=======================
from __future__ import print_function
from sklearn import preprocessing # 用來 normalization
from sklearn.model_selection import train_test_split
from sklearn.datasets.samples_generator import make_classification # 製造 Data
from sklearn.svm import SVC # ML 方法
import matplotlib.pyplot as plt # 畫圖
X, y = make_classification(n_samples=300, n_features=2 , n_redundant=0, n_informative=2,
random_state=22, n_clusters_per_class=1, scale=100,n_classes=2)
# 300 組數據 ， 每一組數據有兩個 features ，Target => 2 個 (n_classes=2)
plt.scatter(X[:, 0], X[:, 1], c=y)
plt.show()
X = preprocessing.minmax_scale(X,feature_range=(0,1)) # normalization step 壓縮到(0~1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)
clf = SVC()
clf.fit(X_train, y_train) # ML
print(clf.score(X_test, y_test)) # ML Score 0.9
# 0.4444444444444444 (No normalization)
=======================
參考
https://morvanzhou.github.io/tutorials/machine-learning/sklearn/3-1-normalization/
https://blog.csdn.net/pipisorry/article/details/52247379
https://blog.csdn.net/u013634684/article/details/49646311
留言列表
C 語言 (1)
