吴裕雄--天生自然 PYTHON数据分析：医疗数据分析

概述import numpy as np # linear algebraimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)# plotlyimport chart_studio.plotly as pyfrom plotly.offline import init_notebook_mode

import numpy as np # linear algebraimport pandas as pd # data processing,CSV file I/O (e.g. pd.read_csv)# plotlyimport chart_studio.plotly as pyfrom plotly.offline import init_notebook_mode,iplotinit_notebook_mode(connected=True)import plotly.graph_obJs as goimport seaborn as sns# word cloud libraryfrom wordcloud import WordCloud# matplotlibimport matplotlib.pyplot as plt# input data files are available in the "../input/" directory.# For example,running this (by clicking run or pressing Shift+Enter) will List the files in the input directory

dataframe = pd.read_csv("F:\kaggleDataSet\healthcare-data\test_2v.csv")

import chart_studio.plotly as pyfrom plotly.graph_obJs import *df_heart_disease = dataframe[dataframe.heart_disease== 1] labels = df_heart_disease.genderpIE1_List=df_heart_disease.heart_diseasedf_hypertension= dataframe[dataframe.hypertension == 1] labels1 = df_hypertension.genderpIE1_List1=df_hypertension.hypertensionlabels2 = dataframe.ResIDence_typepIE1_List2 = dataframe.heart_diseaselabels3 = dataframe.work_typepIE1_List3 = dataframe.heart_diseasefig = {    ‘data‘: [        {            ‘labels‘: labels,‘values‘: pIE1_List,‘type‘: ‘pIE‘,‘name‘: ‘Heart disease‘,‘marker‘: {‘colors‘: [‘rgb(56,75,126)‘,‘rgb(18,36,37)‘,‘rgb(34,53,101)‘,‘rgb(36,55,57)‘,‘rgb(6,4,4)‘]},‘domain‘: {‘x‘: [0,.48],‘y‘: [0,.49]},‘hoverinfo‘:‘label+percent+name‘,‘textinfo‘:‘none‘        },{            ‘labels‘: labels1,‘values‘: pIE1_List1,‘marker‘: {‘colors‘: [‘rgb(177,127,38)‘,‘rgb(205,152,36)‘,‘rgb(99,79,‘rgb(129,180,179)‘,‘rgb(124,103,37)‘]},‘name‘: ‘Hypertension‘,‘domain‘: {‘x‘: [.52,1],‘textinfo‘:‘none‘        },{            ‘labels‘: labels2,‘values‘: pIE1_List2,‘marker‘: {‘colors‘: [‘rgb(33,99)‘,‘rgb(79,129,102)‘,‘rgb(151,179,100)‘,‘rgb(175,49,35)‘,73,147)‘]},‘name‘: ‘ResIDence Type‘,‘y‘: [.51,1]},{            ‘labels‘: labels3,‘values‘: pIE1_List3,‘marker‘: {‘colors‘: [‘rgb(146,123,21)‘,‘rgb(177,34)‘,‘rgb(206,206,40)‘,51,‘rgb(35,21)‘]},‘name‘:‘Work Type‘,‘textinfo‘:‘none‘        }            ],‘layout‘: {‘Title‘: ‘‘,‘showlegend‘: False}}iplot(fig)

import chart_studio.plotly as pyimport plotly.graph_obJs as go# Create random data with numpyimport numpy as npdf_250 = dataframe.iloc[:250,:]random_x = df_250.indexrandom_y0 =  df_250.avg_glucose_levelrandom_y1 =  df_250.bmirandom_y2 =  df_250.age# Create tracestrace0 = go.Scatter(    x = random_x,y = random_y0,mode = ‘markers‘,name = ‘Avg. glucose Level‘)trace1 = go.Scatter(    x = random_x,y = random_y1,mode = ‘lines+markers‘,name = ‘BMI‘)trace2 = go.Scatter(    x = random_x,y = random_y2,mode = ‘lines‘,name = ‘Age‘)data = [trace0,trace1,trace2]iplot(data,filename=‘scatter-mode‘)

import chart_studio.plotly as pyimport plotly.graph_obJs as godf_heart_disease = dataframe[dataframe.heart_disease==1] labels = df_heart_disease.genderx = labelstrace0 = go.Box(    y=dataframe.age,x=x,name=‘Age‘,marker=dict(        color=‘#3D9970‘    ))trace1 = go.Box(    y=dataframe.avg_glucose_level,name=‘Avg. glucose Level‘,marker=dict(        color=‘#FF4136‘    ))trace2 = go.Box(    y=dataframe.bmi,name=‘BMI‘,marker=dict(        color=‘#FF851B‘    ))data = [trace0,trace2]layout = go.Layout(    yaxis=dict(        Title=‘Attendants Who Has Heart disease‘,zeroline=False    ),Boxmode=‘group‘)fig = go.figure(data=data,layout=layout)iplot(fig)

import chart_studio.plotly as pyimport plotly.graph_obJs as godf_hypertension= dataframe[dataframe.hypertension == 1] labels1 = df_hypertension.genderx = labels1trace0 = go.Box(    y=dataframe.age,trace2]layout = go.Layout(    yaxis=dict(        Title=‘Attendants Who Has Hypertension‘,layout=layout)iplot(fig)

df_heart_disease_1 = dataframe.smoking_status [dataframe.heart_disease == 1  ]        df_hypertension_1  = dataframe.smoking_status [dataframe.hypertension  == 1   ]       trace1 = go.Histogram(    x=df_heart_disease_1,opacity=0.75,name = "Heart disease",marker=dict(color=‘rgba(171,50,96,0.6)‘))trace2 = go.Histogram(    x=df_hypertension_1,name = "Hypertension",marker=dict(color=‘rgba(12,196,0.6)‘))data = [trace1,trace2]layout = go.Layout(barmode=‘overlay‘,Title=‘ Association Between Smoking,Heart disease & Hypertension‘,xaxis=dict(Title=‘Smoking Status‘),yaxis=dict( Title=‘Attendants‘),)fig = go.figure(data=data,layout=layout)iplot(fig)

df_heart_disease_1 = dataframe.work_type [dataframe.heart_disease    == 1  ]        df_hypertension_1 = dataframe.work_type [dataframe.hypertension    == 1   ]     trace1 = go.Histogram(    x=df_heart_disease_1,0.6)‘))data = [trace1,Title=‘ Association Between Work Type,xaxis=dict(Title=‘‘),layout=layout)iplot(fig)

总结

以上是内存溢出为你收集整理的吴裕雄--天生自然 PYTHON数据分析：医疗数据分析全部内容，希望文章能够帮你解决吴裕雄--天生自然 PYTHON数据分析：医疗数据分析所遇到的程序开发问题。

如果觉得内存溢出网站内容还不错，欢迎将内存溢出网站推荐给程序员好友。