5. Classification Models

Activity 5.01: Building a Character Recognition Model with TensorFlow

Solution:

1. Open a new Jupyter notebook.
2. Import the pandas library and use pd as the alias:

   import pandas as pd

3. Create a variable called file_url that contains the URL to the dataset:

   file_url = 'https://raw.githubusercontent.com/PacktWorkshops'\
             '/The-TensorFlow-Workshop/master/Chapter05'\
             '/dataset/letter-recognition.data'

4. Load the dataset into a DataFrame() function called data using read_csv() method, provide the URL to the CSV file, and set header=None as the dataset doesn't provide column names. Print the first five rows using head() method.

   data = pd.read_csv(file_url, header=None)
   data.head()

   The expected output will be as follows:

   Figure 5.42: First five rows of the data

   You can see that the dataset contains 17 columns...