def mnist_digit_recognition():
train_set, test_set = load_mnist_dataset()
n_labels = 10 # 1,2,3,4,5,6,7,9,0
n_features = 28 * 28
draw_ex_images(5, 4, train_set[0].shape[0], train_set[0])
mnist_model = GaussianNaiveBayes(n_labels, n_features)
start = time.time()
mnist_model.train(train_set[0], train_set[1])
end = time.time()
print(end - start)
mnist_model.save_model()
mean, var, pi = mnist_model.get_parameters()
print(f"Model parameters: mean {mean}, var {var}, pi {pi}")
test_data, labels = test_set
limit = 150
test_data, labels = test_data[:limit], labels[:limit]
results = np.arange(limit, dtype=np.int)
for n in range(limit):
results[n] = mnist_model.classify(test_data[n])
print(f"{n} : predicted {results[n]}, correct {labels[n]}")
print("recognition rate: ", (results == labels).mean())
def test_bayes():
iris = load_iris()
#dataframe input required
df = pd.DataFrame(data=np.c_[iris['data'], iris['target']],
columns=iris['feature_names'] + ['target'])
X, y = df.drop('target', 1), df[['target']]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=1, stratify=y, shuffle=True)
clas = GaussianNaiveBayes()
clas.fit(X_train, y_train)
pred2 = clas.predict(X_test)
print("F1: ", f1_score(pred2, y_test, average='micro'))
def figure_1(train_set_results, X_test, y_test):
"""Learning curves best SVMvs GNB"""
best_SVM_params = max(
[(statistics.mean(group_results['test_score']),
group_results['estimator'][0].best_params_)
for group_results in train_set_results['tf']['plain'].values()],
key=lambda x: x[0])
best_SVM = Pipeline([("estimator", SVC(max_iter=1000000))])
best_SVM.set_params(**best_SVM_params[1])
plot_learning_curves_macro(best_SVM, GaussianNaiveBayes(), "SVM", "GNB",
"SVM vs GNB learning curves", X_test, y_test)
def naive_bayes_test():
n_labels, n_features = 2, 2
nb = GaussianNaiveBayes(n_labels, n_features)
# prepare sample training data
data1 = np.random.multivariate_normal([1,4], [[2,0],[0,2]], size=100)
data2 = np.random.multivariate_normal([5,7], [[3,0],[0,1]], size=100)
data = np.concatenate((data1, data2), axis=0)
# prepare training label data
labels = np.concatenate((np.array([0]*100), np.array([1]*100)), axis=0)
print "correct labels"
print labels
# nb.load()
nb.train(data, labels)
# nb.save()
results = nb.classify(data)
print "predicted labels"
print results
print "recognition rate: ", (results == labels).mean()
def mnist_digit_recognition():
train_set, valid_set, test_set = load_mnist_dataset("mnist.pkl.gz")
n_labels = 10 # 1,2,3,4,5,6,7,9,0
n_features = 28*28
mnist_model = GaussianNaiveBayes(n_labels, n_features)
mnist_model.train(train_set[0], train_set[1])
[mean, var], pi = mnist_model.get_parameters()
# visualization of learned means
create_2D_images_horizontal(mean, w=28, h=28)
show()
test_data, labels = test_set
# slice
#limit = len(test_data)
limit = 50
test_data, labels = test_data[:limit], labels[:limit]
results = np.arange(limit, dtype=np.int)
for n in range(limit):
results[n] = mnist_model.classify(test_data[n])
print "%d : predicted %s, correct %s" % (n, results[n], labels[n])
# results = mnist_model.classify(test_data)
print "recognition rate: ", (results == labels).mean()
def mnist_digit_recognition():
train_set, valid_set, test_set = load_mnist_dataset("mnist.pkl.gz")
n_labels = 10 # 1,2,3,4,5,6,7,9,0
n_features = 28 * 28
mnist_model = GaussianNaiveBayes(n_labels, n_features)
mnist_model.train(train_set[0], train_set[1])
[mean, var], pi = mnist_model.get_parameters()
# visualization of learned means
create_2D_images_horizontal(mean, w=28, h=28)
show()
test_data, labels = test_set
# slice
#limit = len(test_data)
limit = 50
test_data, labels = test_data[:limit], labels[:limit]
results = np.arange(limit, dtype=np.int)
for n in range(limit):
results[n] = mnist_model.classify(test_data[n])
print "%d : predicted %s, correct %s" % (n, results[n], labels[n])
# results = mnist_model.classify(test_data)
print "recognition rate: ", (results == labels).mean()
def main():
"""
Loads the dataset and either computes or loads precomputed results and using them (or not) completes task
designated by the task variable
:return: Happiness
"""
from pathlib import Path
class_names = ["ham", "spam"]
X, y = load_set()
# X, _, y, _ = train_test_split(X,y,train_size=0.12) <- use to make dataset smaller for testing
recompute = False
pickled_train_set_results = "gridsearch.pickle"
# load the precomputed results file if exists
if Path(pickled_train_set_results).is_file() and not recompute:
with open(pickled_train_set_results, 'rb') as file:
results = pickle.load(file)
else:
# compute the test results (may take a long time)
pipelines = {
"plain":
Pipeline([("estimator", SVC(max_iter=1000000))]),
"normalized":
Pipeline([("preprocessing", Normalizer()),
("estimator", SVC(max_iter=1000000))]),
"scaled":
Pipeline([("preprocessing", MaxAbsScaler()),
("estimator", SVC(max_iter=1000000))]),
}
datasets = {"tf": X, "tf_idf": transform_tf_to_tf_idf(X)}
Cs = [10.0**x for x in range(-2, 5)]
gammas = [10.0**x for x in range(-8, 1)] + ["scale"]
param_grid = {
"svm-rbf": {
'estimator__kernel': ['rbf'],
'estimator__gamma': gammas,
'estimator__C': [10.0**x for x in range(-1, 10)]
},
"svm-linear": {
'estimator__kernel': ['linear'],
'estimator__C': Cs
},
"svm-poly-d2-c00": {
'estimator__kernel': ['poly'],
'estimator__C': Cs,
'estimator__degree': [2]
},
"svm-poly-d2-c01": {
'estimator__kernel': ['poly'],
'estimator__C': Cs,
'estimator__degree': [2],
'estimator__coef0': [1]
},
"svm-poly-d3-c00": {
'estimator__kernel': ['poly'],
'estimator__C': Cs,
'estimator__degree': [3]
},
"svm-poly-d3-c01": {
'estimator__kernel': ['poly'],
'estimator__C': Cs,
'estimator__degree': [3],
'estimator__coef0': [1]
},
"gnb-sk": {
'estimator': [GaussianNB()]
},
"gnb-my": {
'estimator': [GaussianNaiveBayes()]
},
"multinomialnb": {
'estimator': [MultinomialNB()]
}
}
results = {
dataset: {
pipeline: {group: {}
for group in param_grid.keys()}
for pipeline in pipelines.keys()
}
for dataset in datasets.keys()
}
param_search_cv = StratifiedKFold(n_splits=5,
shuffle=True,
random_state=42)
eval_cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)
progress = np.zeros(3, dtype=np.uint16)
for dataset_name, dataset in datasets.items():
progress = progress * np.array(
[1, 0, 0], dtype=np.uint16) + np.array([1, 0, 0],
dtype=np.uint16)
print(f"Processing dataset {progress[0]} of {len(datasets)}")
for pipeline_name, pipeline in pipelines.items():
progress = progress * np.array(
[1, 1, 0], dtype=np.uint16) + np.array([0, 1, 0],
dtype=np.uint16)
print(f"Processing pipeline {progress[1]} of {len(pipelines)}")
for group_name, group in param_grid.items():
progress = progress * np.array(
[1, 1, 1], dtype=np.uint16) + np.array([0, 0, 1],
dtype=np.uint16)
print(
f"Processing group {progress[2]} of {len(param_grid)}")
param_search = GridSearchCV(pipeline,
group,
n_jobs=-1,
cv=param_search_cv,
verbose=1)
cv_results = cross_validate(param_search,
dataset,
y,
cv=eval_cv,
return_estimator=True,
verbose=1)
results[dataset_name][pipeline_name][
group_name] = cv_results
# save the results for future reuse
with open(pickled_train_set_results, 'wb') as file:
pickle.dump(results, file)
# select your task
task = "table_7" # <-----here
if task == "table_1":
table_1(results)
elif task == "table_2":
table_2(results)
elif task == "table_3":
table_3(results)
elif task == "table_4":
table_4(results)
elif task == "table_5":
table_5(results)
elif task == "table_6":
table_6(results)
elif task == "table_7":
table_7(results)
elif task == "table_8":
table_8(results)
elif task == "figure_1":
figure_1(results, X, y)
elif task == "figure_2":
figure_2(results, X, y)
elif task == "figure_3":
figure_3(results, X, y, class_names)
elif task == "figure_4":
figure_4(X, y, class_names)
elif task == "figure_5":
figure_5(X, y, class_names)
elif task == "experiment":
experiment(X, y)
elif task == "histograms":
plot_feature_histogram(minmax_scale(X), y, feature=7)
else:
print(f"Unknown task; {task}")