I assume this question also follow Question 4 that need to remove ‘GarageCars’ variable.
Here is my code:
import numpy as np
from sklearn.linear_model import RidgeCValphas=np.logspace(-1, 3, num=30)
ridge = make_pipeline(StandardScaler(), SimpleImputer(), RidgeCV(alphas=alphas, store_cv_values=True))from sklearn.model_selection import ShuffleSplit
cv = ShuffleSplit(n_splits=5, random_state=1)
model6_cv = cross_validate(ridge, data_r, target, scoring=‘neg_mean_squared_error’, return_train_score=True, cv=cv, return_estimator=True, n_jobs=-1)coef6 = [estimator[-1].coef_ for estimator in model6_cv[‘estimator’]]
coef6 = pd.DataFrame(coef6, columns=‘numerical_features3’)
When I run the dataframe, it come out this error but I cannot find where is the error.
AssertionError Traceback (most recent call last)
/opt/conda/lib/python3.9/site-packages/pandas/core/internals/construction.py in _list_to_arrays(data, columns, coerce_float, dtype)
567 try:
--> 568 columns = _validate_or_indexify_columns(content, columns)
569 result = _convert_object_array(content, dtype=dtype, coerce_float=coerce_float)
/opt/conda/lib/python3.9/site-packages/pandas/core/internals/construction.py in _validate_or_indexify_columns(content, columns)
691 # caller's responsibility to check for this...
--> 692 raise AssertionError(
693 f"{len(columns)} columns passed, passed data had "
AssertionError: 19 columns passed, passed data had 23 columns
The above exception was the direct cause of the following exception:
ValueError Traceback (most recent call last)
<ipython-input-38-31fed112852d> in <module>
----> 1 coef6 = pd.DataFrame(coef6, columns='numerical_features3')
2 coef6
/opt/conda/lib/python3.9/site-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
568 if is_named_tuple(data[0]) and columns is None:
569 columns = data[0]._fields
--> 570 arrays, columns = to_arrays(data, columns, dtype=dtype)
571 columns = ensure_index(columns)
572
/opt/conda/lib/python3.9/site-packages/pandas/core/internals/construction.py in to_arrays(data, columns, coerce_float, dtype)
550 # last ditch effort
551 data = [tuple(x) for x in data]
--> 552 return _list_to_arrays(data, columns, coerce_float=coerce_float, dtype=dtype)
553
554
/opt/conda/lib/python3.9/site-packages/pandas/core/internals/construction.py in _list_to_arrays(data, columns, coerce_float, dtype)
569 result = _convert_object_array(content, dtype=dtype, coerce_float=coerce_float)
570 except AssertionError as e:
--> 571 raise ValueError(e) from e
572 return result, columns
573
ValueError: 19 columns passed, passed data had 23 columns