Examples from this link

pip install scikit-plot



In [1]:

    
%pylab inline
pylab.rcParams['figure.figsize'] = (14, 14)









    



Populating the interactive namespace from numpy and matplotlib



In [2]:

    
from sklearn.datasets import load_digits as load_data
from sklearn.naive_bayes import GaussianNB



In [3]:

    
# This is all that's needed for scikit-plot
import matplotlib.pyplot as plt
from scikitplot import classifier_factory



In [4]:

    
# Load data
X, y = load_data(return_X_y=True)



In [5]:

    
# Regular instance using GaussianNB class
nb = GaussianNB()



In [6]:

    
# Modification of instance of Scikit-Learn
classifier_factory(nb)









    Out[6]:





GaussianNB(priors=None)



In [7]:

    
# An object of Scikit-Learn using the modified version that can use a method plot_roc_curve
nb.plot_roc_curve(X, y, random_state=1)









    Out[7]:





<matplotlib.axes._subplots.AxesSubplot at 0x107a53110>



In [8]:

    
# Display plot
plt.show()



In [ ]:



In [9]:

    
from sklearn.ensemble import RandomForestClassifier



In [10]:

    
random_forest_clf = RandomForestClassifier(n_estimators=5, max_depth=5, random_state=1)



In [11]:

    
from scikitplot import classifier_factory



In [12]:

    
classifier_factory(random_forest_clf)









    Out[12]:





RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=5, max_features='auto', max_leaf_nodes=None,
            min_impurity_split=1e-07, min_samples_leaf=1,
            min_samples_split=2, min_weight_fraction_leaf=0.0,
            n_estimators=5, n_jobs=1, oob_score=False, random_state=1,
            verbose=0, warm_start=False)



In [13]:

    
random_forest_clf.plot_confusion_matrix(X, y, normalize=True)









    Out[13]:





<matplotlib.axes._subplots.AxesSubplot at 0x108798e90>



In [14]:

    
plt.show()



In [ ]:



In [15]:

    
from scikitplot import plotters as skplt



In [16]:

    
rf = RandomForestClassifier()



In [17]:

    
rf = rf.fit(X, y)



In [18]:

    
preds = rf.predict(X)



In [19]:

    
skplt.plot_confusion_matrix(y_true=y, y_pred=preds)
plt.show()



In [ ]:



In [ ]:



In [20]:

    
from __future__ import absolute_import
import matplotlib.pyplot as plt
from scikitplot import clustering_factory
from sklearn.cluster import KMeans
from sklearn.datasets import load_iris as load_data



In [21]:

    
X, y = load_data(return_X_y=True)



In [22]:

    
kmeans = clustering_factory(KMeans(random_state=1))



In [23]:

    
kmeans.plot_elbow_curve(X, cluster_ranges=range(1, 11))
plt.show()



In [ ]:



In [ ]:



In [24]:

    
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_iris as load_data
import matplotlib.pyplot as plt
from scikitplot import classifier_factory



In [25]:

    
X, y = load_data(return_X_y=True)



In [26]:

    
rf = classifier_factory(RandomForestClassifier(random_state=1))



In [27]:

    
rf.fit(X, y)









    Out[27]:





RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_impurity_split=1e-07, min_samples_leaf=1,
            min_samples_split=2, min_weight_fraction_leaf=0.0,
            n_estimators=10, n_jobs=1, oob_score=False, random_state=1,
            verbose=0, warm_start=False)



In [28]:

    
rf.plot_feature_importances(feature_names=['petal length', 'petal width',
                                           'sepal length', 'sepal width'])
plt.show()



In [ ]:



In [ ]:



In [29]:

    
from __future__ import absolute_import
import matplotlib.pyplot as plt
from scikitplot import classifier_factory
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_breast_cancer as load_data



In [30]:

    
X, y = load_data(return_X_y=True)



In [31]:

    
lr = classifier_factory(LogisticRegression())



In [32]:

    
lr.plot_ks_statistic(X, y, random_state=1)
plt.show()



In [ ]:



In [33]:

    
from scikitplot import plotters as skplt



In [34]:

    
lr = LogisticRegression()



In [35]:

    
lr = lr.fit(X, y)



In [36]:

    
probas = lr.predict_proba(X)



In [37]:

    
skplt.plot_ks_statistic(y_true=y, y_probas=probas)
plt.show()



In [ ]:



In [ ]:



In [38]:

    
from __future__ import absolute_import
import matplotlib.pyplot as plt
from scikitplot import classifier_factory
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_breast_cancer as load_data



In [39]:

    
X, y = load_data(return_X_y=True)



In [40]:

    
rf = classifier_factory(RandomForestClassifier())



In [41]:

    
rf.plot_learning_curve(X, y)
plt.show()



In [ ]:



In [42]:

    
from scikitplot import plotters as skplt



In [43]:

    
rf = RandomForestClassifier()



In [44]:

    
skplt.plot_learning_curve(rf, X, y)
plt.show()



In [ ]:



In [ ]:



In [45]:

    
from sklearn.decomposition import PCA
from sklearn.datasets import load_digits as load_data
import scikitplot.plotters as skplt
import matplotlib.pyplot as plt



In [46]:

    
X, y = load_data(return_X_y=True)



In [47]:

    
pca = PCA(random_state=1)



In [48]:

    
pca.fit(X)









    Out[48]:





PCA(copy=True, iterated_power='auto', n_components=None, random_state=1,
  svd_solver='auto', tol=0.0, whiten=False)



In [49]:

    
skplt.plot_pca_2d_projection(pca, X, y)
plt.show()



In [ ]:



In [ ]:



In [50]:

    
from sklearn.decomposition import PCA
from sklearn.datasets import load_digits as load_data
import scikitplot.plotters as skplt
import matplotlib.pyplot as plt



In [51]:

    
X, y = load_data(return_X_y=True)



In [52]:

    
pca = PCA(random_state=1)



In [53]:

    
pca.fit(X)









    Out[53]:





PCA(copy=True, iterated_power='auto', n_components=None, random_state=1,
  svd_solver='auto', tol=0.0, whiten=False)



In [54]:

    
skplt.plot_pca_component_variance(pca)
plt.show()



In [ ]:



In [ ]:



In [55]:

    
from __future__ import absolute_import
import matplotlib.pyplot as plt
from scikitplot import classifier_factory
from sklearn.naive_bayes import GaussianNB
from sklearn.datasets import load_digits as load_data



In [56]:

    
X, y = load_data(return_X_y=True)



In [57]:

    
nb = classifier_factory(GaussianNB())



In [58]:

    
nb.plot_precision_recall_curve(X, y, random_state=1)
plt.show()



In [ ]:



In [ ]:



In [59]:

    
from __future__ import absolute_import
import matplotlib.pyplot as plt
from scikitplot import classifier_factory
from sklearn.naive_bayes import GaussianNB
from sklearn.datasets import load_digits as load_data



In [60]:

    
X, y = load_data(return_X_y=True)



In [61]:

    
nb = classifier_factory(GaussianNB())



In [62]:

    
nb.plot_roc_curve(X, y, random_state=1)
plt.show()



In [ ]:



In [63]:

    
from scikitplot import plotters as skplt



In [64]:

    
nb = GaussianNB()



In [65]:

    
nb = nb.fit(X, y)



In [66]:

    
probas = nb.predict_proba(X)



In [67]:

    
skplt.plot_roc_curve(y_true=y, y_probas=probas)
plt.show()



In [ ]:



In [ ]:



In [ ]:



In [68]:

    
from __future__ import absolute_import
import matplotlib.pyplot as plt
from scikitplot import clustering_factory
from sklearn.cluster import KMeans
from sklearn.datasets import load_iris as load_data



In [69]:

    
X, y = load_data(return_X_y=True)



In [70]:

    
kmeans = clustering_factory(KMeans(n_clusters=4, random_state=1))



In [71]:

    
kmeans.plot_silhouette(X)
plt.show()



In [ ]:



In [ ]: