def rfecv_credit_example(image="rfecv_credit.png"):
X, y = load_credit()
_, ax = plt.subplots()
cv = StratifiedKFold(5)
oz = RFECV(RandomForestClassifier(), ax=ax, cv=cv, scoring="f1_weighted")
oz.fit(X, y)
oz.show(outpath=os.path.join(IMAGES, image))
def rfecv_sklearn_example(image="rfecv_sklearn_example.png"):
X, y = make_classification(
n_samples=1000,
n_features=25,
n_informative=3,
n_redundant=2,
n_repeated=0,
n_classes=8,
n_clusters_per_class=1,
random_state=0,
)
_, ax = plt.subplots()
oz = RFECV(SVC(kernel="linear", C=1), ax=ax)
oz.fit(X, y)
oz.show(outpath=os.path.join(IMAGES, image))
# In[24]: #instancia a classe reg = LinearRegression() # In[25]: #Ranking das features com RFE com cross validation #O ponto tracejado representa o score maximo com 27 features rfecv = RFECV(reg,step=1, cv=3) rfecv.fit(X,y) rfecv.show() # In[26]: #lista de features utilizadas pelo modelo list(zip(X.columns, rfecv.support_)) # In[27]: #seleciona 5 features para o modelo utilizando somente RFE rfe = RFE(reg, n_features_to_select=5, step=1 ) rfe = rfe.fit(X,y)
"auc_roc_dtree": 9,
"auc_roc_bernoulliNB": 10,
"auc_roc_LDA": 11,
"auc_roc_gaussianNB": 12
}
df_results = df_results.replace({"Best model ROC": model_dict})
y = df_results["Best model ROC"]
cv = StratifiedKFold(2)
visualizer = RFECV(RandomForestClassifier(n_estimators=10),
cv=cv,
scoring='accuracy')
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.show()
print("Optimal number of features : %d" % visualizer.n_features_)
print(visualizer.ranking_)
print(visualizer.estimator_.feature_importances_)
index_list = []
for index, value in enumerate(visualizer.ranking_):
if value == 1:
index_list.append(index)
else:
pass
selected_X = df_results.iloc[:, index_list]
with open('RFE_X_AUCROC_202.pickle', 'wb') as handle:
# def check_model(c, n, X, y, X_test, y_test, class_names, outdir):
# model = svm.LinearSVC(class_weight='balanced', dual=False, max_iter=10000, C=c)
# rfe = RFE(model, n_features_to_select=n)
# fit = rfe.fit(X,y)
# y_predict = fit.predict(X_test)
# predict_df = pd.DataFrame(y_predict.tolist())
# predict_df.to_csv(outdir + '/predict_label.csv', sep='\t', index=False)
# test = [[1e-3,12],[1e-6,7],[1.0,32],[1e-6,27]]
# for c,n in test:
# print(str(c)+ '-' +str(n))
# this_out = 'figures/eva/c' + str(c) + '_n' + str(n)
# check_model(c=c, n=n, outdir=this_out, X=X, y=y, X_test=X_test, y_test=y_test,
# class_names=class_names)
## plot RFECV for LinearSVC
for c in [1e-6, 1e-3, 1]:
model = svm.LinearSVC(class_weight='balanced', dual=False, max_iter=10000, C=c)
viz = RFECV(model, scoring='f1_weighted')
viz.fit(X, y)
viz.show(outpath='figures/linear_svc_rfecv.pdf')