def step_forward(X, y, name):
print(name)
# Inspiration: https://www.kdnuggets.com/2018/06/step-forward-feature-selection-python.html
# Set up training/testing standardized data
X_train_std, X_test_std, y_train, y_test = tts_std(X, y)
# Build RF classifier to use in feature selection: liblinear solver recommended when you have
# high dimension dataset, but once you standardize your data, the accuracy of all solvers is
# pretty much the same. max_iter (maximum number of iterations taken for the solvers to converge.)
# is set to a higher number than default (100) so that the model will actually converge (lower
# values cause a no convergence warning).
clf = skllm.LogisticRegression(penalty='l1',
C=0.1,
solver='liblinear',
max_iter=100)
# Build step forward feature selection: cv (cross validation) is set to zero for no
# cross validation, k_features = 3 means we are selecting the 3 best attributes to desribe
# our feature, and verbose is just used for logging the progress of the feature selector
sfs1 = mlx.SequentialFeatureSelector(clf,
k_features=5,
forward=True,
floating=False,
verbose=0,
scoring='accuracy',
cv=10)
# Perform SFS
sfs1 = sfs1.fit(X_train_std, y_train, custom_feature_names=X.columns)
# Which features?
print('\t' + 'Top 5 features: ' + str(sfs1.k_feature_names_))
feat_cols1 = list(sfs1.k_feature_idx_)
# Build full model with selected features: sfs has no predict function
clf = skllm.LogisticRegression(penalty='l1',
C=0.1,
solver='liblinear',
max_iter=100)
# Now that we have the relevant features according to SFS, we can use logistic regression
# on JUST those features and see how accurately they can predict the classification of
# single loaded, clear, straight, etc.
clf.fit(X_train_std[:, feat_cols1], y_train)
# 'kind' represents the kind of error bar you get in your plot {'std_dev', 'std_err', 'ci',
# None}. This error bar is the error of the cv scores.
fig1 = mlxp.plot_sequential_feature_selection(sfs1.get_metric_dict(),
kind='std_dev')
plt.title('Sequential Forward Feature Selection CV Scores: ' + name +
' (std dev)')
plt.ylabel('Mean CV Score')
plt.grid()
plt.savefig('feature_selection/sfs_' + name + ".png")
plt.close()
# Accuracy
y_train_pred = clf.predict(X_train_std[:, feat_cols1])
print('\tTraining accuracy on selected features: %.3f' %
sklm.accuracy_score(y_train, y_train_pred))
print('\tTraining mean absolute error on selected features: %.3f' %
mean_abs_error(y_train, y_train_pred))
y_test_pred = clf.predict(X_test_std[:, feat_cols1])
print('\tTesting accuracy on selected features: %.3f' %
sklm.accuracy_score(y_test, y_test_pred))
print('\tTesting mean_abs_error on selected features: %.3f' %
mean_abs_error(y_test, y_test_pred))
# Confusion matrix generation
confusion_matrix(y_train, y_train_pred, name + "_sfs_Training_Data_")
confusion_matrix(y_test, y_test_pred, name + "_sfs_Testing_Data_")
my_auc(y_train, X_train_std[:, feat_cols1], name + '_sfs_training',
sfs1.k_feature_names_)
# CV scores
scores = sklms.cross_val_score(clf, X, y, cv=4)
print('\t' + name + ' CVs: ' + str(scores))
return sfs1, clf, pd.DataFrame.from_dict(sfs1.get_metric_dict()).T
n_repeats=10),
scoring='r2',
n_jobs=-1)
selector3 = selector3.fit(dataFrame3[colsNotSalePrice2],
dataFrame3["SalePrice"])
for col in colsNotSalePrice2[selector3.ranking_ == 1]:
print("%s" % col, end=", ")
#Seleção por forward SequentialFeatureSelector
from mlxtend import feature_selection
#SFS para random forests
sfs3 = feature_selection.SequentialFeatureSelector(
estimator3,
k_features=79,
forward=True,
scoring="r2",
cv=model_selection.RepeatedStratifiedKFold(3, 10),
n_jobs=-1)
sfs4 = sfs3.fit(dataFrame3[colsNotSalePrice2], dataFrame3["SalePrice"])
#Gera gráficos com os resultados
# #DataFrame com resultados do SVM
# svmPlot=pd.DataFrame({
# "Nº variáveis": range(5, len(selector3.grid_scores_) + 5),
# "algorithm":"svm",
# "Correlação": selector.grid_scores_})
#DataFrame com resultados do RF
def part_d(x, y):
linear = sklm.LinearRegression()
sfs = mlfs.SequentialFeatureSelector(linear, k_features=1, floating=False, forward=False, cv=0)
sfs_fit = sfs.fit(x, y)
print('\nPART D')
print(sfs_fit.subsets_)
