对linkedin数据集使用贪心聚类

请见我的github:
https://github.com/HMY626/linkedin_data_cluster/blob/master/Clustering_job.py

一些数据分析均可归结于计数，比较文法相似度是计数，雅尔卡系数也是计数等等

我使用的是在kaggle上的linkedin数据集，由于领英上的职位名称差异性不太规范，所以我需要将职位进行标准化

transforms = [
    ('Sr.', 'Senior'),
    ('Sr', 'Senior'),
    ('Jr.', 'Junior'),
    ('Jr', 'Junior'),
    ('CEO', 'Chief Executive Officer'),
    ('COO', 'Chief Operating Officer'),
    ('CTO', 'Chief Technology Officer'),
    ('CFO', 'Chief Finance Officer'),
    ('VP', 'Vice President'),
    ]

将以上职位的缩写建立一个替换列表，用于尽可能地将职位信息进行标准化。

数据集样例

[
    {
        "name": {
            "family_name": "BOLUKBAS, PMP",
            "given_name": "Mustafa"
        },
        "locality": "Turkey",
        "skills": [
            "Project Management",
            "Cross-functional Team Leadership",
            "Business Process Re-engineering",
            "Software Development Life Cycle",
            "Business",
            "Software Project Management",

        "name": {
            "family_name": "Hoffmann",
            "given_name": "Lynette"
        },
        "locality": "South Africa",
        "skills": [
            "Predictive Analytics",
            "Business Analysis",
            "Competitive Analysis",
            "Training Skills",
            "Market Research",
            "Market Analysis",
            "Marketing Strategy",
            "Strategy Development",
            "Pricing Analysis",
            "Pricing Strategy",
            "Pricing"
        ],
        "locality_code": [
            "South Africa",
            [
                -29.002309799194336,
                25.0803165435791
            ]
        ],
        "events": [
            {
                "from": "Eskom",
                "to": "ESKOM Distribution",
                "title1": "Graduate in Marketing",
                "start": 24085,
                "title2": "Market and Customer Services Analyst",
                "end": 24098
            },
            {
                "from": "ESKOM Distribution",
                "to": "Eskom Distribution",
                "title1": "Market and Customer Services Analyst",
                "start": 24098,
                "title2": "Pricing Advisor",
                "end": 24123
            },
            {
                "from": "Eskom Distribution",
                "to": "Ericsson Regional Sub-Saharan Africa",
                "title1": "Pricing Advisor",
                "start": 24123,
                "title2": "Price Manager",
                "end": 24135
            }
        ]

    },
    …………
]

其他不重要的key略

统计地理位置信息

我采用geopy地bing地理位置包统计Linkedin联系人的地理位置编码，以便后期用D3进行可视化

聚类效果