process data

# version 1.0
def connect_mysql(sql, oper_type="select", data_l=None):
    conn = pymysql.connect(host='localhost', user="root", password="123",
                           database="work", port=3306)
    cur = conn.cursor()
    if oper_type == "insert":
        cur.executemany(sql, data_l)
        conn.commit()
    else:
        cur.execute(sql)
    result = cur.fetchall()
    # print(type(result), "result")
    conn.close()
    return result


def process_jobs(field_name):
    sql = "select j." + field_name + " FROM personal_jobs j"
    column_name = connect_mysql(sql, oper_type="select")
    row_total = (len(column_name))
    row_category = set(column_name)

    # init category dict
    category_dict = {}
    for k in row_category:
        category_dict[k] = 0

    # calculate amount
    cal_nmu = 0
    for k in row_category:
        for r in column_name:
            if r == k:
                cal_nmu += 1
        category_dict[k] = cal_nmu
        cal_nmu = 0
    print(type(category_dict.items()), category_dict.items())
    print(row_total, len(category_dict.items()))
    return row_total, category_dict

process_jobs("job_salary")

 

version 1.1
def count_times(all_list):
    ls = []
    item_list = list(set(all_list))
    for m in item_list:
        c = all_list.count(m)
        ls.append([m, c])
    return sorted(ls)


def process_salary(field_name):
    # sql = "select " + field_name + " from work.personal_jobs where job_exp = '1-3年';"
    sql = "select " + field_name + " from work.personal_jobs where job_exp = '1年以内' or job_exp = '经验不限';"
    original_sal = connect_mysql(sql)
    # sort salary order
    row_category = list(set(original_sal))
    general_min, general_avg, general_max = [], [], []
    # cal_num = 0
    for sal in row_category:
        # calculate category amount
        # for cat in column_name:
        #     if cat == sal:
        #         cal_num += 1
        # process salary
        if field_name == "job_salary":
            sal_tmp = str(sal).strip("('").strip("K',)").split("K-")
            general_min.append(int(sal_tmp[0]))
            general_max.append(int(sal_tmp[1]))

        # process experience
        if field_name == "job_exp":
            print(original_sal)

        # initial again
        # cal_num = 0

    # calculate min sal
    min_sal = count_times(general_min)
    for m1 in min_sal:
        min_s = str(m1[0]) + "K"
        m1[0] = min_s

    # calculate max sal
    max_sal = count_times(general_max)
    for m2 in max_sal:
        min_s = str(m2[0]) + "K"
        m2[0] = min_s

    # calculate avg sal
    avg_sal = count_times(original_sal)
    print("original: ", avg_sal)
    for a1 in avg_sal:
        sal_tmp_1 = str(a1[0]).strip("('").strip("K',)").split("K-")
        a1[0] = (int(sal_tmp_1[0]) + int(sal_tmp_1[1])) / 2.0
    avg_sal = sorted(avg_sal)

    for a2 in avg_sal:
        a2[0] = str(a2[0]) + "K"
    # debug
    print(len(min_sal), min_sal)
    print(len(avg_sal), avg_sal)
    print(len(max_sal), max_sal)
    return min_sal, avg_sal, max_sal

# process_salary("job_salary")

 

import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from collections import Counter
from scipy.misc import imread

def process_reqirement(field_name):
    sql = "select " + field_name + " from work.personal_jobs where job_exp = '1年以内' or job_exp = '经验不限';"
    original_req = connect_mysql(sql)
    userdict = ["C", "C#", "C++", "Go", "Linux", "MongoDB", "Mysql", "PostgreSQL", "Ajax", "Bootstrap", "CSS", "Django", "Docker", "Flask", "Git", "http", "tcp", "Java", "JavaScript", "Jquery", "Oracle", "Python", "Redis", "Ruby", "Scrapy", "shell", "Tornado", "Web", "Zabbix", "RESTful", "云计算", "分布式", "前端", "后端", "大数据", "高并发", "数据分析", "数据挖掘", "机器学习", "爬虫", "算法", "自动化", "运维", "集群"]

    jieba.load_userdict(userdict)
    # print(type(original_req), str(original_req))
    text0 = Counter(jieba.cut(str(original_req)))
    text1 = " ".join(jieba.cut(str(original_req)))
    [item for item in sorted(text0.values())]
    # print(text0.keys(), text0.values())
    # print(type(text0), text0)

    # # create word cloud
    # wordcloud = WordCloud(font_path=r"D:\wwj\work\script\web\personal\database_operation\MSYH.TTC",
    #                       background_color="white", mask=imread("china.jpg")).generate(text1)
    # plt.imshow(wordcloud)
    # plt.axis("off")
    # plt.show()

    # find requirement item what we really need
    req_list = []
    # print(len(text0.keys()), text0)
    for k, v in text0.items():
        for kk, vv in text0.items():
            if str(k).lower() == str(kk).lower():
                # print(k, v)
                req_list.append([k, (v + vv)])
                # print(k, v)
                break
    print(len(req_list), req_list)

    for t in userdict:
        for k, v in text0.items():
            if t.lower() == str(k).lower():
                req_list.append([t, v])
                break
    # print(req_list)
    return req_list
process_reqirement("job_requirement")

 

def user_defined(file_name):
    user_list = []
    with open(file_name, "r", encoding="utf8") as f:
        for i in f:
            user_list.append(i.strip())
    return user_list

def process_company(field_name):
    sql = "select " + field_name + " from work.personal_jobs"
    company = [list(i) for i in connect_mysql(sql)]
    user_list = user_defined("t.txt")
    user_list = ['C','C#','C++','Go','Linux','MongoDB','Mysql','PostgreSQL','Ajax','Bootstrap','CSS','Django','Docker','Flask','Git','http','tcp','Java','JavaScript','Jquery','Oracle','Python','Redis','Ruby','Scrapy','shell','Tornado','Web','RESTful','云计算','分布式','前端','后端','大数据','高并发','数据分析','数据挖掘','机器学习','爬虫','算法','自动化','测试','运维','集群']
    jieba.load_userdict(user_list)
    me_list = ['python', 'django', 'linux', '运维', '自动化', '爬虫', '数据分析', 'shell', 'mysql', 'oracle']
    req_list, suit_list = [], []
    for req in company:
        req_dict = Counter(jieba.cut(req[1]))
        req_list.append([req[0], [k for k in req_dict.keys() if k in user_list]])
    for r in req_list:
        if len(r[1]) > 0:
            # print(r[1])
            own = [item for item in me_list if item in r[1]]
            if len(own) > 0:
                suit_list.append([r[0], int(len(own) * 100/len(r[1]))])
    return sorted(suit_list, key=lambda x: x[1])
    # print(sorted(suit_list, key=lambda x: x[1]))
process_company("company_name, job_requirement")

 

转载于:https://www.cnblogs.com/vickey-wu/p/8480227.html