python3對拉勾數(shù)據(jù)進(jìn)行可視化分析的方法詳解

read_file = "analyst.csv"
# 讀取文件獲得數(shù)據(jù)
data = pd.read_csv(read_file, encoding="gbk")
# 去除數(shù)據(jù)中無關(guān)的列
data = data[:].drop(['ID'], axis=1)
# 描述性統(tǒng)計(jì)
data.describe()

print(data['學(xué)歷要求'].unique())
print(data['工作經(jīng)驗(yàn)'].unique())
print(data['薪資'].unique())

# 對薪資進(jìn)行預(yù)處理
def pre_salary(data):
 salarys = data['薪資'].values
 salary_dic = {}
 for salary in salarys:
 # 根據(jù)'-'進(jìn)行分割并去掉'k',分別將兩端的值轉(zhuǎn)換成整數(shù)
 min_sa = int(salary.split('-')[0][:-1])
 max_sa = int(salary.split('-')[1][:-1])
 # 求中位數(shù)
 median_sa = (min_sa + max_sa) / 2
 # 判斷其值并劃分到指定范圍
 if median_sa < 5:
 salary_dic[u'5k以下'] = salary_dic.get(u'5k以下', 0) + 1
 elif median_sa > 5 and median_sa < 10:
 salary_dic[u'5k-10k'] = salary_dic.get(u'5k-10k', 0) + 1
 elif median_sa > 10 and median_sa < 20:
 salary_dic[u'10k-20k'] = salary_dic.get(u'10k-20k', 0) + 1
 elif median_sa > 20 and median_sa < 30:
 salary_dic[u'20k-30k'] = salary_dic.get(u'20k-30k', 0) + 1
 elif median_sa > 30 and median_sa < 40:
 salary_dic[u'30k-40k'] = salary_dic.get(u'30k-40k', 0) + 1
 else:
 salary_dic[u'40以上'] = salary_dic.get(u'40以上', 0) + 1
 print(salary_dic)
 return salary_dic

import jieba
def cut_text(text):
 stopwords =['熟悉','技術(shù)','職位','相關(guān)','工作','開發(fā)','使用','能力',
 '優(yōu)先','描述','任職','經(jīng)驗(yàn)','經(jīng)驗(yàn)者','具有','具備','以上','善于',
 '一種','以及','一定','進(jìn)行','能夠','我們']
 for stopword in stopwords:
 jieba.del_word(stopword)
 
 words = jieba.lcut(text)
 content = " ".join(words)
 return content

def draw_pie(dic):
 labels = []
 count = []
 
 for key, value in dic.items():
 labels.append(key)
 count.append(value)
 
 fig, ax = plt.subplots(figsize=(8, 6), subplot_kw=dict(aspect="equal"))

 # 繪制餅狀圖，wedgeprops 表示每個(gè)扇形的寬度
 wedges, texts = ax.pie(count, wedgeprops=dict(width=0.5), startangle=0)
 # 文本框設(shè)置
 bbox_props = dict(box, fc="w", ec="k", lw=0)
 # 線與箭頭設(shè)置
 kw = dict(xycoords='data', textcoords='data', arrowprops=dict(arrow),
 bbox=bbox_props, zorder=0, va="center")

 for i, p in enumerate(wedges):
 ang = (p.theta2 - p.theta1)/2. + p.theta1
 y = np.sin(np.deg2rad(ang))
 x = np.cos(np.deg2rad(ang))
 # 設(shè)置文本框在扇形的哪一側(cè)
 horizontalalignment = {-1: "right", 1: "left"}[int(np.sign(x))]
 # 用于設(shè)置箭頭的彎曲程度
 connectionstyle = "angle,angleA=0,angleB={}".format(ang)
 kw["arrowprops"].update({"connectionstyle": connectionstyle})
 # annotate()用于對已繪制的圖形做標(biāo)注，text是注釋文本，含 'xy' 的參數(shù)跟坐標(biāo)點(diǎn)有關(guān)
 text = labels[i] + ": " + str('%.2f' %((count[i])/sum(count)*100)) + "%"
 ax.annotate(text, size=13, xy=(x, y), xytext=(1.35*np.sign(x), 1.4*y),
  horizontalalignment=horizontalalignment, **kw)
 plt.show()

def draw_workYear(data):
 workyears = list(data[u'工作經(jīng)驗(yàn)'].values)
 wy_dic = {}
 labels = []
 count = []
 # 得到工作經(jīng)驗(yàn)對應(yīng)的數(shù)目并保存到count中
 for workyear in workyears:
 wy_dic[workyear] = wy_dic.get(workyear, 0) + 1
 print(wy_dic)
 # wy_series = pd.Series(wy_dic)
 # 分別得到 count 的 key 和 value
 for key, value in wy_dic.items():
 labels.append(key)
 count.append(value)
 # 生成 keys 個(gè)數(shù)的數(shù)組
 x = np.arange(len(labels)) + 1
 # 將 values 轉(zhuǎn)換成數(shù)組
 y = np.array(count)
 
 fig, axes = plt.subplots(figsize=(10, 8))
 axes.bar(x, y, color="#1195d0")
 plt.xticks(x, labels, size=13, rotation=0)
 plt.xlabel(u'工作經(jīng)驗(yàn)', fontsize=15)
 plt.ylabel(u'數(shù)量', fontsize=15)
 
 # 根據(jù)坐標(biāo)將數(shù)字標(biāo)在圖中，ha、va 為對齊方式
 for a, b in zip(x, y):
 plt.text(a, b+1, '%.0f' % b, ha='center', va='bottom', fontsize=12)
 plt.show()

from wordcloud import WordCloud
# 繪制詞云圖
def draw_wordcloud(content):
 
 wc = WordCloud(
 font_path = 'c:\\Windows\Fonts\msyh.ttf',
 background_color = 'white',
 max_font_size=150, # 字體最大值
 min_font_size=24, # 字體最小值
 random_state=800, # 隨機(jī)數(shù)
 collocations=False, # 避免重復(fù)單詞
 width=1600,height=1200,margin=35, # 圖像寬高，字間距
 )
 wc.generate(content)

 plt.figure(dpi=160) # 放大或縮小
 plt.imshow(wc, interpolation='catrom',vmax=1000)
 plt.axis("off") # 隱藏坐標(biāo)