from sklearn.tree import DecisionTreeClassifier
import utils
import numpy as np
import matplotlib.pyplot as plot
data = x_train, x_test, y_train, y_test = utils.import_wine(n_samples=5000,
y_transform=None)
# WITHOUT TUNING
base_clf = DecisionTreeClassifier(random_state=0,
criterion='entropy',
max_leaf_nodes=20000,
max_depth=50)
utils.boosting(*data, base_clf, verbose=True)
# 10-FOLD CROSSVALIDATION ON THE LEARNING RATE
scores = []
learning_rates = []
for learning_rate in np.linspace(1.3, 1.45, 5):
print(learning_rate)
learning_rates.append(learning_rate)
scores.append(
utils.boosting_crossval(*data, base_clf,
learning_rate=learning_rate)[1])
plot.style.use('seaborn-darkgrid')
plot.title('Influence of the learning rate on boosting')
utils.knn(*data, n_neighbors=k)
# INFLUENCE OF THE WEIGHTS
utils.knn(*data, n_neighbors=20, weights='distance')
# INFLUENCE OF THE METRICS
metrics = ['manhattan', 'chebyshev']
for metric in metrics:
utils.knn(*data, n_neighbors=20, metric=metric)
# BEST MODEL
data = x_train, x_test, y_train, y_test = utils.import_wine(y_transform=None)
utils.knn(*data, n_neighbors=20)
# LEARNING CURVE
clf = KNeighborsClassifier(n_neighbors=20)
x = []
train = []
test = []
for i in [0.02, 0.1, 1, 2, 3, 5, 10, 15, 25, 32]:
index = int(1000 * i)
x.append(index)
clf.fit(x_train[:index], y_train[:index].values.ravel())
train.append(clf.score(x_train[:index], y_train[:index].values.ravel()))
test.append(clf.score(x_test, y_test.values.ravel()))
x.append(count)
count += 1
plot.bar(x, cataccs, color=color, width=0.75)
x = []
count = 1.25
for _ in range(5):
x.append(count)
count += 1.5
plot.xticks(x, ['None', 'PCA', 'ICA', 'RP', 'VAE'])
plot.xlabel('Feature transformation method')
plot.ylabel('Categorical accuracy (%)')
plot.show()
x_adult, y_adult, x_adult_test, y_adult_test = utils.import_adult()
x_wine, y_wine, x_wine_test, y_wine_test = utils.import_wine()
# K-MEANS
silhouette('adult', range(2, 15), x_adult) # 1025s
cluster_breakdown('adult_kmeans', x_adult,
KMeans(n_clusters=5,
random_state=0).fit_predict(x_adult)) # 10s
cataccs('adult', range(2, 15), 2, x_adult, y_adult) # 91s
silhouette('wine', range(2, 15), x_wine) # 2154s
cluster_breakdown('wine_kmeans', x_wine,
KMeans(n_clusters=3,
random_state=0).fit_predict(x_wine)) # 24s
cataccs('wine reviews', range(2, 15), 5, x_wine, y_wine) # 577s
from keras import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plot
import utils
data = x_train, x_test, y_train, y_test = utils.import_wine(
y_transform='to_categorical')
model = Sequential()
model.add(Dense(10, input_dim=len(x_train.keys()), activation='relu'))
model.add(Dense(15, activation='relu'))
model.add(Dense(len(y_train[0]), activation='softmax'))
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['categorical_accuracy'])
history = model.fit(x_train,
y_train,
validation_data=(x_test, y_test),
epochs=20,
batch_size=50)
utils.plot_ann_history(history)
plot.show()
y_predict = model.predict(x_test[:5])
for i in range(5):
plot.bar([80, 84, 88, 92, 96, 100], [*y_test[i], 0], width=4, align='edge')
plot.bar([80, 84, 88, 92, 96, 100], [*y_predict[i], 0],
import utils
data = x_train, x_test, y_train, y_test = utils.import_wine()
# WITHOUT PRUNING
utils.dt_pruning(*data)
# PRUNING MANUALLY
utils.dt_pruning(*data, 1000, 40)
utils.dt_pruning(*data, 10000, 70)
utils.dt_pruning(*data, 40000, 90)
utils.dt_pruning(*data, 45000, 95)
# PRUNING WITH 10-FOLD CROSS-VALIDATION
clf = utils.dt_crossval(*data,
n_leaf_range=range(41250, 41751, 100),
n_depth_range=range(100, 101))