def show_learning_curve(
est: BaseEstimator,
conf_mat_labels: List,
X_train: DataFrame,
y_train: Series,
X_test: DataFrame,
y_test: Series,
scoring_metric: str = "f1_micro",
cv: StratifiedKFold = StratifiedKFold(n_splits=12),
sizes: np.linspace = np.linspace(0.3, 1.0, 10),
fig_size: Tuple = (8, 8),
savefig: Path = Path().cwd() / "reports" / "figures" / "cm.png",
) -> None:
"""Plot the learning curve"""
fig, ax = plt.subplots(figsize=fig_size)
cm = LearningCurve(est,
cv=cv,
scoring=scoring_metric,
train_sizes=sizes,
n_jobs=-1)
cm = LearningCurve(est, classes=conf_mat_labels, ax=ax)
cm.fit(X_train, y_train)
cm.score(X_test, y_test)
cm.finalize()
if not savefig.is_file():
fig.savefig(savefig, bbox_inches="tight", dpi=300)
def learning_curve_sklearn_example(path="images/learning_curve_sklearn_example.png"):
digits = load_digits()
X, y = digits.data, digits.target
_, ax = plt.subplots(nrows=1, ncols=2, sharey=True, figsize=(9,4))
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
oz = LearningCurve(GaussianNB(), ax=ax[0], cv=cv, n_jobs=4)
oz.fit(X, y)
oz.finalize()
cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
oz = LearningCurve(SVC(gamma=0.001), ax=ax[1], cv=cv, n_jobs=4)
oz.fit(X, y)
oz.poof(outpath=path)
def learning_curve_sklearn_example(
path="images/learning_curve_sklearn_example.png"):
digits = load_digits()
X, y = digits.data, digits.target
_, ax = plt.subplots(nrows=1, ncols=2, sharey=True, figsize=(9, 4))
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
oz = LearningCurve(GaussianNB(), ax=ax[0], cv=cv, n_jobs=4)
oz.fit(X, y)
oz.finalize()
cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
oz = LearningCurve(SVC(gamma=0.001), ax=ax[1], cv=cv, n_jobs=4)
oz.fit(X, y)
oz.poof(outpath=path)
def run_crossvalidation(model,
x_train,
y_train,
cv=5,
scoring="accuracy",
report=None,
model_name=None):
"""
Runs cross validation on a certain model.
Parameters
----------
model : Model
Model to cross validate
x_train : nd-array
Training data
y_train : nd-array
Testing data
cv : int, Crossvalidation Generator, optional
Cross validation method, by default 5
scoring : str, optional
Scoring method, by default 'accuracy'
"""
fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(15, 5))
visualizer_scores = CVScores(model, cv=cv, scoring=scoring, ax=axes[0])
visualizer_scores.fit(x_train, y_train)
visualizer_scores.finalize()
visualizer_lcurve = LearningCurve(model,
cv=cv,
scoring=scoring,
ax=axes[1])
visualizer_lcurve.fit(x_train, y_train)
visualizer_lcurve.finalize()
visualizer_scores.show()
visualizer_lcurve.show()
if report or _global_config['track_experiments']: # pragma: no cover
fig.savefig(os.path.join(IMAGE_DIR, model_name, "cv.png"))