Python機器學習筆記(十三)：使用Scikit-Learn建立資料集

Yanwei Liu

·

Follow

4 min read

·

Apr 23, 2019

--

Share

Blob分類資料

from sklearn.datasets.samples_generator import make_blobs
from matplotlib import pyplot
from pandas import DataFrame
# generate 2d classification dataset
X, y = make_blobs(n_samples=100, centers=3, n_features=2)
# scatter plot, dots colored by class value
df = DataFrame(dict(x=X[:,0], y=X[:,1], label=y))
colors = {0:'red', 1:'blue', 2:'green'}
fig, ax = pyplot.subplots()
grouped = df.groupby('label')
for key, group in grouped:
    group.plot(ax=ax, kind='scatter', x='x', y='y', label=key, color=colors[key])
pyplot.show()

衛星分類資料

from sklearn.datasets import make_moons
from matplotlib import pyplot
from pandas import DataFrame
# generate 2d classification dataset
X, y = make_moons(n_samples=100, noise=0.1)
# scatter plot, dots colored by class value
df = DataFrame(dict(x=X[:,0], y=X[:,1], label=y))
colors = {0:'red', 1:'blue'}
fig, ax = pyplot.subplots()
grouped = df.groupby('label')
for key, group in grouped:
    group.plot(ax=ax, kind='scatter', x='x', y='y', label=key, color=colors[key])
pyplot.show()

同星圓分類資料

from sklearn.datasets import make_circles
from matplotlib import pyplot
from pandas import DataFrame
# generate 2d classification dataset
X, y = make_circles(n_samples=100, noise=0.05)
# scatter plot, dots colored by class value
df = DataFrame(dict(x=X[:,0], y=X[:,1], label=y))
colors = {0:'red', 1:'blue'}
fig, ax = pyplot.subplots()
grouped = df.groupby('label')
for key, group in grouped:
    group.plot(ax=ax, kind='scatter', x='x', y='y', label=key, color=colors[key])
pyplot.show()

回歸資料

from sklearn.datasets import make_regression
from matplotlib import pyplot
# generate regression dataset
X, y = make_regression(n_samples=100, n_features=1, noise=0.1)
# plot regression dataset
pyplot.scatter(X,y)
pyplot.show()