def write_result(c, c_type):
file_name = wkzutils.get_path_sources("14.Titanic.test.csv")
x, passenger_id = load_data(file_name, False)
if type == 3:
x = xgb.DMatrix(x)
y = c.predict(x)
y[y > 0.5] = 1
y[~(y > 0.5)] = 0
predictions_file = open("Prediction_%d.csv" % c_type, "wb")
open_file_object = csv.writer(predictions_file)
open_file_object.writerow(["PassengerId", "Survived"])
open_file_object.writerows(zip(passenger_id, y))
predictions_file.close()
p = 1.0 / (1.0 + np.exp(-y_hat))
# 目标函数J(f)的一阶导【这里导函数是自己设置】
g = p - y.get_label()
# 目标函数J(f)的二阶导【这里导函数是自己设置(h实际是p的一阶导函数)】
h = p * (1.0 - p)
return g, h
def error_rate(y_hat, y):
return 'error', float(sum(y.get_label() != (y_hat > 0.5))) / len(y_hat)
if __name__ == "__main__":
# 读取数据
data_train = xgb.DMatrix(
wkzutils.get_path_sources("14.agaricus_train.txt"))
data_test = xgb.DMatrix(wkzutils.get_path_sources("14.agaricus_test.txt"))
print data_train
print type(data_train)
# 设置参数max_depth树深度,eta防止过拟合(衰减因子里面学习率v,推荐v<0.1,可以防止过拟合,但会造成计算次数增多),
# silent是否输出其它多余信息,objective目标函数(二分类问题)
param = {
'max_depth': 3,
'eta': 0.1,
'silent': 0,
'objective': 'binary:logistic'
} # logitraw
# param = {'max_depth': 3, 'eta': 0.3, 'silent': 1, 'objective': 'reg:logistic'}
# 训练数据和测试数据一起封闭成元组
watchlist = [(data_test, 'eval'), (data_train, 'train')]
print tip + '正确率：%.2f%%' % (100 * np.mean(acc))
def save_image(im, i):
im *= 15.9375
im = 255 - im
a = im.astype(np.uint8)
output_path = wkzutils.get_path_target("HandWritten")
if not os.path.exists(output_path):
os.mkdir(output_path)
Image.fromarray(a).save(output_path + ('\\%d.png' % i))
if __name__ == "__main__":
print 'Load Training File Start...'
data = np.loadtxt(wkzutils.get_path_sources("16.optdigits.tra"),
dtype=np.float,
delimiter=',')
x, y = np.split(data, (-1, ), axis=1)
images = x.reshape(-1, 8, 8)
y = y.ravel().astype(np.int)
print 'Load Test Data Start...'
data = np.loadtxt(wkzutils.get_path_sources("16.optdigits.tes"),
dtype=np.float,
delimiter=',')
x_test, y_test = np.split(data, (-1, ), axis=1)
images_test = x_test.reshape(-1, 8, 8)
y_test = y_test.ravel().astype(np.int)
print 'Load Data OK...'
from utils import wkzutils
def iris_type(s):
it = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
return it[s]
# 'sepal length', 'sepal width', 'petal length', 'petal width'
iris_feature = u'花萼长度', u'花萼宽度', u'花瓣长度', u'花瓣宽度'
if __name__ == "__main__":
mpl.rcParams['font.sans-serif'] = [u'SimHei'] # 黑体 FangSong/KaiTi
mpl.rcParams['axes.unicode_minus'] = False
path = wkzutils.get_path_sources("10.iris.data") # 数据文件路径
data = np.loadtxt(path,
dtype=float,
delimiter=',',
converters={4: iris_type})
x_prime, y = np.split(data, (4, ), axis=1)
feature_pairs = [(0, 1), (0, 2), (0, 3), (1, 2), (1, 3), (2, 3)]
plt.figure(figsize=(10, 9), facecolor='#FFFFFF')
for i, pair in enumerate(feature_pairs):
# 准备数据
x = x_prime[:, pair]
# 决策树学习
clf = DecisionTreeClassifier(criterion='entropy', min_samples_leaf=3)
dt_clf = clf.fit(x, y)
values.append(float(value))
r += 1
# scipy.sparse.csr_matrix((values, (row, col)))是稀疏数据;XX.toarray()是稠密数据
x = scipy.sparse.csr_matrix((values, (row, col))).toarray()
y = np.array(y)
return x, y
def show_accuracy(a, b, tip):
acc = a.ravel() == b.ravel()
print acc
print tip + '正确率：\t', float(acc.sum()) / a.size
if __name__ == '__main__':
x, y = read_data(wkzutils.get_path_sources("14.agaricus_train.txt"))
x_train, x_test, y_train, y_test = train_test_split(x,
y,
random_state=1,
train_size=0.6)
# Logistic回归
lr = LogisticRegression(penalty='l2')
lr.fit(x_train, y_train.ravel())
y_hat = lr.predict(x_test)
show_accuracy(y_hat, y_test, 'Logistic回归 ')
# XGBoost
y_train[y_train == 3] = 0
y_test[y_test == 3] = 0
data_train = xgb.DMatrix(x_train, label=y_train)
if type == 3:
x = xgb.DMatrix(x)
y = c.predict(x)
y[y > 0.5] = 1
y[~(y > 0.5)] = 0
predictions_file = open("Prediction_%d.csv" % c_type, "wb")
open_file_object = csv.writer(predictions_file)
open_file_object.writerow(["PassengerId", "Survived"])
open_file_object.writerows(zip(passenger_id, y))
predictions_file.close()
if __name__ == "__main__":
x, y = load_data(wkzutils.get_path_sources("14.Titanic.train.csv"), True)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.5,
random_state=1)
#
# lr = LogisticRegression(penalty='l2')
# lr.fit(x_train, y_train)
# y_hat = lr.predict(x_test)
# lr_rate = show_accuracy(y_hat, y_test, 'Logistic回归 ')
# # write_result(lr, 1)
rfc = RandomForestClassifier(n_estimators=100)
rfc.fit(x_train, y_train)
y_hat = rfc.predict(x_test)
rfc_rate = show_accuracy(y_hat, y_test, '随机森林 ')
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from utils import wkzutils
"葡萄酒识别分类"
def show_accuracy(a, b, tip):
acc = a.ravel() == b.ravel()
print acc
print tip + '正确率：\t', float(acc.sum()) / a.size
if __name__ == "__main__":
data = np.loadtxt(wkzutils.get_path_sources("14.wine.data"),
dtype=float,
delimiter=',')
y, x = np.split(data, (1, ), axis=1)
# x = StandardScaler().fit_transform(x)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
random_state=1,
test_size=0.5)
# Logistic回归
lr = LogisticRegression(penalty='l2')
lr.fit(x_train, y_train.ravel())
y_hat = lr.predict(x_test)
show_accuracy(y_hat, y_test, 'Logistic回归 ')
def save_result(model):
data_test_hat = model.predict(data_test)
with open('Prediction.csv', 'wb') as f:
writer = csv.writer(f)
writer.writerow(['ImageId', 'Label'])
for i, d in enumerate(data_test_hat):
writer.writerow([i, d])
# writer.writerows(zip(np.arange(1, len(data_test_hat) + 1), data_test_hat))
if __name__ == "__main__":
classifier_type = 'SVM'
print '载入训练数据...'
t = time()
data = pd.read_csv(wkzutils.get_path_sources("16.MNIST.train.csv"),
header=0,
dtype=np.int)
print '载入完成，耗时%f秒' % (time() - t)
y = data['label'].values
x = data.values[:, 1:]
print '图片个数：%d，图片像素数目：%d' % x.shape
images = x.reshape(-1, 28, 28)
y = y.ravel()
print '载入测试数据...'
t = time()
data_test = pd.read_csv(wkzutils.get_path_sources("16.MNIST.test.csv"),
header=0,
dtype=np.int)
data_test = data_test.values
from sklearn.preprocessing import StandardScaler, MinMaxScaler
from sklearn.naive_bayes import GaussianNB, MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from utils import wkzutils
def iris_type(s):
it = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
return it[s]
if __name__ == "__main__":
data = np.loadtxt(wkzutils.get_path_sources("10.iris.data"),
dtype=float,
delimiter=',',
converters={4: iris_type})
print data
x, y = np.split(data, (4, ), axis=1)
x = x[:, :2]
print x
print y
train_test_split(x, y, train_size=0.8)
gnb = Pipeline([('sc', StandardScaler()), ('clf', GaussianNB())])
# gnb = Pipeline([
# ('sc', MinMaxScaler()),
# ('clf', MultinomialNB())])
