小白数据分析——Python职位全链路分析

最近在做Python职位分析的项目,做这件事的背景是因为接触Python这么久,还没有对Python职位有一个全貌的了解。所以想通过本次分析了解Python相关的职位有哪些、在不同城市的需求量有何差异、薪资怎么样以及对工作经验有什么要求等等。分析的链路包括:

数据采集
数据清洗
异常的创建时间
异常的薪资水平
异常的工作经验
统计分析
大盘数据
单维度分析
二维交叉分析
多维钻取
文本分析
文本预处理
词云
FP-Growth关联分析
LDA主题模型分析
分为上下两篇文章。上篇介绍前三部分内容,下篇重点介绍文本分析。

  1. 数据采集
    巧妇难为无米之炊,我们做数据分析大部分情况是用公司的业务数据,因此就不需要关心数据采集的问题。然而我们自己业余时间做的一些数据探索更多的需要自己采集数据,常用的数据采集技术就是爬虫。

本次分享所用的数据是我从拉勾网爬取的,主要分为三部分,确定如何抓取数据、编写爬虫抓取数据、将抓取的数据格式化并保存至MongoDB。关于数据采集这部分内容我之前有一篇文章单独介绍过,源码也开放了,这里我就不再赘述了,想了解的朋友可以翻看之前那篇文章《Python爬职位》。

  1. 数据清洗
    有了数据后,先不要着急分析。我们需要对数据先有个大概的了解,并在这个过程中剔除一些异常的记录,防止它们影响后续的统计结果。

举个例子,假设有101个职位,其中100个的薪资是正常值10k,而另外一个薪资是异常值1000k,如果算上异常值计算的平均薪资是29.7k,而剔除异常值计算的平均薪资是10k,二者差了将近3倍。

所以我们在作分析前要关注数据质量,尤其数据量比较少的情况。本次分析的职位数有1w条左右,属于比较小的数据量,所以在数据清洗这一步花了比较多的时间。

下面我们就从数据清洗开始,进入编码阶段

1.0 筛选python相关的职位
1.3 小节要介绍的按照工作经验清洗异常值也与之类似,为了避免篇幅过长我这里就不贴代码了。总之,按照这3个属性清洗完之后,还剩 9715 个职位。

完成数据清洗后,我们就正式进入分析的环节了,分析分为两部分,统计分析和文本分析,前者是对数值型指标做统计,后者是对文本进行分析。我们平时接触到最多是前者,它可以让我们从宏观的角度去了解被分析的对象。文本分析也有不可替代的价值,我们下篇重点介绍。

  1. 统计分析
    我们做统计分析除了要清楚分析的目外,还需要了解分析结果面向的对象是谁。本次分析中,我假想面向的是在校学生,因为他们是真正想要了解Python职位的人。因此,我们的分析思路就要按照他们所想看的去展开,而不能没有章法的乱堆数据。

2.0 大盘数据
统计分析的数据一般都是按照数据粒度由粗到细展开的,粒度最粗的数据就是不加任何过滤条件、不按照任何维度拆分的数字。在我们的项目里其实就是总职位数,上面我们也看到了 9715 个。如果跟Java、PHP职位去对比,或许我们能得出一些结论,然而单纯看这个总数显然是没有实际参考价值的。

所以接下来我们需要按照维度来进行细粒度的拆分。

2.1 单维度分析
我们由粗到细,先来按照单维度进行分析。对于一个在校生来说,他最迫切想了解的数据是什么?我觉得是不同城市之间职位数量的分布。因为对于学生来说考虑工作的首要问题是考虑在哪个城市,考虑哪个城市需要参考的一点就是职位的数量,职位越多,前景自然更好。
数据上我们发现,需要Python技能的职位里,测试是最多的,数据开发排第二,后端开发比较少,这也符合我们的认知。
https://github.com/users/mw4hveab/projects/1
https://github.com/users/mw4hveab/projects/2
https://github.com/users/hvo909cu/projects/1
https://github.com/users/mw4hveab/projects/3
https://github.com/users/hvo909cu/projects/2
https://github.com/users/mw4hveab/projects/4
https://github.com/users/hvo909cu/projects/3
https://github.com/users/mw4hveab/projects/5
https://github.com/users/hvo909cu/projects/4
https://github.com/users/mw4hveab/projects/6
https://github.com/users/hvo909cu/projects/5
https://github.com/users/mw4hveab/projects/7
https://github.com/users/hvo909cu/projects/6
https://github.com/users/mw4hveab/projects/8
https://github.com/users/hvo909cu/projects/7
https://github.com/users/mw4hveab/projects/9
https://github.com/users/hvo909cu/projects/8
https://github.com/users/hvo909cu/projects/9
https://github.com/users/hvo909cu/projects/10
https://github.com/users/mw4hveab/projects/10
https://github.com/users/hvo909cu/projects/11
https://github.com/users/mw4hveab/projects/11
https://github.com/users/hvo909cu/projects/12
https://github.com/users/mw4hveab/projects/12
https://github.com/users/hvo909cu/projects/13
https://github.com/users/mw4hveab/projects/13
https://github.com/users/hvo909cu/projects/14
https://github.com/users/mw4hveab/projects/14
https://github.com/users/hvo909cu/projects/15
https://github.com/users/mw4hveab/projects/15
https://github.com/users/hvo909cu/projects/16
https://github.com/users/mw4hveab/projects/16
https://github.com/users/hvo909cu/projects/17
https://github.com/users/mw4hveab/projects/17
https://github.com/users/hvo909cu/projects/18
https://github.com/users/mw4hveab/projects/18
https://github.com/users/hvo909cu/projects/19
https://github.com/users/mw4hveab/projects/19
https://github.com/users/hvo909cu/projects/20
https://github.com/users/mw4hveab/projects/20
https://github.com/users/hvo909cu/projects/21
https://github.com/users/mw4hveab/projects/21
https://github.com/users/hvo909cu/projects/22
https://github.com/users/mw4hveab/projects/22
https://github.com/users/hvo909cu/projects/23
https://github.com/users/mw4hveab/projects/23
https://github.com/users/hvo909cu/projects/24
https://github.com/users/mw4hveab/projects/24
https://github.com/users/hvo909cu/projects/25
https://github.com/users/mw4hveab/projects/25
https://github.com/users/hvo909cu/projects/26
https://github.com/users/mw4hveab/projects/26
https://github.com/users/hvo909cu/projects/27
https://github.com/users/mw4hveab/projects/27
https://github.com/users/hvo909cu/projects/28
https://github.com/users/hvo909cu/projects/29
https://github.com/users/mw4hveab/projects/28
https://github.com/users/mw4hveab/projects/29
https://github.com/users/hvo909cu/projects/30
https://github.com/users/hvo909cu/projects/31
https://github.com/users/mw4hveab/projects/30
https://github.com/users/hvo909cu/projects/32
https://github.com/users/mw4hveab/projects/31
https://github.com/users/hvo909cu/projects/33
https://github.com/users/mw4hveab/projects/32
https://github.com/users/hvo909cu/projects/34
https://github.com/users/mw4hveab/projects/33
https://github.com/users/hvo909cu/projects/35
https://github.com/users/mw4hveab/projects/34
https://github.com/users/hvo909cu/projects/36
https://github.com/users/mw4hveab/projects/35
https://github.com/users/mw4hveab/projects/36
https://github.com/users/hvo909cu/projects/37
https://github.com/users/mw4hveab/projects/37
https://github.com/users/hvo909cu/projects/38
https://github.com/users/mw4hveab/projects/38
https://github.com/users/mw4hveab/projects/39
https://github.com/users/hvo909cu/projects/39
https://github.com/users/mw4hveab/projects/40
https://github.com/users/hvo909cu/projects/40
https://github.com/users/mw4hveab/projects/41
https://github.com/users/hvo909cu/projects/41
https://github.com/users/mw4hveab/projects/42
https://github.com/users/hvo909cu/projects/42
https://github.com/users/mw4hveab/projects/43
https://github.com/users/hvo909cu/projects/43
https://github.com/users/mw4hveab/projects/44
https://github.com/users/hvo909cu/projects/44
https://github.com/users/mw4hveab/projects/45
https://github.com/users/mw4hveab/projects/46
https://github.com/users/hvo909cu/projects/45
https://github.com/users/mw4hveab/projects/47
https://github.com/users/hvo909cu/projects/46
https://github.com/users/mw4hveab/projects/48
https://github.com/users/hvo909cu/projects/47
https://github.com/users/mw4hveab/projects/49
https://github.com/users/hvo909cu/projects/48
https://github.com/users/mw4hveab/projects/50
https://github.com/users/hvo909cu/projects/49
https://github.com/users/hvo909cu/projects/50
https://github.com/users/hvo909cu/projects/51
https://github.com/users/hvo909cu/projects/52
https://github.com/users/mw4hveab/projects/51
https://github.com/users/hvo909cu/projects/53
https://github.com/users/mw4hveab/projects/52
https://github.com/users/hvo909cu/projects/54
https://github.com/users/mw4hveab/projects/53
https://github.com/users/hvo909cu/projects/55
https://github.com/users/mw4hveab/projects/54
https://github.com/users/hvo909cu/projects/56
https://github.com/users/mw4hveab/projects/55
https://github.com/users/hvo909cu/projects/57
https://github.com/users/mw4hveab/projects/56
https://github.com/users/mw4hveab/projects/57
https://github.com/users/hvo909cu/projects/58
https://github.com/users/mw4hveab/projects/58
https://github.com/users/hvo909cu/projects/59
https://github.com/users/mw4hveab/projects/59
https://github.com/users/hvo909cu/projects/60
https://github.com/users/mw4hveab/projects/60
https://github.com/users/mw4hveab/projects/61
https://github.com/users/hvo909cu/projects/61
https://github.com/users/hvo909cu/projects/62
https://github.com/users/mw4hveab/projects/62
https://github.com/users/hvo909cu/projects/63
https://github.com/users/mw4hveab/projects/63
https://github.com/users/hvo909cu/projects/64
https://github.com/users/mw4hveab/projects/64
https://github.com/users/hvo909cu/projects/65
https://github.com/users/mw4hveab/projects/65
https://github.com/users/hvo909cu/projects/66
https://github.com/users/mw4hveab/projects/66
https://github.com/users/hvo909cu/projects/67
https://github.com/users/mw4hveab/projects/67
https://github.com/users/hvo909cu/projects/68
https://github.com/users/hvo909cu/projects/69
https://github.com/users/mw4hveab/projects/68
https://github.com/users/hvo909cu/projects/70
https://github.com/users/mw4hveab/projects/69
https://github.com/users/hvo909cu/projects/71
https://github.com/users/mw4hveab/projects/70
https://github.com/users/hvo909cu/projects/72
https://github.com/users/mw4hveab/projects/71
https://github.com/users/mw4hveab/projects/72
https://github.com/users/hvo909cu/projects/73
https://github.com/users/hvo909cu/projects/74
https://github.com/users/mw4hveab/projects/73
https://github.com/users/mw4hveab/projects/74
https://github.com/users/hvo909cu/projects/75
https://github.com/users/hvo909cu/projects/76
https://github.com/users/mw4hveab/projects/75
https://github.com/users/mw4hveab/projects/76
https://github.com/users/hvo909cu/projects/77
https://github.com/users/mw4hveab/projects/77
https://github.com/users/hvo909cu/projects/78
https://github.com/users/mw4hveab/projects/78
https://github.com/users/hvo909cu/projects/79
https://github.com/users/mw4hveab/projects/79
https://github.com/users/hvo909cu/projects/80
https://github.com/users/mw4hveab/projects/80
https://github.com/users/hvo909cu/projects/81
https://github.com/users/hvo909cu/projects/82
https://github.com/users/mw4hveab/projects/81
https://github.com/users/mw4hveab/projects/82
https://github.com/users/hvo909cu/projects/83
https://github.com/users/mw4hveab/projects/83
https://github.com/users/hvo909cu/projects/84
https://github.com/users/mw4hveab/projects/84
https://github.com/users/hvo909cu/projects/85
https://github.com/users/mw4hveab/projects/85
https://github.com/users/hvo909cu/projects/86
https://github.com/users/mw4hveab/projects/86
https://github.com/users/mw4hveab/projects/87
https://github.com/users/hvo909cu/projects/87
https://github.com/users/mw4hveab/projects/88
https://github.com/users/hvo909cu/projects/88
https://github.com/users/hvo909cu/projects/89
https://github.com/users/mw4hveab/projects/89
https://github.com/users/hvo909cu/projects/90
https://github.com/users/mw4hveab/projects/90
https://github.com/users/hvo909cu/projects/91
https://github.com/users/mw4hveab/projects/91
https://github.com/users/hvo909cu/projects/92
https://github.com/users/mw4hveab/projects/92
https://github.com/users/hvo909cu/projects/93
https://github.com/users/mw4hveab/projects/93
https://github.com/users/hvo909cu/projects/94
https://github.com/users/mw4hveab/projects/94
https://github.com/users/hvo909cu/projects/95
https://github.com/users/mw4hveab/projects/95
https://github.com/users/hvo909cu/projects/96
https://github.com/users/mw4hveab/projects/96
https://github.com/users/hvo909cu/projects/97
https://github.com/users/mw4hveab/projects/97
https://github.com/users/hvo909cu/projects/98
https://github.com/users/mw4hveab/projects/98
https://github.com/users/hvo909cu/projects/99
https://github.com/users/hvo909cu/projects/100
https://github.com/users/mw4hveab/projects/99
https://github.com/users/mw4hveab/projects/100
https://github.com/users/hvo909cu/projects/101
https://github.com/users/hvo909cu/projects/102
https://github.com/users/mw4hveab/projects/101
https://github.com/users/hvo909cu/projects/103
https://github.com/users/mw4hveab/projects/102
https://github.com/users/hvo909cu/projects/104
https://github.com/users/mw4hveab/projects/103
https://github.com/users/hvo909cu/projects/105
https://github.com/users/mw4hveab/projects/104
https://github.com/users/hvo909cu/projects/106
https://github.com/users/mw4hveab/projects/105
https://github.com/users/hvo909cu/projects/107
https://github.com/users/mw4hveab/projects/106
https://github.com/users/mw4hveab/projects/107
https://github.com/users/hvo909cu/projects/108
https://github.com/users/mw4hveab/projects/108
https://github.com/users/hvo909cu/projects/109
https://github.com/users/mw4hveab/projects/109
https://github.com/users/hvo909cu/projects/110
https://github.com/users/mw4hveab/projects/110
https://github.com/users/hvo909cu/projects/111
https://github.com/users/mw4hveab/projects/111
https://github.com/users/hvo909cu/projects/112
https://github.com/users/mw4hveab/projects/112
https://github.com/users/hvo909cu/projects/113
https://github.com/users/mw4hveab/projects/113
https://github.com/users/hvo909cu/projects/114
https://github.com/users/mw4hveab/projects/114
https://github.com/users/hvo909cu/projects/115
https://github.com/users/mw4hveab/projects/115
https://github.com/users/hvo909cu/projects/116
https://github.com/users/mw4hveab/projects/116
https://github.com/users/hvo909cu/projects/117
https://github.com/users/mw4hveab/projects/117
https://github.com/users/hvo909cu/projects/118
https://github.com/users/mw4hveab/projects/118
https://github.com/users/hvo909cu/projects/119
https://github.com/users/mw4hveab/projects/119
https://github.com/users/mw4hveab/projects/120
https://github.com/users/hvo909cu/projects/120
https://github.com/users/mw4hveab/projects/121
https://github.com/users/mw4hveab/projects/122
https://github.com/users/hvo909cu/projects/121
https://github.com/users/mw4hveab/projects/123
https://github.com/users/hvo909cu/projects/122
https://github.com/users/mw4hveab/projects/124
https://github.com/users/hvo909cu/projects/123
https://github.com/users/mw4hveab/projects/125
https://github.com/users/hvo909cu/projects/124
https://github.com/users/mw4hveab/projects/126
https://github.com/users/hvo909cu/projects/125
https://github.com/users/hvo909cu/projects/126
https://github.com/users/mw4hveab/projects/127
https://github.com/users/hvo909cu/projects/127
https://github.com/users/mw4hveab/projects/128
https://github.com/users/hvo909cu/projects/128
https://github.com/users/mw4hveab/projects/129
https://github.com/users/hvo909cu/projects/129
https://github.com/users/mw4hveab/projects/130
https://github.com/users/hvo909cu/projects/130
https://github.com/users/mw4hveab/projects/131
https://github.com/users/hvo909cu/projects/131
https://github.com/users/mw4hveab/projects/132
https://github.com/users/hvo909cu/projects/132
https://github.com/users/mw4hveab/projects/133
https://github.com/users/hvo909cu/projects/133
https://github.com/users/mw4hveab/projects/134
https://github.com/users/hvo909cu/projects/134
https://github.com/users/mw4hveab/projects/135
https://github.com/users/hvo909cu/projects/135
https://github.com/users/mw4hveab/projects/136
https://github.com/users/hvo909cu/projects/136
https://github.com/users/mw4hveab/projects/137
https://github.com/users/hvo909cu/projects/137
https://github.com/users/mw4hveab/projects/138
https://github.com/users/mw4hveab/projects/139
https://github.com/users/hvo909cu/projects/138
https://github.com/users/mw4hveab/projects/140
https://github.com/users/hvo909cu/projects/139
https://github.com/users/mw4hveab/projects/141
https://github.com/users/mw4hveab/projects/142
https://github.com/users/mw4hveab/projects/143
https://github.com/users/hvo909cu/projects/140
https://github.com/users/mw4hveab/projects/144
https://github.com/users/hvo909cu/projects/141
https://github.com/users/mw4hveab/projects/145
https://github.com/users/hvo909cu/projects/142
https://github.com/users/mw4hveab/projects/146
https://github.com/users/hvo909cu/projects/143
https://github.com/users/hvo909cu/projects/144
https://github.com/users/mw4hveab/projects/147
https://github.com/users/hvo909cu/projects/145
https://github.com/users/mw4hveab/projects/148
https://github.com/users/mw4hveab/projects/149
https://github.com/users/hvo909cu/projects/146
https://github.com/users/hvo909cu/projects/147
https://github.com/users/mw4hveab/projects/150
https://github.com/users/hvo909cu/projects/148
https://github.com/users/mw4hveab/projects/151
https://github.com/users/hvo909cu/projects/149
https://github.com/users/mw4hveab/projects/152
https://github.com/users/hvo909cu/projects/150
https://github.com/users/mw4hveab/projects/153
https://github.com/users/hvo909cu/projects/151
https://github.com/users/mw4hveab/projects/154
https://github.com/users/hvo909cu/projects/152
https://github.com/users/mw4hveab/projects/155
https://github.com/users/hvo909cu/projects/153
https://github.com/users/mw4hveab/projects/156
https://github.com/users/hvo909cu/projects/154
https://github.com/users/mw4hveab/projects/157
https://github.com/users/hvo909cu/projects/155
https://github.com/users/mw4hveab/projects/158
https://github.com/users/mw4hveab/projects/159
https://github.com/users/hvo909cu/projects/156
https://github.com/users/mw4hveab/projects/160
https://github.com/users/hvo909cu/projects/157
https://github.com/users/mw4hveab/projects/161
https://github.com/users/hvo909cu/projects/158
https://github.com/users/mw4hveab/projects/162
https://github.com/users/hvo909cu/projects/159
https://github.com/users/mw4hveab/projects/163
https://github.com/users/hvo909cu/projects/160
https://github.com/users/mw4hveab/projects/164
https://github.com/users/hvo909cu/projects/161
https://github.com/users/mw4hveab/projects/165
https://github.com/users/hvo909cu/projects/162
https://github.com/users/mw4hveab/projects/166
https://github.com/users/hvo909cu/projects/163
https://github.com/users/mw4hveab/projects/167
https://github.com/users/hvo909cu/projects/164
https://github.com/users/mw4hveab/projects/168
https://github.com/users/hvo909cu/projects/165
https://github.com/users/mw4hveab/projects/169
https://github.com/users/hvo909cu/projects/166
https://github.com/users/mw4hveab/projects/170
https://github.com/users/hvo909cu/projects/167
https://github.com/users/mw4hveab/projects/171
https://github.com/users/hvo909cu/projects/168
https://github.com/users/mw4hveab/projects/172
https://github.com/users/hvo909cu/projects/169
https://github.com/users/mw4hveab/projects/173
https://github.com/users/hvo909cu/projects/170
https://github.com/users/mw4hveab/projects/174
https://github.com/users/hvo909cu/projects/171
https://github.com/users/mw4hveab/projects/175
https://github.com/users/hvo909cu/projects/172
https://github.com/users/mw4hveab/projects/176
https://github.com/users/hvo909cu/projects/173
https://github.com/users/mw4hveab/projects/177
https://github.com/users/hvo909cu/projects/174
https://github.com/users/mw4hveab/projects/178
https://github.com/users/hvo909cu/projects/175
https://github.com/users/mw4hveab/projects/179
https://github.com/users/hvo909cu/projects/176
https://github.com/users/mw4hveab/projects/180
https://github.com/users/hvo909cu/projects/177
https://github.com/users/mw4hveab/projects/181
https://github.com/users/hvo909cu/projects/178
https://github.com/users/mw4hveab/projects/182
https://github.com/users/hvo909cu/projects/179
https://github.com/users/mw4hveab/projects/183
https://github.com/users/hvo909cu/projects/180
https://github.com/users/mw4hveab/projects/184
https://github.com/users/hvo909cu/projects/181
https://github.com/users/mw4hveab/projects/185
https://github.com/users/hvo909cu/projects/182
https://github.com/users/mw4hveab/projects/186
https://github.com/users/hvo909cu/projects/183
https://github.com/users/mw4hveab/projects/187
https://github.com/users/hvo909cu/projects/184
https://github.com/users/mw4hveab/projects/188
https://github.com/users/mw4hveab/projects/189
https://github.com/users/hvo909cu/projects/186
https://github.com/users/mw4hveab/projects/190
https://github.com/users/hvo909cu/projects/187
https://github.com/users/mw4hveab/projects/191
https://github.com/users/hvo909cu/projects/188
https://github.com/users/mw4hveab/projects/192
https://github.com/users/hvo909cu/projects/189
https://github.com/users/mw4hveab/projects/193
https://github.com/users/hvo909cu/projects/190
https://github.com/users/mw4hveab/projects/194
https://github.com/users/mw4hveab/projects/195
https://github.com/users/hvo909cu/projects/191
https://github.com/users/mw4hveab/projects/196
https://github.com/users/hvo909cu/projects/192
https://github.com/users/hvo909cu/projects/193
https://github.com/users/mw4hveab/projects/197
https://github.com/users/hvo909cu/projects/194
https://github.com/users/hvo909cu/projects/195
https://github.com/users/mw4hveab/projects/198
https://github.com/users/hvo909cu/projects/196
https://github.com/users/mw4hveab/projects/199
https://github.com/users/hvo909cu/projects/197
https://github.com/users/hvo909cu/projects/198
https://github.com/users/mw4hveab/projects/200
https://github.com/users/hvo909cu/projects/199
https://github.com/users/mw4hveab/projects/201
https://github.com/users/hvo909cu/projects/200
https://github.com/users/mw4hveab/projects/202
https://github.com/users/hvo909cu/projects/201
https://github.com/users/mw4hveab/projects/203
https://github.com/users/hvo909cu/projects/202
https://github.com/users/mw4hveab/projects/204
https://github.com/users/hvo909cu/projects/203
https://github.com/users/hvo909cu/projects/204
https://github.com/users/mw4hveab/projects/205
https://github.com/users/hvo909cu/projects/205
https://github.com/users/hvo909cu/projects/206
https://github.com/users/hvo909cu/projects/207
https://github.com/users/mw4hveab/projects/206
https://github.com/users/mw4hveab/projects/207
https://github.com/users/hvo909cu/projects/208
https://github.com/users/hvo909cu/projects/209
https://github.com/users/mw4hveab/projects/208
https://github.com/users/mw4hveab/projects/209
https://github.com/users/hvo909cu/projects/210
https://github.com/users/mw4hveab/projects/210
https://github.com/users/hvo909cu/projects/211
https://github.com/users/mw4hveab/projects/211
https://github.com/users/hvo909cu/projects/212
https://github.com/users/mw4hveab/projects/212
https://github.com/users/hvo909cu/projects/213
https://github.com/users/hvo909cu/projects/214
https://github.com/users/mw4hveab/projects/213
https://github.com/users/mw4hveab/projects/214
https://github.com/users/hvo909cu/projects/215
https://github.com/users/mw4hveab/projects/215
https://github.com/users/hvo909cu/projects/216
https://github.com/users/mw4hveab/projects/216
https://github.com/users/mw4hveab/projects/217

这里我们看的指标是职位数量,当然你也可以看平均薪资。

从城市、职位分类这俩维度,我们对Python职位有了一个大概的认知了。那其他的维度还需要看吗,比如:薪资、工作经验,并且这俩维度也是大家比较关心的。我认为,从单维度来看,城市和职位分类就够了,其他都没有实际参考价值。因为薪资一定是跟某一类岗位相关的,人工智能职位工资自然偏高;同样地,工作经验也是跟岗位类别相关,大数据刚起步的时候,职位的工作经验自然就偏低。所以这俩维度从单维度上看没有参考价值,一定是需要限定了某类职位后去看才有意义。我们在做统计分析时不要乱堆数据,要想清楚数据背后的逻辑,以及对决策人是否有价值。

2.1 二维交叉分析
对于一个学生来说,当他确定了自己工作的城市,也了解了不同的职位分布,接下来我们需要给他展示什么样的数据能为他提供择业的决策呢?

对于想去北京发展的学生来说,他想了解北京的不同类型的职位分布、薪资情况、工作经验的要求、什么样的公司在招聘。同样的,想去上海、深圳、广州的同学也有类似的需求。这样,我们就确定了我们需要分析的维度和指标了,维度是城市、职位类别,且需要二者交叉。指标是职位数量、平均薪资、工作经验和公司,前三个好说,但第四个需要找一个量化指标去刻画,这里我选的是公司规模。

上一篇:2021年Java开发人员需要掌握的Java最新趋势、工具、技术和功能


下一篇:QT: QByteArray储存二进制数据(包括结构体,自定义QT对象)