Assessment - MODULE 4

Choose the appropriate option

• Which of the following approaches is used for text classification?

1. Rule-based approach

2. Machine-based approach

3. Hybrid Approaches

4. All of the above

• The target variable for the classification problem should be a

1. Quantitative data

2. Qualitative data

3. No target variable

4. None of the above

• Logistic regression uses ________________ function

1. Softmax function

2. Logistic Function

3. Relu Activation Function

4. All of the mentioned

• The output value of logistic regression like between?

1. –α to +α

2. 0 to 1

3. -1 to +1

4. Both A & C

• Support vector machines uses ____________________ to construct margins

1. Support Vectors

2. Hyper Plane

3. Regression line

4. None of the above

Fill in the spaces with appropriate answers

1. True Negative refers to the ratio of negatives correctly predicted from all the false labels. 

2. True Positive is the proportion of true positives out of predicted positives. 

3. F1 Score is the harmonic means of precision and recall.

4. What is accuracy?  Accuracy is defined as the total number of correct classifications divided by the total number of classifications. 

5. What is Sensitivity?  The total number of positive results how many positives were correctly predicted by the model.

True or False

• •  Logistic regression is used for regression tasks.

1. 1. True

   2. False (used for classification tasks, not regression tasks )

• Accuracy is not the best metric for classification problem statements.

  1. True

  2. False

•  We need to perform data cleaning before we pass the text data into the machine learning algorithm.

  1. True

  2. False
     
     

• ROC helps us to choose the best model amongst the models for which we have plotted the ROC curves.

  1. True

  2. False

• Kernel function in SVM is to compute in a higher-dimensional space without calculating the new coordinates in that higher dimension.

  1. True

  2. False

Programming Assignment 

Using the data from the below URL.

https://www.kaggle.com/balaka18/email-spam-classification-dataset-csv?select=emails.csv

Links to an external site.

By referring to the code used in tasks, perform the following tasks on the above text.

• Text cleaning

• Feature Extraction using TF-IDF

• Build the Machine Learning model

• Evaluate the performance on the Test set

• Pickle the Model

• Create a UI for the Model on Streamlit