The translucent search box now floats inside the hero area below the banner title. Pick a dropdown suggestion and the page will jump to the matching item inside the same resource card with stronger highlighting.
This page hosts public download resources, including algorithm project files, handwritten digit project files, and the newly added calculus PDF.
Gaoshu Lianxi
A public advanced calculus practice PDF for local review or printing.
Gaoshu Lianxi PDF
The original uploaded file was 练习.pdf; the public filename is gaoshu-lianxi.pdf.
Iris K-means learning bundle
Everything below belongs to the same article: K-means 聚类算法入门：基于 Iris 数据集的 C 语言实现.
You can read the article first, or download the dataset, source code, flowchart, visualization, and zip archive from this single grouped card.
K-means article
The article now includes a detailed flowchart and a 2D scatter visualization of the clustering result.
Iris.csv
The original Iris dataset with 150 samples, 4 numeric features, and 3 species labels.
Iris_sort_K_mean.c
The refined C implementation with command-line file input, feature standardization, K-means++ initialization, multi-restart selection, and SSE reporting.
Cluster visualization
Download iris-kmeans-cluster-visual.svg
This scatter plot is generated from the current Iris_sort_K_mean.c clustering result using petal length and petal width as the 2D projection axes.
Zip package
Download iris-kmeans-materials.zip
The archive contains Iris.csv, Iris_sort_K_mean.c, the SVG flowchart, and the SVG visualization.
Handwritten digit project bundle
This group belongs to the handwritten digit project series. The materials now connect the dataset article, the C softmax classifier, and the browser playground into one public bundle.
A good order is: start with the dataset article, continue with the C classifier article, and then try the playground.
Handwritten digit dataset article
Start with train.csv, test.csv, labels, and the 784-feature image format before reading the classifier implementation.
digit_softmax_classifier.c
Download digit_softmax_classifier.c
The C source includes CSV loading, normalization, softmax probability calculation, parameter updates, and submission export.
train.csv.zip
The compressed training set with 42000 labeled handwritten digit samples.
test.csv.zip
The compressed test set with 28000 unlabeled samples for final prediction export.
digit-playground-model.json
Download digit-playground-model.json
The compact softmax demo model and sample set used by the browser playground.
digit-sample-grid.svg
Download digit-sample-grid.svg
A small preview grid generated from the handwritten digit training set.
Handwritten digit bundle
Download handwritten-digits-materials.zip
The archive contains the C source, compressed train and test sets, submission files, the browser model JSON, and the preview SVG.