def test(theta):
print '----------------------'
print ur'正在测试'
(raw_data,posiCount) = BinReader.readData(r'c:\data\homework\1218t20_3.bin')
x,real_y,online,result = getXY(np.array(raw_data))
x = mapFeature(x)
values = sigmoid(np.dot(x ,theta))
#第3行是真实的结果，第4行是预测的概率
result[:,3] = values
result = list(result)
result.sort(key=lambda x:x[3],reverse=True)
print ur'共获得结果%d' % sum(values > 0.5)
result = result[:1300]
right = sum([item[2] for item in result])
precision,recall,f1 = print_analyse(right,1300,posiCount)
print ur'测试完毕'
def test(theta):
print '----------------------'
print ur'正在测试'
(raw_data,
posiCount) = BinReader.readData(r'c:\data\homework\1218t20_3.bin')
x, real_y, online, result = getXY(np.array(raw_data))
x = mapFeature(x)
values = sigmoid(np.dot(x, theta))
#第3行是真实的结果，第4行是预测的概率
result[:, 3] = values
result = list(result)
result.sort(key=lambda x: x[3], reverse=True)
print ur'共获得结果%d' % sum(values > 0.5)
result = result[:1300]
right = sum([item[2] for item in result])
precision, recall, f1 = print_analyse(right, 1300, posiCount)
print ur'测试完毕'
from sklearn.ensemble import GradientBoostingClassifier
from BinReader import BinReader
import numpy as np
from sklearn.ensemble.gradient_boosting import GradientBoostingRegressor
(data,label,items) = BinReader.readData(ur'F:\AliRecommendHomeworkData\1212新版\train1217.expand.norm.bin')
X_train = np.array(data)
label = [item[0] for item in label]
y_train = np.array(label)
est = GradientBoostingRegressor(n_estimators=150, learning_rate=0.1,max_depth=3, random_state=0, loss='ls',verbose=1).fit(X_train, y_train)
print 'testing...'
reader = BinReader(ur'F:\AliRecommendHomeworkData\1212新版\test18.expand.norm.bin')
reader.open()
result = [0] * reader.LineCount
for i in xrange(reader.LineCount):
(x,userid,itemid,label) = reader.readline()
x[0] = 1
y = est.predict([x])[0]
result[i] = (userid,itemid,y)
if i % 10000 == 0:
print '%d/%d' % (i,reader.LineCount)
result.sort(key=lambda x:x[2],reverse=True)
result = result[:7000]
print ur'正在输出...'
with open('result.csv','w') as f:
for item in result:
# encoding = utf-8
from sklearn.ensemble import GradientBoostingClassifier
from BinReader import BinReader
import numpy as np
from sklearn.ensemble.gradient_boosting import GradientBoostingRegressor
path_train = ur'data\temp_train.bin'
path_test = ur'data\temp_test.bin'
(data, label, items) = BinReader.readData(path_train)
X_train = np.array(data)
label = [item[0] for item in label]
y_train = np.array(label)
est = GradientBoostingRegressor(n_estimators=150, learning_rate=0.1, max_depth=3, random_state=0, loss='ls',
verbose=1).fit(X_train, y_train)
print 'testing...'
reader = BinReader(path_test)
reader.open()
result = [0] * reader.LineCount
for i in xrange(reader.LineCount):
(x, userid, itemid, label) = reader.readline()
x[0] = 1
y = est.predict([x])[0]
result[i] = (userid, itemid, y)
if i % 10000 == 0:
print '%d/%d' % (i, reader.LineCount)
result.sort(key=lambda x: x[2], reverse=True)
from sklearn.ensemble import GradientBoostingClassifier
from BinReader import BinReader
import numpy as np
from sklearn.ensemble.gradient_boosting import GradientBoostingRegressor
(data,label,items) = BinReader.readData(ur'C:\data\medium\norm\train1217.bin')
X_train = np.array(data)
label = [item[0] for item in label]
y_train = np.array(label)
est = GradientBoostingRegressor(n_estimators=300, learning_rate=0.1,max_depth=5, random_state=0, loss='ls',verbose=1).fit(X_train, y_train)
print 'testing...'
pass
reader = BinReader(ur'C:\data\test1218.bin')
reader.open()
result = [0] * reader.LineCount
for i in xrange(reader.LineCount):
(x,userid,itemid,label) = reader.readline()
x[0] = 1
y = est.predict([x])[0]
result[i] = (userid,itemid,y)
if i % 10000 == 0:
print '%d/%d' % (i,reader.LineCount)
result.sort(key=lambda x:x[2],reverse=True)
result = result[:400]
