붓꽃 데이터 사이킷 런 학습-1

붓꽃 데이터를 이용하여 다양한 머신러닝을 진행해 보았다.

 

sklearn.linear_model.LinearRegression

In [35]:

from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler

import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

In [27]:

# 붓꽃 데이터 세트 로딩
iris = load_iris()

In [28]:

iris_data = iris.data

In [29]:

iris_label = iris.target
print('iris target값:', iris_label)
print('iris target명:', iris.target_names)

iris target값: [0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 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]
iris target명: ['setosa' 'versicolor' 'virginica']

In [30]:

iris_df=pd.DataFrame(data=iris_data, columns = iris.feature_names)
iris_df['label']= iris.target
iris_df.head(3)

Out[30]:

sepal length (cm)sepal width (cm)petal length (cm)petal width (cm)label012

5.1	3.5	1.4	0.2	0
4.9	3.0	1.4	0.2	0
4.7	3.2	1.3	0.2	0

In [31]:

X_train, X_test, y_train, y_test = train_test_split(iris_data, iris_label, test_size=0.2, random_state=11)

dt_clf = DecisionTreeClassifier(random_state=42)

dt_clf.fit(X_train, y_train)

Out[31]:

DecisionTreeClassifier(random_state=42)

In [32]:

pred = dt_clf.predict(X_test)

In [33]:

from sklearn.metrics import accuracy_score
print("예측 정확도: {0:.4f}".format(accuracy_score(y_test,pred)))

예측 정확도: 0.9333

붓꽃 데이터 셋 생성

Load_iris()가 반환하는 객체의 값 출력

In [15]:

from sklearn.datasets import load_iris

iris_data= load_iris()
print(type(iris_data))

<class 'sklearn.utils.Bunch'>

In [16]:

keys = iris_data.keys()
print('붓꽃 데이터 세트의 키들:', keys)

붓꽃 데이터 세트의 키들: dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])

In [17]:

print('\n feature_names의 type:', type(iris_data.feature_names))
print(' feature_names의 shape:', len(iris_data.feature_names))
print(iris_data.feature_names)

print('\n target_names의 type:', type(iris_data.target_names))
print(' target_names의 shape:', len(iris_data.target_names))
print(iris_data.target_names)

print('\n data의 type:', type(iris_data.data))
print(' data의 shape:', len(iris_data.data.shape))
print(iris_data['data'])

print('\n target의 type:', type(iris_data.target))
print(' target의 shape:', len(iris_data.target.shape))
print(iris_data.target)

 feature_names의 type: <class 'list'>
 feature_names의 shape: 4
['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']

 target_names의 type: <class 'numpy.ndarray'>
 target_names의 shape: 3
['setosa' 'versicolor' 'virginica']

 data의 type: <class 'numpy.ndarray'>
 data의 shape: 2
[[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]]

 target의 type: <class 'numpy.ndarray'>
 target의 shape: 1
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 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]

Module Selection

In [19]:

from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

iris = load_iris()
dt_clf = DecisionTreeClassifier()
train_data = iris.data
train_label = iris.target
dt_clf.fit(train_data, train_label)

pred = dt_clf.predict(train_data)
print('예측 정확도:', accuracy_score(train_label, pred))

예측 정확도: 1.0

In [43]:

from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

dt_clf = DecisionTreeClassifier()
iris_data = load_iris()

X_train, X_test, y_train, y_test = train_test_split(iris_data.data, iris_data.target, test_size=0.4, random_state=11)

dt_clf.fit(X_train, y_train)
pred = dt_clf.predict(X_test)
print("예측 정확도: {0:.4f}".format(accuracy_score(y_test,pred)))

예측 정확도: 0.9333

로지스틱 회귀분석

In [36]:

from sklearn.linear_model import LogisticRegression

In [44]:

lg_clf=LogisticRegression()
lg_clf.fit(X_train, y_train)
pred=lg_clf.predict(X_test)
pred

Out[44]:

array([2, 2, 2, 1, 2, 0, 1, 0, 0, 1, 1, 1, 1, 2, 2, 0, 2, 1, 2, 2, 1, 0,
       0, 1, 0, 0, 2, 1, 0, 1, 0, 2, 2, 0, 0, 2, 2, 2, 0, 2, 1, 2, 0, 2,
       2, 1, 1, 0, 2, 0, 2, 2, 1, 1, 1, 0, 0, 1, 0, 0])

In [45]:

print("예측 정확도: {0:.4f}".format(accuracy_score(y_test,pred)))

예측 정확도: 0.9167

In [47]:

from sklearn.datasets import load_boston
housing = load_boston

In [48]:

housing

Out[48]:

<function sklearn.datasets._base.load_boston(*, return_X_y=False)>