I have the below code which works perfectly for a neural network. I know I need the confusion matrix library to find the false positive and false negative rates but I'm not sure how to do it as I'm no expert in programming. Can someone help please?
import pandas as pd
from sklearn import preprocessing
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Dense
# read the csv file and convert into arrays for the machine to process
df = pd.read_csv('dataset_ori.csv')
dataset = df.values
# split the dataset into input features and the feature to predict
X = dataset[:,0:7]
Y = dataset[:,7]
# scale the dataset using sigmoid function min_max_scaler so that all the input features lie between 0 and 1
min_max_scaler = preprocessing.MinMaxScaler()
# store the dataset into an array
X_scale = min_max_scaler.fit_transform(X)
# split the dataset into 30% testing and the rest to train
X_train, X_val_and_test, Y_train, Y_val_and_test = train_test_split(X_scale, Y, test_size=0.3)
# split the val_and_test size equally to the validation set and the test set.
X_val, X_test, Y_val, Y_test = train_test_split(X_val_and_test, Y_val_and_test, test_size=0.5)
# specify the sequential model and describe the layers that will form architecture of the neural network
model = Sequential([Dense(7, activation='relu', input_shape=(7,)), Dense(32, activation='relu'), Dense(5, activation='relu'), Dense(1, activation='sigmoid'),])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
# training the data
hist = model.fit(X_train, Y_train, batch_size=32, epochs=100, validation_data=(X_val, Y_val))
# to find the accuracy of the mf the classifier
scores = model.evaluate(X_test, Y_test)
print("Accuracy: %.2f%%" % (scores[1]*100))
This is the code provided in the answer below. response, model are both highlighted with red for unreslove references
from keras import models
from keras.layers import Dense, Dropout
from keras.utils import to_categorical
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from keras.models import Sequential
from keras.layers import Dense, Activation
from sklearn import metrics
from sklearn.preprocessing import StandardScaler
# read the csv file and convert into arrays for the machine to process
df = pd.read_csv('dataset_ori.csv')
dataset = df.values
# split the dataset into input features and the feature to predict
X = dataset[:,0:7]
Y = dataset[:,7]
# Splitting into Train and Test Set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(dataset,
response,
test_size = 0.2,
random_state = 0)
# Initialising the ANN
classifier = Sequential()
# Adding the input layer and the first hidden layer
classifier.add(Dense(units = 10, kernel_initializer = 'uniform', activation = 'relu', input_dim =7 ))
model.add(Dropout(0.5))
# Adding the second hidden layer
classifier.add(Dense(units = 10, kernel_initializer = 'uniform', activation = 'relu'))
model.add(Dropout(0.5))
# Adding the output layer
classifier.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
# Compiling the ANN
classifier.compile(optimizer = 'adam', loss = 'sparse_categorical_crossentropy', metrics = ['accuracy'])
# Fitting the ANN to the Training set
classifier.fit(X_train, y_train, batch_size = 10, epochs = 20)
# Train model
scaler = StandardScaler()
classifier.fit(scaler.fit_transform(X_train.values), y_train)
# Summary of neural network
classifier.summary()
# Predicting the Test set results & Giving a threshold probability
y_prediction = classifier.predict_classes(scaler.transform(X_test.values))
print ("\n\naccuracy" , np.sum(y_prediction == y_test) / float(len(y_test)))
y_prediction = (y_prediction > 0.5)
#Let's see how our model performed
from sklearn.metrics import classification_report
print(classification_report(y_test, y_prediction))
Your input to confusion_matrix must be an array of int not one hot encodings.
# Predicting the Test set results
y_pred = model.predict(X_test)
y_pred = (y_pred > 0.5)
matrix = metrics.confusion_matrix(y_test.argmax(axis=1), y_pred.argmax(axis=1))
Below output would have come in that manner so by giving a probability threshold .5 will transform this to Binary.
output(y_pred):
[0.87812372 0.77490434 0.30319547 0.84999743]
The sklearn.metrics.accuracy_score(y_true, y_pred) method defines y_pred as:
y_pred : 1d array-like, or label indicator array / sparse matrix. Predicted labels, as returned by a classifier.
Which means y_pred has to be an array of 1's or 0's (predicated labels). They should not be probabilities.
the root cause of your error is a theoretical and not computational issue: you are trying to use a classification metric (accuracy) in a regression (i.e. numeric prediction) model (Neural Logistic Model), which is meaningless.
Just like the majority of performance metrics, accuracy compares apples to apples (i.e true labels of 0/1 with predictions again of 0/1); so, when you ask the function to compare binary true labels (apples) with continuous predictions (oranges), you get an expected error, where the message tells you exactly what the problem is from a computational point of view:
Classification metrics can't handle a mix of binary and continuous target
Despite that the message doesn't tell you directly that you are trying to compute a metric that is invalid for your problem (and we shouldn't actually expect it to go that far), it is certainly a good thing that scikit-learn at least gives you a direct and explicit warning that you are attempting something wrong; this is not necessarily the case with other frameworks - see for example the behavior of Keras in a very similar situation, where you get no warning at all, and one just ends up complaining for low "accuracy" in a regression setting...
from keras import models
from keras.layers import Dense, Dropout
from keras.utils import to_categorical
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from keras.models import Sequential
from keras.layers import Dense, Activation
from sklearn.cross_validation import train_test_split
from sklearn import metrics
from sklearn.cross_validation import KFold, cross_val_score
from sklearn.preprocessing import StandardScaler
# read the csv file and convert into arrays for the machine to process
df = pd.read_csv('dataset_ori.csv')
dataset = df.values
# split the dataset into input features and the feature to predict
X = dataset[:,0:7]
Y = dataset[:,7]
# Splitting into Train and Test Set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(dataset,
response,
test_size = 0.2,
random_state = 0)
# Initialising the ANN
classifier = Sequential()
# Adding the input layer and the first hidden layer
classifier.add(Dense(units = 10, kernel_initializer = 'uniform', activation = 'relu', input_dim =7 ))
model.add(Dropout(0.5))
# Adding the second hidden layer
classifier.add(Dense(units = 10, kernel_initializer = 'uniform', activation = 'relu'))
model.add(Dropout(0.5))
# Adding the output layer
classifier.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
# Compiling the ANN
classifier.compile(optimizer = 'adam', loss = 'sparse_categorical_crossentropy', metrics = ['accuracy'])
# Fitting the ANN to the Training set
classifier.fit(X_train, y_train, batch_size = 10, epochs = 20)
# Train model
scaler = StandardScaler()
classifier.fit(scaler.fit_transform(X_train.values), y_train)
# Summary of neural network
classifier.summary()
# Predicting the Test set results & Giving a threshold probability
y_prediction = classifier.predict_classes(scaler.transform(X_test.values))
print ("\n\naccuracy" , np.sum(y_prediction == y_test) / float(len(y_test)))
y_prediction = (y_prediction > 0.5)
## EXTRA: Confusion Matrix Visualize
from sklearn.metrics import confusion_matrix,accuracy_score
cm = confusion_matrix(y_test, y_pred) # rows = truth, cols = prediction
df_cm = pd.DataFrame(cm, index = (0, 1), columns = (0, 1))
plt.figure(figsize = (10,7))
sn.set(font_scale=1.4)
sn.heatmap(df_cm, annot=True, fmt='g')
print("Test Data Accuracy: %0.4f" % accuracy_score(y_test, y_pred))
#Let's see how our model performed
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))