def validation_curve_classifier_alt( path="images/validation_curve_classifier_alt.png"): data = pd.read_csv(os.path.join(FIXTURES, "game", "game.csv")) target = "outcome" features = [col for col in data.columns if col != target] X = pd.get_dummies(data[features]) y = data[target] _, ax = plt.subplots() cv = StratifiedKFold(4) param_range = np.arange(3, 20, 2) oz = ValidationCurve( KNeighborsClassifier(), ax=ax, param_name="n_neighbors", param_range=param_range, cv=cv, scoring="f1_weighted", n_jobs=8, ) oz.fit(X, y) oz.poof(outpath=path)
def validation_curve_classifier(path="images/validation_curve_classifier.png"): data = pd.read_csv(os.path.join(FIXTURES, "game", "game.csv")) target = "outcome" features = [col for col in data.columns if col != target] X = pd.get_dummies(data[features]) y = data[target] _, ax = plt.subplots() cv = StratifiedKFold(12) param_range = np.logspace(-6, -1, 12) oz = ValidationCurve( SVC(), ax=ax, param_name="gamma", param_range=param_range, logx=True, cv=cv, scoring="f1_weighted", n_jobs=8, ) oz.fit(X, y) oz.poof(outpath=path)
def plot_validation_curve(final_X, final_Y): viz = ValidationCurve(DecisionTreeClassifier(), param_name="max_depth", param_range=np.arange(1, 30), cv=10, scoring="accuracy") viz.fit(final_X, final_Y) viz.poof()
def validation_curve_sklearn_example(path="images/validation_curve_sklearn_example.png"): digits = load_digits() X, y = digits.data, digits.target _, ax = plt.subplots() param_range = np.logspace(-6, -1, 5) oz = ValidationCurve( SVC(), ax=ax, param_name="gamma", param_range=param_range, logx=True, cv=10, scoring="accuracy", n_jobs=4 ) oz.fit(X, y) oz.poof(outpath=path)
def draw_validation_curve(self, param_name, param_range, cv, logx=False, scoring="accuracy", n_jobs=5): visualizer = ValidationCurve(self.model, param_name=param_name, param_range=param_range, logx=logx, cv=cv, scoring=scoring, n_jobs=n_jobs) visualizer.fit(self.training_data, self.training_labels) visualizer.poof()
def validation_curve_sklearn_example( path="images/validation_curve_sklearn_example.png"): digits = load_digits() X, y = digits.data, digits.target _, ax = plt.subplots() param_range = np.logspace(-6, -1, 5) oz = ValidationCurve(SVC(), ax=ax, param_name="gamma", param_range=param_range, logx=True, cv=10, scoring="accuracy", n_jobs=4) oz.fit(X, y) oz.poof(outpath=path)
def validation_curve_regressor(path="images/validation_curve_regressor.png"): data = pd.read_csv(os.path.join(FIXTURES, "energy", "energy.csv")) targets = ["heating load", "cooling load"] features = [col for col in data.columns if col not in targets] X = data[features] y = data[targets[1]] _, ax = plt.subplots() param_range = np.arange(1, 11) oz = ValidationCurve( DecisionTreeRegressor(), ax=ax, param_name="max_depth", param_range=param_range, cv=10, scoring="r2", n_jobs=8, ) oz.fit(X, y) oz.poof(outpath=path)
def validation_curve_classifier_alt(path="images/validation_curve_classifier_alt.png"): data = pd.read_csv(os.path.join(FIXTURES, "game", "game.csv")) target = "outcome" features = [col for col in data.columns if col != target] X = pd.get_dummies(data[features]) y = data[target] _, ax = plt.subplots() cv = StratifiedKFold(4) param_range = np.arange(3, 20, 2) oz = ValidationCurve( KNeighborsClassifier(), ax=ax, param_name="n_neighbors", param_range=param_range, cv=cv, scoring="f1_weighted", n_jobs=8, ) oz.fit(X, y) oz.poof(outpath=path)
def validation_curve(model, X, y): from yellowbrick.model_selection import ValidationCurve from sklearn.model_selection import StratifiedKFold # Create the validation curve visualizer cv = StratifiedKFold(12) # param_range = np.linspace(30.00, 300.00, num=50.00, dtype=np.float64) param_range = np.logspace(30, 300, num=100, dtype=np.int32) viz = ValidationCurve( model, param_name="n_estimators", param_range=param_range, logx=True, cv=cv, scoring="f1_weighted", n_jobs=8, ) viz.fit(X, y) viz.poof()
plt.tight_layout() plt.gcf().set_size_inches(10, 5) plt.show() # Train & Validation Curves mit yellowbricks fig, ax = plt.subplots(figsize=(16, 9)) val_curve = ValidationCurve( KNeighborsRegressor(), param_name='n_neighbors', param_range=n_neighbors, cv=5, scoring=rmse_score, # n_jobs=-1, ax=ax) val_curve.fit(X, y) val_curve.poof() fig.tight_layout() plt.show() fig, ax = plt.subplots(figsize=(16, 9)) l_curve = LearningCurve( KNeighborsRegressor(n_neighbors=best_k), train_sizes=np.arange(.1, 1.01, .1), scoring=rmse_score, cv=5, # n_jobs=-1, ax=ax) l_curve.fit(X, y) l_curve.poof() fig.tight_layout() plt.show()