第一步：读取数据
# 读入数据
import pandas as pd
df = pd.read_csv("data/adult.data", header=None)
print(df.head())
第二步：数据处理
# 数据处理一：去除字符串数值前面的空格
str_cols=[1,3,5,6,7,8,9,13,14]
for col in str_cols:
df.iloc[:,col]=df.iloc[:,col].map(lambda x: x.strip())
# 数据处理二： 删除缺失值样本
# 将?字符串替换为NaN缺失值标志
import numpy as np
df.replace("?",np.nan,inplace=True)
# 此处直接删除缺失值样本(包含缺失值的行都删除)
df.dropna(inplace=True)
# 数据处理三：对字符数据进行编码
from sklearn.preprocessing import LabelEncoder
label_encoder=[] # 放置每一列的encoder
encoded_set = np.empty(df.shape)
for col in range(df.shape[1]):
encoder=None
if df.iloc[:,col].dtype==object: # 字符型数据
encoder=LabelEncoder()
encoded_set[:,col]=encoder.fit_transform(df.iloc[:,col])
else: # 数值型数据
encoded_set[:,col]=df.iloc[:,col]
label_encoder.append(encoder)
# 删除序号为2、10、11的列
data = np.delete(encoded_set, [2,10,11], axis=1)
第三步：建立模型，对数据进行预测
# 划分训练集集和测试集
from sklearn.model_selection import train_test_split
X, y = data[:, :-1], data[:,-1]
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.3, random_state=42)
# 建立朴素贝叶斯分类器模型
from sklearn.naive_bayes import GaussianNB
gaussianNB=GaussianNB()
gaussianNB.fit(train_X,train_y)
# 2 用交叉验证来检验模型的准确性，只是在test set上验证准确性
from sklearn.cross_validation import cross_val_score
num_validations=5
accuracy=cross_val_score(gaussianNB,test_X,test_y,
scoring='accuracy',cv=num_validations)
print('准确率：{:.2f}%'.format(accuracy.mean()*100))
precision=cross_val_score(gaussianNB,test_X,test_y,
scoring='precision_weighted',cv=num_validations)
print('精确度：{:.2f}%'.format(precision.mean()*100))
recall=cross_val_score(gaussianNB,test_X,test_y,
scoring='recall_weighted',cv=num_validations)
print('召回率：{:.2f}%'.format(recall.mean()*100))
f1=cross_val_score(gaussianNB,test_X,test_y,
scoring='f1_weighted',cv=num_validations)
print('F1 值：{:.2f}%'.format(f1.mean()*100))
# 3 打印性能报告
from sklearn.metrics import confusion_matrix
y_pred=gaussianNB.predict(test_X)
confusion_mat = confusion_matrix(test_y, y_pred)
print(confusion_mat) #看看混淆矩阵长啥样
from sklearn.metrics import classification_report
# 直接使用sklearn打印精度，召回率和F1值
target_names = ['<=50K', '>50K']
print(classification_report(test_y, y_pred, target_names=target_names))
