计算机视觉学习笔记

Pandas DataFrame入门教程（图解版） (biancheng.net)http://c.biancheng.net/pandas/dataframe.html

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score


def cv1():
    # 读取数据
    dataframe = pd.read_csv('Iris.csv', header=None, names=["花萼长度", "花萼宽度", "花瓣长度", "花瓣宽度", "花类品质"])
    # 归一化并输出
    max_min_scaler = lambda x: (x - np.min(x)) / (np.max(x) - np.min(x))
    scaler_data = dataframe[['花萼长度', '花萼宽度', '花瓣长度', '花瓣宽度']].apply(max_min_scaler)
    print('归一化结果:',scaler_data)
    #自变量
    x = scaler_data[['花萼长度', '花萼宽度', '花瓣长度', '花瓣宽度']]
    #因变量
    y = dataframe['花类品质']
    #构建测试集
    x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2)
    #初始化决策树模型
    dt=DecisionTreeClassifier()
    #训练模型
    dt.fit(x_train,y_train)
    #使用模型对测试集进行预测
    result=dt.predict(x_test)
    print(result)
    #测试集准确率
    property=accuracy_score(result,y_test)
    print('准确率:',property)

import pandas as pd
from sklearn.naive_bayes import GaussianNB

if __name__ == '__main__':
    data = pd.DataFrame(pd.read_excel('watermelon.xls'))
    #设置映射字典
    dic_target = {'是': 1, '否': 0, }
    dic_color = {'青绿': 1, '乌黑': 2, '浅白': 0}
    dic_found = {'蜷缩': 1, '稍蜷': 2, '硬挺': 0}
    dic_knock = {'浊响': 2, '沉闷': 1, '清脆': 0}
    dic_texture = {'清晰': 0, '稍糊': 1, '模糊': 2}
    dic_umbilical = {'凹陷': 0, '稍凹': 1, '平坦': 2}
    dic_touch = {'硬滑': 1, '软粘': 0}

    #映射目标
    data['好瓜'] = data['好瓜'].map(dic_target)
    data['色泽'] = data['色泽'].map(dic_color)
    data['根蒂'] = data['根蒂'].map(dic_found)
    data['敲声'] = data['敲声'].map(dic_knock)
    data['纹理'] = data['纹理'].map(dic_texture)
    data['脐部'] = data['脐部'].map(dic_umbilical)
    data['触感'] = data['触感'].map(dic_touch)
    #划分训练集，自变量，因变量
    X_train = data.iloc[:, 1:7].values
    Y_train = data.iloc[:, 7].values
    print(X_train)
    print(Y_train)
    #测试集
    X_test = [[1,1, 2, 0, 0, 1]]
    #正态分布作为先验分布，GaussianNB
    GaussianClassifier = GaussianNB()
    GaussianClassifier.fit(X_train, Y_train)
    #预测
    result = GaussianClassifier.predict(X_test)
    #1为好瓜，0为坏瓜
    if result == 0:
        print("坏瓜")
    else:
        print("好瓜")