ann.py

# Artificial Neural Network

# 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

# Part 1 - Data Preprocessing

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values

# 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:]

# 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)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

# Part 2 - Now let's make the ANN!

# Importing the Keras libraries and packages
import keras
from keras.models import Sequential
from keras.layers import Dense

# Part 3 - Making predictions and evaluating the model
classifier=Sequential()
classifier.add(Dense(output_dim=6,input_dim=11,activation='relu',init='uniform'))   #first hidden layer
classifier.add(Dense(output_dim=6,activation='relu',init='uniform'))   #second hidden layer
classifier.add(Dense(output_dim=1,activation='sigmoid',init='uniform'))   #second hidden layer



# working on weights and cost fucntion
classifier.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])



classifier.fit(X_train,y_train,batch_size=10,nb_epoch=50)
# Predicting the Test set results
y_pred = classifier.predict(X_test)   #returns probability
y_pred = (y_pred > 0.5)             #returns true or false


# Predicting a single new observation
"""Predict if the customer with the following informations will leave the bank:
Geography: France
Credit Score: 600
Gender: Male
Age: 40
Tenure: 3
Balance: 60000
Number of Products: 2
Has Credit Card: Yes
Is Active Member: Yes
Estimated Salary: 50000"""
new_prediction = classifier.predict(sc.transform(np.array([[0.0, 0, 600, 1, 40, 3, 60000, 2, 1, 1, 50000]])))
new_prediction = (new_prediction > 0.5)


# Making the Confusion Matrix to validate....... total correct/ total models = accuracy
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)