def statistic_number(df, mysql_url):
"""
人数（权重）分析
:param df:
:param mysql_url:
:return:
"""
parameters = [
(["company_name"], "position_category", ("company__salary",
"salary_range")),
(["company_name"], "position_category", ("company__gender", "gender")),
(["company_name"], "position_category", ("company__address",
"address")),
(["company_name"], "position_category", ("company__school",
"school_name")),
(["company_name"], "position_category", ("company__major", "major")),
(["company_name"], "position_category", ("company__degree", "degree")),
(["industry"], None, ("industry__address", "address")),
(["industry"], "address", ("industry__address__salary",
"salary_range")),
(["industry"], "address", ("industry__address__gender", "gender")),
(["industry"], "address", ("industry__address__salary_work_year",
"work_year_range,salary_range")),
(["position_name"], None, ("position__address", "address")),
(["position_name"], "address", ("position__address__salary_range",
"salary_range")),
(["position_name"], "address", ("position__address__age_range",
"age_range")),
(["position_name"], "address", ("position__address__salary_work_year",
"work_year_range,salary_range")),
]
statistic_dimension(df, mysql_url, parameters, statistic_number_dimension)
def statistic_salary(df, mysql_url):
"""
薪资分析
:param df:
:param mysql_url:
:return:
"""
parameters = [
# 专业维度相关分析
(["major"], "degree", ("major__gender", "gender")),
(["major"], "degree", ("major__address", "address")),
(["major"], "degree", ("major__company", "company_name")),
(["major"], "degree", ("major__industry", "industry")),
# 学校维度相关分析
(["school_name"], "degree", ("school__gender", "gender")),
(["school_name"], "degree", ("school__address", "address")),
(["school_name"], "degree", ("school__company", "company_name")),
(["school_name"], "degree", ("school__industry", "industry")),
# 学校 + 专业 相关维度的分析
(["school_name", "major"], "degree", ("school__major__position",
"position_name", True, True)),
(["school_name", "major"], "degree", ("school__major__industry",
"industry", True, True)),
(["school_name", "major"], "degree", ("school__major__company",
"company_name", True, True)),
(["school_name", "major"], "degree",
("school__major__flow", "company_name,industry", True, True)),
(["industry"], "address", ("industry__address__compare", None, True,
True)),
(["industry"], "address", ("industry__address__age", "age_range")),
(["industry"], "address", ("industry__address__degree", "degree")),
# 职位 + 地点 相关维度分析
(["position_name"], "address", ("position__address__compare", None,
True, True)),
(["position_name"], "address", ("position__address__gender",
"gender")),
(["position_name"], "address", ("position__address__work_year_range",
"work_year_range")),
(["position_name"], "address", ("position__address__degree",
"degree")),
(["address"], "gender", ("person__rank", "age", True, True, True)),
# 含职位别名
(["major"], "degree", ("major__position", "position_name", True, False,
False, True)),
(["school_name"], "degree", ("school__position", "position_name", True,
False, False, True))
]
statistic_dimension(df, mysql_url, parameters, statistic_salary_dimension)
def statistic_major_position(profile_df, education_df, work_df, mysql_url):
"""
专业对口职位统计
:param df:
:param mysql_url:
:return:
"""
# 最后一份教育经历
latest_education_df = education_df.filter(
education_df.edu_index == 1).filter(education_df.school_area == "中国")
resume_df = profile_df.join(latest_education_df,
"resume_id").join(work_df, "resume_id")
# 第一份工作经历
first_work_df = resume_df.filter(
resume_df.work_index == resume_df.work_len)
parameters = [
(["major"], "degree", ("major__position__relation", "position_name")),
]
statistic_dimension(first_work_df, mysql_url, parameters,
statistic_number_dimension)
def statistic_neighbour(df, mysql_url):
"""
当前职位（公司）的上（下）一份职位（公司）分布
:param df:
:param mysql_url:
:return:
"""
parameters = [
(["company_name"], "position_category", ("company__prev_company",
"prev_company")),
(["company_name"], "position_category", ("company__next_company",
"next_company")),
(["position_name"], "address", ("position__address__prev_position",
"prev_position")),
(["position_name"], "address", ("position__address__next_position",
"next_position")),
]
statistic_dimension(df, mysql_url, parameters,
statistic_neighbour_dimension)
statistic_neighbour_special(df, mysql_url)
def statistic_rank(df, mysql_url):
"""
排名相关分析
:param df:
:param mysql_url:
:return:
"""
parameters = [
(["major"], "degree", ("major__rank", None)),
(["school_name"], "degree", ("school__rank", None)),
(["school_name", "major"], "degree", ("school__major__rank", None, True, True)),
(["school_name", "major"], "degree",
("school__major__position__rank", "position_name", True, True, '-person_num', True)),
(["company_name"], None, ("company__rank", None)),
(["industry"], None, ("industry__rank", None),),
(["industry"], "address", ("industry__address__rank", None)),
(["position_name"], None, ("position__rank", None)),
(["position_name"], None, ("position__industry__rank", "industry", True, False, '-person_num',)),
(["position_name"], "address", ("position__address__industry", "industry", False, True, '-person_num')),
]
statistic_dimension(df, mysql_url, parameters, statistic_rank_dimension)