糖尿病数据分析风险预测糖尿病数据分析风险预测糖尿病数据分析风险预测

# import pandas as pd # import requests # import math # import re # import jieba # # pip install wordcloud -i https://pypi.tuna.tsinghua.edu.cn/simple --trusted-host pypi.tuna.tsinghua.edu.cn # from collections import Counter # from wordcloud import WordCloud # import matplotlib.pyplot as plt # import random # import matplotlib # # matplotlib.rcParams['font.sans-serif'] = ['SimHei'] # matplotlib.rcParams['axes.unicode_minus'] = False # import sklearn # from sklearn.feature_extraction.text import CountVectorizer # from sklearn.feature_extraction.text import TfidfTransformer # import matplotlib.pyplot as plt # import matplotlib # from sklearn.feature_extraction.text import TfidfVectorizer # # matplotlib.rcParams['font.sans-serif'] = ['SimHei'] # matplotlib.rcParams['axes.unicode_minus'] = False # import random # import numpy as np # import matplotlib.mlab as mlab # import matplotlib.pyplot as plt # from collections import Counter # import bertvec # from bertvec import bert_vec # def plt_picture_ciyun(n): # """ # 词云 # 传入的n是:我 老婆 走 了 四年 总会 不经意 想起 那 感觉 没 经历 的 很 难 体会 # """ # wc = WordCloud( # # 设置字体，不指定就会出现乱码 # font_path='simhei.ttf', # # 设置背景色 # background_color='white', # # 设置背景宽 # width=500, # # 设置背景高 # height=350, # # 最大字体 # max_font_size=50, # # 最小字体 # min_font_size=10, # mode='RGBA' # # colormap='pink' # ) # # 产生词云 # wc.generate(n) # # 显示图片 # # 指定所绘图名称 # plt.figure("jay") # # # 以图片的形式显示词云 # plt.imshow(wc) # # 关闭图像坐标系 # plt.axis("off") # # 保存词云图片 # # plt.savefig("2209070221.png") # plt.show() # def tfidf_word(corpus): # """ # tfodf 提取关键词： # import sklearn # from sklearn.feature_extraction.text import CountVectorizer # from sklearn.feature_extraction.text import TfidfTransformer # from sklearn.feature_extraction.text import TfidfVectorizer # corpus = ['TF-IDF 主要 思想 是', '算法 一个 重要 特点 可以 脱离 语料库 背景', # '如果 一个 网页 被 很多 其他 网页 链接 说明 网页 重要', # '原始 文本 进行 标记', # '主要 思想'] # """ # vectorizer = TfidfVectorizer() # X = vectorizer.fit_transform(corpus) # data = {'word': vectorizer.get_feature_names_out(), # 'tfidf': X.toarray().sum(axis=0).tolist()} # df = pd.DataFrame(data) # df = df.sort_values(by='tfidf', ascending=True) # True是从小达到 False是从大到小 # res = {} # for i in df.values: # res[i[0]] = i[1] # # print(res){'链接': 0.2556396904397093, '说明': 0.2556396904397093...} # return res # def dict_sort(dic): # """ # 字典排序 # """ # count = sorted(dic.items(), key=lambda x: x[1], reverse=True) # True 是降序 False是升序 # return count # date=pd.read_excel('待处理数据 0812.xlsx') # # date=pd.read_excel('已评分数据.xlsx') # train_data=date['Comment'].values # # datas=[] # for line in train_data: # try: # line =line.split(' ') # temp='' # for i in line: # temp=temp+i+" " # # print(temp) # datas.append(temp) # except: # pass # # # print(len(datas)) # res=tfidf_word(datas) # # print(res) # res=dict_sort(res) # word_list=[] # n='' # for idx,(k ,v) in enumerate(res): # # print(k,v) # word_list.append(k) # n=n+k+" " # if idx==200:break # # # 词云 # plt_picture_ciyun(n) # word_list_vec=[] # for word in word_list: # vec = bert_vec(word) # # print(vec) # word_list_vec.append([word,vec]) import matplotlib.pyplot as plt import matplotlib matplotlib.rcParams['font.sans-serif'] = ['SimHei'] matplotlib.rcParams['axes.unicode_minus'] = False import random import numpy as np import matplotlib.mlab as mlab import matplotlib.pyplot as plt from collections import Counter from sklearn.manifold import TSNE from pylab import mpl mpl.rcParams['font.sans-serif'] = ['SimHei'] #中文字体 mpl.rcParams['axes.unicode_minus'] = False #防止负号出现异常显示 def tsne_em(train_x,train_y): plt.figure(figsize=(15,15)) #定义画布大小 color=['b',"r","g","k"] # 定义颜色 参数c 可以等于：['c', 'b', 'g', 'r', 'm', 'y', 'k', 'w'] color_label=['b',"r","g","k"] marker=[" "," "," "," "] tokens = [] labels = [] for idx,line in enumerate(train_x): # print(str(train_y[idx])) labels.append(train_y[idx]) tokens.append(train_x[idx]) # 存储的是向量 tsne_model = TSNE(perplexity=10, n_components=2, init='pca', n_iter=2500, random_state=23) # perplexity: 默认为30，数据集越大，需要参数值越大，建议值位5-50 , n_components=2 默认为2，嵌入空间的维度（嵌入空间的意思就是结果空间）,别的参数估计不重要 print(len(tokens)) print(tokens) new_values = tsne_model.fit_transform(np.array(tokens)) # 将X投影到一个嵌入空间并返回转换结果 # 降维处理 # print(new_values) x = [] y = [] for value in new_values: x.append(value[0]) y.append(value[1]) for i in range(len(x)): plt.scatter(x[i],y[i],c=color[1],marker=marker[1]) plt.text(x[i],y[i], labels[i], fontsize=10,color=color_label[1]) plt.xticks(fontsize=20) plt.yticks(fontsize=20) plt.show()