Plotting

Plotting functions

sklearn_evaluation.plot.confusion_matrix(y_true, y_pred, target_names=None, normalize=False, cmap=None, ax=None)

Plot confusion matrix.

Parameters

• y_true (array-like, shape = [n_samples]) – Correct target values (ground truth).

• y_pred (array-like, shape = [n_samples]) – Target predicted classes (estimator predictions).

• target_names (list) – List containing the names of the target classes. List must be in order e.g. ['Label for class 0', 'Label for class 1']. If None, generic labels will be generated e.g. ['Class 0', 'Class 1']

• ax (matplotlib Axes) – Axes object to draw the plot onto, otherwise uses current Axes

• normalize (bool) – Normalize the confusion matrix

• cmap (matplotlib Colormap) – If None uses a modified version of matplotlib’s OrRd colormap.

Notes

http://scikit-learn.org/stable/auto_examples/model_selection/plot_confusion_matrix.html

Returns

ax – Axes containing the plot

Return type

matplotlib Axes

Examples

import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

from sklearn_evaluation import plot

data = datasets.make_classification(200, 10, n_informative=5, class_sep=0.65)
X = data[0]
y = data[1]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

est = RandomForestClassifier()
est.fit(X_train, y_train)

y_pred = est.predict(X_test)
y_score = est.predict_proba(X_test)
y_true = y_test

plot.confusion_matrix(y_true, y_pred)
plt.show()

sklearn_evaluation.plot.feature_importances(data, top_n=None, feature_names=None, orientation='horizontal', ax=None)

Get and order feature importances from a scikit-learn model or from an array-like structure. If data is a scikit-learn model with sub-estimators (e.g. RandomForest, AdaBoost) the function will compute the standard deviation of each feature.

Parameters

• data (sklearn model or array-like structure) – Object to get the data from.

• top_n (int) – Only get results for the top_n features.

• feature_names (array-like) – Feature names

• orientation (('horizontal', 'vertical')) – Bar plot orientation

• ax (matplotlib Axes) – Axes object to draw the plot onto, otherwise uses current Axes

Returns

ax – Axes containing the plot

Return type

matplotlib Axes

Examples

"""
Feature importances plot
"""
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

from sklearn_evaluation import plot

X, y = datasets.make_classification(200, 20, n_informative=5, class_sep=0.65)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

model = RandomForestClassifier(n_estimators=1)
model.fit(X_train, y_train)

# plot all features
ax = plot.feature_importances(model)
plt.show()

# only top 5
plot.feature_importances(model, top_n=5)
plt.show()

sklearn_evaluation.plot.grid_search(cv_results_, change, subset=None, kind='line', cmap=None, ax=None)

Plot results from a sklearn grid search by changing two parameters at most.

Parameters

• cv_results (list of named tuples) – Results from a sklearn grid search (get them using the cv_results_ parameter)

• change (str or iterable with len<=2) – Parameter to change

• subset (dictionary-like) – parameter-value(s) pairs to subset from grid_scores. (e.g. {'n_estimators': [1, 10]}), if None all combinations will be used.

• kind (['line', 'bar']) – This only applies whe change is a single parameter. Changes the type of plot

• cmap (matplotlib Colormap) – This only applies when change are two parameters. Colormap used for the matrix. If None uses a modified version of matplotlib’s OrRd colormap.

• ax (matplotlib Axes) – Axes object to draw the plot onto, otherwise uses current Axes

Returns

ax – Axes containing the plot

Return type

matplotlib Axes

Examples

import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
from sklearn import datasets

from sklearn_evaluation.plot import grid_search


iris = datasets.load_iris()


parameters = {
    'n_estimators': [1, 10, 50, 100],
    'criterion': ['gini', 'entropy'],
    'max_features': ['sqrt', 'log2'],
}

est = RandomForestClassifier()
clf = GridSearchCV(est, parameters, cv=5)

X, y = datasets.make_classification(1000, 10, n_informative=5, class_sep=0.7)
clf.fit(X, y)

# changing numeric parameter without any restrictions
# in the rest of the parameter set
grid_search(clf.cv_results_, change='n_estimators')
plt.show()

# you can also use bars
grid_search(clf.cv_results_, change='n_estimators', kind='bar')
plt.show()

# changing a categorical variable without any constraints
grid_search(clf.cv_results_, change='criterion')
plt.show()

# bar
grid_search(clf.cv_results_, change='criterion', kind='bar')
plt.show()

# varying a numerical parameter but constraining
# the rest of the parameter set
grid_search(clf.cv_results_, change='n_estimators',
            subset={'max_features': 'sqrt', 'criterion': 'gini'},
            kind='bar')
plt.show()

# same as above but letting max_features to have two values
grid_search(clf.cv_results_, change='n_estimators',
            subset={'max_features': ['sqrt', 'log2'], 'criterion': 'gini'},
            kind='bar')
plt.show()

# varying two parameters - you can only show this as a
# matrix so the kind parameter will be ignored
grid_search(clf.cv_results_, change=('n_estimators', 'criterion'),
            subset={'max_features': 'sqrt'})
plt.show()

sklearn_evaluation.plot.learning_curve(train_scores, test_scores, train_sizes, ax=None)

Plot a learning curve

Plot a metric vs number of examples for the training and test set

Parameters

• train_scores (array-like) – Scores for the training set

• test_scores (array-like) – Scores for the test set

• train_sizes (array-like) – Relative or absolute numbers of training examples used to generate the learning curve

• ax (matplotlib Axes) – Axes object to draw the plot onto, otherwise uses current Axes

Returns

ax – Axes containing the plot

Return type

matplotlib Axes

Examples

from sklearn.model_selection import learning_curve
from sklearn import model_selection
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.datasets import load_digits
import matplotlib.pyplot as plt
import numpy as np

from sklearn_evaluation import plot

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 = model_selection.ShuffleSplit(digits.data.shape[0],
                                  test_size=0.2, random_state=0)
cv = 5
estimator = GaussianNB()
train_sizes = np.linspace(.1, 1.0, 5)
train_sizes, train_scores, test_scores = learning_curve(
    estimator, X, y, cv=cv, n_jobs=1, train_sizes=train_sizes)
plot.learning_curve(train_scores, test_scores, train_sizes)
plt.show()

# SVC is more expensive so we do a lower number of CV iterations:
cv = model_selection.ShuffleSplit(digits.data.shape[0],
                                  test_size=0.2, random_state=0)
cv = 5
estimator = SVC(gamma=0.001)
train_sizes = np.linspace(.1, 1.0, 5)
train_sizes, train_scores, test_scores = learning_curve(
    estimator, X, y, cv=cv, n_jobs=1, train_sizes=train_sizes)

plot.learning_curve(train_scores, test_scores, train_sizes)
plt.show()

sklearn_evaluation.plot.metrics_at_thresholds(fn, y_true, y_score, n_thresholds=10, start=0.0, ax=None)

Plot metrics at increasing thresholds

sklearn_evaluation.plot.precision_at_proportions(y_true, y_score, ax=None)

Plot precision values at different proportions.

Parameters

• y_true (array-like) – Correct target values (ground truth).

• y_score (array-like) – Target scores (estimator predictions).

• ax (matplotlib Axes) – Axes object to draw the plot onto, otherwise uses current Axes

Returns

ax – Axes containing the plot

Return type

matplotlib Axes

sklearn_evaluation.plot.precision_recall(y_true, y_score, ax=None)

Plot precision-recall curve.

Parameters

• y_true (array-like, shape = [n_samples]) – Correct target values (ground truth).

• y_score (array-like, shape = [n_samples] or [n_samples, 2] for binary) –

  classification or [n_samples, n_classes] for multiclass

  Target scores (estimator predictions).

• ax (matplotlib Axes) – Axes object to draw the plot onto, otherwise uses current Axes

Notes

It is assumed that the y_score parameter columns are in order. For example, if y_true = [2, 2, 1, 0, 0, 1, 2], then the first column in y_score must contain the scores for class 0, second column for class 1 and so on.

Returns

ax – Axes containing the plot

Return type

matplotlib Axes

Examples

import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

from sklearn_evaluation import plot

data = datasets.make_classification(200, 10, n_informative=5, class_sep=0.65)
X = data[0]
y = data[1]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

est = RandomForestClassifier()
est.fit(X_train, y_train)

y_pred = est.predict(X_test)
y_score = est.predict_proba(X_test)
y_true = y_test

plot.precision_recall(y_true, y_score)
plt.show()

sklearn_evaluation.plot.roc(y_true, y_score, ax=None)

Plot ROC curve.

Parameters

• y_true (array-like, shape = [n_samples]) – Correct target values (ground truth).

• y_score (array-like, shape = [n_samples] or [n_samples, 2] for binary) –

  classification or [n_samples, n_classes] for multiclass

  Target scores (estimator predictions).

• ax (matplotlib Axes) – Axes object to draw the plot onto, otherwise uses current Axes

Notes

It is assumed that the y_score parameter columns are in order. For example, if y_true = [2, 2, 1, 0, 0, 1, 2], then the first column in y_score must contain the scores for class 0, second column for class 1 and so on.

Returns

ax – Axes containing the plot

Return type

matplotlib Axes

Examples

import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

from sklearn_evaluation import plot

data = datasets.make_classification(200, 10, n_informative=5, class_sep=0.65)
X = data[0]
y = data[1]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

est = RandomForestClassifier()
est.fit(X_train, y_train)

y_pred = est.predict(X_test)
y_score = est.predict_proba(X_test)
y_true = y_test

plot.roc(y_true, y_score)
plt.show()

sklearn_evaluation.plot.validation_curve(train_scores, test_scores, param_range, param_name=None, semilogx=False, ax=None)

Plot a validation curve

Plot a metric vs hyperparameter values for the training and test set

Parameters

• train_scores (array-like) – Scores for the training set

• test_scores (array-like) – Scores for the test set

• param_range (str) – Hyperparameter values used to generate the curve

• param_range – Hyperparameter name

• semilgo (bool) – Sets a log scale on the x axis

• ax (matplotlib Axes) – Axes object to draw the plot onto, otherwise uses current Axes

Returns

ax – Axes containing the plot

Return type

matplotlib Axes

Examples

import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import load_digits
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import validation_curve

from sklearn_evaluation import plot

digits = load_digits()
X, y = digits.data, digits.target

param_range = np.logspace(-6, -1, 5)
param_name = "gamma"
train_scores, test_scores = validation_curve(
    SVC(), X, y, param_name=param_name,
    param_range=param_range,
    cv=5,
    scoring="accuracy",
    n_jobs=1)

plot.validation_curve(train_scores, test_scores, param_range, param_name,
                      semilogx=True)
plt.show()

param_range = np.array([1, 10, 100])
param_name = "n_estimators"
train_scores, test_scores = validation_curve(
    RandomForestClassifier(), X, y,
    param_name=param_name,
    param_range=param_range,
    cv=10, scoring="accuracy", n_jobs=1)

plot.validation_curve(train_scores, test_scores, param_range, param_name,
                      semilogx=False)
plt.show()