def train_model(model_name, X_train, Y_train, X_val, Y_val):
"""
Trains a supervised classifier using the training data provided, and scores
it using the validation dataset.
Param:
- model_name: a string containing a model type
- Train data:
- X_train
- Y_train
- Validation data:
- X_val
- Y_val
Return:
- model: a supervised classifier, to be used for testing
"""
if model_name == 'svm':
model = SVM()
elif model_name == "random_forest":
max_depth = 2
model = RandomForest(max_depth)
elif model_name == "neural_network":
max_depth = 2
out_size = 2
hidden_size = 30
in_size = X_train.shape[1]
model = NeuralNetwork(in_size, hidden_size, out_size)
elif model_name == "knn":
n_neighbors = 50
model = KNearestNeighbors(n_neighbors)
else:
return "Error: Model not yet implemented..."
print("Training " + model_name + "...")
train_score = model.train(X_train, Y_train)
valid_score = model.score(X_val, Y_val)
print("Training Accuracy: %s" % train_score)
print("Validation Accuracy: %s" % valid_score)
return model
__author__ = "danil.gizdatullin" import config as conf from k_nearest_neighbors import KNearestNeighbors K_Nearest_Neighbors = KNearestNeighbors(file_name=conf.path_to_similarity_data) print K_Nearest_Neighbors.statistics(conf.number_of_nearest_neighbors, histogram=True, number_of_bins=200)
knn_misclassification_rate = np.zeros(3)
for index, k in enumerate([1, 5, 10]):
knn = sklearn.neighbors.KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)
knn_result = knn.predict(X_test)
knn_misclassification_rate[index] = np.mean(knn_result != y_test)
plt.figure()
plt.plot(1 / np.array([1, 5, 10]), knn_misclassification_rate, "-bo")
plt.suptitle("Misclassification rate v.s. 1/k of KNN")
plt.show()
print(knn_misclassification_rate)
# Question 5 #
k_nearest_neighbors = KNearestNeighbors(1)
k_nearest_neighbors.fit(X_train, y_train)
knn_result = k_nearest_neighbors.predict(X_test)
knn_naive_misclassification_rate = np.mean(knn_result != y_test)
print(knn_naive_misclassification_rate)
# Question 7 #
w_knn_misclassification_rate = np.zeros(3)
for index, k in enumerate([1, 5, 10]):
knn = WeightedKNearestNeighbors(n_neighbors=k)
knn.fit(X_train, y_train)
knn_result = knn.predict(X_test)
w_knn_misclassification_rate[index] = np.mean(knn_result != y_test)
plt.figure()
plt.plot(1 / np.array([1, 5, 10]), w_knn_misclassification_rate, "-bo")
plt.suptitle("Misclassification rate v.s. 1/k of weighted KNN")
__author__ = 'danil.gizdatullin'
# import numpy as np
import matplotlib.pyplot as plt
import time
from k_nearest_neighbors import KNearestNeighbors
def special_print(a):
for key in a.iterkeys():
print("Key = %i" % key)
print(a[key].dict)
print("#####################")
start_time = time.time()
k_nn = KNearestNeighbors()
# special_print(k_nn.k_nearest_dict)
# special_print(k_nn.reverse_k_nearest_dict)
distr = k_nn.return_distribution_k_nearest_neighbors()
distr_reverse = k_nn.return_distribution_reverse_k_nearest_neighbors()
print("--- %s seconds ---" % (time.time() - start_time))
# plt.hist(distr)
plt.hist(distr_reverse, bins=100)
plt.show()
