DecisionTreeClassifier 이용한 Data classification¶
In [4]:
from sklearn.datasets import load_iris
iris = load_iris()
print(dir(iris))
# dir()는 객체가 어떤 변수와 메서드를 가지고 있는지 나열함
['DESCR', 'data', 'data_module', 'feature_names', 'filename', 'frame', 'target', 'target_names']
In [5]:
iris_data = iris.data
print(iris_data.shape)
#shape는 배열의 형상정보를 출력
(150, 4)
In [6]:
iris_data[0]
Out[6]:
array([5.1, 3.5, 1.4, 0.2])
In [7]:
iris_data
Out[7]:
array([[5.1, 3.5, 1.4, 0.2],
[4.9, 3. , 1.4, 0.2],
[4.7, 3.2, 1.3, 0.2],
[4.6, 3.1, 1.5, 0.2],
[5. , 3.6, 1.4, 0.2],
[5.4, 3.9, 1.7, 0.4],
[4.6, 3.4, 1.4, 0.3],
[5. , 3.4, 1.5, 0.2],
[4.4, 2.9, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.1],
[5.4, 3.7, 1.5, 0.2],
[4.8, 3.4, 1.6, 0.2],
[4.8, 3. , 1.4, 0.1],
[4.3, 3. , 1.1, 0.1],
[5.8, 4. , 1.2, 0.2],
[5.7, 4.4, 1.5, 0.4],
[5.4, 3.9, 1.3, 0.4],
[5.1, 3.5, 1.4, 0.3],
[5.7, 3.8, 1.7, 0.3],
[5.1, 3.8, 1.5, 0.3],
[5.4, 3.4, 1.7, 0.2],
[5.1, 3.7, 1.5, 0.4],
[4.6, 3.6, 1. , 0.2],
[5.1, 3.3, 1.7, 0.5],
[4.8, 3.4, 1.9, 0.2],
[5. , 3. , 1.6, 0.2],
[5. , 3.4, 1.6, 0.4],
[5.2, 3.5, 1.5, 0.2],
[5.2, 3.4, 1.4, 0.2],
[4.7, 3.2, 1.6, 0.2],
[4.8, 3.1, 1.6, 0.2],
[5.4, 3.4, 1.5, 0.4],
[5.2, 4.1, 1.5, 0.1],
[5.5, 4.2, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.2],
[5. , 3.2, 1.2, 0.2],
[5.5, 3.5, 1.3, 0.2],
[4.9, 3.6, 1.4, 0.1],
[4.4, 3. , 1.3, 0.2],
[5.1, 3.4, 1.5, 0.2],
[5. , 3.5, 1.3, 0.3],
[4.5, 2.3, 1.3, 0.3],
[4.4, 3.2, 1.3, 0.2],
[5. , 3.5, 1.6, 0.6],
[5.1, 3.8, 1.9, 0.4],
[4.8, 3. , 1.4, 0.3],
[5.1, 3.8, 1.6, 0.2],
[4.6, 3.2, 1.4, 0.2],
[5.3, 3.7, 1.5, 0.2],
[5. , 3.3, 1.4, 0.2],
[7. , 3.2, 4.7, 1.4],
[6.4, 3.2, 4.5, 1.5],
[6.9, 3.1, 4.9, 1.5],
[5.5, 2.3, 4. , 1.3],
[6.5, 2.8, 4.6, 1.5],
[5.7, 2.8, 4.5, 1.3],
[6.3, 3.3, 4.7, 1.6],
[4.9, 2.4, 3.3, 1. ],
[6.6, 2.9, 4.6, 1.3],
[5.2, 2.7, 3.9, 1.4],
[5. , 2. , 3.5, 1. ],
[5.9, 3. , 4.2, 1.5],
[6. , 2.2, 4. , 1. ],
[6.1, 2.9, 4.7, 1.4],
[5.6, 2.9, 3.6, 1.3],
[6.7, 3.1, 4.4, 1.4],
[5.6, 3. , 4.5, 1.5],
[5.8, 2.7, 4.1, 1. ],
[6.2, 2.2, 4.5, 1.5],
[5.6, 2.5, 3.9, 1.1],
[5.9, 3.2, 4.8, 1.8],
[6.1, 2.8, 4. , 1.3],
[6.3, 2.5, 4.9, 1.5],
[6.1, 2.8, 4.7, 1.2],
[6.4, 2.9, 4.3, 1.3],
[6.6, 3. , 4.4, 1.4],
[6.8, 2.8, 4.8, 1.4],
[6.7, 3. , 5. , 1.7],
[6. , 2.9, 4.5, 1.5],
[5.7, 2.6, 3.5, 1. ],
[5.5, 2.4, 3.8, 1.1],
[5.5, 2.4, 3.7, 1. ],
[5.8, 2.7, 3.9, 1.2],
[6. , 2.7, 5.1, 1.6],
[5.4, 3. , 4.5, 1.5],
[6. , 3.4, 4.5, 1.6],
[6.7, 3.1, 4.7, 1.5],
[6.3, 2.3, 4.4, 1.3],
[5.6, 3. , 4.1, 1.3],
[5.5, 2.5, 4. , 1.3],
[5.5, 2.6, 4.4, 1.2],
[6.1, 3. , 4.6, 1.4],
[5.8, 2.6, 4. , 1.2],
[5. , 2.3, 3.3, 1. ],
[5.6, 2.7, 4.2, 1.3],
[5.7, 3. , 4.2, 1.2],
[5.7, 2.9, 4.2, 1.3],
[6.2, 2.9, 4.3, 1.3],
[5.1, 2.5, 3. , 1.1],
[5.7, 2.8, 4.1, 1.3],
[6.3, 3.3, 6. , 2.5],
[5.8, 2.7, 5.1, 1.9],
[7.1, 3. , 5.9, 2.1],
[6.3, 2.9, 5.6, 1.8],
[6.5, 3. , 5.8, 2.2],
[7.6, 3. , 6.6, 2.1],
[4.9, 2.5, 4.5, 1.7],
[7.3, 2.9, 6.3, 1.8],
[6.7, 2.5, 5.8, 1.8],
[7.2, 3.6, 6.1, 2.5],
[6.5, 3.2, 5.1, 2. ],
[6.4, 2.7, 5.3, 1.9],
[6.8, 3. , 5.5, 2.1],
[5.7, 2.5, 5. , 2. ],
[5.8, 2.8, 5.1, 2.4],
[6.4, 3.2, 5.3, 2.3],
[6.5, 3. , 5.5, 1.8],
[7.7, 3.8, 6.7, 2.2],
[7.7, 2.6, 6.9, 2.3],
[6. , 2.2, 5. , 1.5],
[6.9, 3.2, 5.7, 2.3],
[5.6, 2.8, 4.9, 2. ],
[7.7, 2.8, 6.7, 2. ],
[6.3, 2.7, 4.9, 1.8],
[6.7, 3.3, 5.7, 2.1],
[7.2, 3.2, 6. , 1.8],
[6.2, 2.8, 4.8, 1.8],
[6.1, 3. , 4.9, 1.8],
[6.4, 2.8, 5.6, 2.1],
[7.2, 3. , 5.8, 1.6],
[7.4, 2.8, 6.1, 1.9],
[7.9, 3.8, 6.4, 2. ],
[6.4, 2.8, 5.6, 2.2],
[6.3, 2.8, 5.1, 1.5],
[6.1, 2.6, 5.6, 1.4],
[7.7, 3. , 6.1, 2.3],
[6.3, 3.4, 5.6, 2.4],
[6.4, 3.1, 5.5, 1.8],
[6. , 3. , 4.8, 1.8],
[6.9, 3.1, 5.4, 2.1],
[6.7, 3.1, 5.6, 2.4],
[6.9, 3.1, 5.1, 2.3],
[5.8, 2.7, 5.1, 1.9],
[6.8, 3.2, 5.9, 2.3],
[6.7, 3.3, 5.7, 2.5],
[6.7, 3. , 5.2, 2.3],
[6.3, 2.5, 5. , 1.9],
[6.5, 3. , 5.2, 2. ],
[6.2, 3.4, 5.4, 2.3],
[5.9, 3. , 5.1, 1.8]])
In [8]:
iris_label = iris.target
print(iris_label.shape)
iris_label
(150,)
Out[8]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])
In [9]:
iris.target_names
Out[9]:
array(['setosa', 'versicolor', 'virginica'], dtype='<U10')
In [10]:
print(iris.DESCR)
.. _iris_dataset:
Iris plants dataset
--------------------
**Data Set Characteristics:**
:Number of Instances: 150 (50 in each of three classes)
:Number of Attributes: 4 numeric, predictive attributes and the class
:Attribute Information:
- sepal length in cm
- sepal width in cm
- petal length in cm
- petal width in cm
- class:
- Iris-Setosa
- Iris-Versicolour
- Iris-Virginica
:Summary Statistics:
============== ==== ==== ======= ===== ====================
Min Max Mean SD Class Correlation
============== ==== ==== ======= ===== ====================
sepal length: 4.3 7.9 5.84 0.83 0.7826
sepal width: 2.0 4.4 3.05 0.43 -0.4194
petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)
petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)
============== ==== ==== ======= ===== ====================
:Missing Attribute Values: None
:Class Distribution: 33.3% for each of 3 classes.
:Creator: R.A. Fisher
:Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
:Date: July, 1988
The famous Iris database, first used by Sir R.A. Fisher. The dataset is taken
from Fisher's paper. Note that it's the same as in R, but not as in the UCI
Machine Learning Repository, which has two wrong data points.
This is perhaps the best known database to be found in the
pattern recognition literature. Fisher's paper is a classic in the field and
is referenced frequently to this day. (See Duda & Hart, for example.) The
data set contains 3 classes of 50 instances each, where each class refers to a
type of iris plant. One class is linearly separable from the other 2; the
latter are NOT linearly separable from each other.
.. topic:: References
- Fisher, R.A. "The use of multiple measurements in taxonomic problems"
Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to
Mathematical Statistics" (John Wiley, NY, 1950).
- Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.
(Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.
- Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
Structure and Classification Rule for Recognition in Partially Exposed
Environments". IEEE Transactions on Pattern Analysis and Machine
Intelligence, Vol. PAMI-2, No. 1, 67-71.
- Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions
on Information Theory, May 1972, 431-433.
- See also: 1988 MLC Proceedings, 54-64. Cheeseman et al"s AUTOCLASS II
conceptual clustering system finds 3 classes in the data.
- Many, many more ...
In [11]:
iris.feature_names
iris.filename
Out[11]:
'iris.csv'
In [12]:
import pandas as pd
print(pd.__version__)
1.3.3
In [13]:
iris_df = pd.DataFrame(data=iris_data, columns=iris.feature_names)
iris_df
Out[13]:
| sepal length (cm) | sepal width (cm) | petal length (cm) | petal width (cm) | |
|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 |
| ... | ... | ... | ... | ... |
| 145 | 6.7 | 3.0 | 5.2 | 2.3 |
| 146 | 6.3 | 2.5 | 5.0 | 1.9 |
| 147 | 6.5 | 3.0 | 5.2 | 2.0 |
| 148 | 6.2 | 3.4 | 5.4 | 2.3 |
| 149 | 5.9 | 3.0 | 5.1 | 1.8 |
150 rows × 4 columns
In [14]:
iris_df["label"] = iris_label #iris.target
iris_df
iris_df.tail()
Out[14]:
| sepal length (cm) | sepal width (cm) | petal length (cm) | petal width (cm) | label | |
|---|---|---|---|---|---|
| 145 | 6.7 | 3.0 | 5.2 | 2.3 | 2 |
| 146 | 6.3 | 2.5 | 5.0 | 1.9 | 2 |
| 147 | 6.5 | 3.0 | 5.2 | 2.0 | 2 |
| 148 | 6.2 | 3.4 | 5.4 | 2.3 | 2 |
| 149 | 5.9 | 3.0 | 5.1 | 1.8 | 2 |
In [19]:
#data testset training set으로 나누기
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(iris_data,
iris_label,
test_size=0.2,
random_state=7)
print('X_train 개수: ', len(X_train),', X_test 개수: ', len(X_test),"\n",'y_train개수: ', len(y_train),"y_test개수: ",len(y_test))
#train_test_split(x value, y value, test_size = ~~, random_state = ~)
#test_size = 0.2 => 20%만 사용한다 테스트에
#random_state = => 얼마나섞을것인지 난수 만들기
X_train 개수: 120 , X_test 개수: 30 y_train개수: 120 y_test개수: 30
In [16]:
X_train.shape, y_train.shape
Out[16]:
((120, 4), (120,))
In [21]:
X_test.shape, y_test.shape
Out[21]:
((30, 4), (30,))
In [22]:
y_train, y_test #random하게 섞인지 확인
Out[22]:
(array([2, 1, 0, 2, 1, 0, 0, 0, 0, 2, 2, 1, 2, 2, 1, 0, 1, 1, 2, 0, 0, 0,
2, 0, 2, 1, 1, 1, 0, 0, 0, 1, 2, 1, 1, 0, 2, 0, 0, 2, 2, 0, 2, 0,
1, 2, 1, 0, 1, 0, 2, 2, 1, 0, 0, 1, 2, 0, 2, 2, 1, 0, 1, 0, 2, 2,
0, 0, 2, 1, 2, 2, 1, 0, 0, 2, 0, 0, 1, 2, 2, 1, 1, 0, 2, 0, 0, 1,
1, 2, 0, 1, 1, 2, 2, 1, 2, 0, 1, 1, 0, 0, 0, 1, 1, 0, 2, 2, 1, 2,
0, 2, 1, 1, 0, 2, 1, 2, 1, 0]),
array([2, 1, 0, 1, 2, 0, 1, 1, 0, 1, 1, 1, 0, 2, 0, 1, 2, 2, 0, 0, 1, 2,
1, 2, 2, 2, 1, 1, 2, 2]))
In [23]:
from sklearn.tree import DecisionTreeClassifier
decision_tree = DecisionTreeClassifier(random_state=32)
print(decision_tree._estimator_type)
classifier
In [24]:
decision_tree.fit(X_train, y_train) #모델 학습시키기(fitting)
Out[24]:
DecisionTreeClassifier(random_state=32)
In [25]:
y_pred = decision_tree.predict(X_test)
y_pred
Out[25]:
array([2, 1, 0, 1, 2, 0, 1, 1, 0, 1, 2, 1, 0, 2, 0, 2, 2, 2, 0, 0, 1, 2,
1, 1, 2, 2, 1, 1, 2, 2])
In [28]:
y_test
Out[28]:
array([2, 1, 0, 1, 2, 0, 1, 1, 0, 1, 1, 1, 0, 2, 0, 1, 2, 2, 0, 0, 1, 2,
1, 2, 2, 2, 1, 1, 2, 2])
In [33]:
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y_test, y_pred) #당연히 크기가 같아야겠쥬?
accuracy #정답데이터/전테데이터
Out[33]:
0.9
In [38]:
y_train.shape
Out[38]:
(120,)
In [28]:
#workflow 개략
# (1) 필요한 모듈 import
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import classification_report
# (2) 데이터 준비
iris = load_iris()
iris_data = iris.data #그냥 이름 통일시키려고 변수 새로 할당한 것임
iris_label = iris.target
# (3) train, test 데이터 분리
X_train, X_test, y_train, y_test = train_test_split(iris_data,
iris_label,
test_size=0.2,
random_state=7)
# (4) 모델 학습 및 예측
decision_tree = DecisionTreeClassifier(random_state=32)
decision_tree.fit(X_train, y_train)
y_pred = decision_tree.predict(X_test)
print(classification_report(y_test, y_pred))
precision recall f1-score support
0 1.00 1.00 1.00 7
1 0.91 0.83 0.87 12
2 0.83 0.91 0.87 11
accuracy 0.90 30
macro avg 0.91 0.91 0.91 30
weighted avg 0.90 0.90 0.90 30
In [29]:
from sklearn.ensemble import RandomForestClassifier
X_train, X_test, y_train, y_test = train_test_split(iris_data,
iris_label,
test_size=0.2,
random_state=21)
random_forest = RandomForestClassifier(random_state=32)
random_forest.fit(X_train, y_train)
y_pred = random_forest.predict(X_test)
print(classification_report(y_test, y_pred))
precision recall f1-score support
0 1.00 1.00 1.00 11
1 1.00 0.83 0.91 12
2 0.78 1.00 0.88 7
accuracy 0.93 30
macro avg 0.93 0.94 0.93 30
weighted avg 0.95 0.93 0.93 30
In [30]:
from sklearn import svm
svm_model = svm.SVC()
print(svm_model._estimator_type)
classifier
In [37]:
# (1) 필요한 모듈 import - svm model 학습시키기
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn import svm #새모델 넣기
# (2) 데이터 준비
iris = load_iris()
iris_data = iris.data #그냥 이름 통일시키려고 변수 새로 할당한 것임
iris_label = iris.target
# (3) train, test 데이터 분리
X_train, X_test, y_train, y_test = train_test_split(iris_data,
iris_label,
test_size=0.2,
random_state=7)
#정확도가 낮아서 학습 데이터를 줄여봤더니 올라갔다! 이유는?
#아마 마진이 넓어져서 그런게 아닐까
# (4) 모델 학습 및 예측
svm_model = svm.SVC() #각각의 분류기마다 자기만의 식이 있다, 이것만 알면됨
svm_model.fit(X_train, y_train)
y_pred = svm_model.predict(X_test)
print(classification_report(y_test, y_pred))
precision recall f1-score support
0 1.00 1.00 1.00 7
1 0.83 0.83 0.83 12
2 0.82 0.82 0.82 11
accuracy 0.87 30
macro avg 0.88 0.88 0.88 30
weighted avg 0.87 0.87 0.87 30
In [38]:
from sklearn.linear_model import SGDClassifier
sgd_model = SGDClassifier() #모델 변수에 할당
sgd_model.fit(X_train, y_train) #모델에 데이터 할당
y_pred = sgd_model.predict(X_test) #정답치 변수 할당
print(classification_report(y_test, y_pred)) #정확도 메서드 이용해 정확도 판별
#확률적 경사하강 모델이라 할때마다 정확도가 변경된다
precision recall f1-score support
0 0.78 1.00 0.88 7
1 1.00 0.08 0.15 12
2 0.55 1.00 0.71 11
accuracy 0.63 30
macro avg 0.78 0.69 0.58 30
weighted avg 0.78 0.63 0.53 30
In [39]:
from sklearn.linear_model import LogisticRegression
logistic_model = LogisticRegression()
logistic_model.fit(X_train, y_train)
y_pred = sgd_model.predict(X_test) #정답치 변수 할당
print(classification_report(y_test, y_pred))
precision recall f1-score support
0 0.78 1.00 0.88 7
1 1.00 0.08 0.15 12
2 0.55 1.00 0.71 11
accuracy 0.63 30
macro avg 0.78 0.69 0.58 30
weighted avg 0.78 0.63 0.53 30
/opt/conda/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:814: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
In [40]:
from sklearn.datasets import load_digits
digits = load_digits()
digits.keys() #해당 데이터 내에서 쓸 수 있는 메서드 같은 느낌
Out[40]:
dict_keys(['data', 'target', 'frame', 'feature_names', 'target_names', 'images', 'DESCR'])
In [41]:
digits_data = digits.data
digits_data.shape
Out[41]:
(1797, 64)
In [42]:
digits_data[0] #imgae data 8x8 = 64
Out[42]:
array([ 0., 0., 5., 13., 9., 1., 0., 0., 0., 0., 13., 15., 10.,
15., 5., 0., 0., 3., 15., 2., 0., 11., 8., 0., 0., 4.,
12., 0., 0., 8., 8., 0., 0., 5., 8., 0., 0., 9., 8.,
0., 0., 4., 11., 0., 1., 12., 7., 0., 0., 2., 14., 5.,
10., 12., 0., 0., 0., 0., 6., 13., 10., 0., 0., 0.])
In [49]:
import matplotlib.pyplot as plt #그림으로 보고싶어서import 시킨다
%matplotlib inline
plt.imshow(digits.data[0].reshape(8,8), cmap='gray') #그레이 안해주면 칼라로나옴 올ㅋ
#일자 어레이 1,64 로 되있는거 다시 펴줘야해!
plt.axis('off') #축 안나타나게 하는거임
plt.show() #산출
In [ ]:
for i in range(10):
plt.subplot(2, 5, i+1) #(row,col,index)
plt.imshow(digits.data[i].reshape(8, 8), cmap='gray')
plt.axis('off')
plt.show()
In [56]:
#여러개 동시에보기
for i in range(30):
plt.subplot(10, 3, i+1) #(row,col,index)
plt.imshow(digits.data[i].reshape(8, 8), cmap='gray')
plt.axis('off')
#ㅇplt.show()
In [57]:
#타겟데이터 보기
digits_label = digits.target
print(digits_label.shape)
digits_label[:20] #20전까지만 타겟데이터 보기
(1797,)
Out[57]:
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
In [58]:
new_label = [3 if i == 3 else 0 for i in digits_label]
#이렇게 말고 다르게 표현도가능한가?
new_label[:20]
Out[58]:
[0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0]
In [70]:
#workflow 개략
# (1) 필요한 모듈 import
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score
#data set
digits = load_digits()
digits_data = digits.data
digits_label = digits.target #기존 정답라벨
new_label = [3 if i == 3 else 0 for i in digits_label]#새로운 정답라벨
# (3) train, test 데이터 분리
X_train, X_test, y_train, y_test = train_test_split(digits_data,
new_label,
test_size=0.2,
random_state=15)
# (4) 모델 학습 및 예측
decision_tree = DecisionTreeClassifier(random_state=15)
decision_tree.fit(X_train, y_train)
y_pred = decision_tree.predict(X_test) #예측값 산출
print(y_pred) #예측값
print(y_test) #정답값
print(accuracy_score(y_test,y_pred)) #accuracy_score(정답값,예측값)
# print(classification_report(y_test, y_pred))
[3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 0 0 0 0 3 0 3 0 0 3 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 3 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 3 0 0 0 3 0 0 0 0 0 3 3 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 0 3 0 0 3 0 0 0 0 0 0 0 0 0 0 0 0 0 3 3 0 3 3 0] [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 3, 0, 0, 0, 0, 0, 0, 3, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 3, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 3, 0, 0, 0, 0, 3, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 3, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 3, 0] 0.9388888888888889
In [69]:
#위의 정확도가 신용불가능한 이유
#다 0값만 산출해도 90퍼가 넘음
fake_pred = [0] * len(y_pred)
print(fake_pred)
accuracy = accuracy_score(y_test, fake_pred)
accuracy
#다 0만 있는 예측값의 경우에도 정확도가 높다
#정답값의 분포에 따라 유념해야함!
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
Out[69]:
0.925
In [72]:
from sklearn.metrics import confusion_matrix
#confusion_matrix
#TP(True Positive), FN(False Neg)
#FP(False Positive), TN(True Neg) 순으로 배열
a = confusion_matrix(y_test, y_pred)
print(a)
[[320 13] [ 9 18]]
In [71]:
print(classification_report(y_test, fake_pred, zero_division=0))
#3의 recall과 precision은 하나도 못맞춤
#label이 불균형하게 분포되어있는 데이터를 다룰 때는 더 조심
precision recall f1-score support
0 0.93 1.00 0.96 333
3 0.00 0.00 0.00 27
accuracy 0.93 360
macro avg 0.46 0.50 0.48 360
weighted avg 0.86 0.93 0.89 360
'Computer Technology 기록부 > 코딩기록부 : Python' 카테고리의 다른 글
| 머신러닝을 위한 sklearn 라이브러리 기능 이용 (0) | 2022.07.05 |
|---|---|
| LSTM 모델을 이용한 인공지능 작사가 구축 (2) | 2022.07.05 |
| MNIST Dataset 이용한 CNN 모델 구축 (0) | 2022.07.05 |
| [최종] 카메라 스티커 만들기 - 예외처리 포함 (0) | 2022.01.13 |
| 카메라 스티커 만들기 (0) | 2022.01.11 |
댓글