def p3():
results = []
model = None
# TODO: Get the Minecraft dataset
data_train, data_test, target_train, target_test = get_minecraft(
'histogram')
for n_estimators in [2, 5, 10, 20, 30]:
# TODO: create a random forest classifier with n_estimators estimators
model = create_random_forest(n_estimators)
#TODO: use the model to fit the training data and predict labels for the training and test data
model = model.fit(data_train, target_train)
predict_train = model.predict(data_train)
predict_test = model.predict(data_test)
# TODO: calculate the accuracies of the models and add them to the results
accuracy_train, accuracy_test = calculate_model_accuracy(
predict_train, predict_test, target_train, target_test)
results.append((n_estimators, accuracy_train, accuracy_test))
print results
return model, results
def p2():
results = []
model = create_decision_tree()
# TODO: Get the Minecraft dataset using get_minecraft() and create a decision tree
data_train, data_test, target_train, target_test = get_minecraft(
'histogram')
for n in [50, 100, 150, 200, 250]:
# TODO: Fit the model using a subset of the training data of size n
# Hint: use the get_first_n_samples function imported from data.py
adjusted_data, adjusted_target = get_first_n_samples(
data_train, target_train, n)
#TODO: use the model to fit the training data and predict labels for the training and test data
model = model.fit(adjusted_data, adjusted_target)
predict_train = model.predict(adjusted_data)
predict_test = model.predict(data_test)
# TODO: Calculate the accuracys of the model (use the training data that fit the model in the current iteration)
accuracy_train_n, accuracy_test = calculate_model_accuracy(
predict_train, predict_test, adjusted_target, target_test)
results.append((n, accuracy_train_n, accuracy_test))
print(results)
return model, results
def p0(featuretype='histogram'):
data_train, data_test, target_train, target_test = get_minecraft(
featuretype)
model = create_decision_tree()
# TODO: Fit the model to the data using its fit method
# TODO: Use the model's predict method to predict labels for the training and test sets
#data_train, data_test, target_train, target_test = train_test_split(features, labels, test_size=0.33, random_state=42)
#gnb = GaussianNB()
#model = gnb.fit(data_train, target_train)
# import some data to play with
X = data_test
y = target_test
#class_names = model.target_names
# Split the data into a training set and a test set
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
# Run classifier, using a model that is too regularized (C too low) to see
# the impact on the results
#classifier = svm.SVC(kernel='linear', C=0.01)
#y_pred = classifier.fit(X_train, y_train).predict(X_test)
# Run classifier, using a model that is too regularized (C too low) to set
# the impact on the results
classifier = svm.SVC(kernel='linear', C=0.01)
y_pred = classifier.fit(X_train, y_train).predict(X_test)
predict_train = y_test
predict_test = y_pred
accuracy_train, accuracy_test = calculate_model_accuracy(
predict_train, predict_test, target_train, target_test)
print('Training accuracy: {0:3f}, Test accuracy: {1:3f}'.format(
accuracy_train, accuracy_test))
cfm = calculate_confusion_matrix(predict_test, target_test)
print "Confusion matrix"
print cfm
for q in range(1, 3):
for p in range(0, q):
#compute confusion between classes p and q
index_pq = [i for i, v in enumerate(target_train) if v in [p, q]]
modelpq = create_decision_tree()
#TODO: fit model to the data only involving classes p and q
data_train, data_test, target_train, target_test = train_test_split(
features, labels, test_size=0.5, random_state=42)
testindex_pq = [
i for i, v in enumerate(target_test) if v in [p, q]
]
#TODO: calculate and print the accuracy
gnb = GaussianNB()
model = gnb.fit(data_train, target_train)
accuracy_pq = gnb.predict(data_test)
print "One-vs-one accuracy between classes", p, "and", q, ":", accuracy_pq
return model, predict_train, predict_test, accuracy_train, accuracy_test
def minecraft_decision_tree():
results = []
model = None
# Get the Minecraft dataset using get_minecraft() and create a decision tree
data_train, data_test, target_train, target_test = get_minecraft(
'histogram')
model = create_decision_tree()
for n in [50, 100, 150, 200, 250]:
# Fit the model using a subset of the training data of size n
nData, nTarget = get_first_n_samples(data_train, target_train, n)
model.fit(nData, nTarget)
# use the model to fit the training data and predict labels for the training and test data
predict_train = model.predict(nData)
# nDataTest, nTargetTest = get_first_n_samples(data_test, target_test,n)
predict_test = model.predict(data_test)
# Calculate the accuracys of the model (use the training data that fit the model in the current iteration)
accuracy_train_n, accuracy_test = calculate_model_accuracy(
predict_train, predict_test, nTarget, target_test)
results.append((n, accuracy_train_n, accuracy_test))
print(results)
return model, results
def log_regression(featuretype='histogram'):
# model = None
data_train, data_test, target_train, target_test = get_minecraft(
featuretype)
model = LogisticRegression()
# Fit the model to the data using its fit method
model.fit(data_train, target_train)
# Use the model's predict method to predict labels for the training and test sets
predict_train = model.predict(data_train)
predict_test = model.predict(data_test)
accuracy_train, accuracy_test = calculate_model_accuracy(
predict_train, predict_test, target_train, target_test)
print('Training accuracy: {0:3f}, Test accuracy: {1:3f}'.format(
accuracy_train, accuracy_test))
cfm = calculate_confusion_matrix(predict_test, target_test)
print "Confusion matrix"
print cfm
for q in range(1, 3):
for p in range(0, q):
#compute confusion between classes p and q
index_pq = [i for i, v in enumerate(target_train) if v in [p, q]]
modelpq = create_decision_tree()
# fit model to the data only involving classes p and q
modelpq.fit([data_train[i] for i in index_pq],
[target_train[i] for i in index_pq])
testindex_pq = [
i for i, v in enumerate(target_test) if v in [p, q]
]
# calculate and print the accuracy
predict_train_pq = modelpq.predict(
[data_train[i] for i in index_pq])
predict_test_pq = modelpq.predict(
[data_test[i] for i in testindex_pq])
accuracy_pq = calculate_model_accuracy(
predict_train_pq, predict_test_pq,
[target_train[i]
for i in index_pq], [target_test[i] for i in testindex_pq])[1]
print "One-vs-one accuracy between classes", p, "and", q, ":", accuracy_pq
return model, predict_train, predict_test, accuracy_train, accuracy_test
def p0(featuretype='histogram'):
data_train, data_test, target_train, target_test = get_minecraft(
featuretype)
model = create_decision_tree()
# TODO: Fit the model to the data using its fit method
model = model.fit(data_train, target_train)
# TODO: Use the model's predict method to predict labels for the training and test sets
predict_train = model.predict(data_train)
predict_test = model.predict(data_test)
accuracy_train, accuracy_test = calculate_model_accuracy(
predict_train, predict_test, target_train, target_test)
print('Training accuracy: {0:3f}, Test accuracy: {1:3f}'.format(
accuracy_train, accuracy_test))
cfm = calculate_confusion_matrix(predict_test, target_test)
print "Confusion matrix"
print cfm
for q in range(1, 3):
for p in range(0, q):
#compute confusion between classes p and q
index_pq = [i for i, v in enumerate(target_train) if v in [p, q]]
modelpq = create_decision_tree()
#TODO: fit model to the data only involving classes p and q
relevant_data_train = [data_train[c] for c in index_pq]
relevant_target_train = [target_train[c] for c in index_pq]
modelpq = model.fit(relevant_data_train, relevant_target_train)
testindex_pq = [
i for i, v in enumerate(target_test) if v in [p, q]
]
#TODO: calculate and print the accuracy
relevant_result = [data_test[c] for c in testindex_pq]
relevant_result2 = [target_test[c] for c in testindex_pq]
accuracy_pq = modelpq.score(relevant_result, relevant_result2)
print "One-vs-one accuracy between classes", p, "and", q, ":", accuracy_pq
return model, predict_train, predict_test, accuracy_train, accuracy_test