Dummy data for classification



In [56]:

    
import seaborn as sns 
import matplotlib.pyplot as plt

%matplotlib inline

from sklearn.datasets import make_blobs

data, labels = make_blobs(n_features=2, centers=2,cluster_std=2,random_state=3)


plt.scatter(data[:,0], data[:,1], c = labels, cmap='coolwarm');

Attempt to Classify Data



In [59]:

    
#Import LinearSVC
from sklearn.svm import LinearSVC

#Create instance of Support Vector Classifier
svc = LinearSVC()

#Fit estimator to 70% of the data
svc.fit(data[:70], labels[:70])

#Predict final 30%
y_pred = svc.predict(data[70:])

#Establish true y values
y_true = labels[70:]

Metrics

Precision Score

TP - True Positives
FP - False Positives

Precision - Accuracy of positive predictions.
Precision = TP/(TP + FP)



In [74]:

    
from sklearn.metrics import precision_score

print("Precision score: {}".format(precision_score(y_true,y_pred)))









    



Precision score: 1.0

Recall Score

FN - False Negatives

Recall (aka sensitivity or true positive rate): Fraction of positives That were correctly identified.
Recall = TP/(TP+FN)



In [75]:

    
from sklearn.metrics import recall_score

print("Recall score: {}".format(recall_score(y_true,y_pred)))









    



Recall score: 0.9333333333333333

Accuracy Score



In [62]:

    
from sklearn.metrics import accuracy_score

print("Accuracy score: {}".format(accuracy_score(y_true,y_pred)))









    



Accuracy score: 0.9666666666666667

Confusion Matrix



In [67]:

    
from sklearn.metrics import confusion_matrix
import pandas as pd

confusion_df = pd.DataFrame(confusion_matrix(y_true,y_pred),
             columns=["Predicted Class " + str(class_name) for class_name in [0,1]],
             index = ["Class " + str(class_name) for class_name in [0,1]])

print(confusion_df)









    



         Predicted Class 0  Predicted Class 1
Class 0                 15                  0
Class 1                  1                 14

Classification Report



In [68]:

    
from sklearn.metrics import classification_report

print(classification_report(y_true,y_pred))









    



             precision    recall  f1-score   support

          0       0.94      1.00      0.97        15
          1       1.00      0.93      0.97        15

avg / total       0.97      0.97      0.97        30

F1 Score



In [72]:

    
from sklearn.metrics import f1_score

print("F1 Score: {}".format(f1_score(y_true,y_pred)))









    



F1 Score: 0.9655172413793104

Accuracy Score



In [62]:

    
from sklearn.metrics import accuracy_score

print("Accuracy score: {}".format(accuracy_score(y_true,y_pred)))









    



Accuracy score: 0.9666666666666667

Metric Curves



In [ ]:

    
from sklearn.metrics import precision_recall_curve

precisions,recalls, thresholds



In [ ]:

Other classification metrics available from sklearn.metrics

auc
average_precision_score
brier_score_loss
cohen_kappa_score
dcg_score
fbeta_score
hamming_loss
hinge_loss
jaccard_similarity_score
loss..matthews_corrcoef
precision_recall_curve
precision_recall_fscore_support
roc_auc_score
roc_curve
zero_one_loss

sklearn.metrics also offers Regression Metrics, Model Selection Scorer, Multilabel ranking metrics, Clusterin Metrics, Biclustering metrics, and Pairwise metrics.



In [ ]: