[ML L2 - N19] Naive Bayes GaussianNB
ML L2 Bayes Naive
2023-09-14 08:59:13 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
- ML-DL-各种资源汇总
- 【学习总结】GirlsInAI ML-diary day-11-while循环
- [ML] Cost Function
- Atitit 标记语言ML(Markup Language) 目录 1. 标记语言ML Markup Language1 1.1. 简介1 2. 置标语言置标语言通常可以分为三类:标识性的、过程
- ML与Optimality:最优化理论(GD随机梯度下降/QN拟牛顿法/CG共轭梯度法/L-BFGS/TR置信域/GA遗传算法/SA模拟退火算法)在机器学习中的简介、常用方法、案例应用之详细攻略
- ML之catboost:基于人类性别相关属性的数据集利用catboost模型实现二分类预测(男女性别预测,全流程案例,包括代码实现)
- ML之FE:基于单个csv文件数据集(自动切分为两个dataframe表)利用featuretools工具实现自动特征生成/特征衍生
- ML之LassoR&RidgeR:基于datasets糖尿病数据集利用LassoR和RidgeR算法(alpha调参)进行(9→1)回归预测
- ML与Optimality:最优化理论(GD随机梯度下降/QN拟牛顿法/CG共轭梯度法/L-BFGS/TR置信域/GA遗传算法/SA模拟退火算法)在机器学习中的简介、常用方法、案例应用之详细攻略
- ML之CF:基于MovieLens电影评分数据集利用基于用户协同过滤算法(余弦相似度)实现对用户进行Top5电影推荐案例
- ML之Clustering之K-means:K-means算法简介、应用、经典案例之详细攻略
- ML之Clustering之普聚类算法:普聚类算法的相关论文、主要思路、关键步骤、代码实现等相关配图之详细攻略
- 【关于时间序列的ML】项目 2 :使用机器学习预测股票价格
- 【ML】探索性数据分析 (EDA)
- 【ML】第 1 章 :分布式机器学习:术语和概念
- 【AI with ML】第 8 章 :使用 TensorFlow 创建文本
- 【ML特征工程】第 3 章 :文本数据:扁平化、过滤和分块