Scribd Logo
Upload

Welcome to Scribd!

  • 137 views

    Confusion Matrix

    Uploaded by

    retno
    This document discusses confusion matrices and their use in evaluating machine learning models. It defines true positives, false positives, false negatives, and true negatives. It then explains how to calculate several important evaluation metrics from a confusion matrix, including accuracy, misclassification rate, precision, recall, F1-score, and false positive rate. These metrics provide insights into a model's performance at classification tasks. The document also provides code examples for calculating these metrics using scikit-learn.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Confusion Matrix

    Uploaded by

    retno
    137 views5 pages
    This document discusses confusion matrices and their use in evaluating machine learning models. It defines true positives, false positives, false negatives, and true negatives. It then explains how to calculate several important evaluation metrics from a confusion matrix, including accuracy, misclassification rate, precision, recall, F1-score, and false positive rate. These metrics provide insights into a model's performance at classification tasks. The document also provides code examples for calculating these metrics using scikit-learn.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses confusion matrices and their use in evaluating machine learning models. It defines true positives, false positives, false negatives, and true negatives. It then explains how to calculate several important evaluation metrics from a confusion matrix, including accuracy, misclassification rate, precision, recall, F1-score, and false positive rate. These metrics provide insights into a model's performance at classification tasks. The document also provides code examples for calculating these metrics using scikit-learn.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    137 views5 pages

    Confusion Matrix

    Uploaded by

    retno
    This document discusses confusion matrices and their use in evaluating machine learning models. It defines true positives, false positives, false negatives, and true negatives. It then explains how to calculate several important evaluation metrics from a confusion matrix, including accuracy, misclassification rate, precision, recall, F1-score, and false positive rate. These metrics provide insights into a model's performance at classification tasks. The document also provides code examples for calculating these metrics using scikit-learn.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 5

    See discussions, stats, and author profiles for this publication at: https://www.researchgate.

    net/publication/355096788

    Confusion Matrix

    Research · October 2021

    CITATION READS

    1 8,334

    1 author:

    Zohreh Karimi
    Kharazmi University
    16 PUBLICATIONS   3 CITATIONS   

    SEE PROFILE

    Some of the authors of this publication are also working on these related projects:

    Data Cleaning Process View project

    All content following this page was uploaded by Zohreh Karimi on 06 October 2021.

    The user has requested enhancement of the downloaded file.


    Written by zohreh karimi(junior machine learning engineer)

    Confusion Matrix

    * The confusion matrix is a tool for predictive analysis In machine


    learning. In order to check the performance of a classification based
    machine learning model, the confusion matix is deployed.
    * Also we can say Confusion matrix is a summerized table of the
    number of correct and incorrect predictions yielded by a classifier (or
    a classification model) for binary classification tasks.
    * A Confusion matrix is an N x N matrix used for evaluating the
    performance of a classification model, where N is the number of target
    classes.
    By visualzing the confusion matrix, an individual could determine the
    accuracy of the model by observing the diagonal values for measuring
    the number of accurate classification.

    The confusion matrix is in the form of a square matrix whre the column
    represents the actual values and the row depicts the predicted value of
    the model and vica versa.

    1
    Written by zohreh karimi(junior machine learning engineer)

    • TP: True Positive: The actual value was positive and the model
    predicted a positive value

    • FP: False Positive: Your prediction is positive, and it is false. (Also


    known as the Type 1 error)

    • FN: False Negative: Your prediction is negative, and result it is also


    false. (Also known as the Type 2 error)

    • TN: True Negative: The actual value was negative and the model
    predicted a negative value

    1- Accuracy:

    Accuracy is a measure for how many correct predictions your model

    made for the complete test dataset. Accuracy is a good basic metric to
    measure the performance of the model. In unbalanced datasets, accuracy
    becomes a poor metric
    𝑇𝑃+𝑇𝑁
    accuracy=
    𝑇𝑃+𝑇𝑁+𝐹𝑃+𝐹𝑁

    2- Misclassification:
    𝐹𝑃+𝐹𝑁
    misclassification=
    𝑇𝑃+𝑇𝑁+𝐹𝑃+𝐹𝑁

    3- Precison
    Precison tells us how many of the correctly predicted case actually
    turned out to be positive. This would determine whether our model is
    reliable or not.

    2
    Written by zohreh karimi(junior machine learning engineer)

    Precison is a useful metric in case where False Pasitive is a higher


    concern than False Negative.
    𝑇𝑃
    Precision=
    𝑇𝑃+𝑇𝑁

    4- Recall(sensivity)
    Recall tells us how many of the actual positive cases we were able to
    predict correctly with our model.
    Recall is a useful metric in cases where False Negative trumps False
    Positive.
    𝑇𝑃
    Recall=
    𝑇𝑃+𝐹𝑁

    A higher recall means that most of the positive cases (TP+FN) will be
    labeled as positive(TP). This wil lead to a higher number of FP
    measurement and a lower overall accuracy.
    A low recall means that you have a high number of FN (should have
    been positive but labeled as negative). This means that you have more
    certainty if you found a positive case, this is like to be a true positive.

    5- F1-Score
    When we try to increase the precision of model , the recall grows down
    and vice-versa.
    F1-Score is a harmonic mean of Precison and Recall and so it gives a
    combined idea about these two metrics. It is maximum when precision
    is equal to recall.
    1
    F1-Score= 1 1
    +
    𝑟𝑒𝑐𝑎𝑙𝑙 𝑝𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛

    3
    Written by zohreh karimi(junior machine learning engineer)

    The interpretability of the F1-Score is poor, it means that we don't know


    what our classifier is maximising- precision or recall. So, we use it in
    combination with other evaluation metrics which gives us a complete
    picture of the result

    6-False Positive rate


    False positive rate is a measure for how many results get predicted as
    positive out of all the negative cases.
    𝐹𝑃
    FPR=
    𝑇𝑁+𝐹𝑃

    How to get these metrics in scikitlearn


    from sklearn.metrics import accuracy_score, precision_score,
    recall_score, f1_score
    # Accuracy
    accuracy_score(y_test, y_predicted)
    # Precision
    precision_score(y_test, y_predicted)
    # Recall
    recall_score(y_test, y_predicted)
    # F1-score
    f1_score(y_test, y_predicted)

    View publication stats

    You might also like