头歌·深入浅出 Python 机器学习：数据生成

第1关：生成分类数据集

from sklearn.datasets import make_blobs

import numpy as np

samples=int(input())

classNum=int(input())

random_state=int(input())

data=make_blobs(n_samples=samples, centers=classNum, random_state=random_state)

X, y=data

print(round(np.mean(X),2))#均值np.mean()

第2关：生成回归数据集

from sklearn.datasets import make_regression

import numpy as np

samples=int(input())

random_state=int(input())

data=make_regression(n_samples=samples,  random_state=random_state)

X, y=data

print(round(np.mean(y),2))

第3关：给数据添加噪音

from sklearn.datasets import make_classification

import numpy as np

samples=int(input())

classNum=int(input())

random_state=int(input())

noise=int(input())

info=int(input())

data=make_classification(n_samples=samples, n_informative=info, n_classes =classNum, flip_y=noise ,random_state=random_state)

X, y=data

print(round(np.mean(X), 2))

第4关：使用内置数据集

from sklearn.datasets import load_wine

from sklearn.model_selection import train_test_split

import numpy as np

test_ratio=float(input())

data=load_wine()

X_train, X_test, Y_train, Y_test = train_test_split(data['data'], data['target'], test_size=test_ratio, random_state=1)

print(round(np.var(X_train),1))#方差np.var()

print(round(np.var(X_test),1))