I am confused by the prediction given by WEKA for the trained model:
ARFF schema
#RELATION sportsArffWithEmpty
#ATTRIBUTE "annotation" {"DIFFERENT","SAME"}
#ATTRIBUTE "item_name" REAL
#ATTRIBUTE "brand" {"EMPTY","IGNORE","MATCHED","NOT_MATCH"}
#ATTRIBUTE "manufacturer" {"EMPTY","IGNORE","MATCHED","NOT_MATCH"}
#ATTRIBUTE "part_number" {"EMPTY","IGNORE","MATCHED","NOT_MATCH"}
#ATTRIBUTE "color" {"EMPTY","IGNORE","MATCHED","NOT_MATCH"}
#ATTRIBUTE "size" {"EMPTY","IGNORE","MATCHED","NOT_MATCH"}
Trained model
=== Run information ===
Scheme: weka.classifiers.functions.SimpleLogistic -I 0 -M 500 -H 50 -W 0.0
Relation: sportsArffWithEmpty
Instances: 263
Attributes: 7
annotation
item_name
brand
manufacturer
part_number
color
size
Test mode: user supplied test set: size unknown (reading incrementally)
=== Classifier model (full training set) ===
SimpleLogistic:
Class 0 :
-2 +
[color=MATCHED] * 1.15 +
[size=IGNORE] * 1.03 +
[size=MATCHED] * -0.56 +
[size=NOT_MATCH] * 1.12
Class 1 :
2 +
[color=MATCHED] * -1.15 +
[size=IGNORE] * -1.03 +
[size=MATCHED] * 0.56 +
[size=NOT_MATCH] * -1.12
Instance
#DATA
"SAME","0.632","MATCHED","NOT_MATCH","MATCHED","MATCHED","MATCHED"
Prediction given by WEKA
=== Predictions on test set ===
inst#,actual,predicted,error,prediction
1,2:SAME,2:SAME,,0.945
Personal calculation
The coefficient should be
-2 +
[color=MATCHED] * -1.15 +
[size=IGNORE] * -1.03 +
[size=MATCHED] * 0.56 +
[size=NOT_MATCH] * -1.12
= -2+ 1*-1.15 + 0*-1.03 + 1* 0.56 + 0* -1.12
= 1.41
So the output should be 1/(1+ e^-1.41) = 0.8037, but the prediction given by WEKA is 0.945
what is the problem here?
Why the trained model does not take item_name, brand etc. into consideration?
Answer to question 1
According to WEKA forum,
SimpleLogistic uses what’s called a symmetric model by Friedman et al.
(2000), “Additive logistic regression: A statistical view of boosting”,
Annals of Statistics 28(2). See page 354 in that paper.
So the answer of quesion 1 is calculated as e^1.41/(e^1.41 + e^ (-1.41)) = 0.94
Quesion
Why the trained model does not take item_name, brand etc. into consideration, is it related to my dataset's bias?
Related
This is the code I am implementing: I am using a subset of the CalTech256 dataset to classify images of 10 different kinds of animals. We will go over the dataset preparation, data augmentation and then steps to build the classifier.
def train_and_validate(model, loss_criterion, optimizer, epochs=25):
'''
Function to train and validate
Parameters
:param model: Model to train and validate
:param loss_criterion: Loss Criterion to minimize
:param optimizer: Optimizer for computing gradients
:param epochs: Number of epochs (default=25)
Returns
model: Trained Model with best validation accuracy
history: (dict object): Having training loss, accuracy and validation loss, accuracy
'''
start = time.time()
history = []
best_acc = 0.0
for epoch in range(epochs):
epoch_start = time.time()
print("Epoch: {}/{}".format(epoch+1, epochs))
# Set to training mode
model.train()
# Loss and Accuracy within the epoch
train_loss = 0.0
train_acc = 0.0
valid_loss = 0.0
valid_acc = 0.0
for i, (inputs, labels) in enumerate(train_data_loader):
inputs = inputs.to(device)
labels = labels.to(device)
# Clean existing gradients
optimizer.zero_grad()
# Forward pass - compute outputs on input data using the model
outputs = model(inputs)
# Compute loss
loss = loss_criterion(outputs, labels)
# Backpropagate the gradients
loss.backward()
# Update the parameters
optimizer.step()
# Compute the total loss for the batch and add it to train_loss
train_loss += loss.item() * inputs.size(0)
# Compute the accuracy
ret, predictions = torch.max(outputs.data, 1)
correct_counts = predictions.eq(labels.data.view_as(predictions))
# Convert correct_counts to float and then compute the mean
acc = torch.mean(correct_counts.type(torch.FloatTensor))
# Compute total accuracy in the whole batch and add to train_acc
train_acc += acc.item() * inputs.size(0)
#print("Batch number: {:03d}, Training: Loss: {:.4f}, Accuracy: {:.4f}".format(i, loss.item(), acc.item()))
# Validation - No gradient tracking needed
with torch.no_grad():
# Set to evaluation mode
model.eval()
# Validation loop
for j, (inputs, labels) in enumerate(valid_data_loader):
inputs = inputs.to(device)
labels = labels.to(device)
# Forward pass - compute outputs on input data using the model
outputs = model(inputs)
# Compute loss
loss = loss_criterion(outputs, labels)
# Compute the total loss for the batch and add it to valid_loss
valid_loss += loss.item() * inputs.size(0)
# Calculate validation accuracy
ret, predictions = torch.max(outputs.data, 1)
correct_counts = predictions.eq(labels.data.view_as(predictions))
# Convert correct_counts to float and then compute the mean
acc = torch.mean(correct_counts.type(torch.FloatTensor))
# Compute total accuracy in the whole batch and add to valid_acc
valid_acc += acc.item() * inputs.size(0)
#print("Validation Batch number: {:03d}, Validation: Loss: {:.4f}, Accuracy: {:.4f}".format(j, loss.item(), acc.item()))
# Find average training loss and training accuracy
avg_train_loss = train_loss/train_data_size
avg_train_acc = train_acc/train_data_size
# Find average training loss and training accuracy
avg_valid_loss = valid_loss/valid_data_size
avg_valid_acc = valid_acc/valid_data_size
history.append([avg_train_loss, avg_valid_loss, avg_train_acc, avg_valid_acc])
epoch_end = time.time()
print("Epoch : {:03d}, Training: Loss: {:.4f}, Accuracy: {:.4f}%, \n\t\tValidation : Loss : {:.4f}, Accuracy: {:.4f}%, Time: {:.4f}s".format(epoch, avg_train_loss, avg_train_acc*100, avg_valid_loss, avg_valid_acc*100, epoch_end-epoch_start))
# Save if the model has best accuracy till now
torch.save(model, dataset+'_model_'+str(epoch)+'.pt')
return model, history
# Load pretrained ResNet50 Model
resnet50 = models.resnet50(pretrained=True)
#resnet50 = resnet50.to('cuda:0')
# Freeze model parameters
for param in resnet50.parameters():
param.requires_grad = False
# Change the final layer of ResNet50 Model for Transfer Learning
fc_inputs = resnet50.fc.in_features
resnet50.fc = nn.Sequential(
nn.Linear(fc_inputs, 256),
nn.ReLU(),
nn.Dropout(0.4),
nn.Linear(256, num_classes), # Since 10 possible outputs
nn.LogSoftmax(dim=1) # For using NLLLoss()
)
# Convert model to be used on GPU
# resnet50 = resnet50.to('cuda:0')
# Change the final layer of ResNet50 Model for Transfer Learning
fc_inputs = resnet50.fc.in_features
resnet50.fc = nn.Sequential(
nn.Linear(fc_inputs, 256),
nn.ReLU(),
nn.Dropout(0.4),
nn.Linear(256, num_classes), # Since 10 possible outputs
nn.LogSoftmax(dienter code herem=1) # For using NLLLoss()
)
# Convert model to be used on GPU
# resnet50 = resnet50.to('cuda:0')`enter code here`
Error is this:
RuntimeError Traceback (most recent call
last) in ()
6 # Train the model for 25 epochs
7 num_epochs = 30
----> 8 trained_model, history = train_and_validate(resnet50, loss_func, optimizer, num_epochs)
9
10 torch.save(history, dataset+'_history.pt')
in train_and_validate(model,
loss_criterion, optimizer, epochs)
43
44 # Compute loss
---> 45 loss = loss_criterion(outputs, labels)
46
47 # Backpropagate the gradients
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in
call(self, *input, **kwargs)
539 result = self._slow_forward(*input, **kwargs)
540 else:
--> 541 result = self.forward(*input, **kwargs)
542 for hook in self._forward_hooks.values():
543 hook_result = hook(self, input, result)
~\Anaconda3\lib\site-packages\torch\nn\modules\loss.py in
forward(self, input, target)
202
203 def forward(self, input, target):
--> 204 return F.nll_loss(input, target, weight=self.weight, ignore_index=self.ignore_index, reduction=self.reduction)
205
206
~\Anaconda3\lib\site-packages\torch\nn\functional.py in
nll_loss(input, target, weight, size_average, ignore_index, reduce,
reduction) 1836 .format(input.size(0),
target.size(0))) 1837 if dim == 2:
-> 1838 ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index) 1839 elif dim == 4: 1840 ret = torch._C._nn.nll_loss2d(input, target,
weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes'
failed. at
C:\Users\builder\AppData\Local\Temp\pip-req-build-0i480kur\aten\src\THNN/generic/ClassNLLCriterion.c:97
This happens when there are either incorrect labels in your dataset, or the labels are 1-indexed (instead of 0-indexed). As from the error message, cur_target must be smaller than the total number of classes (10). To verify the issue, check the maximum and minimum label in your dataset. If the data is indeed 1-indexed, just minus one from all annotations and you should be fine.
Note, another possible reason is that there exists some -1 labels in the data. Some (esp older) datasets use -1 as indication of a wrong/dubious label. If you find such labels, just discard them.
I have a dataset of 1127 patients. My goal was to classify each patient to 0 or 1.
I have two different classifiers but with the same purpose - to classify the patient to 0 or 1.
I've run one classifier on 364 patients and the second classifier on the 763 patients.
for each classifier\group, I generated the ROC curve.
Now, I would like to combine the curves.
someone could guide me on how to do it?
I'm thinking of calculating the weighted FPR and TPR, but I'm not sure how to do it.
The number of FPR\TPR pairs is different between the curves (The first ROC curve based on 312 pairs and the second ROC curve based on 666 pairs).
Thanks!!!
Imports
import numpy as np
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt
Data generation
# simulate first dataset with 364 obs
df1 = \
pd.DataFrame(i for i in range(364))
df1['predict_proba_1'] = np.random.normal(0,1,len(df1))
df1['epsilon'] = np.random.normal(0,1,len(df1))
df1['true'] = (0.7*df1['epsilon'] < df1['predict_proba_1']) * 1
df1 = df1.drop(columns=[0, 'epsilon'])
# simulate second dataset with 763 obs
df2 = \
pd.DataFrame(i for i in range(763))
df2['predict_proba_2'] = np.random.normal(0,1,len(df2))
df2['epsilon'] = np.random.normal(0,1,len(df2))
df2['true'] = (0.7*df2['epsilon'] < df2['predict_proba_2']) * 1
df2 = df2.drop(columns=[0, 'epsilon'])
Quick look at generated data
df1
predict_proba_1 true
0 1.234549 1
1 -0.586544 0
2 -0.229539 1
3 0.132185 1
4 -0.411284 0
.. ... ...
359 -0.218775 0
360 -0.985565 0
361 0.542790 1
362 -0.463667 0
363 1.119244 1
[364 rows x 2 columns]
df2
predict_proba_2 true
0 0.278755 1
1 0.653663 0
2 -0.304216 1
3 0.955658 1
4 -1.341669 0
.. ... ...
758 1.359606 1
759 -0.605894 0
760 0.379738 0
761 1.571615 1
762 -1.102565 0
[763 rows x 2 columns]
Necessary functions
def show_ROCs(scores_list: list, ys_list: list, labels_list:list = None):
"""
This function plots a couple of ROCs. Corresponding labels are optional.
Parameters
----------
scores_list : list of array-likes with scorings or predicted probabilities.
ys_list : list of array-likes with ground true labels.
labels_list : list of labels to be displayed in plotted graph.
Returns
----------
None
"""
if len(scores_list) != len(ys_list):
raise Exception('len(scores_list) != len(ys_list)')
fpr_dict = dict()
tpr_dict = dict()
for x in range(len(scores_list)):
fpr_dict[x], tpr_dict[x], _ = roc_curve(ys_list[x], scores_list[x])
for x in range(len(scores_list)):
try:
plot_ROC(fpr_dict[x], tpr_dict[x], str(labels_list[x]) + ' AUC:' + str(round(auc(fpr_dict[x], tpr_dict[x]),3)))
except:
plot_ROC(fpr_dict[x], tpr_dict[x], str(x) + ' ' + str(round(auc(fpr_dict[x], tpr_dict[x]),3)))
plt.show()
def plot_ROC(fpr, tpr, label):
"""
This function plots a single ROC. Corresponding label is optional.
Parameters
----------
fpr : array-likes with fpr.
tpr : array-likes with tpr.
label : label to be displayed in plotted graph.
Returns
----------
None
"""
plt.figure(1)
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(fpr, tpr, label=label)
plt.xlabel('False positive rate')
plt.ylabel('True positive rate')
plt.title('ROC curve')
plt.legend(loc='best')
Plotting
show_ROCs(
[df1['predict_proba_1'], df2['predict_proba_2']],
[df1['true'], df2['true']],
['df1 with {} obs'.format(len(df1)), 'df2 with {} obs'.format(len(df2))]
)
I am building a neural network to learn to recognize handwritten digits from MNIST. I have confirmed that backpropagation calculates the gradients perfectly (gradient checking gives error < 10 ^ -10).
It appears that no matter how I train the weights, the cost function always tends towards around 3.24-3.25 (never below that, just approaching from above) and the training/test set accuracy is very low (around 11% for the test set). It appears that the h values in the end are all very close to 0.1 and to each other.
I cannot find why my program cannot produce better results. I was wondering if anyone could maybe take a look at my code and please tell me any reasons for this occurring. Thank you so much for all your help, I really appreciate it!
Here is my Python code:
import numpy as np
import math
from tensorflow.examples.tutorials.mnist import input_data
# Neural network has four layers
# The input layer has 784 nodes
# The two hidden layers each have 5 nodes
# The output layer has 10 nodes
num_layer = 4
num_node = [784,5,5,10]
num_output_node = 10
# 30000 training sets are used
# 10000 test sets are used
# Can be adjusted
Ntrain = 30000
Ntest = 10000
# Sigmoid Function
def g(X):
return 1/(1 + np.exp(-X))
# Forwardpropagation
def h(W,X):
a = X
for l in range(num_layer - 1):
a = np.insert(a,0,1)
z = np.dot(a,W[l])
a = g(z)
return a
# Cost Function
def J(y, W, X, Lambda):
cost = 0
for i in range(Ntrain):
H = h(W,X[i])
for k in range(num_output_node):
cost = cost + y[i][k] * math.log(H[k]) + (1-y[i][k]) * math.log(1-H[k])
regularization = 0
for l in range(num_layer - 1):
for i in range(num_node[l]):
for j in range(num_node[l+1]):
regularization = regularization + W[l][i+1][j] ** 2
return (-1/Ntrain * cost + Lambda / (2*Ntrain) * regularization)
# Backpropagation - confirmed to be correct
# Algorithm based on https://www.coursera.org/learn/machine-learning/lecture/1z9WW/backpropagation-algorithm
# Returns D, the value of the gradient
def BackPropagation(y, W, X, Lambda):
delta = np.empty(num_layer-1, dtype = object)
for l in range(num_layer - 1):
delta[l] = np.zeros((num_node[l]+1,num_node[l+1]))
for i in range(Ntrain):
A = np.empty(num_layer-1, dtype = object)
a = X[i]
for l in range(num_layer - 1):
A[l] = a
a = np.insert(a,0,1)
z = np.dot(a,W[l])
a = g(z)
diff = a - y[i]
delta[num_layer-2] = delta[num_layer-2] + np.outer(np.insert(A[num_layer-2],0,1),diff)
for l in range(num_layer-2):
index = num_layer-2-l
diff = np.multiply(np.dot(np.array([W[index][k+1] for k in range(num_node[index])]), diff), np.multiply(A[index], 1-A[index]))
delta[index-1] = delta[index-1] + np.outer(np.insert(A[index-1],0,1),diff)
D = np.empty(num_layer-1, dtype = object)
for l in range(num_layer - 1):
D[l] = np.zeros((num_node[l]+1,num_node[l+1]))
for l in range(num_layer-1):
for i in range(num_node[l]+1):
if i == 0:
for j in range(num_node[l+1]):
D[l][i][j] = 1/Ntrain * delta[l][i][j]
else:
for j in range(num_node[l+1]):
D[l][i][j] = 1/Ntrain * (delta[l][i][j] + Lambda * W[l][i][j])
return D
# Neural network - this is where the learning/adjusting of weights occur
# W is the weights
# learn is the learning rate
# iterations is the number of iterations we pass over the training set
# Lambda is the regularization parameter
def NeuralNetwork(y, X, learn, iterations, Lambda):
W = np.empty(num_layer-1, dtype = object)
for l in range(num_layer - 1):
W[l] = np.random.rand(num_node[l]+1,num_node[l+1])/100
for k in range(iterations):
print(J(y, W, X, Lambda))
D = BackPropagation(y, W, X, Lambda)
for l in range(num_layer-1):
W[l] = W[l] - learn * D[l]
print(J(y, W, X, Lambda))
return W
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# Training data, read from MNIST
inputpix = []
output = []
for i in range(Ntrain):
inputpix.append(2 * np.array(mnist.train.images[i]) - 1)
output.append(np.array(mnist.train.labels[i]))
np.savetxt('input.txt', inputpix, delimiter=' ')
np.savetxt('output.txt', output, delimiter=' ')
# Train the weights
finalweights = NeuralNetwork(output, inputpix, 2, 5, 1)
# Test data
inputtestpix = []
outputtest = []
for i in range(Ntest):
inputtestpix.append(2 * np.array(mnist.test.images[i]) - 1)
outputtest.append(np.array(mnist.test.labels[i]))
np.savetxt('inputtest.txt', inputtestpix, delimiter=' ')
np.savetxt('outputtest.txt', outputtest, delimiter=' ')
# Determine the accuracy of the training data
count = 0
for i in range(Ntrain):
H = h(finalweights,inputpix[i])
print(H)
for j in range(num_output_node):
if H[j] == np.amax(H) and output[i][j] == 1:
count = count + 1
print(count/Ntrain)
# Determine the accuracy of the test data
count = 0
for i in range(Ntest):
H = h(finalweights,inputtestpix[i])
print(H)
for j in range(num_output_node):
if H[j] == np.amax(H) and outputtest[i][j] == 1:
count = count + 1
print(count/Ntest)
Your network is tiny, 5 neurons make it basically a linear model. Increase it to 256 per layer.
Notice, that trivial linear model has 768 * 10 + 10 (biases) parameters, adding up to 7690 floats. Your neural network on the other hand has 768 * 5 + 5 + 5 * 5 + 5 + 5 * 10 + 10 = 3845 + 30 + 60 = 3935. In other words despite being nonlinear neural network, it is actualy a simpler model than a trivial logistic regression applied to this problem. And logistic regression obtains around 11% error on its own, thus you cannot really expect to beat it. Of course this is not a strict argument, but should give you some intuition for why it should not work.
Second issue is related to other hyperparameters, you seem to be using:
huge learning rate (is it 2?) it should be more of order 0.0001
very little training iterations (are you just executing 5 epochs?)
your regularization parameter is huge (it is set to 1), so your network is heavily penalised for learning anything, again - change it to something order of magnitude smaller
The NN architecture is most likely under-fitting. Maybe, the learning rate is high/low. Or there are most issues with the regularization parameter.
I'm trying to make several training examples to get a set of weights and bias for the particular network which correctly implements a hard threshold activation function.
Four inputs x_1, ... x_4 , where x_i is Real number, and the network must output(y) 1 if x_1 < x_2 < x_3 < x_4 (sorted order), and 0
otherwise.
A hard threshold activation function ;
f(z) = 1 (if z>= 0) or 0 (if z <0)
h1 = x1w11 + x2w12 + x3w13 + x4w14 + b11
h2 = x1w21 + x2w22 + x3w23 + x4w24 + b21
h3 = x1w31 + x2w32 + x3w33 + x4w34 + b31
y = w1h1 + h2w2 + h3w3 + b (*Actually h1, h2, h3 are f(h1),f(h2),f(h3) because of activation function)
And, f(y).
I guess training example should be
(-2,-1,0,1) -> output 1, (0,0,0,0) -> output 0, (0,0,0,1) -> output 0,
(1,2,3,4) -> output 1.
.. and so on.
But the domain of input is too broad to build specific examples to use multilayer perception algorithm.
Can you help me to get proper example for applying the algorithm?
No, its not to broad, you can just concentrate in the [0, 1] range for each x_i, as in any case you need normalized data to train a neural network.
So basically you can just generate uniformly distributed random numbers in the [0, 1] range, check if they are sorted or not, and produce the label accordingly. Then you repeat say for 10K or 100K and then you have a dataset to train an MLP. You could also discretize the [0, 1] range with a chosen step to generate the numbers.
I have 10+ features and a dozen thousand of cases to train a logistic regression for classifying people's race. First example is French vs non-French, and second example is English vs non-English. The results are as follows:
//////////////////////////////////////////////////////
1= fr
0= non-fr
Class count:
0 69109
1 30891
dtype: int64
Accuracy: 0.95126
Classification report:
precision recall f1-score support
0 0.97 0.96 0.96 34547
1 0.92 0.93 0.92 15453
avg / total 0.95 0.95 0.95 50000
Confusion matrix:
[[33229 1318]
[ 1119 14334]]
AUC= 0.944717975754
//////////////////////////////////////////////////////
1= en
0= non-en
Class count:
0 76125
1 23875
dtype: int64
Accuracy: 0.7675
Classification report:
precision recall f1-score support
0 0.91 0.78 0.84 38245
1 0.50 0.74 0.60 11755
avg / total 0.81 0.77 0.78 50000
Confusion matrix:
[[29677 8568]
[ 3057 8698]]
AUC= 0.757955582999
//////////////////////////////////////////////////////
However, I am getting some very strange looking AUC curves with trianglar shapes instead of jagged round curves. Any explanation as to why I am getting such shape? Any possible mistake I have made?
Codes:
all_dict = []
for i in range(0, len(my_dict)):
temp_dict = dict(my_dict[i].items() + my_dict2[i].items() + my_dict3[i].items() + my_dict4[i].items()
+ my_dict5[i].items() + my_dict6[i].items() + my_dict7[i].items() + my_dict8[i].items()
+ my_dict9[i].items() + my_dict10[i].items() + my_dict11[i].items() + my_dict12[i].items()
+ my_dict13[i].items() + my_dict14[i].items() + my_dict15[i].items() + my_dict16[i].items()
)
all_dict.append(temp_dict)
newX = dv.fit_transform(all_dict)
# Separate the training and testing data sets
half_cut = int(len(df)/2.0)*-1
X_train = newX[:half_cut]
X_test = newX[half_cut:]
y_train = y[:half_cut]
y_test = y[half_cut:]
# Fitting X and y into model, using training data
#$$
lr.fit(X_train, y_train)
# Making predictions using trained data
#$$
y_train_predictions = lr.predict(X_train)
#$$
y_test_predictions = lr.predict(X_test)
#print (y_train_predictions == y_train).sum().astype(float)/(y_train.shape[0])
print 'Accuracy:',(y_test_predictions == y_test).sum().astype(float)/(y_test.shape[0])
print 'Classification report:'
print classification_report(y_test, y_test_predictions)
#print sk_confusion_matrix(y_train, y_train_predictions)
print 'Confusion matrix:'
print sk_confusion_matrix(y_test, y_test_predictions)
#print y_test[1:20]
#print y_test_predictions[1:20]
#print y_test[1:10]
#print np.bincount(y_test)
#print np.bincount(y_test_predictions)
# Find and plot AUC
false_positive_rate, true_positive_rate, thresholds = roc_curve(y_test, y_test_predictions)
roc_auc = auc(false_positive_rate, true_positive_rate)
print 'AUC=',roc_auc
plt.title('Receiver Operating Characteristic')
plt.plot(false_positive_rate, true_positive_rate, 'b', label='AUC = %0.2f'% roc_auc)
plt.legend(loc='lower right')
plt.plot([0,1],[0,1],'r--')
plt.xlim([-0.1,1.2])
plt.ylim([-0.1,1.2])
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
plt.show()
You're doing it wrong. According to documentation:
y_score : array, shape = [n_samples]
Target scores, can either be probability estimates of the positive class or confidence values.
Thus at this line:
roc_curve(y_test, y_test_predictions)
You should pass into roc_curve function result of decision_function (or some of two columns from predict_proba result) instead of actual predictions.
Look at these examples http://scikit-learn.org/stable/auto_examples/model_selection/plot_roc.html#example-model-selection-plot-roc-py
http://scikit-learn.org/stable/auto_examples/model_selection/plot_roc_crossval.html#example-model-selection-plot-roc-crossval-py