Fitting ANN model to my dataset

Question

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

#Importing Dataset

dataset = pd.read_csv('C:/Users/Rupali Singh/Desktop/ML A-Z/Machine Learning A-Z Template Folder/Part 8 - Deep Learning/Section 39 - Artificial Neural Networks (ANN)/Churn_Modelling.csv')
print(dataset)
X = dataset.iloc[:, [3, 13]].values
Y = dataset.iloc[:, 13].values
print(X)

#Categorical Data

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder1 = LabelEncoder()
X[:, 1] = labelencoder1.fit_transform(X[:, 1])
try:
    labelencoder2 = LabelEncoder()
    X[:, 2] = labelencoder2.fit_transform(X[:, 2])
except IndexError: pass

#Dummy Variable
onehotencoder = OneHotEncoder(categorical_features=[1])
X = onehotencoder.fit_transform(X).toarray()

#Splitting the dataset into 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)
print(Y_test)

#Feature Scaling

from sklearn.preprocessing import StandardScaler
feature_scaling = StandardScaler()
X_train = feature_scaling.fit_transform(X_train)
X_test = feature_scaling.transform(X_test)
print(X_train)

#Importing Keras libraries and packages

import keras
from keras.models import Sequential
from keras.layers import Dense

#Initialising the ANN

classifier = Sequential()

#Adding the input layer and hidden layer
classifier.add(Dense(input_dim=11, units=6, kernel_initializer='uniform', activation='relu'))

#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'))

#Compiling the ANN(Applying Stochastic Gradient)
classifier.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

#Fitting ANN to training set
classifier.fit(X_train, Y_train, batch_size=10, nb_epoch=100)
# predicting the test result
Y_pred = classifier.predict(X_test)
Y_pred = (Y_pred > 0.5)


# Making the confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)

I am trying to fit the ANN model to my dataset, after preprocessing of data and importing the keras library, the following error comes during model fitting.

Traceback (most recent call last):
  File "<input>", line 2, in <module>
  File "C:\Users\Rupali Singh\PycharmProjects\Machine_Learning\venv\lib\site-packages\keras\engine\training.py", line 952, in fit
    batch_size=batch_size)
  File "C:\Users\Rupali Singh\PycharmProjects\Machine_Learning\venv\lib\site-packages\keras\engine\training.py", line 751, in _standardize_user_data
    exception_prefix='input')
  File "C:\Users\Rupali Singh\PycharmProjects\Machine_Learning\venv\lib\site-packages\keras\engine\training_utils.py", line 138, in standardize_input_data
    str(data_shape))
ValueError: Error when checking input: expected dense_1_input to have shape (11,) but got array with shape (3,)

I cannot understand what is wrong, please help.

Answer 1

You ANN is expecting an input of size 11 as you specified with the parmaters input_dim

classifier.add(Dense(input_dim=11, units=6, kernel_initializer='uniform', activation='relu'))

But your training set is sending array of size 3. It's probably due to tour dummy variables :

#Dummy Variable
onehotencoder = OneHotEncoder(categorical_features=[1])
X = onehotencoder.fit_transform(X).toarray()

you can set your ANN to get correct input:

classifier.add(Dense(input_dim=3, units=6, kernel_initializer='uniform', activation='relu'))

Answer 2

Adding to @vico 's answer:

In order to use binary crossentropy loss you need a one hot encoded target variable. Your output layer, instead, has only one node.

Answer 3

Thanks everyone for your help. The problem was with pre processing of my data. And after using the labelencoder and onehotencoder, I did'nt update my X array(Independent Variable).

#Importing Dataset

dataset = pd.read_csv('C:/Users/Rupali Singh/Desktop/ML A-Z/Machine Learning A-Z Template Folder/Part 8 - Deep Learning/Section 39 - Artificial Neural Networks (ANN)/Churn_Modelling.csv')
print(dataset)
X = dataset.iloc[:, 3:13].values
Y = dataset.iloc[:, 13].values
print(X)

#Categorical Data

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder1 = LabelEncoder()
X[:, 1] = labelencoder1.fit_transform(X[:, 1])
labelencoder2 = LabelEncoder()
X[:, 2] = labelencoder2.fit_transform(X[:, 2])

#Dummy Variable
onehotencoder = OneHotEncoder(categorical_features=[1])
X = onehotencoder.fit_transform(X).toarray()
X = X[:, 1:]   #Updating X