On the left side the learning curve of a naive Bayes classifier is shown for the digits dataset. Note that the training score and the cross-validation score are both not very good at the end. However, the shape of the curve can be found in more complex datasets very often: the training score is very high at the beginning and decreases and the cross-validation score is very low at the beginning and increases. On the right side we see the learning curve of an SVM with RBF kernel. We can see clearly that the training score is still around the maximum and the validation score could be increased with more training samples.
import sklearn sklearn.__version__
print(__doc__) import plotly.plotly as py import plotly.graph_objs as go from plotly import tools import numpy as np from sklearn.naive_bayes import GaussianNB from sklearn.svm import SVC from sklearn.datasets import load_digits from sklearn.model_selection import learning_curve from sklearn.model_selection import ShuffleSplit
Automatically created module for IPython interactive environment
fig = tools.make_subplots(rows=1, cols=2, subplot_titles=("Learning Curves (Naive Bayes)", "Learning Curves (SVM, RBF kernel, gamma=0.001)")) def plot_learning_curve(estimator, X, y, colnum, cv=None, n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5), ): """ Generate a simple plot of the test and training learning curve. Parameters ---------- estimator : object type that implements the "fit" and "predict" methods An object of that type which is cloned for each validation. title : string Title for the chart. X : array-like, shape (n_samples, n_features) Training vector, where n_samples is the number of samples and n_features is the number of features. y : array-like, shape (n_samples) or (n_samples, n_features), optional Target relative to X for classification or regression; None for unsupervised learning. ylim : tuple, shape (ymin, ymax), optional Defines minimum and maximum yvalues plotted. cv : int, cross-validation generator or an iterable, optional Determines the cross-validation splitting strategy. Possible inputs for cv are: - None, to use the default 3-fold cross-validation, - integer, to specify the number of folds. - An object to be used as a cross-validation generator. - An iterable yielding train/test splits. For integer/None inputs, if ``y`` is binary or multiclass, :class:`StratifiedKFold` used. If the estimator is not a classifier or if ``y`` is neither binary nor multiclass, :class:`KFold` is used. Refer :ref:`User Guide <cross_validation>` for the various cross-validators that can be used here. n_jobs : integer, optional Number of jobs to run in parallel (default 1). """ train_sizes, train_scores, test_scores = learning_curve( estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes) train_scores_mean = np.mean(train_scores, axis=1) train_scores_std = np.std(train_scores, axis=1) test_scores_mean = np.mean(test_scores, axis=1) test_scores_std = np.std(test_scores, axis=1) if(colnum==1): leg=True else: leg=False p1 = go.Scatter(x=train_sizes, y=test_scores_mean + test_scores_std, mode='lines', line=dict(color="green", width=1), showlegend=False, ) fig.append_trace(p1, 1, colnum) p2 = go.Scatter(x=train_sizes, y=test_scores_mean - test_scores_std, mode='lines', line=dict(color="green", width=1), showlegend=False, fill='tonexty') fig.append_trace(p2, 1, colnum) p3 = go.Scatter(x=train_sizes, y=train_scores_mean + train_scores_std, mode='lines', line=dict(color="red", width=1), showlegend=False) fig.append_trace(p3, 1, colnum) p4 = go.Scatter(x=train_sizes, y=train_scores_mean - train_scores_std, mode='lines', line=dict(color="red", width=1), showlegend=False, fill='tonexty') fig.append_trace(p4, 1, colnum) p5 = go.Scatter(x=train_sizes, y=train_scores_mean, marker=dict(color='red'), name="Training score", showlegend=leg) fig.append_trace(p5, 1, colnum) p6 = go.Scatter(x=train_sizes, y=test_scores_mean, marker=dict(color='green'), name="Cross-validation score", showlegend=leg) fig.append_trace(p6, 1, colnum)
This is the format of your plot grid: [ (1,1) x1,y1 ] [ (1,2) x2,y2 ]
digits = load_digits() X, y = digits.data, digits.target # Cross validation with 100 iterations to get smoother mean test and train # score curves, each time with 20% data randomly selected as a validation set. cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0) estimator = GaussianNB() plot_learning_curve(estimator, X, y, 1, cv=cv, n_jobs=4) # SVC is more expensive so we do a lower number of CV iterations: cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0) estimator = SVC(gamma=0.001) plot_learning_curve(estimator, X, y, 2, cv=cv, n_jobs=4) fig['layout'].update(hovermode='closest')