Table of Contents

1. Challenge

   Practice Encoding Categorical Data

   Jupyter Guide

   To get started, open the file on the right entitled "Step 1...". You'll complete each task for Step 1 in that Jupyter Notebook file. Remember, you must run the cells (ctrl/cmd(⌘) + Enter) for each task before moving onto the next task in the Jupyter Notebook. Continue until you have completed all tasks in this step.

   ---

   Practice Encoding Categorical Data

   To review the concepts covered in this step, please refer to the One-hot Encoding module of the Convert Categorical Variables into Quantitative Variables course.

   Encoding categorical variables is important because it allows us to convert these variables into a format that can be understood by machine learning algorithms. In this step, we will practice encoding nominal and ordinal data using an ordinal encoding and one-hot encoding.

   In this hands-on practice, we will be encoding nominal and ordinal data using Pandas's Series.replace() method. We'll also use one-hot encoding. We will use Pandas's Pandas.get_dummies() function to perform one-hot encoding.

   ---

   Task 1.1: Load the Dataset and Visualize

   Load the dataset 'Qualitative_Data.csv' into a pandas DataFrame and display the first 5 rows of the data.

   🔍 Hint

   Use the pd.read_csv() function to load the dataset, and the DataFrame.head() method to display the first 5 rows. The file path is 'Qualitative_Data.csv'.

   🔑 Solution

   import pandas as pd
   
   df = pd.read_csv('Qualitative_Data.csv')
   print(df.head())
   

   ---

   Task 1.2: Ordinal Encoding without Overwriting

   Encode the 'Product Feedback' column using ordinal encoding and store the encoded values in a new column named 'Product Feedback Encoded'. The categories in the column are 'Positive', 'Neutral', and 'Negative'. Encode these as 2, 1, and 0 respectively.

   🔍 Hint

   Create a dictionary with the following mapping: {'Positive': 2, 'Neutral': 1, 'Negative': 0}. Use this dictionary with the Series.replace() method to create the new column.

   🔑 Solution

   feedback_dict = {'Positive': 2, 'Neutral': 1, 'Negative': 0}
   df['Product Feedback Encoded'] = df['Product Feedback'].replace(feedback_dict)
   

   ---

   Task 1.3: In-Place One-hot Encoding with Prefix

   Perform one-hot encoding on the 'Social Media Activity' column in the df DataFrame itself, adding a prefix to the new columns to identify them. Use the pd.get_dummies() function with an in-place update.

   🔍 Hint

   Use the pd.get_dummies() function with the columns=['Social Media Activity'] and prefix='SMA' arguments. The pd.get_dummies() function will return the DataFrame with the one-hot encoded columns, which should then replace the original df.

   🔑 Solution

   df = pd.get_dummies(df, columns=['Social Media Activity'], prefix='SMA')
   

   ---

   Task 1.4: Inspect the Updated DataFrame

   Print the first 5 rows of the updated DataFrame df with the one-hot encoded columns.

   🔍 Hint

   Use the DataFrame.head() method to print the first 5 rows of the updated DataFrame df.

   🔑 Solution

   print(df.head())