4. Regression and Classification Models

Activity 4.01: Creating a Multi-Layer ANN with TensorFlow

Solution:

1. Open a new Jupyter notebook to implement this activity.
2. Import the TensorFlow and pandas libraries:

   import tensorflow as tf
   import pandas as pd

3. Load in the dataset using the pandas read_csv function:

   df = pd.read_csv('superconductivity.csv')

   Note

   Make sure you change the path (highlighted) to the CSV file based on its location on your system. If you're running the Jupyter notebook from the same directory where the CSV file is stored, you can run the preceding code without any modification.

4. Drop the date column and drop any rows that have null values:

   df.dropna(inplace=True)

5. Create target and feature datasets:

   target = df['critical_temp']
   features = df.drop('critical_temp', axis=1)

6. Rescale the feature dataset:

   from sklearn.preprocessing import StandardScaler
   scaler = StandardScaler()
   feature_array = scaler.fit_transform...