Machine Learning Datasets
机器学习数据集

此存储库包含 MachineLearningMastery.com 教程中使用的机器学习数据集的副本。

创建此存储库是为了确保教程中使用的数据集保持可用，并且不依赖于不可靠的第三方。

所有回归和分类问题 CSV 文件都没有标题行，列之间没有空格，目标是最后一列，缺失值用问号字符 （'？'） 标记。

在许多情况下，教程将直接链接到原始数据集 URL，因此数据集文件名在添加到存储库后不应更改。

Datasets
本部分提供此存储库中数据集的摘要。

Binary Classification Datasets【二值分类数据集】
Breast Cancer (Wisconsin) (breast-cancer-wisconsin.csv)
Breast Cancer (Yugoslavia) (breast-cancer.csv)
Breast Cancer (Haberman's) (haberman.csv)
Bank Note Authentication (banknote_authentication.csv)
Horse Colic (horse-colic.csv)
Ionosphere (ionosphere.csv)
Pima Indians Diabetes (pima-indians-diabetes.csv)
Sonar Returns (sonar.csv)
German Credit (german.csv)
Credit Card Fraud (creditcard.csv.zip)
Adult Income (adult-all.csv)
Mammography (mammography.csv)
Oil Spill (oil-spill.csv)
Phoneme (phoneme.csv)

Multiclass Classification Datasets【多类分类数据集】
Glass Identification (glass.csv)
Iris Flower Species (iris.csv)
Wheat Seeds (wheat-seeds.csv)
Wine (wine.csv)
Ecoli (ecoli.csv)
Thyroid Gland (new-thyroid.csv)

Regression Datasets【回归的数据集】
Boston Housing (housing.csv)
Auto Insurance Total Claims (auto-insurance.csv)
Auto Imports Prices (auto_imports.csv)
Abalone Age (abalone.csv)
Wine Quality Red (winequality-red.csv)
Wine Quality White (winequality-white.csv)

Univariate Time Series Datasets【单变量时间序列数据集】
Daily Minimum Temperatures in Melbourne (daily-min-temperatures.csv)
Daily Maximum Temperatures in Melbourne (daily-max-temperatures.csv)
Daily Female Births in California (daily-total-female-births.csv)
Monthly International Airline Passengers (monthly-airline-passengers.csv)
Monthly Armed Robberies in Boston (monthly-robberies.csv)
Monthly Sunspots (monthly-sunspots.csv)
Monthly Champagne Sales (monthly_champagne_sales.csv)
Monthly Shampoo Sales (monthly-shampoo-sales.csv)
Monthly Car Sales (monthly-car-sales.csv)
Monthly Mean Temperatures in Nottingham Castle (monthly-mean-temp.csv)
Monthly Specialty Writing Paper Sales (monthly-writing-paper-sales.csv)
Yearly Water Usage in Baltimore (yearly-water-usage.csv)

Multivariate Time Series Datasets【多元时间序列数据集】
Hourly Pollution Levels in Beijing (pollution.csv)
Minutely Individual Household Electric Power Consumption (household_power_consumption.zip)
Human Activity Recognition Using Smartphones (HAR_Smartphones.zip)
Indoor Movement Prediction (IndoorMovement.zip)
Yearly Longley Economic Employment (longley.csv)

Natural Language Processing【自然语言处理】
Flickr 8k Photo Caption Dataset (Flickr8k_Dataset.zip, Flickr8k_text.zip)
Movie Review Polarity (review_polarity.tar.gz)
German to English Translation (deu-eng.txt)
The Republic, by Plato (republic.txt)

ARFF Datasets【飞机救援消防的数据集】
Weka UCI Datasets (weka-datasets.zip)
Weka Numeric Datasets (weka-datasets-numeric.zip)