背景介绍：

      本节将根据14个属性建立分类器评估一个收入阶层，高于‘50k’的为一个阶层，低于‘50k’的为一个阶层。主要是数据的读取有点难，数据放在txt文件中，并且标签是字符串。。我最后的准确率并不是很高，大家可以调调参，或者对数据在进行处理。。数据下载地址：https://archive.ics.uci.edu/ml/datasets/Census+Income     

第一步：数据的读取

def read_data(path):X = []count_least50k = 0   # 收入低于50kcount_morethan50k = 0  # 收入高于50knum_images_threshold = 10000  # 我们两种类型的数据只打算各收集10000条with open(path, 'r') as f:for line in f.readlines():if '?' in line:continue   # 代表有缺失值  我们直接扔掉  因为数据量本身很大data = line.strip().split(',')    # 读出当前行的数据 把标签去掉，并且把逗号空格搞掉# print(data)if data[-1] == ' <=50K' and count_least50k < num_images_threshold:X.append(data)count_least50k += 1elif data[-1] == ' >50K' and count_morethan50k < num_images_threshold:X.append(data)count_morethan50k += 1if count_least50k > num_images_threshold and count_morethan50k > num_images_threshold:breakX = np.array(X)return X

       这里我们读取数据，并且设了一个阈值，>50k和小于50k的数据分别只读取10000条，主要是为了防止数据倾斜。。

第二步： 数据的预处理

        很明显 ，数据中存在一些字符串数据，它在一列中的取值是有限个，跟标签很像，所以，我们用sklearn中的LabelEncoder将字符串转化为数字

def process_data(data):# 对数据进行预处理Label_coder = []x_encoded = np.empty(data.shape)for i, item in enumerate(data[1]):    # 遍历每一列， 将一些字符串转换为数字if item.isdigit():    # 判断当前是否是数字x_encoded[:, i] = data[:, i]   # 是数字则不变else:Label_coder.append(LabelEncoder())   # 为每一列添加一个标签编码器x_encoded[:, i] = Label_coder[-1].fit_transform(data[:, i])X = x_encoded[:, :-1].astype(np.int)y = x_encoded[:, -1].astype(np.int)return X, y

处理后的数据：

第三步：建立模型，对数据进行预测

    这里我们分别用了贝叶斯和随机森林

def model(X, y):X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)gn = GaussianNB()gn.fit(X_train, y_train)rd = RandomForestClassifier(n_estimators=100, criterion="gini", max_depth=8)rd.fit(X_train, y_train)print("贝叶斯训练集准确率:{}, 测试集准确率:{}".format(gn.score(X_train, y_train), gn.score(X_test, y_test)))print("随机森林训练集准确率:{}, 测试集准确率:{}".format(rd.score(X_train, y_train), rd.score(X_test, y_test)))

输出结果：

源代码：

from sklearn import preprocessing
from sklearn.naive_bayes import GaussianNB
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifierdef read_data(path):X = []count_least50k = 0   # 收入低于50kcount_morethan50k = 0  # 收入高于50knum_images_threshold = 10000  # 我们两种类型的数据只打算各收集10000条with open(path, 'r') as f:for line in f.readlines():if '?' in line:continue   # 代表有缺失值  我们直接扔掉  因为数据量本身很大data = line.strip().split(',')    # 读出当前行的数据 把标签去掉，并且把逗号空格搞掉# print(data)if data[-1] == ' <=50K' and count_least50k < num_images_threshold:X.append(data)count_least50k += 1elif data[-1] == ' >50K' and count_morethan50k < num_images_threshold:X.append(data)count_morethan50k += 1if count_least50k > num_images_threshold and count_morethan50k > num_images_threshold:breakX = np.array(X)return Xdef process_data(data):# 对数据进行预处理Label_coder = []x_encoded = np.empty(data.shape)for i, item in enumerate(data[1]):    # 遍历每一列， 将一些字符串转换为数字if item.isdigit():    # 判断当前是否是数字x_encoded[:, i] = data[:, i]   # 是数字则不变else:Label_coder.append(LabelEncoder())   # 为每一列添加一个标签编码器x_encoded[:, i] = Label_coder[-1].fit_transform(data[:, i])X = x_encoded[:, :-1].astype(np.int)y = x_encoded[:, -1].astype(np.int)return X, ydef model(X, y):X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)gn = GaussianNB()gn.fit(X_train, y_train)rd = RandomForestClassifier(n_estimators=100, criterion="gini", max_depth=8)rd.fit(X_train, y_train)print("贝叶斯训练集准确率:{}, 测试集准确率:{}".format(gn.score(X_train, y_train), gn.score(X_test, y_test)))print("随机森林训练集准确率:{}, 测试集准确率:{}".format(rd.score(X_train, y_train), rd.score(X_test, y_test)))if __name__ == '__main__':path = './data/adult.data.txt'data = read_data(path) # 读数据# print(data)# 接着对数据进行预处理X, y = process_data(data)print(X)print(y)print(X.shape)print(y.shape)# 下一步构造模型model(X, y)