设计了一个用于从头开始特征提取的层次聚类框架，应用于使用聚类分析的90K+行数据...
Devised a hierarchical clustering framework for feature extraction from scratch, applied to 90K+ rows data using cluster centroids. Transformed data enhanced KNN classifier performance from 90% to 97%, confirmed via K-fold cross-validation & base classification comparison. (2023-05-08, Jupyter Notebook, 311KB, 下载0次)
利用特征提取至少97.5%的时间正确分类猫和狗的图片
Leverages feature extraction to correctly classify pictures of cats and dogs at least 97.5% of the time (2019-02-24, Jupyter Notebook, 2KB, 下载0次)
对具有10个细胞核特征（半径、纹理等）的数字化质量图像进行统计EDA和归一化分析...
Performed statistical-EDA and normalization analysis on digitized mass images with 10 nuclei features (radius, texture) Predicted malignant - benign cancer using Logistic, LDA-QDA, KNN, Lasso-Ridge classifiers with 0.89, 0.88, 0.92, 0.96 and 0.97 accuracies respectively along with decision boundaries and ROC curves (2022-03-18, Jupyter Notebook, 1293KB, 下载0次)
一种新的基于逻辑分类的酒店评论情绪分析方法，具有高F1分（0.97）
A novel hotel review sentiment analysis method with a high F1 score (0.97) based on logistic classification (2017-03-07, Jupyter Notebook, 881KB, 下载0次)
开发了一个分类模型，使用TF-IDF矢量器和L...
Developed a Classification model that identifies personal attacks in Wikipedia comments using TF-IDF Vectorizer and LinearSVC with F1-Score of 0.97 (2020-12-21, Jupyter Notebook, 25075KB, 下载0次)