Commit 69d8cb9

committed

knn_data_num

1 parent 7eb8da3 commit 69d8cb9Copy full SHA for 69d8cb9

File tree

+22

-5

lines changed

+22

-5

lines changed

Lines changed: 1 addition & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -48,7 +48,7 @@`
`48`	`48`	`np.savez('knn_data.npz', train=train, train_labels=train_labels,test=test,test_labels=test_labels)`
`49`	`49`
`50`	`50`	`# Now load the data`
`51`		`-with np.load('knn_data.npz') as data:`
	`51`	`+with np.load('knn_data_num.npz') as data:`
`52`	`52`	`print(data.files)`
`53`	`53`	`train = data['train']`
`54`	`54`	`train_labels = data['train_labels']`

Lines changed: 10 additions & 3 deletions

Original file line number	Diff line number	Diff line change
`@@ -14,7 +14,7 @@`
`14`	`14`
`15`	`15`	`# Load the data, converters convert the letter to a number`
`16`	`16`	`data = np.loadtxt('../data/letter-recognition.data', dtype='float32', delimiter=',',`
`17`		`- converters={0: lambda ch: ord(ch) - ord('A')})`
	`17`	`+ converters={0: lambda ch: ord(ch) - ord('A')})#20000个`
`18`	`18`	`# split the data to two, 10000 each for train and test`
`19`	`19`	`train, test = np.vsplit(data, 2)`
`20`	`20`	`# split trainData and testData to features and responses`
`@@ -29,6 +29,13 @@`
`29`	`29`	`correct = np.count_nonzero(result == labels)`
`30`	`30`	`accuracy = correct * 100.0 / 10000`
`31`	`31`	`print(accuracy)`
`32`		`-#准确率到了 93.22%。同样你可以增加练样本的数来提准确率。`
	`32`	`+#准确率到了 93.22%。同样你可以增加训练样本的数量来提准确率。`
`33`	`33`
`34`		`-#TODO 怎样预测字母?`
	`34`	`+with np.load('knn_data_alphabet.npz') as data:`
	`35`	`+ print(data.files)`
	`36`	`+ train = data['train']`
	`37`	`+ train_labels = data['train_labels']`
	`38`	`+ test = data['test']`
	`39`	`+ test_labels = data['test_labels']`
	`40`	`+`
	`41`	`+#怎样预测字母?跟预测数字的一样`

Lines changed: 10 additions & 0 deletions

Lines changed: 1 addition & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -12,7 +12,7 @@`
`12`	`12`	`import cv2`
`13`	`13`	`from matplotlib import pyplot as plt`
`14`	`14`
`15`		`-with np.load('knn_data.npz') as data:`
	`15`	`+with np.load('knn_data_num.npz') as data:`
`16`	`16`	`print(data.files)`
`17`	`17`	`train = data['train']`
`18`	`18`	`train_labels = data['train_labels']`

Comments

(0)