Machine learning

Méthode naïve de Bayes

On charge les données et on parcours les données sur lesquelles nous allons travailler

In [1]:
from sklearn import datasets
wine = datasets.load_wine()
print(wine.DESCR)
.. _wine_dataset:

Wine recognition dataset
------------------------

**Data Set Characteristics:**

    :Number of Instances: 178 (50 in each of three classes)
    :Number of Attributes: 13 numeric, predictive attributes and the class
    :Attribute Information:
 		- Alcohol
 		- Malic acid
 		- Ash
		- Alcalinity of ash  
 		- Magnesium
		- Total phenols
 		- Flavanoids
 		- Nonflavanoid phenols
 		- Proanthocyanins
		- Color intensity
 		- Hue
 		- OD280/OD315 of diluted wines
 		- Proline

    - class:
            - class_0
            - class_1
            - class_2
		
    :Summary Statistics:
    
    ============================= ==== ===== ======= =====
                                   Min   Max   Mean     SD
    ============================= ==== ===== ======= =====
    Alcohol:                      11.0  14.8    13.0   0.8
    Malic Acid:                   0.74  5.80    2.34  1.12
    Ash:                          1.36  3.23    2.36  0.27
    Alcalinity of Ash:            10.6  30.0    19.5   3.3
    Magnesium:                    70.0 162.0    99.7  14.3
    Total Phenols:                0.98  3.88    2.29  0.63
    Flavanoids:                   0.34  5.08    2.03  1.00
    Nonflavanoid Phenols:         0.13  0.66    0.36  0.12
    Proanthocyanins:              0.41  3.58    1.59  0.57
    Colour Intensity:              1.3  13.0     5.1   2.3
    Hue:                          0.48  1.71    0.96  0.23
    OD280/OD315 of diluted wines: 1.27  4.00    2.61  0.71
    Proline:                       278  1680     746   315
    ============================= ==== ===== ======= =====

    :Missing Attribute Values: None
    :Class Distribution: class_0 (59), class_1 (71), class_2 (48)
    :Creator: R.A. Fisher
    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
    :Date: July, 1988

This is a copy of UCI ML Wine recognition datasets.
https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data

The data is the results of a chemical analysis of wines grown in the same
region in Italy by three different cultivators. There are thirteen different
measurements taken for different constituents found in the three types of
wine.

Original Owners: 

Forina, M. et al, PARVUS - 
An Extendible Package for Data Exploration, Classification and Correlation. 
Institute of Pharmaceutical and Food Analysis and Technologies,
Via Brigata Salerno, 16147 Genoa, Italy.

Citation:

Lichman, M. (2013). UCI Machine Learning Repository
[https://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
School of Information and Computer Science. 

.. topic:: References

  (1) S. Aeberhard, D. Coomans and O. de Vel, 
  Comparison of Classifiers in High Dimensional Settings, 
  Tech. Rep. no. 92-02, (1992), Dept. of Computer Science and Dept. of  
  Mathematics and Statistics, James Cook University of North Queensland. 
  (Also submitted to Technometrics). 

  The data was used with many others for comparing various 
  classifiers. The classes are separable, though only RDA 
  has achieved 100% correct classification. 
  (RDA : 100%, QDA 99.4%, LDA 98.9%, 1NN 96.1% (z-transformed data)) 
  (All results using the leave-one-out technique) 

  (2) S. Aeberhard, D. Coomans and O. de Vel, 
  "THE CLASSIFICATION PERFORMANCE OF RDA" 
  Tech. Rep. no. 92-01, (1992), Dept. of Computer Science and Dept. of 
  Mathematics and Statistics, James Cook University of North Queensland. 
  (Also submitted to Journal of Chemometrics).

In [2]:
print('Features: ', wine.feature_names)
print('Labels: ', wine.target_names)
Features:  ['alcohol', 'malic_acid', 'ash', 'alcalinity_of_ash', 'magnesium', 'total_phenols', 'flavanoids', 'nonflavanoid_phenols', 'proanthocyanins', 'color_intensity', 'hue', 'od280/od315_of_diluted_wines', 'proline']
Labels:  ['class_0' 'class_1' 'class_2']
In [3]:
data = wine.data
target = wine.target
In [4]:
print(data)
print(target)
[[1.423e+01 1.710e+00 2.430e+00 ... 1.040e+00 3.920e+00 1.065e+03]
 [1.320e+01 1.780e+00 2.140e+00 ... 1.050e+00 3.400e+00 1.050e+03]
 [1.316e+01 2.360e+00 2.670e+00 ... 1.030e+00 3.170e+00 1.185e+03]
 ...
 [1.327e+01 4.280e+00 2.260e+00 ... 5.900e-01 1.560e+00 8.350e+02]
 [1.317e+01 2.590e+00 2.370e+00 ... 6.000e-01 1.620e+00 8.400e+02]
 [1.413e+01 4.100e+00 2.740e+00 ... 6.100e-01 1.600e+00 5.600e+02]]
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 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 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]

On sépare les données en deux parties : une pour l'entrainement et une pour le test

In [5]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=.3, random_state=109)

Classifieur naïf de Bayes

In [6]:
from sklearn.naive_bayes import GaussianNB
nb = GaussianNB()
nb.fit(X_train, y_train)
Out[6]:
GaussianNB(priors=None, var_smoothing=1e-09)
In [7]:
y_pred = nb.predict(X_test)
In [8]:
from sklearn import metrics
scores = metrics.accuracy_score(y_test, y_pred)
print('Accuracy: ','{:2.2%}'.format(scores))
Accuracy:  90.74%
In [9]:
cm = metrics.confusion_matrix(y_test, y_pred)
print(cm)
[[20  1  0]
 [ 2 15  2]
 [ 0  0 14]]
In [11]:
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))
              precision    recall  f1-score   support

           0       0.91      0.95      0.93        21
           1       0.94      0.79      0.86        19
           2       0.88      1.00      0.93        14

    accuracy                           0.91        54
   macro avg       0.91      0.91      0.91        54
weighted avg       0.91      0.91      0.91        54

In [13]:
import numpy as np
print(np.sum(np.diag(cm)/np.sum(cm)))
0.9074074074074074
In [ ]: