test = af.data
KNC = KNeighborsClassifier(
n_neighbors=3,
weights='uniform',
)
KNC.fit(all_data[:, :-1], all_data[:, -1])
print(KNC.score(test[:, :-1], test[:, -1]))
# 0, -1, -1, 0, 0, 0, 0, -1, 0, 0, -1, 0, 0, -1 - 1
catagory = np.zeros(len(all_data)) * -1
# catagory[3]= 0
# catagory[1] = -1
# catagory[2] = -1
# catagory[7] = -1
# catagory[10] = -1
# catagory[13] = -1
# catagory[14] = -1
weight_type = ['inverse_distance', 'no_weight']
KK = KNNClassifier(catagory, k=3, weight_type=weight_type[0], normalize=False)
KK.fit(all_data[:, :-1], all_data[:, -1])
print('fitted')
filepath = 'Magic_test.arff'
af.load_arff(filepath)
test = af.data
print(KK.score(test[:, :-1], test[:, -1]))
norm_train_data[:, col] = where
test_data = raw_data[int(raw_data.shape[0] * split) + 1:, :-1]
norm_test_data = test_data.copy()
test_labels = raw_data[int(raw_data.shape[0] * split) + 1:, -1]
for col in range(norm_test_data.shape[1]):
column = norm_test_data[:, col]
col_min = min(column)
col_max = max(column)
where = np.where(True, (column - col_min) / (col_max - col_min), 0)
norm_test_data[:, col] = where
KNN_weight = KNNClassifier(k_val=15,
label_type='nominal',
col_types=mat.attr_types,
weight_type='inverse_distance')
KNN_weight.fit(norm_train_data, train_labels)
weight_scores = KNN_weight.score(norm_test_data, test_labels)
K_vals = np.arange(1, 17, 2)
#plt.plot(K_vals, scores, label="non-weighted")
plt.plot(K_vals, weight_scores, label="weighted")
plt.title("Credit Approval")
plt.ylabel("Accuracy")
plt.xlabel("K nearest neighbors")
plt.savefig("part5_plot_credit.png")
plt.show()
from KNN import KNNClassifier
from model_selection import train_test_split
from metric import accuracy_score
import pandas as pd
import numpy as np
if __name__ == '__main__':
"""
"""
iris = pd.read_csv('../iris.data', header=None)
iris_data = iris.loc[:, :].values
x_data = iris_data[:, [0, 2]]
y_data = iris_data[:, 4]
x_predict = np.array([[5.1, 2.1]])
x_train, y_train, x_test, y_test = train_test_split(x_data, y_data)
best_score = 0.0
best_k = -1
for k in range(1, 11):
knn_clf = KNNClassifier(n_neighbors=k)
knn_clf.fit(x_train, y_train)
score = knn_clf.score(x_test, y_test)
if score > best_score:
best_k = k
best_score = score
print("best_k =", best_k)
print('best_score =', best_score)
from KNN import KNNClassifier
from tools.arff import Arff
import numpy as np
diabetes_train = "../data/KNN/diabetes.arff"
diabetes_test = "../data/KNN/diabetes_test.arff"
seismic_train = "../data/KNN/seismic-bumps_train.arff"
seismic_test = "../data/KNN/seismic-bumps_test.arff"
mat = Arff(seismic_train, label_count=1)
mat2 = Arff(seismic_test, label_count=1)
raw_data = mat.data
h, w = raw_data.shape
train_data = raw_data[:, :-1]
train_labels = raw_data[:, -1]
raw_data2 = mat2.data
h2, w2 = raw_data2.shape
test_data = raw_data2[:, :-1]
test_labels = raw_data2[:, -1]
KNN = KNNClassifier(15, "nominal", weight_type='inverse_distance')
KNN.fit(train_data, train_labels)
pred = KNN.predict(test_data)
score = KNN.score(test_data, test_labels)
print(f"Score: {score[1]*100:.2f}%")
#np.savetxt("diabetes-prediction.csv", pred, delimiter=',', fmt="%i")