def get_confusion_matrix():
# db = DoubleBayes()
# predicted, actual = db.generate_predictions(weighted=True)
nb = Naive_Bayes()
predicted, actual = nb.generate_predictions()
cnf_matrix = confusion_matrix(actual, predicted)
return cnf_matrix
def post():
if request.is_json:
data = request.get_json()
else:
return jsonify({'request': request.get_data()})
assert (len(data) == 3)
try:
age = int(data['age'])
condition_list = list(data['conditions'])
state = str(data['state'])
except KeyError:
return jsonify(dict())
nb = Naive_Bayes(age, state, condition_list)
return jsonify({'probability': nb.get_probability()})
def train(self, training_data):
"""
Data should be nx(m+1) numpy matrix where n is the
number of examples and m is the number of features
(recall that the first element of the vector is the label).
I recommend implementing the specific algorithms in a
seperate module and then determining which method to call
based on classifier_type. E.g. if you had a module called
neural_nets:
if self.classifier_type == 'neural_net':
import neural_nets
neural_nets.train_neural_net(self.params, training_data)
Note that your training algorithms should be modifying the parameters
so make sure that your methods are actually modifying self.params
You should print the accuracy, precision, and recall on the training data.
"""
if self.classifier_type == 'neural_network':
#change num_input, num_output based upon the data
self.nn = Neural_Network("neural_network",weights = [], num_input=self.params['num_input'], num_hidden=1000, num_output=self.params['num_output'], alt_weight=self.params['one']=='1', momentum=self.params['two']=='1')
self.nn.train(training_data)
elif self.classifier_type == 'naive_bayes':
self.nb = Naive_Bayes("naive_bayes")
self.nb.train(training_data)
elif self.classifier_type =='decision_tree':
self.dt = Decision_Tree("decision_tree", pruning=self.params['one']=='1',
info_gain_ratio=self.params['two']=='1')
self.dt.train(training_data)
from decision_tree import Decision_Tree
from naive_bayes import Naive_Bayes
import load_data as ld
import pdb
# nb = Decision_Tree("decision_tree", pruning=False, info_gain_ratio=True)
nb = Naive_Bayes("naive_bayes")
# monks3 = ld.load_monks(1)
# monks3 = ld.load_monks(2)
# monks3 = ld.load_monks(3)
# monks3 = ld.load_iris(.75)
monks3 = ld.load_congress_data(0.75)
# nb.train(monks3[0])
"""tot, hit = 0, 0
for person in monks3[1]:
predict = nb.predict(person)
if predict == person[0]:
hit += 1
tot += 1"""
# classify = nb.train(monks3[0])
nb.train(monks3[0])
# nb.train(monks3[0])
# nb.train(monks3[0])
# nb.train(monks3[0])
# pdb.set_trace()
# nb.test(monks3[1])
hmm.fit(data_train)
print(f"Duration of training: {time.time() - start_time}")
# evaluation hmm
# -------------------------------------------------------------------------
# plot confusion matrix, calculate precision, recall, f1-score
hmm.evaluate(data_test)
# show misclassifications
features_test, labels_test = separate_labels_from_features(data_test)
predictions = hmm.predict(features_test)
show_misclassifications(data_test, predictions)
elif model_type == "NB":
# fit naive bayes model
# -------------------------------------------------------------------------
nb = Naive_Bayes()
data_train_featurized = feature_maker.get_pos_features_nltk(
data_train
) if not load_entities else feature_maker.get_ner_features_nltk(data_train)
data_train_featurized = flatten(data_train_featurized)
start_time = time.time()
nb.fit_nltk(data_train_featurized)
print(f"Duration of training: {time.time() - start_time}")
# evaluation naive bayes
# -------------------------------------------------------------------------
data_test_featurized = feature_maker.get_pos_features_nltk(
data_test
) if not load_entities else feature_maker.get_ner_features_nltk(data_test)
class Classifier:
def __init__(self, classifier_type, **kwargs):
"""
Initializer. Classifier_type should be a string which refers
to the specific algorithm the current classifier is using.
Use keyword arguments to store parameters
specific to the algorithm being used. E.g. if you were
making a neural net with 30 input nodes, hidden layer with
10 units, and 3 output nodes your initalization might look
something like this:
neural_net = Classifier(weights = [], num_input=30, num_hidden=10, num_output=3)
Here I have the weight matrices being stored in a list called weights (initially empty).
"""
self.classifier_type = classifier_type
self.params = kwargs
"""
The kwargs you inputted just becomes a dictionary, so we can save
that dictionary to be used in other methods.
"""
def train(self, training_data):
"""
Data should be nx(m+1) numpy matrix where n is the
number of examples and m is the number of features
(recall that the first element of the vector is the label).
I recommend implementing the specific algorithms in a
seperate module and then determining which method to call
based on classifier_type. E.g. if you had a module called
neural_nets:
if self.classifier_type == 'neural_net':
import neural_nets
neural_nets.train_neural_net(self.params, training_data)
Note that your training algorithms should be modifying the parameters
so make sure that your methods are actually modifying self.params
You should print the accuracy, precision, and recall on the training data.
"""
if self.classifier_type == 'neural_network':
#change num_input, num_output based upon the data
self.nn = Neural_Network("neural_network",weights = [], num_input=self.params['num_input'], num_hidden=1000, num_output=self.params['num_output'], alt_weight=self.params['one']=='1', momentum=self.params['two']=='1')
self.nn.train(training_data)
elif self.classifier_type == 'naive_bayes':
self.nb = Naive_Bayes("naive_bayes")
self.nb.train(training_data)
elif self.classifier_type =='decision_tree':
self.dt = Decision_Tree("decision_tree", pruning=self.params['one']=='1',
info_gain_ratio=self.params['two']=='1')
self.dt.train(training_data)
def predict(self, data):
"""
Predict class of a single data vector
Data should be 1x(m+1) numpy matrix where m is the number of features
(recall that the first element of the vector is the label).
I recommend implementing the specific algorithms in a
seperate module and then determining which method to call
based on classifier_type.
This method should return the predicted label.
"""
def test(self, test_data):
"""
Data should be nx(m+1) numpy matrix where n is the
number of examples and m is the number of features
(recall that the first element of the vector is the label).
You should print the accuracy, precision, and recall on the test data.
"""
#pdb.set_trace()
#Accuracy, Recall, and Precision
relevant_and_retrieved, relevant, retrieved, total, hit = 0, 0, 0, 0, 0
for person in test_data:
predict = 0
if self.classifier_type == 'neural_network':
predict = self.nn.predict(person)
elif self.classifier_type == 'naive_bayes':
predict = self.nb.predict(person)
elif self.classifier_type == 'decision_tree':
predict = self.dt.predict(person)
if predict == person[0]:
if predict == 0:
relevant_and_retrieved += 1
hit += 1
if person[0] == 0:
relevant += 1
if predict == 0:
retrieved += 1
total += 1
accuracy = hit/float(total)
recall = relevant_and_retrieved/float(relevant)
precision = relevant_and_retrieved/float(retrieved)
print "Accuracy: ", accuracy
print "Precision ", precision
print "Recall: " , recall
def train(instances, algorithm, high_idx, learn_rate, iterate, peg_lambda,
k_val, T, clus_lambda, K, clus_iter):
if (algorithm == "perceptron"):
classifier = Perceptron(instances, high_idx, learn_rate)
#iterate the training
for i in range(iterate):
classifier.train(instances)
return classifier
elif (algorithm == "averaged_perceptron"):
classifier2 = AveragePerceptron(instances, high_idx, learn_rate)
for i in range(iterate):
classifier2.train(instances)
return classifier2
elif (algorithm == "pegasos"):
classifier3 = Pegasos(instances, high_idx, peg_lambda)
for i in range(iterate):
classifier3.train(instances)
return classifier3
elif (algorithm == "margin_perceptron"):
classifier4 = PerceptronMargin(instances, high_idx, learn_rate,
iterate)
for i in range(iterate):
classifier4.train(instances)
return classifier4
elif (algorithm == "knn"):
classifier5 = KNN(instances, k_val, high_idx)
for i in range(iterate):
classifier5.train(instances)
return classifier5
elif (algorithm == "distance_knn"):
classifier6 = Distance_KNN(instances, k_val, high_idx)
for i in range(iterate):
classifier6.train(instances)
return classifier6
elif (algorithm == "adaboost"):
classifier7 = Adaboost(instances, T, high_idx)
for i in range(iterate):
classifier7.train(instances)
return classifier7
elif (algorithm == "lambda_means"):
classifier8 = Lambda_Means2(instances, high_idx, clus_lambda,
clus_iter)
for i in range(iterate):
#print "##################Training", i+1, "out of", iterate,"###############"
classifier8.train(instances)
return classifier8
elif (algorithm == "nb_clustering"):
classifier9 = Naive_Bayes(instances, high_idx, K)
for i in range(iterate):
#print "##################Training", i+1, "out of", iterate,"###############"
classifier9.train(instances)
return classifier9
elif (algorithm == "mc_perceptron"):
classifier10 = MC_Perceptron(instances, high_idx)
for i in range(iterate):
classifier10.train(instances)
return classifier10
else:
return None
from naive_bayes import Naive_Bayes
import load_data as ld
import pdb
nb = Naive_Bayes("naive_bayes")
congress = ld.load_congress_data(0.75)
# iris = ld.load_iris(.75)
classify = nb.train(congress[0])
# nb.train(iris[0])
# pdb.set_trace()
# nb.test(congress[1])
tot, hit = 0, 0
for person in congress[1]:
predict = nb.predict(person)
if predict == person[0]:
hit += 1
tot += 1
print hit, tot, hit / float(tot)
