下载UCI数据集《Secondary Mushroom》

说明：

查看代码

1. Title: Primary mushroom data2. Sources:(a) Mushroom species drawn from source book:Patrick Hardin.Mushrooms & Toadstools.Zondervan, 1999(b) Inspired by this mushroom data:Jeff Schlimmer.Mushroom Data Set. Apr. 1987.url:https://archive.ics.uci.edu/ml/datasets/Mushroom.(c) Repository containing the related Python scripts and all the data sets: https://mushroom.mathematik.uni-marburg.de/files/ (d) Author: Dennis Wagner(e) Date: 05 September 20203. Relevant information:This dataset includes 173 species of mushrooms with caps from various families and oneentry for each species.Each species is identified as definitely edible, definitely poisonous, or of unknownedibility and not recommended (the latter class was combined with the poisonous class).Of the 20 variables, 17 are nominal and 3 are metrical. The values of each nominal variableare a set of possible values and for the metrical variables a range of possible values.4. Data generation:The related Python project (Sources (c)) contains a Python module primary_data_generation.pyused to generate a first version of this data from the HTML version of the book (Sources (a))found in primary_data_generated.csv.The primary data is cleaned and enriched by going through the book manually resulting inprimary_data_edited.csv (used for the simulation of the secondary data).5. Class information:1. family		String of the name of the family of mushroom species (multinomial)2. name			String of the of the mushroom species (multinomial)3. class		poisonous=p, edibile=e (binary)6. Variable Information:(n: nominal, m: metrical; nominal values as sets of values)1. cap-diameter (m):			float number(s) in cmtwo values=min max, one value=mean2. cap-shape (n):            bell=b, conical=c, convex=x, flat=f,sunken=s, spherical=p, others=o3. cap-surface (n):          fibrous=i, grooves=g, scaly=y, smooth=s,shiny=h, leathery=l, silky=k, sticky=t,wrinkled=w, fleshy=e4. cap-color (n):            brown=n, buff=b, gray=g, green=r, pink=p,purple=u, red=e, white=w, yellow=y, blue=l, orange=o,  black=k5. does-bruise-bleed (n):	bruises-or-bleeding=t,no=f6. gill-attachment (n):      adnate=a, adnexed=x, decurrent=d, free=e, sinuate=s, pores=p, none=f, unknown=?7. gill-spacing (n):         close=c, distant=d, none=f8. gill-color (n):           see cap-color + none=f9. stem-height (m):			float number(s) in cmtwo values=min max, one value=mean10. stem-width (m):			float number(s) in mmtwo values=min max, one value=mean	   11. stem-root (n):           bulbous=b, swollen=s, club=c, cup=u, equal=e,rhizomorphs=z, rooted=r12. stem-surface (n): 		see cap-surface + none=f13. stem-color (n):			see cap-color + none=f14. veil-type (n):           partial=p, universal=u15. veil-color (n):          see cap-color + none=f16. has-ring (n):            ring=t, none=f17. ring-type (n):           cobwebby=c, evanescent=e, flaring=r, grooved=g, large=l, pendant=p, sheathing=s, zone=z, scaly=y, movable=m, none=f, unknown=?18. spore-print-color (n):   see cap color19. habitat (n):             grasses=g, leaves=l, meadows=m, paths=p, heaths=h,urban=u, waste=w, woods=d20. season (n):				spring=s, summer=u, autumn=a, winter=w

注意：

1. 要开魔法才能运行，把数据集下载下来。
2. 在下载依赖包后，在PyCharm中还是会报错，但是不用管，只要开魔法就行

具体代码：

# pip install ucimlrepo
# https://archive.ics.uci.edu/dataset/848/secondary+mushroom+dataset
from ucimlrepo import fetch_ucirepo
import os
import pandas as pd# 创建数据保存目录（如果不存在）
data_dir = r'd:\PycharmProjects\机器学习大作业\data2'
os.makedirs(data_dir, exist_ok=True)# 下载数据集
secondary_mushroom = fetch_ucirepo(id=848)# 获取特征和目标数据
X = secondary_mushroom.data.features
y = secondary_mushroom.data.targets# 合并并保存完整数据集
full_data = pd.concat([X, y], axis=1)
full_data.to_csv(os.path.join(data_dir, 'full_dataset.csv'), index=False)print(f"数据集已成功保存到 {data_dir} 目录")