GithubHelp home page GithubHelp logo

ctr_xlearn's People

Contributors

fly12357 avatar

Stargazers

 avatar  avatar  avatar

Watchers

 avatar

ctr_xlearn's Issues

预测速度不快

您好,按照您给的方法,预测主要分成两部分,线性和非线性两块,上线后发现了一个问题,预测两百个条目,当压力上来时,较慢,如果超过100毫秒算超时的话,超时挺多的,我已将模型和预测的条目都缓存到本地了,想问问有没有,更好的办法,提升预测的速度,谢谢!(60个field, 8w向量,模型500w行)。

结果不正确

首先很荣幸能看到你的代码,
目前有问题想咨询您:
用你提供的预测方式,跟xlearn 自带的预测结果不同:
ffm_model.setTest("./single_predict_data") # 测试数据
ffm_model.predict("./model.out", "./output1.txt")

我用的是xlearn0.44, 甚至xlearn新开发的api也不行
string = "0,1:22166:1,2:22169:1,3:22175:1,4:22302:1,5:0:1,6:6:1,7:16:1,8:18:1,9:39:1,10:1062:1,11:1079:1,12:1089:1,13:1092:1,14:1094:1,15:1096:1,16:1098:1,17:1100:1,18:1102:1,19:1104:1,20:1107:1,21:1108:1,22:1110:1,23:1114:1,24:1564:1,25:20787:1,26:20804:1,27:20914:1,28:22161:1,29:181:1,30:20804:1,31:20993:1,32:1117:1,33:1062:1,34:1474:1,35:1095:1,36:1096:1,37:1104:1,38:1101:1,39:1080:1,29:181:1,30:20804:1,31:20993:1,32:1117:1,33:1062:1,34:1474:1,35:1095:1,36:1096:1,37:1104:1,38:1101:1,39:1080:1"
r = string.split(',')
X = [0]*22320
field_map = [0]*22320
for index, i in enumerate(r):
if index == 0:
continue
field_value = int(i.split(':')[0])
feature_index = int(i.split(':')[1])
feature_value = int(i.split(':')[2])
X[feature_index] = feature_value
field_map[feature_index] = field_value

X = np.array(X)
X = X.reshape((1, -1))
X = check_array(X, accept_sparse=['csr'])
test_set = xl.DMatrix(X, None, field_map=field_map)
fm_model = xl.create_ffm() # Use factorization machine
fm_model.setTest(test_set)
fm_model.disableNorm()
pred = fm_model.predict('./model.out')
print(pred)

想问您遇到过此问题吗。是否xlearn有了一些额外的逻辑?

非常感谢您的回答。

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.