YPL_ZML的博客

import pandas as pdimport numpy as np# 类别数据转化# 加载数据detail = pd.read_excel('meal_order_detail.xlsx')# print(detail.columns)# 进行哑变量数据转换 --> 稀疏矩阵# data = pd.get_dummies(detail['dishes_name']...

from sklearn.feature_extraction.text import TfidfVectorizerimport jieba# text = ['This is the first document.', 'This is the second second document.', 'And the third one.',# 'Is this the f...

from sklearn.feature_extraction.text import CountVectorizerimport jieba# 实例化一个con_vec对象# con_vec = CountVectorizer(min_df=1)# 准备文本数据# text = ['This is the first document.', 'This is the second...

import pandas as pdimport numpy as npfrom sklearn.neighbors import KNeighborsClassifier# 加载数据mov = pd.read_excel('电影分类数据.xlsx')# print(mov)train = mov.iloc[:, 1:6]train.loc[train.loc[:, '电影类...

import numpy as npimport pandas as pdimport osimport matplotlib.pyplot as plt# 分析--》训练集里面 构建分类器模型# ---在测试集里面进行应用，来评估分类器性能# 加载数据# def deal_data(dir_path):# """# 处理数据# :param di...

import pandas as pdimport numpy as npdef distance(v1, v2): """ 自实现距离计算 :param v1: 点v1 :param v2: 点v2 :return: 距离 """ # 法一 # ndim = len(v1) # summary = 0 # f...

import pandas as pdimport numpy as npimport matplotlib.pyplot as pltfrom sklearn.cluster import KMeansdef show_res(data, center, y_predict): """ 实现结果展示 :param data: 数据 :param cen...

import numpy as npimport matplotlib.pyplot as plt# 要进行聚类， 得有样本# 加载样本数据data = []with open('test.txt', 'r') as f: lines = f.readlines() # print(lines) for line in lines: line_...

import numpy as npimport pandas as pdfrom sklearn.model_selection import train_test_splitfrom sklearn.linear_model.logistic import LogisticRegressionfrom sklearn.preprocessing import StandardScale...