These problems relate to the Python package Tensorflow. We will again use the famous iris data set. Save your work as a single Jupyter notebook file in a GitHub repository.
Use Tensorflow to create a model to predict the species of Iris from a flower's sepal width, sepal length, petal width, and petal length.
Split the data set into a training set and a testing set. You should investigate the best way to do this, and list any online references used in your notebook. If you wish to, you can write some code to randomly separate the data on the fly.
Use the testing set to train your model.
Use the testing set to test your model, clearly calculating and displaying the error rate.
You can find detailed solution in Iris-Keras.ipynb which is Jupyter notebook file.
Due to numerous Python libraries used like numpy, pandas, keras and Tensorflow, you may encounter dependancy problems. If you do, try to recreate my working enviroment by running pip3 install -r requirements.txt.