from IPython.display import display, Image
라이브러리이름.__version__
라이브러리이름.version
import sys
print("파이썬 버전 :", sys.version)
파이썬 버전 : 3.8.5 (default, Sep 4 2020, 02:22:02) [Clang 10.0.0 ]
import pandas as pd
print("판다스 버전 :", pd.__version__)
판다스 버전 : 1.1.3
import matplotlib
import numpy as np
import scipy as sp
display(Image(filename='img/iris_setosa01.png'))
from sklearn.datasets import load_iris
iris = load_iris()
iris
{'data': 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]]), 'target': 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]), 'frame': None, 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'), 'DESCR': '.. _iris_dataset:\n\nIris plants dataset\n--------------------\n\n**Data Set Characteristics:**\n\n :Number of Instances: 150 (50 in each of three classes)\n :Number of Attributes: 4 numeric, predictive attributes and the class\n :Attribute Information:\n - sepal length in cm\n - sepal width in cm\n - petal length in cm\n - petal width in cm\n - class:\n - Iris-Setosa\n - Iris-Versicolour\n - Iris-Virginica\n \n :Summary Statistics:\n\n ============== ==== ==== ======= ===== ====================\n Min Max Mean SD Class Correlation\n ============== ==== ==== ======= ===== ====================\n sepal length: 4.3 7.9 5.84 0.83 0.7826\n sepal width: 2.0 4.4 3.05 0.43 -0.4194\n petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)\n petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)\n ============== ==== ==== ======= ===== ====================\n\n :Missing Attribute Values: None\n :Class Distribution: 33.3% for each of 3 classes.\n :Creator: R.A. Fisher\n :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n :Date: July, 1988\n\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\nfrom Fisher\'s paper. Note that it\'s the same as in R, but not as in the UCI\nMachine Learning Repository, which has two wrong data points.\n\nThis is perhaps the best known database to be found in the\npattern recognition literature. Fisher\'s paper is a classic in the field and\nis referenced frequently to this day. (See Duda & Hart, for example.) The\ndata set contains 3 classes of 50 instances each, where each class refers to a\ntype of iris plant. One class is linearly separable from the other 2; the\nlatter are NOT linearly separable from each other.\n\n.. topic:: References\n\n - Fisher, R.A. "The use of multiple measurements in taxonomic problems"\n Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to\n Mathematical Statistics" (John Wiley, NY, 1950).\n - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\n (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.\n - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System\n Structure and Classification Rule for Recognition in Partially Exposed\n Environments". IEEE Transactions on Pattern Analysis and Machine\n Intelligence, Vol. PAMI-2, No. 1, 67-71.\n - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions\n on Information Theory, May 1972, 431-433.\n - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al"s AUTOCLASS II\n conceptual clustering system finds 3 classes in the data.\n - Many, many more ...', 'feature_names': ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)'], 'filename': '/Users/toto/Documents/anaconda3/lib/python3.8/site-packages/sklearn/datasets/data/iris.csv'}
# iris 데이터 셋의 key값들
print( type(iris) )
print(iris.keys()) # iris가 가진 값들
print(iris['target_names']) # 붓꽃의 label의 종류명
print(iris['target']) # 붓꽃의 종류의 label의 값
print(iris['data']) # 붓꽃의 꽃잎과 꽃받침의 값
<class 'sklearn.utils.Bunch'> dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename']) ['setosa' 'versicolor' 'virginica'] [0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 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] [[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]]
# iris 데이터 셋의 설명 확인
iris['DESCR']
'.. _iris_dataset:\n\nIris plants dataset\n--------------------\n\n**Data Set Characteristics:**\n\n :Number of Instances: 150 (50 in each of three classes)\n :Number of Attributes: 4 numeric, predictive attributes and the class\n :Attribute Information:\n - sepal length in cm\n - sepal width in cm\n - petal length in cm\n - petal width in cm\n - class:\n - Iris-Setosa\n - Iris-Versicolour\n - Iris-Virginica\n \n :Summary Statistics:\n\n ============== ==== ==== ======= ===== ====================\n Min Max Mean SD Class Correlation\n ============== ==== ==== ======= ===== ====================\n sepal length: 4.3 7.9 5.84 0.83 0.7826\n sepal width: 2.0 4.4 3.05 0.43 -0.4194\n petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)\n petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)\n ============== ==== ==== ======= ===== ====================\n\n :Missing Attribute Values: None\n :Class Distribution: 33.3% for each of 3 classes.\n :Creator: R.A. Fisher\n :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n :Date: July, 1988\n\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\nfrom Fisher\'s paper. Note that it\'s the same as in R, but not as in the UCI\nMachine Learning Repository, which has two wrong data points.\n\nThis is perhaps the best known database to be found in the\npattern recognition literature. Fisher\'s paper is a classic in the field and\nis referenced frequently to this day. (See Duda & Hart, for example.) The\ndata set contains 3 classes of 50 instances each, where each class refers to a\ntype of iris plant. One class is linearly separable from the other 2; the\nlatter are NOT linearly separable from each other.\n\n.. topic:: References\n\n - Fisher, R.A. "The use of multiple measurements in taxonomic problems"\n Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to\n Mathematical Statistics" (John Wiley, NY, 1950).\n - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\n (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.\n - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System\n Structure and Classification Rule for Recognition in Partially Exposed\n Environments". IEEE Transactions on Pattern Analysis and Machine\n Intelligence, Vol. PAMI-2, No. 1, 67-71.\n - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions\n on Information Theory, May 1972, 431-433.\n - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al"s AUTOCLASS II\n conceptual clustering system finds 3 classes in the data.\n - Many, many more ...'
print( iris['data'].shape ) # iris 데이터의 'data'의 값이 가지는 행열 확인
print( iris['feature_names']) # iris 데이터 셋의 피처이름 확인
print( iris['data'][:5]) # 5개의 데이터 확인
print( iris['target_names'][:5])
print( iris['target'][:5])
(150, 4) ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)'] [[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]] ['setosa' 'versicolor' 'virginica'] [0 0 0 0 0]
print(iris['target'].shape) # 타켓
print(iris['data'].shape)
print(type(iris['target']) , type(iris['data']) )
(150,) (150, 4) <class 'numpy.ndarray'> <class 'numpy.ndarray'>
from sklearn.model_selection import train_test_split
X = iris['data']
y = iris['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
# 데이터 사이즈
print(X_train.shape) # 훈련 데이터 셋 사이즈
print(X_test.shape) # 테스트 데이터 셋 사이즈
print(y_train.shape) # 훈련 데이터 레이블 사이즈
print(y_test.shape) # 테스트 데이터 레이블 사이즈
(112, 4) (38, 4) (112,) (38,)
import seaborn as sns
print(iris['feature_names']) # 붓꽃의 꽃잎과 꽃받침의 feature 이름
['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']
iris_df = pd.DataFrame(X_train, columns=iris.feature_names)
iris_df['species'] = y_train
iris_df['species'] = iris_df['species'].astype('category') # 자료형 변환
iris_df.head()
sepal length (cm) | sepal width (cm) | petal length (cm) | petal width (cm) | species | |
---|---|---|---|---|---|
0 | 5.9 | 3.0 | 4.2 | 1.5 | 1 |
1 | 5.8 | 2.6 | 4.0 | 1.2 | 1 |
2 | 6.8 | 3.0 | 5.5 | 2.1 | 2 |
3 | 4.7 | 3.2 | 1.3 | 0.2 | 0 |
4 | 6.9 | 3.1 | 5.1 | 2.3 | 2 |
print(iris_df.shape)
print(iris_df.info())
(112, 5) <class 'pandas.core.frame.DataFrame'> RangeIndex: 112 entries, 0 to 111 Data columns (total 5 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 sepal length (cm) 112 non-null float64 1 sepal width (cm) 112 non-null float64 2 petal length (cm) 112 non-null float64 3 petal width (cm) 112 non-null float64 4 species 112 non-null category dtypes: category(1), float64(4) memory usage: 3.8 KB None
sns.pairplot(iris_df.iloc[ : ,0:4]) # 1~4열 선택
<seaborn.axisgrid.PairGrid at 0x7f850ad86ac0>
pd.plotting.scatter_matrix(iris_df, c=y_train, # 색
figsize=(15,15), # 크기
marker='o', # 표시
hist_kwds={'bins':20}, # 막대의 개수
s=60, # size
alpha=0.8 ) # 투명도
array([[<AxesSubplot:xlabel='sepal length (cm)', ylabel='sepal length (cm)'>, <AxesSubplot:xlabel='sepal width (cm)', ylabel='sepal length (cm)'>, <AxesSubplot:xlabel='petal length (cm)', ylabel='sepal length (cm)'>, <AxesSubplot:xlabel='petal width (cm)', ylabel='sepal length (cm)'>], [<AxesSubplot:xlabel='sepal length (cm)', ylabel='sepal width (cm)'>, <AxesSubplot:xlabel='sepal width (cm)', ylabel='sepal width (cm)'>, <AxesSubplot:xlabel='petal length (cm)', ylabel='sepal width (cm)'>, <AxesSubplot:xlabel='petal width (cm)', ylabel='sepal width (cm)'>], [<AxesSubplot:xlabel='sepal length (cm)', ylabel='petal length (cm)'>, <AxesSubplot:xlabel='sepal width (cm)', ylabel='petal length (cm)'>, <AxesSubplot:xlabel='petal length (cm)', ylabel='petal length (cm)'>, <AxesSubplot:xlabel='petal width (cm)', ylabel='petal length (cm)'>], [<AxesSubplot:xlabel='sepal length (cm)', ylabel='petal width (cm)'>, <AxesSubplot:xlabel='sepal width (cm)', ylabel='petal width (cm)'>, <AxesSubplot:xlabel='petal length (cm)', ylabel='petal width (cm)'>, <AxesSubplot:xlabel='petal width (cm)', ylabel='petal width (cm)'>]], dtype=object)
from sklearn.neighbors import KNeighborsClassifier
model = KNeighborsClassifier(n_neighbors=2) # 2개의 이웃을 기준
model.fit(X_train, y_train)
KNeighborsClassifier(n_neighbors=2)
X_new = np.array([[5, 2.9, 1, 0.2]])
### 예측시키기
pred = model.predict(X_new)
pred_targetname = iris['target_names'][pred]
print("예측 : ", pred)
print("예측한 타깃의 이름: ", pred_targetname)
예측 : [0] 예측한 타깃의 이름: ['setosa']
y_pred = model.predict(X_test)
print("예측값 :\n", y_pred)
예측값 : [2 1 0 2 0 2 0 1 1 1 2 1 1 1 1 0 1 1 0 0 2 1 0 0 2 0 0 1 1 0 2 1 0 2 2 1 0 2]
print("테스트 세트의 정확도 : {:.2f}".format(np.mean(y_pred == y_test)))
테스트 세트의 정확도 : 0.97