I'm using the show_prediction function in the eli5 package to understand how my XGBoost classifier arrived at a prediction. For some reason I seem to be getting a regression score instead of a probability for my model.
Below is a fully reproducible example with a public dataset.
from sklearn.datasets import load_breast_cancer
from xgboost import XGBClassifier
from sklearn.model_selection import train_test_split
from eli5 import show_prediction
# Load dataset
data = load_breast_cancer()
# Organize our data
label_names = data['target_names']
labels = data['target']
feature_names = data['feature_names']
features = data['data']
# Split the data
train, test, train_labels, test_labels = train_test_split(
features,
labels,
test_size=0.33,
random_state=42
)
# Define the model
xgb_model = XGBClassifier(
n_jobs=16,
eval_metric='auc'
)
# Train the model
xgb_model.fit(
train,
train_labels
)
show_prediction(xgb_model.get_booster(), test[0], show_feature_values=True, feature_names=feature_names)
This gives me the following result. Note the score of 3.7, which is definitely not a probability.
The official eli5 documentation correctly shows a probability though.
The missing probability seems to be related to my use of xgb_model.get_booster(). Looks like the official documentation doesn't use that and passes the model as-is instead, but when I do that I get TypeError: 'str' object is not callable, so that doesn't seem to be an option.
I'm also concerned that eli5 is not explaining the prediction by traversing the xgboost trees. It appears that the "score" I'm getting is actually just a sum of all the feature contributions, like I would expect if eli5 wasn't actually traversing the tree but fitting a linear model instead. Is that true? How can I also make eli5 traverse the tree?
Fixed my own problem. According to this Github Issue eli5 only supports an older version of XGBoost (<=0.6). I was using XGBoost version 0.80 and eli5 version 0.8.
Posting the solution from the issue:
import eli5
from xgboost import XGBClassifier, XGBRegressor
def _check_booster_args(xgb, is_regression=None):
# type: (Any, bool) -> Tuple[Booster, bool]
if isinstance(xgb, eli5.xgboost.Booster): # patch (from "xgb, Booster")
booster = xgb
else:
booster = xgb.get_booster() # patch (from "xgb.booster()" where `booster` is now a string)
_is_regression = isinstance(xgb, XGBRegressor)
if is_regression is not None and is_regression != _is_regression:
raise ValueError(
'Inconsistent is_regression={} passed. '
'You don\'t have to pass it when using scikit-learn API'
.format(is_regression))
is_regression = _is_regression
return booster, is_regression
eli5.xgboost._check_booster_args = _check_booster_args
And then replacing the last line of my question's code snippet with:
show_prediction(xgb_model, test[0], show_feature_values=True, feature_names=feature_names)
fixed my problem.
Related
I am new to Sklearn, and I am trying to combine KNN, Decision Tree, SVM, and Gaussian NB for BaggingClassifier.
Part of my code looks like this:
best_KNN = KNeighborsClassifier(n_neighbors=5, p=1)
best_KNN.fit(X_train, y_train)
majority_voting = VotingClassifier(estimators=[('KNN', best_KNN), ('DT', best_DT), ('SVM', best_SVM), ('gaussian', gaussian_NB)], voting='hard')
majority_voting.fit(X_train, y_train)
bagging = BaggingClassifier(base_estimator=majority_voting)
bagging.fit(X_train, y_train)
But this causes an error saying:
TypeError: Underlying estimator KNeighborsClassifier does not support sample weights.
The "bagging" part worked fine if I remove KNN.
Does anyone have any idea to solve this issue? Thank you for your time.
In BaggingClassifier you can only use base estimators that support sample weights because it relies on score method, which takes in sample_weightparam.
You can list all the available classifiers like:
import inspect
from sklearn.utils.testing import all_estimators
for name, clf in all_estimators(type_filter='classifier'):
if 'sample_weight' in inspect.getargspec(clf.fit)[0]:
print(name)
I've read through a few pages but need someone to help explain how to make this work for.
I'm using TPOTRegressor() to get an optimal pipeline, but from there I would love to be able to plot the .feature_importances_ of the pipeline it returns:
best_model = TPOTRegressor(cv=folds, generations=2, population_size=10, verbosity=2, random_state=seed) #memory='./PipelineCache', memory='auto',
best_model.fit(X_train, Y_train)
feature_importance = best_model.fitted_pipeline_.steps[-1][1].feature_importances_
I saw this kind of set up from a now closed issue on Github, but currently I get the error:
Best pipeline: LassoLarsCV(input_matrix, normalize=True)
Traceback (most recent call last):
File "main2.py", line 313, in <module>
feature_importance = best_model.fitted_pipeline_.steps[-1][1].feature_importances_
AttributeError: 'LassoLarsCV' object has no attribute 'feature_importances_'
So, how would I get these feature importances from the optimal pipeline, regardless of which one it lands on? Or is this even possible? Or does someone have a better way of going about trying to plot feature importances from a TPOT run?
Thanks!
UPDATE
For clarification, what is meant by Feature Importance is the determination of how important each feature (X's) of your dataset is in determining the predicted (Y) label, using a barchart to plot each feature's level of importance in coming up with its predictions. TPOT doesn't do this directly (I don't think), so I was thinking I'd grab the pipeline it came up with, re-run it on the training data, and then somehow use a .feature_imprtances_ to then be able to graph the feature importances, as these are all sklearn regressor's I'm using?
Very nice question.
You just need to fit again the best model in order to get the feature importances.
best_model.fit(X_train, Y_train)
exctracted_best_model = best_model.fitted_pipeline_.steps[-1][1]
The last line returns the best model based on the CV.
You can then use:
exctracted_best_model.fit(X_train, Y_train)
to train it. If the best model has the desired attribure, then you will be able to access it after exctracted_best_model.fit(X_train, Y_train)
More details (in my comments) and a Toy example:
from tpot import TPOTRegressor
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
digits = load_digits()
X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target,
train_size=0.75, test_size=0.25)
# reduce training features for time sake
X_train = X_train[:100,:]
y_train = y_train[:100]
# Fit the TPOT pipeline
tpot = TPOTRegressor(cv=2, generations=5, population_size=50, verbosity=2)
# Fit the pipeline
tpot.fit(X_train, y_train)
# Get the best model
exctracted_best_model = tpot.fitted_pipeline_.steps[-1][1]
print(exctracted_best_model)
AdaBoostRegressor(base_estimator=None, learning_rate=0.5, loss='square',
n_estimators=100, random_state=None)
# Train the `exctracted_best_model` using THE WHOLE DATASET.
# You need to use the whole dataset in order to get feature importance for all the
# features in your dataset.
exctracted_best_model.fit(X, y) # X,y IMPORTNANT
# Access it's features
exctracted_best_model.feature_importances_
# Plot them using barplot
# Here I fitted the model on X_train, y_train and not on the whole dataset for TIME SAKE
# So I got importances only for the features in `X_train`
# If you use `exctracted_best_model.fit(X, y)` we will have importances for all the features !!!
positions= range(exctracted_best_model.feature_importances_.shape[0])
plt.bar(positions, exctracted_best_model.feature_importances_)
plt.show()
IMPORTNANT NOTE: *In the above example, the best model based on the pipeline was AdaBoostRegressor(base_estimator=None, learning_rate=0.5, loss='square'). This model indeed has the attribute feature_importances_.
In the case where the best model does not have an attribute feature_importances_, the exact same code will not work. You will need to read the docs and see the attributes of each returned best model. E.g. if the best model was LassoCV then you would use the coef_ attribute.
Output:
I am implementing a pipeline using important features selection and then using the same features to train my random forest classifier. Following is my code.
m = ExtraTreesClassifier(n_estimators = 10)
m.fit(train_cv_x,train_cv_y)
sel = SelectFromModel(m, prefit=True)
X_new = sel.transform(train_cv_x)
clf = RandomForestClassifier(5000)
model = Pipeline([('m', m),('sel', sel),('X_new', X_new),('clf', clf),])
params = {'clf__max_features': ['auto', 'sqrt', 'log2']}
gs = GridSearchCV(model, params)
gs.fit(train_cv_x,train_cv_y)
So X_new are the new features selected via SelectFromModel and sel.transform. Then I want to train my RF using the new features selected.
I am getting the following error:
All intermediate steps should be transformers and implement fit and transform,
ExtraTreesClassifier ...
Like the traceback says: each step in your pipeline needs to have a fit() and transform() method (except the last, which just needs fit(). This is because a pipeline chains together transformations of your data at each step.
sel.transform(train_cv_x) is not an estimator and doesn't meet this criterion.
In fact, it looks like based on what you're trying to do, you can leave this step out. Internally, ('sel', sel) already does this transformation--that's why it's included in the pipeline.
Secondly, ExtraTreesClassifier (the first step in your pipeline), doesn't have a transform() method, either. You can verify that here, in the class docstring. Supervised learning models aren't made for transforming data; they're made for fitting on it and predicting based off that.
What type of classes are able to do transformations?
Ones that scale your data. See preprocessing and normalization.
Ones that transform your data (in some other way than the above). Decomposition and other unsupervised learning methods do this.
Without reading between the lines too much about what you're trying to do here, this would work for you:
First split x and y using train_test_split. The test dataset produced by this is held out for final testing, and the train dataset within GridSearchCV's cross-validation will be further broken out into smaller train and validation sets.
Build a pipeline that satisfies what your traceback is trying to tell you.
Pass that pipeline to GridSearchCV, .fit() that grid search on X_train/y_train, then .score() it on X_test/y_test.
Roughly, that would look like this:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.33, random_state=444)
sel = SelectFromModel(ExtraTreesClassifier(n_estimators=10, random_state=444),
threshold='mean')
clf = RandomForestClassifier(n_estimators=5000, random_state=444)
model = Pipeline([('sel', sel), ('clf', clf)])
params = {'clf__max_features': ['auto', 'sqrt', 'log2']}
gs = GridSearchCV(model, params)
gs.fit(X_train, y_train)
# How well do your hyperparameter optimizations generalize
# to unseen test data?
gs.score(X_test, y_test)
Two examples for further reading:
Pipelining: chaining a PCA and a logistic regression
Sample pipeline for text feature extraction and evaluation
You may also get the error in the title if you were oversampling or undersampling your data using imblearn module and fitting it into a model in a pipeline. If you got this message, then it means you have imported sklearn.pipeline.Pipeline. Import imblearn.pipeline.Pipeline instead and you're golden. For example,
from imblearn.pipeline import Pipeline
pipe = Pipeline([('o', SMOTE()), ('svc', SVC())])
The problem is, if you're sampling your data, the intermediate steps obviously need to sample the data as well, which is not supported by sklearn's Pipeline but is supported by imblearn's Pipeline.
This has happened because the first transformer you pass in a pipeline must have both a fit and transform method.
m = ExtraTreesClassifier(n_estimators = 10)
m.fit(train_cv_x,train_cv_y)
Here m does not have a transform method as ExtraTreesClassifier model does not have a transform method and so fails in the pipeline.
So change the order of the pipeline and add another transformer for the first step in the pipeline
I'm working on an online course and used the provided code to create two different predictive models. I played around with them a bit to see if I can get different results, which went fine.
My concern is why they are giving me identical accuracy and cross validation scores.
Logit Regression:
Decision Tree:
I've provided a snippet of code below, as well as the function for classification that I took from python 2.x code. Currently, I am working with python 3.x and 0.17.1 of scikit-learn.
# import models from scikit-learn
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import KFold # for K-fold cross validation
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn import metrics
# generic fxn for making classification model and processing accessing performance
def classification_model(model, data, predictors, outcome):
model.fit(data[predictors], data[outcome]) # fit model
predictions = model.predict(data[predictors]) # make predictions on training set
# print accuracy
accuracy = metrics.accuracy_score(predictions, data[outcome])
print("Accuracy: %s" % "{0:.3%}".format(accuracy))
# k-fold cross validatiom, 5 folds
kf = KFold(data.shape[0], n_folds = 5)
error = []
for train, test in kf:
train_predictors = (data[predictors].iloc[train,:]) # filter training data
train_target = data[outcome].iloc[train]
model.fit(train_predictors, train_target)
# record error from each run
error.append(model.score(data[predictors].iloc[test,:], data[outcome].iloc[test]))
print("Cross-Validation Score: %s" % "{0:.3%}".format(np.mean(error)))
# fit model (again) so it can be referred to outside fxn
model.fit(data[predictors], data[outcome])
Am I using outdated parameter names? Or is there something wrong with the classifier function?
I currently am not getting any errors from the code that I'm running but getting the exact same accuracy and cross validation scores is concerning.
It is common to scale the training and testing data separately before training and predicting progress of a classification task.
I want to embed the aforementioned process in RFECV which runs CV tests thus I tried the following:
Do
X_scaled = preprocessing.scale(X) in the first place, where X is the whole data set. By doing so, training and testing data are not scaled separately, which is not considered.
The other way I tried is to pass:
scaling_svm = Pipeline([('scaler', preprocessing.StandardScaler()),
('svm',LinearSVC(penalty=penalty, dual=False, class_weight='auto'))])
as parameter to the argument in RFECV :
rfecv = RFECV(estimator=scaling_svm, step=1, cv=StratifiedKFold(y, 7),
scoring=score, verbose=0)
However, I got an error since RFECV needs the estimator to have attribute .coef_.
What should I suppose to do? Any help would be appreciated.
A bit late to the party, admittedly, but if anyone is interested you can create a customised pipeline as follows:
from sklearn.pipeline import Pipeline
class RfePipeline(Pipeline):
#property
def coef_(self):
return self._final_estimator.coef_
And then replace Pipeline with RfePipeline in your code.
See similar question here.