def kmeans():
train_x, test_x, train_y, test_y = data_scan.data_split()
pca = PCA(n_components=2)
pca.fit(train_x)
pca.transform(train_x)
y_pred = KMeans(n_clusters=2, random_state=2).fit_predict(train_x)
plt.scatter(train_x[:, 0], train_x[:, 1], c=y_pred)
plt.show()
def train_and_test():
train_x, test_x, train_y, test_y = data_scan.data_split()
classifier = BayesClassifier()
classifier.train(train_x, train_y)
# 测试集
print("验证测试集", test_x.shape)
correct_size = 0
for i in range(len(test_y)):
# print(data)
test_data_x = test_x[i]
test_data_y = test_y[i]
result = classifier.classify(test_data_x.reshape(1, 21))
print(test_data_x, test_data_y, result[0])
if result[0] == test_data_y:
correct_size = correct_size + 1
print("正确率：%f%%" % (correct_size * 100 / test_x.shape[0]))
def load_total_data():
train_x, test_x, train_y, test_y = data_split(
path='../../data/data_preceded.csv')
threshold = 26
train = []
for label in train_y:
temp = np.zeros(2)
temp[label] = 1
train.append(temp.T)
train_y = np.array(train)
test = []
for label in test_y:
temp = np.zeros(2)
temp[label] = 1
test.append(temp.T)
test_y = np.array(test)
return (train_x / threshold), (test_x / threshold), train_y, test_y
def load_data(is_load_train_data):
train_x, test_x, train_y, test_y = data_split(
path='../../../data/data_preceded.csv')
# 一定要标准化呀！！！
threshold = 26
if is_load_train_data:
data = train_x
labels = train_y
else:
data = test_x
labels = test_y
ls = []
for label in labels:
temp = np.zeros(2)
temp[label] = 1
ls.append(temp.T)
labels = np.array(ls)
return (data / threshold), labels
# @Author : Equator
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsRegressor
from sklearn.model_selection import KFold, cross_val_score, GridSearchCV
from code.preprocessing.data_scan import data_split
num_folds = 10
seed = 7
scoring = 'neg_mean_squared_error'
def knn_improve(train_x, train_y):
scaler = StandardScaler().fit(train_x)
rescaledX = scaler.transform(train_x)
param_gird = {'n_neighbors': [1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21]}
model = KNeighborsRegressor()
fold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
grid = GridSearchCV(model, param_gird, scoring=scoring, cv=fold)
grid_result = grid.fit(X=rescaledX, y=train_y)
cv_result = zip(grid_result.cv_results_['mean_test_score'],
grid_result.cv_results_['std_test_score'],
grid_result.cv_results_['params'])
for mean, std, param in cv_result:
print("%f (%f) with %r" % (mean, std, param))
print('最优：%s 使用 %s' % (grid_result.best_score_, grid_result.best_params_))
if __name__ == '__main__':
train_x, test_x, train_y, test_y = data_split()
knn_improve(train_x, train_y)
