[ML L2 - N19] Naive Bayes GaussianNB
ML L2 Bayes Naive
2023-09-14 09:00:47 时间
ClassifyNB.py:
def classify(features_train, labels_train): ### import the sklearn module for GaussianNB from sklearn.naive_bayes import GaussianNB ### create classifier clf = GaussianNB() ### fit the classifier on the training features and labels clf.fit(features_train, labels_train) ### return the fit classifier 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}} return X_train, y_train, X_test, y_test # return training_data, test_data
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
studentMain.py
#!/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())
Calculating NB Accuracy
def NBAccuracy(features_train, labels_train, features_test, labels_test): from sklearn.naive_bayes import GaussianNB clf = GaussianNB() clf.fit(features_train, labels_train) pred = clf.predict(features_test) accuracy = clf.score(features_test, labels_test) return accuracy
相关文章
- 【学习总结】GirlsInAI ML-diary day-13-Try/Except 异常处理
- [ML L3] SVM Intro
- ML之CatBoost:CatBoost算法的简介、安装、案例应用之详细攻略
- ML:机器学习中与模型相关的一些常见的判断逻辑(根据自调整阈值计算阳性率)
- ML之shap:基于FIFA 2018 Statistics(2018年俄罗斯世界杯足球赛)球队比赛之星分类预测数据集利用RF随机森林+计算SHAP值单样本力图/依赖关系贡献图可视化实现可解释性之攻略
- ML之ME/LF:机器学习中常见模型评估指标/损失函数(LiR损失、L1损失、L2损失、Logistic损失)求梯度/求导、案例应用之详细攻略
- ML之FE:利用pandas的pd.cut函数对【数字型】字段进行分箱处理函数封装并统计个数
- ML之xgboost:利用xgboost算法(sklearn+7CrVa)训练mushroom蘑菇数据集(22+1,6513+1611)来预测蘑菇是否毒性(二分类预测)
- ML之SVM:基于Js代码利用SVM算法的实现根据Kaggle数据集预测titanic(泰坦尼克号)数据集生存人员
- ML之shap:基于boston波士顿房价回归预测数据集利用Shap值对LiR线性回归模型实现可解释性案例
- ML之SVM:基于SVM(sklearn+subplot)的鸢尾花iris数据集的前两个特征(线性不可分的两个样本),判定鸢尾花是哪一种类型
- 【关于时间序列的ML】项目 7 :使用机器学习进行每日出生预测
- 【关于时间序列的ML】项目 5 :用机器学习预测天气
- Andrew Ng-ML-第十七章-推荐系统
- 【Spark ML】第 2 章: Spark和Spark简介