如何解决如何可视化交易矩阵
这是交易矩阵（数据帧）的样子：
{'Avg. Winter temp 0-10C': {0: 1.0,1: 1.0},'Avg. Winter temp < 0C': {0: 0.0,1: 0.0},'Avg. Winter temp > 10C': {0: 0.0,'Avg. summer temp 11-20C': {0: 0.0,'Avg. summer temp 20-25C': {0: 1.0,'Avg. summer temp > 25C': {0: 0.0,'GENDER_DESC:F': {0: 0.0,'GENDER_DESC:M': {0: 1.0,'MODEL_TYPE:FED EMP': {0: 0.0,'MODEL_TYPE:HCPROV': {0: 0.0,'MODEL_TYPE:IPA': {0: 0.0,'MODEL_TYPE:MED A': {0: 0.0,'MODEL_TYPE:MED ADVG': {0: 0.0,'MODEL_TYPE:MED B': {0: 1.0,'MODEL_TYPE:MED SNPG': {0: 0.0,'MODEL_TYPE:MED UNSP': {0: 0.0,'MODEL_TYPE:MEDICAID': {0: 0.0,'MODEL_TYPE:MEDICARE': {0: 0.0,'MODEL_TYPE:PPO': {0: 0.0,'MODEL_TYPE:TPA': {0: 0.0,'MODEL_TYPE:UNSPEC': {0: 0.0,'MODEL_TYPE:WORK COMP': {0: 0.0,'Multiple_Cancer_Flag:No': {0: 1.0,'Multiple_Cancer_Flag:Yes': {0: 0.0,'PATIENT_AGE_GROUP 30-65': {0: 0.0,'PATIENT_AGE_GROUP 65-69': {0: 0.0,'PATIENT_AGE_GROUP 69-71': {0: 1.0,'PATIENT_AGE_GROUP 71-77': {0: 0.0,'PATIENT_AGE_GROUP 77-85': {0: 0.0,'PATIENT_LOCATION:ARIZONA': {0: 0.0,'PATIENT_LOCATION:CALIFORNIA': {0: 0.0,'PATIENT_LOCATION:CONNECTICUT': {0: 0.0,'PATIENT_LOCATION:DELAWARE': {0: 0.0,'PATIENT_LOCATION:FLORIDA': {0: 0.0,'PATIENT_LOCATION:GEORGIA': {0: 0.0,'PATIENT_LOCATION:IOWA': {0: 0.0,'PATIENT_LOCATION:KANSAS': {0: 0.0,'PATIENT_LOCATION:KENTUCKY': {0: 0.0,'PATIENT_LOCATION:LOUISIANA': {0: 0.0,'PATIENT_LOCATION:MARYLAND': {0: 0.0,'PATIENT_LOCATION:MASSACHUSETTS': {0: 0.0,'PATIENT_LOCATION:MICHIGAN': {0: 0.0,'PATIENT_LOCATION:MINNESOTA': {0: 0.0,'PATIENT_LOCATION:MISSISSIPPI': {0: 0.0,'PATIENT_LOCATION:MISSOURI': {0: 0.0,'PATIENT_LOCATION:NEBRASKA': {0: 0.0,'PATIENT_LOCATION:NEW JERSEY': {0: 0.0,'PATIENT_LOCATION:NEW MEXICO': {0: 1.0,'PATIENT_LOCATION:NEW YORK': {0: 0.0,'PATIENT_LOCATION:OKLAHOMA': {0: 0.0,'PATIENT_LOCATION:OREGON': {0: 0.0,'PATIENT_LOCATION:PENNSYLVANIA': {0: 0.0,'PATIENT_LOCATION:SOUTH CAROLINA': {0: 0.0,'PATIENT_LOCATION:TENNESSEE': {0: 0.0,'PATIENT_LOCATION:TEXAS': {0: 0.0,'PATIENT_LOCATION:VIRGINIA': {0: 0.0,'PATIENT_LOCATION:WASHINGTON': {0: 0.0,'PAYER_TYPE:Commercial': {0: 0.0,'PAYER_TYPE:Managed Medicaid': {0: 0.0,'PAYER_TYPE:Medicare': {0: 1.0,'PAYER_TYPE:Medicare D': {0: 0.0,'PLAN_NAME:ALL OTHER THIRD PARTY': {0: 0.0,'PLAN_NAME:BCBS FL UNSPECIFIED': {0: 0.0,'PLAN_NAME:BCBS MI MEDICARE D GENERAL (MI)': {0: 0.0,'PLAN_NAME:BCBS TEXAS GENERAL (TX)': {0: 0.0,'PLAN_NAME:BLUE CARE (MS)': {0: 0.0,'PLAN_NAME:BLUE PREFERRED PPO (AZ)': {0: 0.0,'PLAN_NAME:CMMNWLTH CRE MED SNP GENERAL(MA)': {0: 0.0,'PLAN_NAME:DEPT OF VETERANS AFFAIRS': {0: 0.0,'PLAN_NAME:EMBLEMHEALTH/HIP/GHI UNSPEC': {0: 0.0,'PLAN_NAME:ESSENCE MED ADV GENERAL (MO)': {0: 0.0,'PLAN_NAME:HEALTH NET MED D GENERAL (OR)': {0: 0.0,'PLAN_NAME:HIGHMARK UNSPECIFIED': {0: 0.0,'PLAN_NAME:HUMANA MED D GENERAL(MN)': {0: 0.0,'PLAN_NAME:HUMANA-UNSPECIFIED': {0: 0.0,'PLAN_NAME:KEYSTONE FIRST (PA)': {0: 0.0,'PLAN_NAME:MEDICARE A': {0: 0.0,'PLAN_NAME:MEDICARE A KENTUCKY (KY)': {0: 0.0,'PLAN_NAME:MEDICARE A MINNESOTA (MN)': {0: 0.0,'PLAN_NAME:MEDICARE B': {0: 0.0,'PLAN_NAME:MEDICARE B ARIZONA (AZ)': {0: 0.0,'PLAN_NAME:MEDICARE B IOWA (IA)': {0: 0.0,'PLAN_NAME:MEDICARE B KANSAS (KS)': {0: 0.0,'PLAN_NAME:MEDICARE B NEW MEXICO (NM)': {0: 1.0,'PLAN_NAME:MEDICARE B PENNSYLVANIA (PA)': {0: 0.0,'PLAN_NAME:MEDICARE B TEXAS (TX)': {0: 0.0,'PLAN_NAME:MEDICARE B VIRGINIA (VA)': {0: 0.0,'PLAN_NAME:MEDICARE UNSP': {0: 0.0,'PLAN_NAME:MOLINA HEALTHCARE (FL)': {0: 0.0,'PLAN_NAME:OPTUMHEALTH PHYSICAL HEALTH': {0: 0.0,'PLAN_NAME:PACIFICSOURCE HP MED ADV GNRL': {0: 0.0,'PLAN_NAME:PAI PLANNED ADMIN INC (SC)': {0: 0.0,'PLAN_NAME:PEOPLES HLTH NETWORK': {0: 0.0,'PLAN_NAME:THE COVENTRY CORP UNSPECIFIED': {0: 0.0,'PLAN_NAME:UHC/PAC/AARP MED D GENERAL (FL)': {0: 0.0,'PLAN_NAME:UHC/PAC/AARP MED D GENERAL (MD)': {0: 0.0,'PLAN_NAME:UHC/PAC/AARP MED D GENERAL (NY)': {0: 0.0,'PLAN_NAME:UHC/PAC/AARP MED D GENERAL (TX)': {0: 0.0,'PLAN_NAME:UHC/PAC/AARP MED D GENERAL (WA)': {0: 0.0,'PLAN_NAME:UNITED HLTHCARE-(CT) CT PPO': {0: 0.0,'PLAN_NAME:UNITED HLTHCARE-(NE) MIDLANDS': {0: 0.0,'PLAN_NAME:UNITED HLTHCARE-UNSPECIFIED': {0: 0.0,'PLAN_NAME:UNITED MEDICAL RESOURCES/UMR': {0: 0.0,'PLAN_NAME:WORKERS COMP - EMPLOYER': {0: 0.0,'PRI_SPECIALTY_DESC:DERMATOLOGY': {0: 0.0,'PRI_SPECIALTY_DESC:HEMATOLOGY/ONCOLOGY': {0: 1.0,'PRI_SPECIALTY_DESC:INTERNAL MEDICINE': {0: 0.0,'PRI_SPECIALTY_DESC:MEDICAL ONCOLOGY': {0: 0.0,'PRI_SPECIALTY_DESC:NURSE PRACTITIONER': {0: 0.0,'PRI_SPECIALTY_DESC:OBSTETRICS & GYNECOLOGY': {0: 0.0,'PROVIDER_LOCATION:ARIZONA': {0: 0.0,'PROVIDER_LOCATION:CALIFORNIA': {0: 0.0,'PROVIDER_LOCATION:CONNECTICUT': {0: 0.0,'PROVIDER_LOCATION:DELAWARE': {0: 0.0,'PROVIDER_LOCATION:FLORIDA': {0: 0.0,'PROVIDER_LOCATION:IOWA': {0: 0.0,'PROVIDER_LOCATION:KANSAS': {0: 0.0,'PROVIDER_LOCATION:KENTUCKY': {0: 0.0,'PROVIDER_LOCATION:LOUISIANA': {0: 0.0,'PROVIDER_LOCATION:MASSACHUSETTS': {0: 0.0,'PROVIDER_LOCATION:MICHIGAN': {0: 0.0,'PROVIDER_LOCATION:MINNESOTA': {0: 0.0,'PROVIDER_LOCATION:MISSISSIPPI': {0: 0.0,'PROVIDER_LOCATION:MISSOURI': {0: 0.0,'PROVIDER_LOCATION:NEBRASKA': {0: 0.0,'PROVIDER_LOCATION:NEW MEXICO': {0: 1.0,'PROVIDER_LOCATION:NEW YORK': {0: 0.0,'PROVIDER_LOCATION:OREGON': {0: 0.0,'PROVIDER_LOCATION:PENNSYLVANIA': {0: 0.0,'PROVIDER_LOCATION:SOUTH CAROLINA': {0: 0.0,'PROVIDER_LOCATION:TENNESSEE': {0: 0.0,'PROVIDER_LOCATION:TEXAS': {0: 0.0,'PROVIDER_LOCATION:VIRGINIA': {0: 0.0,'PROVIDER_LOCATION:WASHINGTON': {0: 0.0,'PROVIDER_TYP_DESC:PROFESSIONAL': {0: 1.0,'Region:MIDWEST': {0: 0.0,'Region:NORTHEAST': {0: 0.0,'Region:SOUTH': {0: 0.0,'Region:WEST': {0: 1.0,'Vials Consumption == 1': {0: 0.0,'Vials_Consumption_GROUP 1-2': {0: 0.0,'Vials_Consumption_GROUP 12-91': {0: 0.0,'Vials_Consumption_GROUP 2-3': {0: 0.0,'Vials_Consumption_GROUP 3-6': {0: 0.0,'Vials_Consumption_GROUP 6-12': {0: 1.0,'keytruda_flag:No': {0: 1.0,'keytruda_flag:Yes': {0: 0.0,'libtayo_flag:No': {0: 0.0,'libtayo_flag:Yes': {0: 1.0,'optivo_flag:No': {0: 1.0,'optivo_flag:Yes': {0: 0.0,1:
0.0}}
这是一个交易矩阵。使用此创建规则：
from mlxtend.frequent_patterns import apriori
frequent_itemsets = apriori(train_bucket,min_support=0.2,use_colnames=True)
print (frequent_itemsets)
并使用此创建规则：
from mlxtend.frequent_patterns import association_rules
association_rules(frequent_itemsets,metric="confidence",min_threshold=0.7)
rules = association_rules(frequent_itemsets,metric="lift",min_threshold=1.2)
print (len(rules["antecedents"]))
它给出了 10k 条规则。我需要能够形象化这些。我尝试使用这个： https://intelligentonlinetools.com/blog/2018/02/10/how-to-create-data-visualization-for-association-rules-in-data-mining/
我尝试了 networkX 示例，结果如下：
如果我全部绘制，它就会变得混乱。
我想过应用 t-SNE，但在初始事务矩阵上使用这并没有多大意义。试过这个方法
import numpy as np
from sklearn.manifold import TSNE
X = train_bucket
X_embedded = TSNE(n_components=2).fit_transform(X)
X_embedded.shape
from sklearn.manifold import TSNE
from matplotlib import pyplot as plt
import seaborn as sns
sns.set(rc={'figure.figsize':(11.7,8.27)})
palette = sns.color_palette("bright",10)
sns.scatterplot(X_embedded[:,0],X_embedded[:,1],legend='full',palette=palette)
我不知道如何理解它。我可以探索哪些选项？
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。