Precision and Recall

In machine learning model, we have mentioned that, there is an important concept called metrics. However, for classifications problems, accuracy is one of the metrics. There are other important metrics.

In this exercise, we will test our model with new metrics: Precision and Recall

Please answer Questions

To help you understand precision and recall. Please answer questions below by searching and input your answers.

Question 1: What is your understanding of these terms: true postive, false postive, true negative, false negative?
Question 2: What are the relationships between those terms and precision or recall?
Please write down your answer by two simple methematical equation

Answer: Please double click the cell and input your answer here.



In [1]:

    
from sklearn import svm, datasets
from sklearn.model_selection import train_test_split
import numpy as np

Below is an example for how to get precision of your model

Attention : You need to finish one line of code to implement the whole example.



In [3]:

    
#Let's load iris data again
iris = datasets.load_iris()
X = iris.data
y = iris.target



In [4]:

    
# Let's split the data to training and testing data.
random_state = np.random.RandomState(0)
n_samples, n_features = X.shape
X = np.c_[X, random_state.randn(n_samples, 200 * n_features)]

# Limit to the two first classes, and split into training and test
X_train, X_test, y_train, y_test = train_test_split(X[y < 2], y[y < 2],
                                                    test_size=.5,
                                                    random_state=random_state)



In [5]:

    
# Create a simple classifier
classifier = svm.LinearSVC(random_state=random_state)



In [ ]:

    
# How could we fit the model? Please find your solutions from our example, and write down your code to fit the svm model 
# from training data.



In [6]:

    
# After you have fit the model, then we make predicions.
y_score = classifier.decision_function(X_test)

Get the average precision score, Run the cell below



In [ ]:

    
from sklearn.metrics import average_precision_score
average_precision = average_precision_score(y_test, y_score)

print('Average precision-recall score: {0:0.2f}'.format(
      average_precision))