机器学习进阶笔记之一~~~朴素贝叶斯之一

有两篇文章写的比我详细，内容比这里多，但是本宝宝没有抄袭，这是学习笔记，附别人的链接：

https://blog.csdn.net/u012084802/article/details/78865445

https://www.cnblogs.com/amanda-x/p/7801427.html

scikit-learn参考链接：

http://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_score.html

http://scikit-learn.org/stable/modules/naive_bayes.html

http://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.GaussianNB.html#examples-using-sklearn-naive-bayes-gaussiannb

注：

*.ipynb的是运行文件

运行命令：

jupyter notebook *.ipynb

源代码之码云下载：

https://gitee.com/iscas/machine_learning_improve/tree/master

执行文件：

class_vis.py

#!/usr/bin/python

#from udacityplots import *
import warnings
warnings.filterwarnings("ignore")

import matplotlib 
matplotlib.use('agg')

import matplotlib.pyplot as plt
import pylab as pl
import numpy as np

#import numpy as np
#import matplotlib.pyplot as plt
#plt.ioff()
def prettyPicture(clf, X_test, y_test):
    x_min = 0.0; x_max = 1.0
    y_min = 0.0; y_max = 1.0

    # Plot the decision boundary. For that, we will assign a color to each
    # point in the mesh [x_min, m_max]x[y_min, y_max].
    h = .01  # step size in the mesh
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])

    # Put the result into a color plot
    Z = Z.reshape(xx.shape)
    plt.xlim(xx.min(), xx.max())
    plt.ylim(yy.min(), yy.max())

    plt.pcolormesh(xx, yy, Z, cmap=pl.cm.seismic)

    # Plot also the test points
    grade_sig = [X_test[ii][0] for ii in range(0, len(X_test)) if y_test[ii]==0]
    bumpy_sig = [X_test[ii][1] for ii in range(0, len(X_test)) if y_test[ii]==0]
    grade_bkg = [X_test[ii][0] for ii in range(0, len(X_test)) if y_test[ii]==1]
    bumpy_bkg = [X_test[ii][1] for ii in range(0, len(X_test)) if y_test[ii]==1]

    plt.scatter(grade_sig, bumpy_sig, color = "b", label="fast")
    plt.scatter(grade_bkg, bumpy_bkg, color = "r", label="slow")
    plt.legend()
    plt.xlabel("bumpiness")
    plt.ylabel("grade")

    plt.savefig("test.png")
    
import base64
import json
import subprocess

def output_image(name, format, bytes):
    image_start = "BEGIN_IMAGE_f9825uweof8jw9fj4r8"
    image_end = "END_IMAGE_0238jfw08fjsiufhw8frs"
    data = {}
    data['name'] = name
    data['format'] = format
    data['bytes'] = base64.encodestring(bytes)
    print image_start+json.dumps(data)+image_end

classify.py

#!/usr/bin/python

from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score
    
def NBAccuracy(features_train, labels_train, features_test, labels_test):
    """ compute the accuracy of your Naive Bayes classifier """
    ### import the sklearn module for GaussianNB

    ### create classifier
    clf = GaussianNB()

    ### fit the classifier on the training features and labels
    clf.fit(features_train, labels_train)

    ### use the trained classifier to predict labels for the test features
    pred = clf.predict(features_test)

    ### calculate and return the accuracy on the test data
    ### this is slightly different than the example, 
    ### where we just print the accuracy
    ### you might need to import an sklearn module
    accuracy = accuracy_score(labels_test, pred)
    return accuracy

ClassifyNB.py

#!/usr/bin/python
from sklearn.naive_bayes import GaussianNB

def classify(features_train, labels_train):   
    ### import the sklearn module for GaussianNB
    ### create classifier
    ### fit the classifier on the training features and labels
    ### return the fit classifier
    
    
    ### your code goes here!
	gnb = GaussianNB()
	clf = gnb.fit(features_train, labels_train)
    
	print '--clf---'
	print clf
	print '---clf--'
    
	return clf
	

prep_terrain_data.py

#!/usr/bin/python
import random


def makeTerrainData(n_points=1000):
###############################################################################
### make the toy dataset
    random.seed(42)
    grade = [random.random() for ii in range(0,n_points)]
    bumpy = [random.random() for ii in range(0,n_points)]
    error = [random.random() for ii in range(0,n_points)]
    y = [round(grade[ii]*bumpy[ii]+0.3+0.1*error[ii]) for ii in range(0,n_points)]
    for ii in range(0, len(y)):
        if grade[ii]>0.8 or bumpy[ii]>0.8:
            y[ii] = 1.0

### split into train/test sets
    X = [[gg, ss] for gg, ss in zip(grade, bumpy)]
    split = int(0.75*n_points)
    X_train = X[0:split]
    X_test  = X[split:]
    y_train = y[0:split]
    y_test  = y[split:]

    grade_sig = [X_train[ii][0] for ii in range(0, len(X_train)) if y_train[ii]==0]
    bumpy_sig = [X_train[ii][1] for ii in range(0, len(X_train)) if y_train[ii]==0]
    grade_bkg = [X_train[ii][0] for ii in range(0, len(X_train)) if y_train[ii]==1]
    bumpy_bkg = [X_train[ii][1] for ii in range(0, len(X_train)) if y_train[ii]==1]

#    training_data = {"fast":{"grade":grade_sig, "bumpiness":bumpy_sig}
#            , "slow":{"grade":grade_bkg, "bumpiness":bumpy_bkg}}


    grade_sig = [X_test[ii][0] for ii in range(0, len(X_test)) if y_test[ii]==0]
    bumpy_sig = [X_test[ii][1] for ii in range(0, len(X_test)) if y_test[ii]==0]
    grade_bkg = [X_test[ii][0] for ii in range(0, len(X_test)) if y_test[ii]==1]
    bumpy_bkg = [X_test[ii][1] for ii in range(0, len(X_test)) if y_test[ii]==1]

    test_data = {"fast":{"grade":grade_sig, "bumpiness":bumpy_sig}
            , "slow":{"grade":grade_bkg, "bumpiness":bumpy_bkg}}

    ###print X_train
    ### print '\n'
    ###print y_train 
    ###print '\n'
    ###print X_test
    ###print '\n'
    ###print y_test
    return X_train, y_train, X_test, y_test
#    return training_data, test_data

Studentcode.ipynb

#!/usr/bin/python

from class_vis import prettyPicture
from prep_terrain_data import makeTerrainData
from classify import NBAccuracy

import matplotlib.pyplot as plt
import numpy as np
import pylab as pl


features_train, labels_train, features_test, labels_test = makeTerrainData()

def submitAccuracy(_features_train, _labels_train, _features_test, _labels_test):
    accuracy = NBAccuracy(_features_train, _labels_train, _features_test, _labels_test)
    return accuracy

if __name__ == '__main__':
    print submitAccuracy(features_train, labels_train, features_test, labels_test)

studentMain.ipynb

#!/usr/bin/python

""" Complete the code in ClassifyNB.py with the sklearn
    Naive Bayes classifier to classify the terrain data.
    
    The objective of this exercise is to recreate the decision 
    boundary found in the lesson video, and make a plot that
    visually shows the decision boundary """


from prep_terrain_data import makeTerrainData
from class_vis import prettyPicture, output_image
from ClassifyNB import classify

import numpy as np
import pylab as pl


features_train, labels_train, features_test, labels_test = makeTerrainData()

### the training data (features_train, labels_train) have both "fast" and "slow" points mixed
### in together--separate them so we can give them different colors in the scatterplot,
### and visually identify them
grade_fast = [features_train[ii][0] for ii in range(0, len(features_train)) if labels_train[ii]==0]
bumpy_fast = [features_train[ii][1] for ii in range(0, len(features_train)) if labels_train[ii]==0]
grade_slow = [features_train[ii][0] for ii in range(0, len(features_train)) if labels_train[ii]==1]
bumpy_slow = [features_train[ii][1] for ii in range(0, len(features_train)) if labels_train[ii]==1]


# You will need to complete this function imported from the ClassifyNB script.
# Be sure to change to that code tab to complete this quiz.
clf = classify(features_train, labels_train)


### draw the decision boundary with the text points overlaid
prettyPicture(clf, features_test, labels_test)
output_image("test.png", "png", open("test.png", "rb").read())