# Diamond Price Prediction — Data

来源：https://www.kaggle.com/competitions/diamond-price-prediction-competition/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

This dataset contains the prices and physical attributes of 53,940 diamonds. It is a classic dataset for regression analysis, where the goal is to predict the market value (price) based on a mix of continuous and categorical features.Feature DictionaryColumnTypeDescriptionpriceIntegerPrice in US dollars ($326–$18,823). This is the target variable.caratFloatWeight of the diamond (0.2–5.01).cutCategoricalQuality of the cut (Fair, Good, Very Good, Premium, Ideal).colorCategoricalDiamond color, from J (worst) to D (best).clarityCategoricalMeasurement of how clear the diamond is (I1 (worst), SI2, SI1, VS2, VS1, VVS2, VVS1, IF (best)).xFloatLength in mm (0–10.74).yFloatWidth in mm (0–58.9).zFloatDepth in mm (0–31.8).depthFloatTotal depth percentage = z / mean(x, y) = 2 * z / (x + y). Range: 43–79.tableFloatWidth of the top of the diamond relative to the widest point. Range: 43–95.Attribute DetailsThe 4 Cs: The dataset includes the four industry-standard benchmarks: Carat (weight), Cut (quality of the shape), Color (rarity of the hue), and Clarity (purity/lack of inclusions).Dimensions: The x, y, and z columns provide the raw physical measurements. Note that some diamonds in the set may have a value of 0 for these dimensions, which represents missing or erroneous data that should be addressed during preprocessing.Proportions: The depth and table features are calculated percentages used by gemologists to determine how well the diamond reflects light. Table specifically refers to the width of the flat facet on the very top of the stone.Dataset StatisticsTotal Records: 53,940Total Columns: 10Categorical Features: 3 (Cut, Color, Clarity)Numerical Features: 7 (Price, Carat, Depth, Table, x, y, z)