{"id":267,"date":"2021-09-24T21:52:55","date_gmt":"2021-09-24T21:52:55","guid":{"rendered":"https:\/\/www.kindsonthegenius.com\/data-science\/?p=267"},"modified":"2021-09-30T10:17:38","modified_gmt":"2021-09-30T10:17:38","slug":"class-6-introduction-to-classification","status":"publish","type":"post","link":"https:\/\/www.kindsonthegenius.com\/data-science\/class-6-introduction-to-classification\/","title":{"rendered":"Class 6 – Introduction to Classification"},"content":{"rendered":"

This would be class 6 of our complete data science for beginner series. In this class, we would apply all we’ve learnt to actually perform an analysis: Building a Classifier<\/p>\n

We would cover the following sub-topics:<\/p>\n

    \n
  1. What is Classification?<\/a><\/li>\n
  2. Building an NB Classifier<\/a><\/li>\n
  3. Evaluation Metrics – TP, FP, TN, FN<\/a><\/li>\n
  4. Evaluation Metrics – Accuracy, Precision, Sensitivity and Specificity<\/a><\/li>\n<\/ol>\n

     <\/p>\n

    1. What is Classification<\/strong><\/h4>\n

    As the name suggests, classification is the process of predicting a category from measured values of the attributes. You can remember the iris dataset from Class 1. In the iris dataset, we have 4 attributes (Sepal Length, Sepal Width, Petal Length, and Petal Width). Given this set of attribute, the record can be classified as 1 of 3 classes of iris (Setosa, Virginica and Versicolor).<\/p>\n

    Classification under under set of machine learning approaches called Supervised Learning. And generally, one we have a dataset, the task would be to determine the function that maps the inputs(attributes) to the outputs (classes). This is what we call the model (this mapping between input and output).<\/p>\n

    More topics on classification can be found here:<\/p>\n

     <\/p>\n

    2. Building a Classifier<\/strong><\/h4>\n

    As usual, we would follow 5 steps to build and test our classifier:<\/p>\n

    Step 1<\/strong> – Import the necessary modules
    \n<\/p>\n

    #1. Import the necessary modules<\/span>\r\nimport<\/span> sklearn.datasets<\/span> as<\/span> ds<\/span>\r\nimport<\/span> pandas<\/span> as<\/span> pd<\/span>\r\nimport<\/span> numpy<\/span> as<\/span> np<\/span>\r\n<\/pre>\n
     <\/p>\n
    Step 2<\/strong> – Obtain your dataset
    \n<\/p>\n
    #2. Obtain and prepare your datase<\/span>\r\nbc_array =<\/span> ds.<\/span>load_breast_cancer()\r\n\r\nfeatures =<\/span> bc_array['data'<\/span>]\r\nclasses =<\/span> bc_array['target'<\/span>]\r\nfeature_names =<\/span> bc_array['feature_names'<\/span>]\r\ncolumn_names =<\/span> np.<\/span>append(feature_columns_names,'Class'<\/span>)\r\nbc_df =<\/span> pd.<\/span>DataFrame(data =<\/span> np.<\/span>c_[features, classes], columns =<\/span> column_names)\r\n<\/pre>\n
     <\/p>\n
    Step 3<\/strong> – Split the Dataset into Train and Test Data<\/p>\n
    So now, we need to split out dataset into train and test data sets.<\/p>\n
    #3. Split your dataset into test and train<\/span>\r\nfrom<\/span> sklearn.model_selection<\/span> import<\/span> train_test_split\r\nXtrain, Xtest, Ytrain, Ytest =<\/span> \r\ntrain_test_split(bc_df[feature_names], bc_df['Class'<\/span>], test_size =<\/span> 0.3<\/span>, random_state=<\/span>50<\/span>)\r\n<\/pre>\n
     <\/p>\n
    Step\u00a0 4<\/strong> – Build the Model<\/p>\n
    We would build the model using Naive Bayes algorithm<\/p>\n
    #4. Build the Model<\/span>\r\nfrom<\/span> sklearn.naive_bayes<\/span> import<\/span> GaussianNB\r\ngnb =<\/span> GaussianNB()\r\nmodel =<\/span> gnb.<\/span>fit(Xtrain, Ytrain)\r\n<\/pre>\n
     <\/p>\n
    Step\u00a0 5<\/strong> – Check Model Accuracy<\/p>\n
    To see the model performance, we would use the model to make predictions based on the test dataset.
    \n<\/p>\n
    #5. Check Model Accuracy<\/span>\r\nfrom<\/span> sklearn.metrics<\/span> import<\/span> accuracy_score\r\ny_pred =<\/span> gnb.<\/span>predict(Xtest)\r\nprint<\/span>(accuracy_score(Ytest, y_pred))\r\n<\/pre>\n
    The above would display the accuracy score. For me it gave<\/p>\n
    \n
    \n
    \n
    \n
    \n
    0.935672514619883<\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
     <\/p>\n
    3. Evaluation Metrics – TP, FP, TN, FN<\/strong><\/h4>\n
    Although we have gotten the accuracy of our classifier, we still need to calculate other metrics that explain the classifier performance. The following are the metrics of interest.<\/p>\n
    \n
    \n
    \n
    \n
    You already know about data splitting from Class 5<\/a>. You can review it.<\/p>\n