Python Deep Learning Cookbook

How to do it...

1. Start with importing all libraries as follows:

import numpy as npimport pandas as pdfrom sklearn.preprocessing import LabelEncoderfrom keras.models import Sequentialfrom keras.layers import Densefrom keras.callbacks import EarlyStopping

2. Next, we load the dataset:

dataframe = pandas.read_csv("Data/sonar.all-data", header=None)data = dataframe.values

3. Let's split the labels from the features:

X = data[:,0:60].astype(float)y = data[:,60]

4. Currently, the labels are strings. We need to binarize them for our network:

encoder = LabelEncoder()encoder.fit(y)y = encoder.transform(y)

5. Let's define a simple network with one hidden layer:

model = Sequential()model.add(Dense(32, input_dim=60, activation='relu'))model.add(Dense(1, ...