How to get a subgraph using SPARQL query in Python

Knowledge Graph is one of the most common forms of Factual Knowledge. Many researches have combined pretrained language model with knowledge graph to improve its performance on NLU tasks. Before injecting the knowledge into the model, we should go through the tagging (named entity recognition), entity grounding (entity linking), and retrieving (e.g. SPARQL)process. This blog is talking about how to get a specific subgraph by SPARQL queries.

Posted on Knowledge Graph

ICM 2021 | Social Network | Cracking the Secret of Musical Influence

We participated in ICM 2021 during Feb 5th - Feb 9th and finally honored Meritorious Winner(Top 7%)😆. Because we 3 people are all music enthusiasts, we chose the problem D about data mining in music similarity and influence. We thought we could do better in this field. It turns out that we were right. Here is our thinking and solution to this problem.

Posted on Social Network

A Renewable Energy Certificate Trading System Based on Blockchain

I participated in this project during my internship at State Grid Blockchain Technology (Beijing) Co., LTD. We designed an energy trading system on blockchain.

Posted on Blockchain

Sentiment Analysis | Netizen Sentiment Recognition During COVID-19

The emergence of the COVID-19 has disrupted our normal life. People’s psychological state can also receive a great negative impact. We chose such a topic with humanistic concern in Data Warehouse and Data Mining course, hoping that through Weibo posts we can gain more insight into people’s emotional state during the COVID-19. We are awarded the best project (1/23) in this course, and we think we could do more in psychological care during COVID-19.

Posted on Natural Language Processing

MCM 2020 | Sentiment Analysis | Find the relationship between review and star ranking

This is my second time for MCM & ICM. I teamed up with two friends. This is how we divide the work: one of my friends collecting information and the other writing the essay. I was responsible for modeling and coding. We finally got Meritorious Winner(Top 5%). I’m so proud of it.

Posted on Natural Language Processing

Predicting the price by its description | ML Algorithms

This is a task in the course Introduction to Data Science. Our team was going to predict the price of products by their description.

Posted on Machine Learning

Forward and backward propagation in neural networks

Deduce forward propagation and back propagation algorithms of neural network with single hidden layer, and program (neural network in ‘Sklearn’ can be used). discuss the impact of 10,30,100,300,1000, different number of hidden nodes on network performance. Explore the influence of different learning rate and iteration times on network performance. Change the standardized method of data to explore the impact on training.

Posted on Machine Learning

Finds and ID3 Algorithm

Implement FindS and ID3 algorithms.

Posted on Machine Learning

Implementation of KNN and Naive_Bayes

Implement kNN and Naive Bayes using Breast_cancer dataset.

Posted on Machine Learning

Fisher, SVM, K-Means and their optimization

Implement Fisher, SVM and K-Means algorithms and optimize them.

Posted on Machine Learning