PYTHON MACHINE LEARNING: MACHINE LEARNING AND DEEP LEARNING FROM SCRATCH ILLUSTRATED WITH PYTHON, SCIKIT-LEARN, KERAS, THEANO AND TENSORFLOW by MOUBACHIR MADANI FADOUL

Author:MOUBACHIR MADANI FADOUL [MADANI FADOUL, MOUBACHIR]
Language: eng
Format: azw3
Published: 2020-05-29T16:00:00+00:00

Dropout is implemented in libraries such as Pytorch and TensorFlow by keeping the output of the randomly selected neurons as 0. That is, though the neuron exists, its output is overwritten as 0.

Chapter 5. Python Deep Learning - Implementations

This chapter of Deep learning uses data of a certain bank. The objective is to predict the customer churning or data attrition - which customers are likely to leave this bank service. We use small Dataset is that contains 10000 rows with 14 columns. We already installed an Anaconda distribution, and frameworks like TensorFlow, Theano and Keras. Keras is built on top of Theano and Tensorflow.

# Artificial Neural Network

# Installing Theano

pip install --upgrade theano

# Installing Tensorflow

pip install –upgrade tensorflow

# Installing Keras

pip install --upgrade keras

Step 1: Data preprocessing

In[]:

# Importing the libraries

import numpy as np

import matplotlib.pyplot as plt

import pandas as pd

# Importing the database

dataset = pd.read_csv('Churn_Modelling.csv')

Step 2

Matrices of the dataset features and the target variable have been created, which is column 14, labeled as “Exited”.

The initial look of data is as shown below −

In[]:

X = dataset.iloc[:, 3:13].values

Y = dataset.iloc[:, 13].values

X

Output

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.