Dataset
Breast Cancer Diagnostic Data (ZIP)
569 instances with 30 real-valued features computed from digitized FNA images, used for malignant/benign classification
—Records
50.1 KBFile size
ZIPDelivery formats
—Data updated
Breast Cancer Wisconsin · Ace Data Cloud
Wisconsin Breast Cancer Diagnostic Dataset：
Medical AI's Classic Benchmark
UCI classic medical dataset, containing 569 samples and 30 real-valued features extracted from fine needle aspiration (FNA) images for the classification of malignant and benign breast tumors—standard starting point for medical artificial intelligence research.
ZIP format · 50 KB
CC BY 4.0 License
UCI Machine Learning Classic Dataset
569
Number of Samples
30
Number of Features
2
Number of Classes (Malignant/Benign)
50KB
Data Size
Dataset Highlights
The Wisconsin Breast Cancer Diagnostic Dataset is one of the most popular benchmark datasets in the field of medical AI.
Medical Diagnosis
Real clinical data on breast tumor diagnoses, sourced from fine needle aspiration biopsy cases at the University of Wisconsin Hospital, with genuine medical research value.
High-Dimensional Features
30 precise features extracted from FNA images, covering the mean, standard deviation, and maximum values of 10 metrics including the radius, texture, perimeter, and area of the cell nucleus.
Binary Classification
Classification task of malignant (Malignant) versus benign (Benign), with a clear objective, making it an ideal dataset for evaluating binary classification algorithms.
UCI Classic
One of the most influential classic datasets in the field of machine learning, widely cited and used in countless papers, tutorials, and courses around the world.
No Missing Values
The data is complete and clean, requiring no complex preprocessing or missing value imputation, suitable for quick experiments and algorithm comparisons.
Interpretability
The meaning of features is clear, with each feature having a distinct physical significance, making it very suitable for research on interpretability in medical AI and feature importance analysis.
Applicable Scenarios
From disease diagnosis to model interpretation - common uses of the Wisconsin breast cancer dataset
Disease Diagnosis Classification
Train models such as SVM, random forests, and logistic regression to achieve automatic classification of breast tumors as malignant/benign
Feature Selection
Utilize 30-dimensional features for feature importance ranking, dimensionality reduction analysis, and redundant feature selection research
Model Interpretability
Use methods like SHAP and LIME to explain model predictions, promoting the trustworthy application of medical AI
Medical AI Education
As a standard teaching dataset for medical artificial intelligence courses, helping students understand clinical data modeling
Data Preview
Sample examples from the Wisconsin breast cancer diagnostic dataset
id,diagnosis,radius_mean,texture_mean,perimeter_mean,area_mean,smoothness_mean 842302,M,17.99,10.38,122.80,1001.0,0.11840 842517,M,20.57,17.77,132.90,1326.0,0.08474 84300903,M,19.69,21.25,130.00,1203.0,0.10960 84348301,M,11.42,20.38,77.58,386.1,0.14250 84358402,M,20.29,14.34,135.10,1297.0,0.10030
id Sample ID
diagnosis Diagnosis Result
radius_mean Mean Radius
texture_mean Mean Texture
perimeter_mean Mean Perimeter
area_mean Mean Area
smoothness_mean Mean Smoothness
3 Steps to Get Started Quickly
From browsing to usage, just a few minutes
01
Browse the Dataset
View detailed descriptions, field definitions, and data previews of the Wisconsin Breast Cancer dataset on the Ace Data Cloud platform.
02
Download ZIP File
One-click download of a 50 KB ZIP file to your local machine, no registration, no payment, get it immediately.
03
Load and Use
Load the data with Python and scikit-learn, start training classification models or performing interpretability analysis.
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.metrics import classification_report
# Load data
df = pd.read_csv("breast-cancer-wisconsin.csv")
# Features and labels
X = df.drop(columns=["id", "diagnosis"])
y = df["diagnosis"]
# Standardize features
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
# Split into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(
X_scaled, y, test_size=0.3, random_state=42
)
# Train SVM classifier
clf = SVC(kernel="rbf", random_state=42)
clf.fit(X_train, y_train)
# Evaluate model
y_pred = clf.predict(X_test)
print(classification_report(y_test, y_pred, target_names=["Benign (B)", "Malignant (M)"]))
Support Medical AI Research
The Wisconsin Breast Cancer Diagnostic Dataset is a classic benchmark for medical AI research. Download for free and start exploring immediately.
Introduction
Datasets
Pricing