In [1]:
# Installing Theano
# pip install --upgrade --no-deps git+git://github.com/Theano/Theano.git
# Installing Tensorflow
# pip install tensorflow
# Installing Keras
# pip install --upgrade keras
In [1]:
# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('./Artificial_Neural_Networks/Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values
In [3]:
print (X.shape)
X
Out[3]:
In [4]:
print (y.shape)
y
Out[4]:
In [2]:
# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X_1 = LabelEncoder()
X[:, 1] = labelencoder_X_1.fit_transform(X[:, 1])
labelencoder_X_2 = LabelEncoder()
X[:, 2] = labelencoder_X_2.fit_transform(X[:, 2])
onehotencoder = OneHotEncoder(categorical_features = [1])
X = onehotencoder.fit_transform(X).toarray()
X = X[:, 1:]
In [6]:
print (X.shape)
X
Out[6]:
In [7]:
print (y.shape)
y
Out[7]:
In [3]:
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
In [4]:
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
In [5]:
# Importing the Keras libraries and packages
import keras
from keras.models import Sequential
from keras.layers import Dense
In [11]:
# Initialising the ANN
classifier = Sequential()
In [12]:
# Adding the input layer and the first hidden layer
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu', input_dim = 11))
# Adding the second hidden layer
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu'))
# Adding the output layer
classifier.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
In [13]:
# Compiling the ANN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
# Fitting the ANN to the Training set
classifier.fit(X_train, y_train, batch_size = 10, epochs = 100)
Out[13]:
In [14]:
y_pred = classifier.predict(X_test)
y_pred = (y_pred > 0.5)
In [15]:
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
In [16]:
cm
Out[16]:
In [7]:
# Evaluating the ANN
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import cross_val_score
from keras.models import Sequential
from keras.layers import Dense
def build_classifier():
classifier = Sequential()
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu', input_dim = 11))
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu'))
classifier.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
return classifier
classifier = KerasClassifier(build_fn = build_classifier, batch_size = 10, epochs = 100)
accuracies = cross_val_score(estimator = classifier, X = X_train, y = y_train, cv = 10, n_jobs = -1)
mean = accuracies.mean()
variance = accuracies.std()
In [ ]:
# Improving the ANN
# Dropout Regularization to reduce overfitting if needed
# Tuning the ANN
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import GridSearchCV
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
def build_classifier(optimizer):
classifier = Sequential()
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu', input_dim = 11))
# classifier.add(Dropout(p = 0.1))
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu'))
# classifier.add(Dropout(p = 0.1))
classifier.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
classifier.compile(optimizer = optimizer, loss = 'binary_crossentropy', metrics = ['accuracy'])
return classifier
classifier = KerasClassifier(build_fn = build_classifier)
parameters = {'batch_size': [25, 32],
'epochs': [100, 500],
'optimizer': ['adam', 'rmsprop']}
grid_search = GridSearchCV(estimator = classifier,
param_grid = parameters,
scoring = 'accuracy',
cv = 10)
grid_search = grid_search.fit(X_train, y_train)
best_parameters = grid_search.best_params_
best_accuracy = grid_search.best_score_
Drop out regularization: A solution for overfitting - high variance
Using Dropout() argument:
p: the fraction of the input units you want to drop/disable at each iteration. For example: if we have 10 neurons, p=0.1 (10%), this means at each iteration, 1 neuron will be disabled.