利用Python分析數(shù)據(jù)分析師招聘現(xiàn)狀

import pandas as pdimport numpy as npimport matplotlib.pyplot as pltfrom matplotlib.font_manager import FontManagerfrom matplotlib import gridspec
jobData = pd.read_csv('zhaopin.csv')jobData.drop_duplicates(inplace = True) # 刪除重復(fù)數(shù)據(jù)jobData

isTrue = jobData['positionName'].str.contains('數(shù)據(jù)分析') # 職位中是否包含‘數(shù)據(jù)分析’jobData = jobData[isTrue] # 篩選出想要的字段jobData.reset_index(inplace=True) # 重置行索引jobData

jobData['salary'] = jobData['salary'].str.lower()\                    .str.extract(r'(\d+)[k]-(\d+)k')\                    .applymap(lambda x:int(x))\                    .mean(axis=1) # 用薪水區(qū)間的均值作為薪水
jobData

jobData['job_detail'] = jobData['job_detail'].str.lower().fillna('') # 將字母小寫，缺失值賦為空字符串jobData['python'] = jobData['job_detail'].map(lambda x:1 if('python' in x) else 0)jobData['SQL'] = jobData['job_detail'].map(lambda x:1 if('sql' in x) or ('hive' in x) else 0)jobData['Tableau'] = jobData['job_detail'].map(lambda x:1 if 'tableau' in x else 0)jobData['Excel'] = jobData['job_detail'].map(lambda x:1 if 'excel' in x else 0)jobData['SPSS/SAS'] = jobData['job_detail'].map(lambda x:1 if ('spss' in x) or ('sas' in x) else 0)jobData['R'] = jobData['job_detail'].map(lambda x:1 if('r' in x) else 0)jobData['數(shù)據(jù)挖掘'] = jobData['job_detail'].map(lambda x:1 if('挖掘') else 0)jobData

plt.rcParams['font.family'] = 'Heiti TC'plt.figure(figsize=(12, 9))cities = jobData['city'].value_counts()plt.barh(y = cities.index[::-1],        width = cities.values[::-1],        color = '#78a355')plt.box(False) # 不顯示邊框plt.title(label='各城市數(shù)據(jù)分析崗位的需求量',         fontsize = 32, weight = 'bold', color = 'white',         backgroundcolor = '#f47920', pad = 30)plt.tick_params(labelsize = 16)plt.grid(ls = '--', axis = 'x', linewidth = 0.5, color = '#78a355')

industry_index = jobData['industryField'].value_counts()[:10].indexindustry = jobData.loc[jobData['industryField'].isin(industry_index), 'industryField']plt.figure(figsize=(12, 9))plt.barh(y = industry_index[::-1],        width=pd.Series.value_counts(industry.values).values[::-1],        color = '#78a355')plt.box(False) # 不顯示邊框plt.title('不同領(lǐng)域?qū)?shù)據(jù)分析崗位的需求量(前十)',         fontsize = 32, weight = 'bold', color = 'white',         backgroundcolor = '#f47920', pad = 30)plt.tick_params(labelsize = 16)plt.grid(ls = '--', axis = 'x', linewidth = 0.5, color = '#78a355')

plt.figure(figsize=(12, 9))city_salary = jobData.groupby('city')['salary'].mean().sort_values(ascending=False)plt.bar(x = city_salary.index, height = city_salary.values,       color = plt.cm.coolwarm_r(np.linspace(0,1,len(city_salary))))plt.title('各大城市的薪資對比',         fontsize = 32, weight = 'bold', color = 'white',         backgroundcolor = '#f47920', pad = 30)plt.tick_params(labelsize = 16)plt.grid(ls = '--', axis = 'y', linewidth = 0.5, color = '#a1a3a6')plt.yticks(ticks=np.arange(0, 25, step=5), labels=['', '5k', '10,', '15k', '20k'])plt.box(False)

work_salary = jobData.pivot_table(index='city', columns='workYear', values='salary')work_salary = work_salary[['應(yīng)屆畢業(yè)生', '1-3年', '3-5年', '5-10年', '10年以上']]\                .sort_values(by='10年以上', ascending=False)data = work_salary.valuesdata = np.repeat(data, 4, axis=1)plt.figure(figsize=(12, 9))# plt.cm.OrRd_rplt.imshow(data, cmap='RdBu_r')plt.yticks(np.arange(13), work_salary.index)plt.xticks(np.array([1.5, 5.5, 9.5, 13.5, 17.5]), work_salary.columns)h, w = data.shapefor x in range(w):    for y in range(h):        if (x%4==0) and (~np.isnan(data[y, x])):            text = plt.text(x+1.5, y, round(data[y, x], 1),                           ha='center', va='center', color='r', fontsize=16)plt.colorbar(shrink=0.72)plt.title('工作經(jīng)驗與薪水關(guān)系',         fontsize = 32, weight = 'bold', color = 'white',         backgroundcolor = '#f47920', pad = 30)plt.tick_params(labelsize = 16)

education = jobData['education'].value_counts(normalize=True)plt.figure(figsize=(9, 9))plt.pie(education, labels=education.index, autopct='%0.2f%%',       wedgeprops=dict(linewidth=3, width=0.5), pctdistance=0.8,       textprops=dict(fontsize=20))plt.title(label='學歷要求',         fontsize=32, weight='bold',         color='white', backgroundcolor='#f47920')

def get_level(x):    if x['python'] == 1:        x['skill'] = 'Python/R'    elif x['R'] == 1:        x['skill'] = 'Python/R'    elif x['SQL'] == 1:        x['skill'] = 'SQL'    elif x['Excel'] == 1:        x['skill'] = 'Excel'    elif x['SPSS/SAS'] == 1:        x['skill'] = 'SPSS/SAS'    else:        x['skill'] = '其他'    return x
jobData = jobData.apply(get_level, axis=1) # 數(shù)據(jù)轉(zhuǎn)換
# 獲取主要技能x = jobData.loc[jobData.skill!='其他'][['salary', 'skill']]condition1 = x['skill'] == 'Python/R'condition2 = x['skill'] == 'SQL'condition3 = x['skill'] == 'Excel'condition4 = x['skill'] == 'SPSS/SAS'
plt.figure(figsize=(12, 8))plt.title(label='不同技能的薪資水平對比',         fontsize=32, weight='bold', color='white',         backgroundcolor='#f47920', pad=30)
plt.boxplot(x=[jobData.loc[jobData.skill!='其他']['salary'][condition1],              jobData.loc[jobData.skill!='其他']['salary'][condition2],              jobData.loc[jobData.skill!='其他']['salary'][condition3],              jobData.loc[jobData.skill!='其他']['salary'][condition4]],            vert=False, labels=['Python/R', 'SQL', 'Excel', 'SPSS/SAS'])
plt.tick_params(axis='both', labelsize=16)plt.grid(axis='x', linewidth=0.75)plt.xticks(np.arange(0, 61, 10), [str(i)+'k' for i in range(0, 61, 10)])plt.box(False)plt.xlabel('工資', fontsize=18)plt.ylabel('技能', fontsize=18)

job_skills = jobData[jobData['companySize'] == '2000人以上']
labels = ['Python', 'SQL', 'Tableau', 'Excel', 'SPSS/SAS', '數(shù)據(jù)挖掘']counts =[]counts.append(jobData['python'].sum())counts.append(jobData['SQL'].sum())counts.append(jobData['Tableau'].sum())counts.append(jobData['Excel'].sum())counts.append(jobData['SPSS/SAS'].sum())counts.append(jobData['數(shù)據(jù)挖掘'].sum())
plt.figure(figsize=(9, 6))
plt.bar(x=labels, height=counts,       width=0.5,       color=plt.cm.coolwarm_r(np.linspace(0,1,len(counts))))np.linspace(0,1,len(counts))
plt.title(label='大公司對技能的要求',         fontsize=32, weight='bold', color='white',         backgroundcolor='#f47920', pad=30)plt.tick_params(labelsize=16,)plt.grid(axis='y')plt.box(False)

color_map = {    5:"#ff0000",    4:"#ffa500",    3:"#c5b783",    2:"#3c7f99",    1:"#0000cd"}
cond = jobData.workYear.isin({'5-10年':5, '3-5年':4, '1-3年':3, '1年以下':2, '應(yīng)屆畢業(yè)?':1})
jobData = jobData[cond]
jobData['workYear'] = jobData.workYear.map(workYear_map)
# 根據(jù)companySize進?排序，?數(shù)從多到少jobData['companySize'] = jobData['companySize'].astype('category')# list_custom = ['2000?以上', '500-2000?','150-500?','50-150?','15-50?','少于15?']list_custom = ['2000人以上', '500-2000人', '150-500人', '50-150人', '15-50人', '少于15人']# inplace = True，使 recorder_categories生效jobData['companySize'].cat.reorder_categories(list_custom, inplace=True)# inplace = True，使 df生效jobData.sort_values(by = 'companySize',inplace = True,ascending = False)
plt.figure(figsize=(12,11))gs = gridspec.GridSpec(10,1)plt.subplot(gs[:8])plt.suptitle(t=' 不同規(guī)模公司的??需求差異 ',    fontsize=32,    weight='bold', color='white', backgroundcolor='#3c7f99')
# 畫散點圖plt.scatter(jobData.salary,jobData.companySize,    c = jobData.workYear.map(color_map),    s = (jobData.workYear*100),    alpha = 0.35)plt.scatter(jobData.salary,jobData.companySize,    c = jobData.workYear.map(color_map))
plt.grid(axis = 'x')plt.xticks(np.arange(0,61,10), [str(i)+"k" for i in range(0,61,10)])plt.xlabel('?資', fontsize=18)plt.box(False)plt.tick_params(labelsize = 18)               # 繪制底部標記plt.subplot(gs[9:])x = np.arange(5)[::-1]y = np.zeros(len(x))s = x*100plt.scatter(x,y,s=s,c=color_map.values(),alpha=0.3)plt.scatter(x,y,c=color_map.values())plt.box(False)plt.xticks(ticks=x,labels=list(workYear_map.keys()),fontsize=14)plt.yticks(np.arange(1),labels=[' 經(jīng)驗：'],fontsize=18)