How to choose the best model dynamically using python

问题

Here is my code im building 6 models and i am getting accuracy in that, how do i choose that dynamically which accuracy is greater and i want to execute only that model which as highest accuracy.

"prepare configuration for cross validation test harness"

seed = 7

"prepare models"

models = []
models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('RF',RandomForestClassifier()))

#models.append(('SVM', SVC()))

"evaluate each model in turn"

results = []
names = []
scoring = 'accuracy'
for name, model in models:
    kfold = model_selection.KFold(n_splits=10, random_state=seed)
    cv_results = model_selection.cross_val_score(model, orginal_telecom_80p_test[features], orginal_telecom_80p_test["Churn"], cv=kfold, scoring=scoring)
    results.append(cv_results)
    names.append(name)
    msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
    print(msg)

This is my accuracy

LR: 0.787555 (0.039036)
LDA: 0.780460 (0.039821)
KNN: 0.759916 (0.030417)
CART: 0.706669 (0.035827)
NB: 0.731637 (0.050813)
RF: 0.752054 (0.048660)

回答1:

As I mentionned in a comment, most of your snippet is totally irrelevant and should be replaced by a simplified runnable example.

Now if you question is "I have those objects for which I can get a 'score' and I want to select the one with the higher score", it's quite simple: store the scores along with the objects, sort this base on score and keep the one with the highest score:

import random

def get_score(model):
    # dumbed down example 
    return random.randint(1, 10)


class Model1(object):
    pass

class Model2(object):
    pass

class Model3(object):
    pass

models = [Model1, Model2, Model3]

# build a list of (score, model) tuples
scores = [(get_score(model), model) for model in models]

# sort it on score
scores.sort(key=item[0])

# get the model with the best score, which is the
# the second element of the last item
best = scores[-1][1]

Now please do yourself and the world a favour: LEARN TO ASK CLEAR QUESTIONS WITH ALL RELEVANT INFORMATIONS AND ONLY RELEVANT INFORMATIONS.

https://stackoverflow.com/help/how-to-ask

https://stackoverflow.com/help/mcve

https://stackoverflow.com/help/tagging

来源：https://stackoverflow.com/questions/49383494/how-to-choose-the-best-model-dynamically-using-python

标签

python

models