw.Media_Cost))
Error persist..
cw["Media_Cost"] = cw["Media_Cost"].str.replace('$','').str.replace(',', '.').astype(float)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-382-f5688d76abed> in <module>
1 # cw.Media_Cost = cw.Media_Cost.apply(lambda x: float(cw.Media_Cost))
----> 2 cw["Media_Cost"] = cw["Media_Cost"].str.replace('$','').str.replace(',', '.').astype(float)
3
4 # cw.Media_Cost = float(cw.Media_Cost)
5
~\Anaconda3\lib\site-packages\pandas\core\generic.py in astype(self, dtype, copy, errors, **kwargs)
5689 # else, only a single dtype is given
5690 new_data = self._data.astype(dtype=dtype, copy=copy, errors=errors,
-> 5691 **kwargs)
5692 return self._constructor(new_data).__finalize__(self)
5693
~\Anaconda3\lib\site-packages\pandas\core\internals\managers.py in astype(self, dtype, **kwargs)
529
530 def astype(self, dtype, **kwargs):
--> 531 return self.apply('astype', dtype=dtype, **kwargs)
532
533 def convert(self, **kwargs):
~\Anaconda3\lib\site-packages\pandas\core\internals\managers.py in apply(self, f, axes, filter, do_integrity_check, consolidate, **kwargs)
393 copy=align_copy)
394
--> 395 applied = getattr(b, f)(**kwargs)
396 result_blocks = _extend_blocks(applied, result_blocks)
397
~\Anaconda3\lib\site-packages\pandas\core\internals\blocks.py in astype(self, dtype, copy, errors, values, **kwargs)
532 def astype(self, dtype, copy=False, errors='raise', values=None, **kwargs):
533 return self._astype(dtype, copy=copy, errors=errors, values=values,
--> 534 **kwargs)
535
536 def _astype(self, dtype, copy=False, errors='raise', values=None,
~\Anaconda3\lib\site-packages\pandas\core\internals\blocks.py in _astype(self, dtype, copy, errors, values, **kwargs)
631
632 # _astype_nansafe works fine with 1-d only
--> 633 values = astype_nansafe(values.ravel(), dtype, copy=True)
634
635 # TODO(extension)
~\Anaconda3\lib\site-packages\pandas\core\dtypes\cast.py in astype_nansafe(arr, dtype, copy, skipna)
700 if copy or is_object_dtype(arr) or is_object_dtype(dtype):
701 # Explicit copy, or required since NumPy can't view from / to object.
--> 702 return arr.astype(dtype, copy=True)
703
704 return arr.view(dtype)
ValueError: could not convert string to float: '1.443.48'
You can try:
cw = pd.DataFrame({"campaign": "151515151515", "Media_Cost": "$ 1,443.48" }, index=[0])
cw["Media_Cost"] = cw["Media_Cost"].str.replace('$','').str.replace(',', '').astype(float)
cw.dtypes
Result:
campaign object
Media_Cost float64
dtype: object
Starting with a python object, I'm getting an error when I try to convert the string to a float using astype(string).astype(float).
I've used regular expressions to remove the units and spaces and removed rows with NA.
df['Length'] = df['Length'].astype(str).astype(float)
ValueError Traceback (most recent call last)
<ipython-input-137-724df1c0091a> in <module>
1 df['Length'] = df['Length'].astype(str).astype(float)
2 #df['Length'].astype(str).astype(float)
3 #df['Width'].astype(str).astype(float)
/anaconda3/lib/python3.7/site-packages/pandas/core/generic.py in astype(self, dtype, copy, errors, **kwargs)
5689 # else, only a single dtype is given
5690 new_data = self._data.astype(dtype=dtype, copy=copy, errors=errors,
-> 5691 **kwargs)
5692 return self._constructor(new_data).__finalize__(self)
5693
/anaconda3/lib/python3.7/site-packages/pandas/core/internals/managers.py in astype(self, dtype, **kwargs)
529
530 def astype(self, dtype, **kwargs):
--> 531 return self.apply('astype', dtype=dtype, **kwargs)
532
533 def convert(self, **kwargs):
/anaconda3/lib/python3.7/site-packages/pandas/core/internals/managers.py in apply(self, f, axes, filter, do_integrity_check, consolidate, **kwargs)
393 copy=align_copy)
394
--> 395 applied = getattr(b, f)(**kwargs)
396 result_blocks = _extend_blocks(applied, result_blocks)
397
/anaconda3/lib/python3.7/site-packages/pandas/core/internals/blocks.py in astype(self, dtype, copy, errors, values, **kwargs)
532 def astype(self, dtype, copy=False, errors='raise', values=None, **kwargs):
533 return self._astype(dtype, copy=copy, errors=errors, values=values,
--> 534 **kwargs)
535
536 def _astype(self, dtype, copy=False, errors='raise', values=None,
/anaconda3/lib/python3.7/site-packages/pandas/core/internals/blocks.py in _astype(self, dtype, copy, errors, values, **kwargs)
631
632 # _astype_nansafe works fine with 1-d only
--> 633 values = astype_nansafe(values.ravel(), dtype, copy=True)
634
635 # TODO(extension)
/anaconda3/lib/python3.7/site-packages/pandas/core/dtypes/cast.py in astype_nansafe(arr, dtype, copy, skipna)
700 if copy or is_object_dtype(arr) or is_object_dtype(dtype):
701 # Explicit copy, or required since NumPy can't view from / to object.
--> 702 return arr.astype(dtype, copy=True)
703
704 return arr.view(dtype)
ValueError: could not convert string to float:
As John pointed out the error is on converting string to float.
To visually check for empty strings use df['Length'] == ''.
To count the number of empty strings use: sum(df['Length'] == '')
To drop the rows with empty strings use: df = df[df['Length'] != '']. This will modify your whole data frame and not just df['Length'].
Hope that helps.