Có mô-đun AI trong Python không?

Machine Learning, như tên cho thấy, là khoa học lập trình máy tính mà chúng có thể học từ các loại dữ liệu khác nhau. Một định nghĩa tổng quát hơn do Arthur Samuel đưa ra là – “Machine Learning là lĩnh vực nghiên cứu cung cấp cho máy tính khả năng học hỏi mà không cần lập trình rõ ràng. ” Chúng thường được sử dụng để giải quyết các loại vấn đề khác nhau trong cuộc sống.  

Trước đây, mọi người thường thực hiện các tác vụ Học máy bằng cách mã hóa thủ công tất cả các thuật toán và công thức toán học và thống kê. Điều này làm cho việc xử lý tốn thời gian, tẻ nhạt và không hiệu quả. Nhưng trong thời hiện đại, nó trở nên rất dễ dàng và hiệu quả hơn so với ngày xưa với nhiều thư viện, khung và mô-đun python khác nhau. Ngày nay, Python là một trong những ngôn ngữ lập trình phổ biến nhất cho nhiệm vụ này và nó đã thay thế nhiều ngôn ngữ trong ngành, một trong những lý do là bộ sưu tập thư viện khổng lồ của nó. Các thư viện Python được sử dụng trong Machine Learning là.  
 

• Nặng nề
• scipy
• Scikit-học
• theano
• TenorFlow
• máy ảnh
• PyTorch
• gấu trúc
• Matplotlib

 

Nặng nề

 

NumPy là một thư viện python rất phổ biến để xử lý ma trận và mảng đa chiều lớn, với sự trợ giúp của một bộ sưu tập lớn các hàm toán học cấp cao. Nó rất hữu ích cho các tính toán khoa học cơ bản trong Machine Learning. Nó đặc biệt hữu ích cho các khả năng đại số tuyến tính, biến đổi Fourier và số ngẫu nhiên. Các thư viện cao cấp như TensorFlow sử dụng NumPy nội bộ để thao tác với Tensors.  
 

Python3

# Python program using NumPy

# for some basic mathematical

# operations

 

import

!pip install imageio
import imageio
from imageio import imread, imsave

0

 

!pip install imageio
import imageio
from imageio import imread, imsave

1

!pip install imageio
import imageio
from imageio import imread, imsave

2

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

4_______0_______5

!pip install imageio
import imageio
from imageio import imread, imsave

6

!pip install imageio
import imageio
from imageio import imread, imsave

7

!pip install imageio
import imageio
from imageio import imread, imsave

8

!pip install imageio
import imageio
from imageio import imread, imsave

9

!pip install imageio
import imageio
from imageio import imread, imsave

6

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

1

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

2

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

3

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

4_______11_______6

!pip install imageio
import imageio
from imageio import imread, imsave

6

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

8

!pip install imageio
import imageio
from imageio import imread, imsave

8

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

0

!pip install imageio
import imageio
from imageio import imread, imsave

6

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

2

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

2

 

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

4

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

5

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

7

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

8_______0_______6

[ 5 12 21 32]

0

[ 5 12 21 32]

1

[ 5 12 21 32]

2_______0_______3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

7

[ 5 12 21 32]

5

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

7

[ 5 12 21 32]

1

 

[ 5 12 21 32]

9

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0_______40_______1

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

2

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

3

 

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

4

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0_______40_______6

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

2

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

3

 

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

9

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0____382_______1

đầu ra.  
 

219 

[29 67] 

[[19 22]
 [43 50]]

Để biết thêm chi tiết tham khảo Numpy.  
  
 

khoa học viễn tưởng

SciPy là một thư viện rất phổ biến đối với những người đam mê Machine Learning vì nó chứa các mô-đun khác nhau để tối ưu hóa, đại số tuyến tính, tích hợp và thống kê. Có sự khác biệt giữa thư viện SciPy và ngăn xếp SciPy. SciPy là một trong những gói cốt lõi tạo nên ngăn xếp SciPy. SciPy cũng rất hữu ích cho thao tác hình ảnh.   

Python3

# Python program using NumPy2

# Python program using NumPy3

 

# Python program using NumPy4 # Python program using NumPy5import # Python program using NumPy7

 

# Python program using NumPy8

# Python program using NumPy9

!pip install imageio
import imageio
from imageio import imread, imsave

3 # for some basic mathematical1# for some basic mathematical2

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

3# for some basic mathematical4

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0____383_______6

 

# for some basic mathematical7

# for some basic mathematical8

!pip install imageio
import imageio
from imageio import imread, imsave

3 # Python program using NumPy9# operations1 # operations2

!pip install imageio
import imageio
from imageio import imread, imsave

5

!pip install imageio
import imageio
from imageio import imread, imsave

6# operations5

!pip install imageio
import imageio
from imageio import imread, imsave

6# operations7# operations8

 

# operations9

import0import1import2

 

import3

import4

!pip install imageio
import imageio
from imageio import imread, imsave

3 import6import7

!pip install imageio
import imageio
from imageio import imread, imsave

6import7

!pip install imageio
import imageio
from imageio import imread, imsave

00

 

!pip install imageio
import imageio
from imageio import imread, imsave

01

import0

!pip install imageio
import imageio
from imageio import imread, imsave

03

!pip install imageio
import imageio
from imageio import imread, imsave

04

Nếu scipy. misc nhập imread, imsave, imresize không hoạt động trên hệ điều hành của bạn, thay vào đó hãy thử mã bên dưới để tiếp tục với mã trên

!pip install imageio
import imageio
from imageio import imread, imsave

Ảnh gốc.  

Hình ảnh được tô màu.  
 

Đã thay đổi kích thước hình ảnh được tô màu.  
 

Để biết thêm chi tiết tham khảo tài liệu.  
  
 

Scikit-học

 

Scikit-learning là một trong những thư viện ML phổ biến nhất cho các thuật toán ML cổ điển. Nó được xây dựng dựa trên hai thư viện Python cơ bản, viz. , NumPy và SciPy. Scikit-learning hỗ trợ hầu hết các thuật toán học có giám sát và không giám sát. Scikit-learning cũng có thể được sử dụng để khai thác dữ liệu và phân tích dữ liệu, điều này làm cho nó trở thành một công cụ tuyệt vời cho những người mới bắt đầu với ML.  
 

 

Python3

!pip install imageio
import imageio
from imageio import imread, imsave

05

!pip install imageio
import imageio
from imageio import imread, imsave

06

 

!pip install imageio
import imageio
from imageio import imread, imsave

07

# Python program using NumPy4

!pip install imageio
import imageio
from imageio import imread, imsave

09import

!pip install imageio
import imageio
from imageio import imread, imsave

11

# Python program using NumPy4

!pip install imageio
import imageio
from imageio import imread, imsave

09import

!pip install imageio
import imageio
from imageio import imread, imsave

15

# Python program using NumPy4

!pip install imageio
import imageio
from imageio import imread, imsave

17import

!pip install imageio
import imageio
from imageio import imread, imsave

19

 

!pip install imageio
import imageio
from imageio import imread, imsave

20

!pip install imageio
import imageio
from imageio import imread, imsave

21

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

23

 

!pip install imageio
import imageio
from imageio import imread, imsave

24

!pip install imageio
import imageio
from imageio import imread, imsave

25

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

27

!pip install imageio
import imageio
from imageio import imread, imsave

28

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0______0_______30

 

!pip install imageio
import imageio
from imageio import imread, imsave

31

!pip install imageio
import imageio
from imageio import imread, imsave

32______0_______3

!pip install imageio
import imageio
from imageio import imread, imsave

34

!pip install imageio
import imageio
from imageio import imread, imsave

35

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

37

 

!pip install imageio
import imageio
from imageio import imread, imsave

38

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0_______0_______40

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0_______0_______42

đầu ra.  
 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

  
Để biết thêm chi tiết tham khảo tài liệu.  
  
 

theano

 

Chúng ta đều biết rằng Machine Learning về cơ bản là toán học và thống kê. Theano là một thư viện python phổ biến được sử dụng để xác định, đánh giá và tối ưu hóa các biểu thức toán học liên quan đến mảng nhiều chiều một cách hiệu quả. Nó đạt được bằng cách tối ưu hóa việc sử dụng CPU và GPU. Nó được sử dụng rộng rãi để kiểm tra đơn vị và tự xác minh để phát hiện và chẩn đoán các loại lỗi khác nhau. Theano là một thư viện rất mạnh đã được sử dụng trong các dự án khoa học chuyên sâu tính toán quy mô lớn trong một thời gian dài nhưng đủ đơn giản và dễ tiếp cận để các cá nhân sử dụng cho các dự án của riêng họ.  
 

Python3

!pip install imageio
import imageio
from imageio import imread, imsave

43

!pip install imageio
import imageio
from imageio import imread, imsave

44

!pip install imageio
import imageio
from imageio import imread, imsave

45

 

import

!pip install imageio
import imageio
from imageio import imread, imsave

47

import

!pip install imageio
import imageio
from imageio import imread, imsave

49

!pip install imageio
import imageio
from imageio import imread, imsave

2

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

52_______0_______53

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

3

!pip install imageio
import imageio
from imageio import imread, imsave

55

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

5

!pip install imageio
import imageio
from imageio import imread, imsave

58

!pip install imageio
import imageio
from imageio import imread, imsave

59

!pip install imageio
import imageio
from imageio import imread, imsave

5

!pip install imageio
import imageio
from imageio import imread, imsave

61

!pip install imageio
import imageio
from imageio import imread, imsave

62

!pip install imageio
import imageio
from imageio import imread, imsave

63

!pip install imageio
import imageio
from imageio import imread, imsave

64

!pip install imageio
import imageio
from imageio import imread, imsave

65

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

67

!pip install imageio
import imageio
from imageio import imread, imsave

68

!pip install imageio
import imageio
from imageio import imread, imsave

69

!pip install imageio
import imageio
from imageio import imread, imsave

6

!pip install imageio
import imageio
from imageio import imread, imsave

5_______0_______8

!pip install imageio
import imageio
from imageio import imread, imsave

63

!pip install imageio
import imageio
from imageio import imread, imsave

5

!pip install imageio
import imageio
from imageio import imread, imsave

6

!pip install imageio
import imageio
from imageio import imread, imsave

63

!pip install imageio
import imageio
from imageio import imread, imsave

7

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

2

đầu ra.  
 

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

Để biết thêm chi tiết tham khảo tài liệu.  
  
 

TenorFlow

TensorFlow là một thư viện nguồn mở rất phổ biến dành cho tính toán số hiệu suất cao do nhóm Google Brain ở Google phát triển. Đúng như tên gọi, Tensorflow là một framework liên quan đến việc xác định và chạy các tính toán liên quan đến tenxơ. Nó có thể đào tạo và chạy các mạng thần kinh sâu có thể được sử dụng để phát triển một số ứng dụng AI. TensorFlow được sử dụng rộng rãi trong lĩnh vực nghiên cứu và ứng dụng deep learning.  

Thí dụ

Python3

!pip install imageio
import imageio
from imageio import imread, imsave

79

!pip install imageio
import imageio
from imageio import imread, imsave

80

 

!pip install imageio
import imageio
from imageio import imread, imsave

81

import

!pip install imageio
import imageio
from imageio import imread, imsave

83

 

!pip install imageio
import imageio
from imageio import imread, imsave

84

!pip install imageio
import imageio
from imageio import imread, imsave

85

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

87

!pip install imageio
import imageio
from imageio import imread, imsave

5_______0_______6

!pip install imageio
import imageio
from imageio import imread, imsave

7

!pip install imageio
import imageio
from imageio import imread, imsave

6

!pip install imageio
import imageio
from imageio import imread, imsave

9

!pip install imageio
import imageio
from imageio import imread, imsave

6

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

1

[ 5 12 21 32]

1

!pip install imageio
import imageio
from imageio import imread, imsave

96

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

87

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

6

!pip install imageio
import imageio
from imageio import imread, imsave

6

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

8

!pip install imageio
import imageio
from imageio import imread, imsave

6

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

0

!pip install imageio
import imageio
from imageio import imread, imsave

6

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

2

[ 5 12 21 32]

1

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

07

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

08

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

10

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

11

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

12

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

14

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

15

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0____11_______17

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

18

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

19

đầu ra.  
 

[ 5 12 21 32]

Để biết thêm chi tiết tham khảo tài liệu.    

máy ảnh

 

Nó cung cấp nhiều phương thức sẵn có để mò mẫm, kết hợp và lọc dữ liệu

Keras là một thư viện Machine Learning rất phổ biến cho Python. Đây là API mạng thần kinh cấp cao có khả năng chạy trên TensorFlow, CNTK hoặc Theano. Nó có thể chạy liền mạch trên cả CPU và GPU. Keras làm cho nó thực sự dành cho những người mới bắt đầu học máy để xây dựng và thiết kế Mạng nơ-ron. Một trong những điều tốt nhất về Keras là nó cho phép tạo mẫu dễ dàng và nhanh chóng

Để biết thêm chi tiết tham khảo tài liệu.    

PyTorch

PyTorch là thư viện Machine Learning nguồn mở phổ biến dành cho Python dựa trên Torch, đây là thư viện Machine Learning nguồn mở được triển khai trong C với trình bao bọc trong Lua. Nó có nhiều lựa chọn công cụ và thư viện hỗ trợ Thị giác máy tính, Xử lý ngôn ngữ tự nhiên (NLP) và nhiều chương trình ML khác. Nó cho phép các nhà phát triển thực hiện tính toán trên Tensors với khả năng tăng tốc GPU và cũng giúp tạo các biểu đồ tính toán.  

Thí dụ

Python3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

20

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

21

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

22

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

23

 

import

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

25

 

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

26_______0_______3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

28

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

29

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

30

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

32

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

33

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

35

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

36

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

37

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

38_______0_______3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

40

!pip install imageio
import imageio
from imageio import imread, imsave

6

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

42

!pip install imageio
import imageio
from imageio import imread, imsave

6

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

44

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

0

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

47

!pip install imageio
import imageio
from imageio import imread, imsave

2

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

50

!pip install imageio
import imageio
from imageio import imread, imsave

3_______11_______52

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

54

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

3

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

57

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

52

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

54

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

62

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

63

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

65

!pip install imageio
import imageio
from imageio import imread, imsave

3_______11_______52

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

54

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

70_______0_______3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

72

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

52

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

54

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

77_______0_______3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

79

!pip install imageio
import imageio
from imageio import imread, imsave

63

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

8

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

82

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

83

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

84

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

85

!pip install imageio
import imageio
from imageio import imread, imsave

59

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

87

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

88

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

90

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

92

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

94

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

96

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

98

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

99

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

69

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

04

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

06

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

08

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

10

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

12

!pip install imageio
import imageio
from imageio import imread, imsave

63

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

14

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

15

!pip install imageio
import imageio
from imageio import imread, imsave

59

!pip install imageio
import imageio
from imageio import imread, imsave

7

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

18

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

19

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

20

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

0

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

23

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

25

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

27

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

29 # operations1

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

12

!pip install imageio
import imageio
from imageio import imread, imsave

63

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

33

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

35

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

37

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

39

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

41

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

43

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

45

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

47

!pip install imageio
import imageio
from imageio import imread, imsave

69# operations8

!pip install imageio
import imageio
from imageio import imread, imsave

3

!pip install imageio
import imageio
from imageio import imread, imsave

69

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

53

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

55

 

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

57

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

63

!pip install imageio
import imageio
from imageio import imread, imsave

63

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

77# operations1

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

53

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

89

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

70

!pip install imageio
import imageio
from imageio import imread, imsave

63

!pip install imageio
import imageio
from imageio import imread, imsave

3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        50
           1       1.00      1.00      1.00        50
           2       1.00      1.00      1.00        50

   micro avg       1.00      1.00      1.00       150
   macro avg       1.00      1.00      1.00       150
weighted avg       1.00      1.00      1.00       150

[[50  0  0]
 [ 0 50  0]
 [ 0  0 50]]

77# operations1

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

35

đầu ra.  
 

0 47168344.0
1 46385584.0
2 43153576.0
...
...
...
497 3.987660602433607e-05
498 3.945609932998195e-05
499 3.897604619851336e-05

Để biết thêm chi tiết tham khảo tài liệu.  

gấu trúc

Pandas là một thư viện Python phổ biến để phân tích dữ liệu. Nó không liên quan trực tiếp đến Machine Learning. Như chúng ta biết rằng tập dữ liệu phải được chuẩn bị trước khi đào tạo. Trong trường hợp này, Pandas rất hữu ích vì nó được phát triển đặc biệt để trích xuất và chuẩn bị dữ liệu. Nó cung cấp các cấu trúc dữ liệu cấp cao và nhiều công cụ khác nhau để phân tích dữ liệu. Nó cung cấp nhiều phương pháp sẵn có để nhóm, kết hợp và lọc dữ liệu

Python3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

72

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

73

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

74

 

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

75

import

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

77

 

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

78

!pip install imageio
import imageio
from imageio import imread, imsave

3

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

80

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

81

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

82

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

83

!pip install imageio
import imageio
from imageio import imread, imsave

6

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

85

!pip install imageio
import imageio
from imageio import imread, imsave

6

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

87

!pip install imageio
import imageio
from imageio import imread, imsave

6

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

89

!pip install imageio
import imageio
from imageio import imread, imsave

6

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

91

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

92

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

93

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

94

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

82

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

96

!pip install imageio
import imageio
from imageio import imread, imsave

6

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

98

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

00

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

02

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

04

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

92

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

93

[ 5 12 21 32]

07

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

82

[ 5 12 21 32]

09

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

11

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

13

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

15

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

17

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

92

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

93

[ 5 12 21 32]

20

array([[0.5, 0.73105858],
       [0.26894142, 0.11920292]])

82

[ 5 12 21 32]

22

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

24

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

26

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

28

!pip install imageio
import imageio
from imageio import imread, imsave

6

[ 5 12 21 32]

30

[ 5 12 21 32]

31

Tôi có thể viết mã AI bằng Python không?

Python nào tốt nhất cho AI?