def feature_correlation_pearson(path="images/feature_correlation_pearson.png"):
data = datasets.load_diabetes()
X, y = data['data'], data['target']
feature_names = np.array(data['feature_names'])
visualizer = FeatureCorrelation(labels=feature_names)
visualizer.fit(X, y)
visualizer.poof(outpath=path, clear_figure=True)
def test_feature_correlation_integrated_mutual_info_regression(self):
"""
Test FeatureCorrelation visualizer with mutual information regression
"""
viz = FeatureCorrelation(method='mutual_info-regression')
viz.fit(self.X, self.y, random_state=23456)
viz.poof()
self.assert_images_similar(viz)
def test_feature_correlation_integrated_mutual_info_regression(self):
"""
Test FeatureCorrelation visualizer with mutual information regression
"""
viz = FeatureCorrelation(method='mutual_info-regression')
viz.fit(self.X, self.y, random_state=23456)
viz.poof()
self.assert_images_similar(viz)
def feature_correlation_pearson(
path="images/feature_correlation_pearson.png"):
data = datasets.load_diabetes()
X, y = data['data'], data['target']
feature_names = np.array(data['feature_names'])
visualizer = FeatureCorrelation(labels=feature_names)
visualizer.fit(X, y)
visualizer.poof(outpath=path, clear_figure=True)
def test_feature_correlation_integrated_pearson(self):
"""
Test FeatureCorrelation visualizer with pearson correlation
coefficient
"""
viz = FeatureCorrelation()
viz.fit(self.X, self.y)
viz.poof()
self.assert_images_similar(viz)
def test_feature_correlation_integrated_pearson(self):
"""
Test FeatureCorrelation visualizer with pearson correlation
coefficient
"""
viz = FeatureCorrelation()
viz.fit(self.X, self.y)
viz.poof()
self.assert_images_similar(viz)
def mutual_info_classification(classes, feature_names, X, y):
from sklearn import datasets
from yellowbrick.target import FeatureCorrelation
# Load the regression data set
visualizer = FeatureCorrelation(method='mutual_info-classification',
feature_names=feature_names,
sort=True)
visualizer.fit(X, y, random_state=0)
visualizer.poof()
def pearson_correlation(classes, fetures, X, Y):
from sklearn import datasets
from yellowbrick.target import FeatureCorrelation
# Load the regression data set
# data = datasets.load_diabetes()
# X, y = data['data'], data['target']
# feature_names = np.array(data['feature_names'])
visualizer = FeatureCorrelation(labels=fetures)
visualizer.fit(X, Y)
visualizer.poof()
def report(self, pipeline: AbstractPipeline):
folder = get_cache_path()
path = pkg_resources.resource_filename(
'crcdal', 'cache/' + folder + '/' + self.sub_folder + '/')
pkg_resources.ensure_directory(path)
feature_names = list(pipeline.train.columns())
visualizer = FeatureCorrelation(labels=feature_names)
visualizer.fit(pipeline.train, pipeline.train_y)
visualizer.poof(outpath=path + pipeline.dataset_tag +
'_model_feature_correlation_report.csv')
def feature_correlation_mutual_info_classification(
path="images/feature_correlation_mutual_info_classification.png"):
data = datasets.load_wine()
X, y = data['data'], data['target']
feature_names = np.array(data['feature_names'])
X_pd = pd.DataFrame(X, columns=feature_names)
feature_to_plot = ['alcohol', 'ash', 'hue', 'proline', 'total_phenols']
visualizer = FeatureCorrelation(method='mutual_info-classification',
feature_names=feature_to_plot)
visualizer.fit(X_pd, y, random_state=0)
visualizer.poof(outpath=path, clear_figure=True)
def test_feature_correlation_integrated_mutual_info_classification(self):
"""
Test FeatureCorrelation visualizer with mutual information
on wine dataset (classification)
"""
data = datasets.load_wine()
X, y = data['data'], data['target']
viz = FeatureCorrelation(method='mutual_info-classification')
viz.fit(X, y, random_state=12345)
viz.poof()
self.assert_images_similar(viz)
def test_feature_correlation_integrated_mutual_info_classification(self):
"""
Test FeatureCorrelation visualizer with mutual information
on wine dataset (classification)
"""
data = datasets.load_wine()
X, y = data['data'], data['target']
viz = FeatureCorrelation(method='mutual_info-classification')
viz.fit(X, y, random_state=12345)
viz.poof()
self.assert_images_similar(viz)
def mutual_info_regress(classes, feature_names, X, y):
from sklearn import datasets
from yellowbrick.target import FeatureCorrelation
# Load the regression data set
discrete_features = [False for _ in range(len(feature_names))]
discrete_features[1] = True
visualizer = FeatureCorrelation(method='mutual_info-regression',
labels=feature_names)
visualizer.fit(X, y, discrete_features=discrete_features, random_state=0)
visualizer.poof()
def feature_correlation_mutual_info_regression(
path="images/feature_correlation_mutual_info_regression.png"):
data = datasets.load_diabetes()
X, y = data['data'], data['target']
feature_names = np.array(data['feature_names'])
discrete_features = [False for _ in range(len(feature_names))]
discrete_features[1] = True
visualizer = FeatureCorrelation(method='mutual_info-regression',
labels=feature_names, sort=True)
visualizer.fit(X, y, discrete_features=discrete_features, random_state=0)
visualizer.poof(outpath=path, clear_figure=True)
def feature_correlation_mutual_info_classification(
path="images/feature_correlation_mutual_info_classification.png"):
data = datasets.load_wine()
X, y = data['data'], data['target']
feature_names = np.array(data['feature_names'])
X_pd = pd.DataFrame(X, columns=feature_names)
feature_to_plot = ['alcohol', 'ash', 'hue', 'proline', 'total_phenols']
visualizer = FeatureCorrelation(method='mutual_info-classification',
feature_names=feature_to_plot)
visualizer.fit(X_pd, y, random_state=0)
visualizer.poof(outpath=path, clear_figure=True)
def feature_correlation_mutual_info_regression(
path="images/feature_correlation_mutual_info_regression.png"):
data = datasets.load_diabetes()
X, y = data['data'], data['target']
feature_names = np.array(data['feature_names'])
discrete_features = [False for _ in range(len(feature_names))]
discrete_features[1] = True
visualizer = FeatureCorrelation(method='mutual_info-regression',
labels=feature_names,
sort=True)
visualizer.fit(X, y, discrete_features=discrete_features, random_state=0)
visualizer.poof(outpath=path, clear_figure=True)
cv=cv) clf = scores['estimator'][np.argmax(scores['test_score'])] print(np.max(scores['test_score'])) # %% explainer = shap.TreeExplainer(clf) shap_values = explainer.shap_values(Xv) # %% shap.summary_plot(shap_values, Xv, plot_type="bar") # %% feat = feature_names[feat][np.mean(abs(shap_values), axis=0) > 0.55] print(feat) X = X[feat] # %% visualizer = FeatureCorrelation(method='mutual_info-classification') visualizer.fit(X, y) visualizer.poof() # %% # This step doesn't always produce the same result, idk why. feat = visualizer.features_[visualizer.scores_ > 0.04] X = X[feat] # %% # Our final 10 features: # [263, 268, 287, 288, 300, 302, 307, 308, 313, 315] print(feat)
def draw_feature_correlation(self):
visualizer = FeatureCorrelation(method='mutual_info-classification',
labels=self.get_feature_labels(),
sort=True)
visualizer.fit(self.training_data, self.training_labels)
visualizer.poof()