机器学习朴素贝叶斯GaussianNB鸢尾花数据集分类

最新推荐文章于 2024-04-01 17:06:00 发布
最新推荐文章于 2024-04-01 17:06:00 发布
阅读量4k 收藏 11
点赞数 5
分类专栏： 机器学习
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_38662930/article/details/85140105
版权 
import pandas as pd
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn import  datasets



iris=datasets.load_iris()
print(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 ...', 'filename': 'e:\\application\\python\\lib\\site-packages\\sklearn\\datasets\\data\\iris.csv', '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]]), 'feature_names': ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)'], '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]), 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10')}

X_train,Xtest,y_train,y_test=train_test_split(iris.data,iris.target,
                                              random_state=12)


print(X_train.shape)
print(Xtest.shape)

(112, 4)
(38, 4)

clf=GaussianNB()
clf.fit(X_train,y_train)

GaussianNB(priors=None, var_smoothing=1e-09)

clf.predict(Xtest)

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

clf.predict_proba(Xtest)

array([[1.00000000e+000, 2.32926069e-017, 1.81656357e-023],
       [4.28952299e-154, 2.48576754e-002, 9.75142325e-001],
       [1.00000000e+000, 7.45528845e-018, 3.79800436e-024],
       [3.59748710e-076, 9.99751806e-001, 2.48194200e-004],
       [2.20411871e-239, 4.45798016e-009, 9.99999996e-001],
       [1.23795145e-173, 1.95814902e-003, 9.98041851e-001],
       [2.45866589e-206, 2.34481513e-007, 9.99999766e-001],
       [1.00000000e+000, 2.61810906e-017, 2.67446831e-023],
       [3.07448595e-259, 9.07196639e-011, 1.00000000e+000],
       [1.00000000e+000, 1.14549667e-010, 3.00314173e-017],
       [1.64566141e-101, 9.87428016e-001, 1.25719837e-002],
       [1.00000000e+000, 5.62770009e-016, 8.77233124e-022],
       [1.00000000e+000, 9.78098062e-014, 4.81247272e-020],
       [1.00000000e+000, 3.96616431e-015, 3.17162008e-021],
       [2.58159395e-110, 7.85918892e-001, 2.14081108e-001],
       [8.01004975e-208, 8.36611920e-006, 9.99991634e-001],
       [2.27845999e-193, 5.52863568e-004, 9.99447136e-001],
       [2.52133012e-090, 9.94597495e-001, 5.40250471e-003],
       [1.00000000e+000, 4.06675976e-017, 2.53312064e-023],
       [3.29537129e-123, 9.22312452e-001, 7.76875484e-002],
       [1.00000000e+000, 4.66765440e-017, 1.99662820e-023],
       [7.54708431e-074, 9.99690656e-001, 3.09343577e-004],
       [6.27117035e-136, 1.83265786e-001, 8.16734214e-001],
       [4.68960290e-103, 9.82756006e-001, 1.72439943e-002],
       [1.00000000e+000, 2.15636250e-014, 2.25086772e-020],
       [5.92924136e-199, 5.41122729e-007, 9.99999459e-001],
       [4.07679795e-141, 7.38689632e-002, 9.26131037e-001],
       [2.77929930e-083, 9.99806458e-001, 1.93541791e-004],
       [1.00000000e+000, 4.48465501e-017, 4.36464333e-023],
       [1.00000000e+000, 1.64440161e-014, 1.13341951e-021],
       [1.00000000e+000, 8.68192867e-017, 6.71630735e-023],
       [7.15007036e-050, 9.99997055e-001, 2.94492877e-006],
       [1.73414331e-178, 2.06441448e-003, 9.97935586e-001],
       [1.00000000e+000, 4.90168069e-019, 3.86471595e-024],
       [1.35600871e-156, 2.28929843e-002, 9.77107016e-001],
       [1.00000000e+000, 1.78544881e-015, 1.09390819e-020],
       [1.86074590e-058, 9.99948860e-001, 5.11400371e-005],
       [3.69548269e-057, 9.99992986e-001, 7.01435008e-006]])

accuracy_score(y_test,clf.predict(Xtest))

0.9736842105263158





import numpy as np 
import pandas as pd
import random
dataSet=pd.read_csv('iris.txt',header=None)
dataSet.head(10)
01234
05.13.51.40.2Iris-setosa
14.93.01.40.2Iris-setosa
24.73.21.30.2Iris-setosa
34.63.11.50.2Iris-setosa
45.03.61.40.2Iris-setosa
55.43.91.70.4Iris-setosa
64.63.41.40.3Iris-setosa
75.03.41.50.2Iris-setosa
84.42.91.40.2Iris-setosa
94.93.11.50.1Iris-setosa
dataSet.shape
dataSet.index
list(dataSet.index)


[0,
 1,
 2,
 3,
 4,
 5,
 6,
 7,
 8,
 9,
 10,
 11,
 12,
 13,
 14,
 15,
 16,
 17,
 18,
 19,
 20,
 21,
 22,
 23,
 24,
 25,
 26,
 27,
 28,
 29,
 30,
 31,
 32,
 33,
 34,
 35,
 36,
 37,
 38,
 39,
 40,
 41,
 42,
 43,
 44,
 45,
 46,
 47,
 48,
 49,
 50,
 51,
 52,
 53,
 54,
 55,
 56,
 57,
 58,
 59,
 60,
 61,
 62,
 63,
 64,
 65,
 66,
 67,
 68,
 69,
 70,
 71,
 72,
 73,
 74,
 75,
 76,
 77,
 78,
 79,
 80,
 81,
 82,
 83,
 84,
 85,
 86,
 87,
 88,
 89,
 90,
 91,
 92,
 93,
 94,
 95,
 96,
 97,
 98,
 99,
 100,
 101,
 102,
 103,
 104,
 105,
 106,
 107,
 108,
 109,
 110,
 111,
 112,
 113,
 114,
 115,
 116,
 117,
 118,
 119,
 120,
 121,
 122,
 123,
 124,
 125,
 126,
 127,
 128,
 129,
 130,
 131,
 132,
 133,
 134,
 135,
 136,
 137,
 138,
 139,
 140,
 141,
 142,
 143,
 144,
 145,
 146,
 147,
 148,
 149]

import random
def randSplit(dataSet,rate):
    l=list(dataSet.index)
    random.shuffle(l)
    dataSet.index=l
    n=dataSet.shape[0]
    m=int(n*rate)
    train=dataSet.loc[range(m),:]
    test=dataSet.loc[range(m,n),:]
    dataSet.index=range(dataSet.shape[0])
    test.index=range(test.shape[0])
    return train,test
    

x_train,x_test=randSplit(dataSet,0.8)

x_train
01234
05.03.51.30.3Iris-setosa
15.62.74.21.3Iris-versicolor
26.33.34.71.6Iris-versicolor
34.43.01.30.2Iris-setosa
45.52.64.41.2Iris-versicolor
56.43.15.51.8Iris-virginica
64.92.43.31.0Iris-versicolor
75.43.91.30.4Iris-setosa
86.03.44.51.6Iris-versicolor
96.42.85.62.2Iris-virginica
105.03.51.60.6Iris-setosa
116.02.75.11.6Iris-versicolor
125.02.03.51.0Iris-versicolor
134.93.01.40.2Iris-setosa
145.13.31.70.5Iris-setosa
156.32.54.91.5Iris-versicolor
165.62.93.61.3Iris-versicolor
175.03.31.40.2Iris-setosa
187.32.96.31.8Iris-virginica
194.63.21.40.2Iris-setosa
205.84.01.20.2Iris-setosa
216.53.05.22.0Iris-virginica
225.52.34.01.3Iris-versicolor
235.13.81.90.4Iris-setosa
246.32.95.61.8Iris-virginica
255.22.73.91.4Iris-versicolor
266.72.55.81.8Iris-virginica
274.92.54.51.7Iris-virginica
286.73.05.22.3Iris-virginica
297.13.05.92.1Iris-virginica
..................
907.23.26.01.8Iris-virginica
917.03.24.71.4Iris-versicolor
925.43.41.70.2Iris-setosa
935.82.74.11.0Iris-versicolor
946.83.05.52.1Iris-virginica
955.13.71.50.4Iris-setosa
965.63.04.11.3Iris-versicolor
975.72.94.21.3Iris-versicolor
986.02.24.01.0Iris-versicolor
997.63.06.62.1Iris-virginica
1006.53.25.12.0Iris-virginica
1014.52.31.30.3Iris-setosa
1025.72.55.02.0Iris-virginica
1035.43.41.50.4Iris-setosa
1047.42.86.11.9Iris-virginica
1055.82.75.11.9Iris-virginica
1066.23.45.42.3Iris-virginica
1074.63.61.00.2Iris-setosa
1086.13.04.91.8Iris-virginica
1095.03.61.40.2Iris-setosa
1105.52.54.01.3Iris-versicolor
1116.22.84.81.8Iris-virginica
1126.53.05.82.2Iris-virginica
1136.73.14.41.4Iris-versicolor
1144.83.01.40.1Iris-setosa
1156.12.94.71.4Iris-versicolor
1165.93.24.81.8Iris-versicolor
1174.93.11.50.1Iris-setosa
1186.33.45.62.4Iris-virginica
1195.82.73.91.2Iris-versicolor

120 rows × 5 columns

x_test
01234
05.74.41.50.4Iris-setosa
16.42.75.31.9Iris-virginica
26.03.04.81.8Iris-virginica
35.13.81.50.3Iris-setosa
44.83.41.60.2Iris-setosa
54.63.11.50.2Iris-setosa
66.53.05.51.8Iris-virginica
74.93.11.50.1Iris-setosa
86.32.55.01.9Iris-virginica
95.43.91.70.4Iris-setosa
105.13.41.50.2Iris-setosa
115.13.51.40.2Iris-setosa
124.83.01.40.3Iris-setosa
136.62.94.61.3Iris-versicolor
145.93.05.11.8Iris-virginica
155.23.41.40.2Iris-setosa
167.72.66.92.3Iris-virginica
175.43.04.51.5Iris-versicolor
185.82.75.11.9Iris-virginica
196.73.05.01.7Iris-versicolor
205.82.64.01.2Iris-versicolor
214.73.21.60.2Iris-setosa
226.33.36.02.5Iris-virginica
235.02.33.31.0Iris-versicolor
245.33.71.50.2Iris-setosa
255.73.81.70.3Iris-setosa
266.73.14.71.5Iris-versicolor
277.93.86.42.0Iris-virginica
285.12.53.01.1Iris-versicolor
296.22.94.31.3Iris-versicolor
labels=x_train.loc[:,4]#标签索引
labels=x_train.iloc[:,-1]#位置索引

labels

0          Iris-setosa
1      Iris-versicolor
2      Iris-versicolor
3          Iris-setosa
4      Iris-versicolor
5       Iris-virginica
6      Iris-versicolor
7          Iris-setosa
8      Iris-versicolor
9       Iris-virginica
10         Iris-setosa
11     Iris-versicolor
12     Iris-versicolor
13         Iris-setosa
14         Iris-setosa
15     Iris-versicolor
16     Iris-versicolor
17         Iris-setosa
18      Iris-virginica
19         Iris-setosa
20         Iris-setosa
21      Iris-virginica
22     Iris-versicolor
23         Iris-setosa
24      Iris-virginica
25     Iris-versicolor
26      Iris-virginica
27      Iris-virginica
28      Iris-virginica
29      Iris-virginica
            ...       
90      Iris-virginica
91     Iris-versicolor
92         Iris-setosa
93     Iris-versicolor
94      Iris-virginica
95         Iris-setosa
96     Iris-versicolor
97     Iris-versicolor
98     Iris-versicolor
99      Iris-virginica
100     Iris-virginica
101        Iris-setosa
102     Iris-virginica
103        Iris-setosa
104     Iris-virginica
105     Iris-virginica
106     Iris-virginica
107        Iris-setosa
108     Iris-virginica
109        Iris-setosa
110    Iris-versicolor
111     Iris-virginica
112     Iris-virginica
113    Iris-versicolor
114        Iris-setosa
115    Iris-versicolor
116    Iris-versicolor
117        Iris-setosa
118     Iris-virginica
119    Iris-versicolor
Name: 4, Length: 120, dtype: object

labels=x_train.iloc[:,-1].value_counts()

labels

Index(['Iris-versicolor', 'Iris-virginica', 'Iris-setosa'], dtype='object')

labels=x_train.iloc[:,-1].value_counts().index
labels

Index(['Iris-versicolor', 'Iris-virginica', 'Iris-setosa'], dtype='object')

### 计算方差与均值

mean=[]
std=[]

for i in labels:

    item=x_train.loc[x_train.iloc[:,-1]==i,:]
    m=item.iloc[:,:-1]
    

item
01234
06.02.25.01.5Iris-virginica
26.03.04.81.8Iris-virginica
35.82.75.11.9Iris-virginica
67.23.66.12.5Iris-virginica
116.33.36.02.5Iris-virginica
136.73.05.22.3Iris-virginica
186.83.05.52.1Iris-virginica
227.42.86.11.9Iris-virginica
256.33.45.62.4Iris-virginica
266.43.15.51.8Iris-virginica
316.13.04.91.8Iris-virginica
367.23.05.81.6Iris-virginica
376.32.95.61.8Iris-virginica
406.12.65.61.4Iris-virginica
467.32.96.31.8Iris-virginica
526.32.55.01.9Iris-virginica
637.93.86.42.0Iris-virginica
647.73.86.72.2Iris-virginica
656.23.45.42.3Iris-virginica
694.92.54.51.7Iris-virginica
726.73.35.72.1Iris-virginica
736.53.05.22.0Iris-virginica
746.93.25.72.3Iris-virginica
816.32.74.91.8Iris-virginica
826.93.15.42.1Iris-virginica
836.42.75.31.9Iris-virginica
847.13.05.92.1Iris-virginica
867.72.66.92.3Iris-virginica
907.73.06.12.3Iris-virginica
935.62.84.92.0Iris-virginica
946.53.05.82.2Iris-virginica
976.42.85.62.1Iris-virginica
1016.32.85.11.5Iris-virginica
1026.42.85.62.2Iris-virginica
1096.83.25.92.3Iris-virginica
1117.23.26.01.8Iris-virginica
1126.93.15.12.3Iris-virginica
m

0    4.970270
1    3.383784
2    1.443243
3    0.243243
dtype: float64

mean=[]
std=[]

for i in labels:

    item=x_train.loc[x_train.iloc[:,-1]==i,:]
    m=item.iloc[:,:-1].mean()
    

m

0    4.970270
1    3.383784
2    1.443243
3    0.243243
dtype: float64

mean=[]
std=[]

for i in labels:

    item=x_train.loc[x_train.iloc[:,-1]==i,:]
    m=item.iloc[:,:-1].mean()
    
    s=np.sum((item.iloc[:,:-1]-m)**2)/item.shape[0]
(item.iloc[:,:-1]-m)**2
0123
00.0008840.0135060.0205190.003221
30.3252080.1472900.0205190.001870
70.1846680.2664790.0205190.024573
100.0008840.0135060.0245730.127275
130.0049380.1472900.0018700.001870
140.0168300.0070200.0659240.065924
170.0008840.0070200.0018700.001870
190.1371000.0337760.0018700.001870
200.6884510.3797220.0591670.001870
230.0168300.1732360.2086270.024573
370.3252080.2340470.0018700.001870
400.0527760.0135060.0032210.001870
430.0008840.0337760.0591670.001870
440.1371000.0002630.0018700.003221
450.0008840.1472900.0245730.001870
490.1846680.0999930.0032210.001870
560.0289920.0002630.2086270.001870
590.4492620.1472900.1178160.020519
650.0168300.1732360.0245730.001870
710.0168300.0135060.0018700.003221
740.0730460.0337760.0205190.001870
750.2806140.6662090.0018700.001870
760.3252080.0337760.0205190.001870
770.0049380.0805330.0032210.020519
800.0527760.5129660.0032210.020519
810.0008840.0002630.0032210.001870
840.0008840.0002630.0245730.024573
860.2806140.0135060.0205190.001870
870.0289920.0805330.0245730.001870
920.1846680.0002630.0659240.001870
950.0168300.0999930.0032210.024573
1010.2211541.1745870.0205190.003221
1030.1846680.0002630.0032210.024573
1070.1371000.0467490.1964650.001870
1090.0008840.0467490.0018700.001870
1140.0289920.1472900.0018700.020519
1170.0049380.0805330.0032210.020519
s

0    0.119386
1    0.137034
2    0.034887
3    0.012725
dtype: float64

mean=[]
std=[]

for i in labels:

    item=x_train.loc[x_train.iloc[:,-1]==i,:]
    m=item.iloc[:,:-1].mean()
    
    s=np.sum((item.iloc[:,:-1]-m)**2)/item.shape[0]
    mean.append(m)
    std.append(s)
means=pd.DataFrame(mean,index=labels)
stds=pd.DataFrame(std,index=labels)

mean

[0    5.935714
 1    2.766667
 2    4.276190
 3    1.326190
 dtype: float64, 0    6.600000
 1    2.978049
 2    5.548780
 3    2.034146
 dtype: float64, 0    4.970270
 1    3.383784
 2    1.443243
 3    0.243243
 dtype: float64]

std

[0    0.226105
 1    0.101270
 2    0.174195
 3    0.036695
 dtype: float64, 0    0.370732
 1    0.092445
 2    0.264450
 3    0.077858
 dtype: float64, 0    0.119386
 1    0.137034
 2    0.034887
 3    0.012725
 dtype: float64]

means
0123
Iris-versicolor5.9357142.7666674.2761901.326190
Iris-virginica6.6000002.9780495.5487802.034146
Iris-setosa4.9702703.3837841.4432430.243243
stds
0123
Iris-versicolor0.2261050.1012700.1741950.036695
Iris-virginica0.3707320.0924450.2644500.077858
Iris-setosa0.1193860.1370340.0348870.012725
for j in range(x_test.shape[0]):
    iset=x_test.iloc[j,:-1]

iset

0    6.2
1    2.9
2    4.3
3    1.3
Name: 29, dtype: object

for j in range(x_test.shape[0]):
    iset=x_test.iloc[j,:-1].tolist()

iset

[6.2, 2.9, 4.3, 1.3]

for j in range(x_test.shape[0]):
    iset=x_test.iloc[j,:-1].tolist()
    iprob=np.exp(-1*(iset-means)**2/(stds*2))/np.sqrt(2*np.pi*stds)

iset-means
0123
Iris-versicolor0.2642860.1333330.023810-0.026190
Iris-virginica-0.400000-0.078049-1.248780-0.734146
Iris-setosa1.229730-0.4837842.8567571.056757
iprob
0123
Iris-versicolor0.7189111.1482869.543013e-012.063229e+00
Iris-virginica0.5280371.2695794.066561e-024.488144e-02
Iris-setosa0.0020510.4587973.406877e-513.100002e-19
iprob[0]

Iris-versicolor    0.718911
Iris-virginica     0.528037
Iris-setosa        0.002051
Name: 0, dtype: float64

for j in range(x_test.shape[0]):
    iset=x_test.iloc[j,:-1].tolist()
    iprob=np.exp(-1*(iset-means)**2/(stds*2))/np.sqrt(2*np.pi*stds)
    prob=1
    for k in range(x_test.shape[1]-1):
        prob*=iprob[k]

prob

Iris-versicolor    1.625391e+00
Iris-virginica     1.223539e-03
Iris-setosa        9.936339e-73
Name: 0, dtype: float64

prob.values

array([1.62539149e+00, 1.22353864e-03, 9.93633857e-73])

prob.index

Index(['Iris-versicolor', 'Iris-virginica', 'Iris-setosa'], dtype='object')


np.argmax(prob.values)

0

result=[]
for j in range(x_test.shape[0]):
    iset=x_test.iloc[j,:-1].tolist()
    iprob=np.exp(-1*(iset-means)**2/(stds*2))/np.sqrt(2*np.pi*stds)
    prob=1
    for k in range(x_test.shape[1]-1):
        prob*=iprob[k]
    cla=prob.index[(np.argmax(prob.values))]
    result.append(cla)
x_test['predict']=result
    acc=(x_test.iloc[:,-1]==x_test.iloc[:,-2]).mean()
    print("accuracy rate is",acc)


  File "<ipython-input-374-38f3e0c25417>", line 11
    acc=(x_test.iloc[:,-1]==x_test.iloc[:,-2]).mean()
    ^
IndentationError: unexpected indent

result

x_test

cla



def gnb_classify(x_train,x_test):
    labels=x_train.iloc[:,-1].value_counts()
    mean=[]
    std=[]
    result=[]

    for i in labels:

        item=x_train.loc[x_train.iloc[:,-1]==i,:]
        m=item.iloc[:,:-1].mean()

        s=np.sum((item.iloc[:,:-1]-m)**2)/item.shape[0]
        mean.append(m)
        std.append(s)
    means=pd.DataFrame(mean,index=labels)
    stds=pd.DataFrame(std,index=labels)
    for j in range(x_test.shape[0]):
        iset=x_test.iloc[j,:-1].tolist()
        iprob=np.exp(-1*(iset-means)**2/(stds*2))/np.sqrt(2*np.pi*stds)
        prob=1
        for k in range(x_test.shape[1]-1):
            prob*=iprob[k]
        cla=prob.index[(np.argmax(prob.values))]
        result.append(cla)
    x_test['predict']=result
#     acc=(x_test.iloc[:,-1]==x_test.iloc[:,-2]).mean()
#     print("accuracy rate is",acc)
    return x_test

gnb_classify(x_train,x_test)
执笔论英雄
关注
专栏目录
AI：16-朴素贝叶斯算法之鸢尾花特征分类【机器学习】【伯努利分布,多项式分布,高斯分布】
一键难忘的博客
06-21 3822
1.熟悉机器学习之朴素贝叶斯算法 2.使用朴素贝叶斯算法解决问题 贝叶斯定理是关于随机事件a和B的条件概率（或边际概率）的定理。其中p（a | B）是当B发生时a发生的可能性。 朴素贝叶斯算法： 对于样本集： 其中m表示有m个样本，N表示有N个特征。yi，i=1,2，。。，M表示样本类别，值为{c1，C2，…，ck}。 朴素贝叶斯分类的基本公式： 计算先验概率：计算样本类别数k。对于每个样本y=ck，计算P（y=ck）。这是总样本集中CK类的频率。 计算条件概率：将样本集划分为k个子样本集，分别计算属于
机器学习算法-朴素贝叶斯（一）：朴素贝叶斯简介和鸢尾花分类实战（代码附详细注释）
qq_41669491的博客
12-24 4693
朴素贝叶斯 朴素贝叶斯的介绍 朴素贝叶斯算法（Naive Bayes, NB) 是应用最为广泛的分类算法之一。它是基于贝叶斯定义和特征条件独立假设的分类器方法。由于朴素贝叶斯法基于贝叶斯公式计算得到，有着坚实的数学基础，以及稳定的分类效率。NB模型所需估计的参数很少，对缺失数据不太敏感，算法也比较简单。当年的垃圾邮件分类都是基于朴素贝叶斯分类器识别的。 我们用一句话理解贝叶斯：世间很多事都存在某种联系，假设事件A和事件B。人们常常使用已经发生的某个事件去推断我们想要知道的之间的概率。 例如，医生在确诊的时候
matlab-朴素贝叶斯-鸢尾花数据集
08-31
朴素贝叶斯算法写的关于鸢尾花分类的程序，有需要的可以自己下载修改使用.
机器学习实验：朴素贝叶斯算法实现对iris鸢尾花数据集的分类
m0_46553432的博客
04-14 1万+
机器学习实验：朴素贝叶斯算法实现对iris鸢尾花数据集的分类 实验内容： 通过sklearn提供的贝叶斯算法模型实现对iris鸢尾花数据集的分类及预测 使用PCA降维，并通过matplotlib对决策边进行绘制 代码如下： 导入相关库 import pandas as pd import numpy as np import matplotlib.colors as colors import matplotlib as mpl import matplotlib.pyplot as plt imp
朴素贝叶斯对鸢尾花数据集进行分类
weixin_33716557的博客
01-09 1万+
注：本人纯粹为了练手熟悉各个方法的用法 使用高斯朴素贝叶斯对鸢尾花数据进行分类 代码： 1 # 通过朴素贝叶斯对鸢尾花数据进行分类 2 3 from sklearn import datasets 4 from sklearn.model_selection import train_test_split 5 from sklearn.naive_bayes impo...
朴素贝叶斯处理鸢尾花数据集分类
weixin_46302044的博客
05-30 9648
一、实验目的 (1) 掌握贝叶斯算法原理； (2) 掌握朴素贝叶斯原理； (3) 使用朴素贝叶斯处理鸢尾花数据集分类 二、实验内容 （1）导入库，加载鸢尾花数据，输出样本和鸢尾花特征 （2）数据分割，数据分割，形成模型训练数据和测试数据 （3）高斯贝叶斯模型构建 （4）计算预测值并计算准确率 （5）画图 三、实验代码 import numpy as np import pandas as pd import matplotlib.pyplot as plt import matplotlib as mpl
机器学习实战篇：使用贝叶斯模型对鸢尾花数据集分类
人工智能讲师团
03-11 7948
1、简介 本文主要讲解朴素贝叶斯及其推理，并实现鸢尾花数据的分类问题 2、算法解释 朴素贝叶斯最初来源于统计科学领域。根据朴素贝叶斯公式： 由于类似然涉及到多个特征的组合求解较为困难。所以为了简化运算，降低计算复杂度，我们假设每个特征具备统计独立性，即特征间不存在关联性。这样就可以简化上述贝叶斯公式为： 上述公式即为朴素贝叶斯通用公式，我们进一步化简去除无关证据项得： 根据...
鸢尾花python贝叶斯分类_机器学习之鸢尾花-朴素贝叶斯方法
weixin_39852647的博客
02-12 3859
在所有的机器学习分类算法中，朴素贝叶斯和其他绝大多数的分类算法都不同。 对于大多数的分类算法，比如决策树,KNN,逻辑回归，支持向量机等，他们都是判别方法，也就是直接学习出特征输出Y和特征X之间的关系，要么是决策函数Y=f(X),要么是条件分布P(Y|X)。 朴素贝叶斯方法是基于贝叶斯定理的一组有监督学习算法，即“简单”地假设每对特征之间相互独立，也就是直接找出特征输出Y和特征X的联合分布P(X,...
基于朴素贝叶斯网络的iris鸢尾花数据集分类到新闻分类
m0_46557838的博客
04-26 6695
本篇文章是对最简单的朴素贝叶斯网络的运用进行python实践，先对iris鸢尾花数据集做一个分类预实验，再对实际新闻进行分类预测 有关贝叶斯网络原理可以查看这篇文章 ：贝叶斯网络基础 一、iris鸢尾花数据集分类 1、开头先导入相关模块： import matplotlib.pyplot as plt # 绘图 from sklearn.datasets import load_iris #导...
基于朴素贝叶斯的鸢尾花数据集分类
热门推荐
ZHW-鲜橙大AI课题组的博客
04-06 2万+
本博文实现了基于朴素贝叶斯的鸢尾花数据集分类
实现贝叶斯分类器_基于鸢尾花数据集的贝叶斯分类
weixin_33001561的博客
01-14 792
sklearn.naive_bayes 的超简单介绍在sklearn中，朴素贝叶斯主要有以下几种方法：更为详细的说明可参考下方链接中的官方文档：1.9. Naive Bayes​scikit-learn.org（哈哈哈哈这部分照应小标题：超简单介绍。没有啦没有啦，主要是官方文档很清晰的介绍了，各种参数说明都有，甚至于还有实例。）也许纯碎地看上面的文档介绍，会看得蒙蒙的，但别急，下面的小案例会让你慢...
基于鸢尾花数据集实战贝叶斯分类
与你的博客
12-23 2881
本文为记录自己参加阿里云机器学习训练营所做的学习记录，代码以及知识内容均来源于训练营。 鸢尾花数据集–贝叶斯分类 Step1：库函数导入 import warnings warnings.filterwarnings('ignore') import numpy as np # 加载莺尾花数据集 from sklearn import datasets # 导入高斯朴素贝叶斯分类器 from sklearn.naive_bayes import GaussianNB from sklearn.model_s
利用鸢尾花数据集实践贝叶斯分类
qq_45435247的博客
12-19 3654
前面我们已经详细介绍过鸢尾花数据集以及sklearn的使用，下面我们就来调用sklearn中的贝叶斯分类器来实现鸢尾花数据集的分类。 首先，我们需要导入需要用到的包，模型以及数据集 import numpy as np # 导入sklearn中有关于数据集的包 from sklearn import datasets # 导入高斯朴素贝叶斯分类器 from sklearn.naive_bayes import GaussianNB from sklearn.model_selection import
GuassianNB 对鸢尾花数据分类 python
qq_38120760的博客
10-22 761
#coding=utf-8 import numpy as np import matplotlib.pyplot as plt import matplotlib as mpl from sklearn.naive_bayes import GaussianNB from sklearn.datasets import load_iris from sklearn.model_selectio...
朴素贝叶斯sklearn实现
weixin_42263508的博客
05-19 1138
朴素贝叶斯是一类比较简单的算法，scikit-learn中朴素贝叶斯类库的使用也比较简单。相对于决策树，KNN之类的算法，朴素贝叶斯需要关注的参数是比较少的，这样也比较容易掌握。在scikit-learn中，一共有3个朴素贝叶斯的分类算法类。分别是GaussianNB，MultinomialNB和BernoulliNB。 其中GaussianNB就是先验为高斯分布的朴素贝叶斯，Multinomia...
【项目实战】Python实现Naive Bayes贝叶斯分类模型(GaussianNB、MultinomialNB算法)项目实战
张陈亚的博客
11-21 7391
Python实现Naive Bayes贝叶斯分类模型(GaussianNB、MultinomialNB算法)项目实战
朴素贝叶斯的三个常用模型：高斯(GaussianNB)、多项式(multinomial model)、伯努利(Bernoulli model)
qq_36134437的博客
11-14 6652
文本分类 在文本分类中，假设我们有一个文档d∈X，X是文档向量空间(document space)，和一个固定的类集合C={c1,c2,…,cj}，类别又称为标签。显然，文档向量空间是一个高维度空间。我们把一堆打了标签的文档集合<d,c>作为训练样本，<d,c>∈X×C。例如： <d,c>={Beijing joins the World Trade Organ...
机器学习实战17-高斯朴素贝叶斯(GaussianNB)模型的实际应用，结合生活中的生动例子帮助大家理解
最新发布
weixin_42878111的博客
04-01 3593
大家好，我是微学AI，今天给大家介绍一下机器学习实战17-高斯朴素贝叶斯(GaussianNB)模型的实际应用，结合生活中的生动例子帮助大家理解。GaussianNB，即高斯朴素贝叶斯模型，是一种基于概率论的分类算法，广泛应用于机器学习领域。该模型假设特征之间相互独立，并且每个特征服从高斯分布（正态分布），通过学习训练数据集中的先验概率和条件概率来实现对未知数据的预测。
朴素贝叶斯鸢尾花识别系统设计与Python实现详解
这份文档专注于运用朴素贝叶斯算法对鸢尾花进行分类，它在数据科学和机器学习领域具有重要意义。 1. 主要研究内容： - 鸢尾花分类：该系统利用朴素贝叶斯分类器，这是一个简单而有效的统计学习方法，它假设特征...
评论 1
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值