使用python基于上市公司的基本面制作特征标签制作企业画像（用户画像）

 

首先通过聚宽平台得到A股上市公司的基本面数据（使用了2018年三季度报），以下是两段代码

# -*- coding: utf-8 -*-
import numpy as np
import pandas as pd
def getdata(statdate):
    q = query(
         valuation.code,  #代码
            valuation.circulating_market_cap,  #流通市值
            income.operating_revenue,  #营业收入
            income.net_profit,   #净利润
            indicator.roe ,   #净资产收益率
            indicator.inc_net_profit_year_on_year,   #同比净利润增长率
            indicator.inc_revenue_year_on_year,   #同比营业收入增长率
            valuation.pe_ratio

    ).order_by(

            valuation.code.asc())
    df = get_fundamentals(q, statDate=statdate)
    
    
    # 计算PE/G
    df['peg'] = df.apply(lambda x: x['pe_ratio'] / x['inc_net_profit_year_on_year'], axis=1)
    return df



list=['2018q3']
for statdate in list:
    data=getdata(statdate)
    #print data
    print data.describe()
    string=str(statdate)+'.csv'
    data.to_csv(string)
    print'已储存%s'%(statdate)

,code,circulating_market_cap,operating_revenue,net_profit,roe,inc_net_profit_year_on_year,inc_revenue_year_on_year,pe_ratio,peg
0,000001.XSHE,1897.3123,29423000000.0,7084000000.0,3.06,7.35,14.21,7.9032,1.07526530612
1,000002.XSHE,2360.7864,70047601929.8,8275197572.38,3.54,73.72,48.12,8.9798,0.121809549647
2,000004.XSHE,13.1991,101687269.45,-8707323.76,-3.54,-255.04,143.8,93.2252,-0.365531681305
3,000005.XSHE,27.9659,109210039.65,-320649.1,-0.12,-108.05,-1.28,75.5136,-0.69887644609
4,000006.XSHE,76.8536,538306410.16,95888304.29,1.51,6.19,19.71,7.9166,1.27893376414
5,000007.XSHE,24.1906,9869023.09,2391978.85,0.64,122.29,-19.99,-173.2484,-1.41670128383
6,000008.XSHE,111.7546,559512300.25,67621384.87,0.88,-5.83,36.23,14.1008,-2.41866209262
7,000009.XSHE,98.3582,2311391267.14,35251102.6,-0.32,-76.87,19.52,59.3517,-0.772104852348
8,000010.XSHE,25.1687,79822035.82,-103783049.58,-10.51,-278.8,-78.23,-3.5897,0.0128755380201
9,000011.XSHE,20.4352,373989694.46,61216163.81,2.14,-71.1,-72.0,20.2743,-0.285151898734
10,000012.XSHE,85.055,2680693459.0,126815665.0,1.31,-60.57,-5.83,17.8674,-0.294987617632
11,000014.XSHE,21.3807,64250683.71,717746.61,-0.11,-52.27,-49.05,315.9694,-6.04494738856
12,000016.XSHE,67.3754,12136315129.3,170499305.0,1.1,69.79,38.58,1.893,0.0271242298324
13,000017.XSHE,14.1189,33515376.48,744334.9,3.17,44.68,-28.06,680.5813,15.2323478066
14,000018.XSHE,19.5759,672083613.81,-119696581.38,-5.52,-182.87,-59.52,17.2826,-0.0945075736862
15,000019.XSHE,37.3943,80047887.79,-12304627.46,-1.27,-20.84,-13.54,-81.8247,3.92632917466
16,000020.XSHE,21.4319,148975383.05,-2500879.5,-0.78,-39.09,-36.03,2066.41,-52.8628805321
17,000021.XSHE,89.629,4346119773.92,278526318.19,4.46,67.66,22.82,22.1247,0.326998226426
18,000022.XSHE,89.8573,539467699.85,176578341.66,3.01,-26.2,-21.39,22.8897,-0.873652671756
19,000023.XSHE,16.7479,366731234.42,11742201.12,2.38,-29.39,15.72,137.4432,-4.67652943178
20,000025.XSHE,78.2306,92625770.58,8976401.03,0.9,-41.52,19.69,124.0927,-2.98874518304
21,000026.XSHE,27.8595,868796654.1,50293172.83,1.96,1.55,-0.84,20.6577,13.3275483871
22,000027.XSHE,215.2719,4395780680.65,94001099.81,0.32,-79.07,2.91,24.3778,-0.308306563804
23,000028.XSHE,140.5161,10987540368.8,321206456.68,2.73,20.33,2.17,17.0967,0.840959173635
24,000029.XSHE,99.5984,282588259.93,44981269.72,1.41,262.57,21.13,29.9878,0.11420878242
25,000030.XSHE,74.2238,1869046899.48,173334495.15,2.96,-11.37,11.74,8.9314,-0.785523306948
26,000031.XSHE,104.6518,2876856784.03,473519075.1,3.92,-38.51,-26.45,7.4006,-0.192173461439
27,000032.XSHE,21.349,353414860.79,24853217.83,1.74,22.23,-15.01,63.3878,2.85145299145
28,000034.XSHE,53.3375,20307694413.0,78168324.52,2.12,-28.73,44.04,12.3895,-0.431239122868
29,000035.XSHE,58.802,504117169.46,80429588.6,2.52,16.8,11.72,26.1296,1.55533333333
30,000036.XSHE,58.6353,1302991218.0,392474599.76,8.12,867.94,618.84,8.7689,0.010103117727
31,000037.XSHE,18.3342,540079674.1,4612888.75,0.36,-78.16,-22.61,47.5735,-0.608668116684
32,000038.XSHE,22.9279,865848124.41,100733324.55,1.89,21.87,298.12,22.7376,1.03967078189
33,000039.XSHE,150.0725,23345749000.0,1537017000.0,4.29,121.19,13.46,13.1984,0.108906675468
34,000040.XSHE,112.3923,1726093346.18,94579820.85,0.68,-44.76,-12.05,8.2889,-0.185185433423
35,000042.XSHE,87.8153,1132541480.98,42255610.11,0.56,-55.38,45.35,10.1741,-0.183714337306
36,000043.XSHE,46.7441,1214245345.65,673497829.87,15.34,716.87,-10.97,11.2132,0.0156418876505
37,000045.XSHE,29.2491,533270021.4,-3948916.65,0.11,-114.88,61.11,68.2193,-0.593830954039
38,000046.XSHE,269.9226,1324106553.07,513514996.9,2.26,32.61,3.4,8.2922,0.254283961975
39,000048.XSHE,85.1717,579938695.86,23016344.33,1.48,375.87,25.77,22.807,0.0606778939527
40,000049.XSHE,51.4751,5379740462.8,186052921.47,9.07,118.48,72.6,16.1152,0.136016205267
41,000050.XSHE,170.2178,7763594189.64,434935277.01,1.67,-35.37,10.72,28.1068,-0.79465083404
42,000055.XSHE,32.287,793250321.93,91338344.89,2.78,-31.31,21.47,4.7972,-0.153216224848
43,000056.XSHE,111.8822,228003867.76,61306087.55,0.94,-20.61,-16.07,80.2833,-3.895356623
44,000058.XSHE,25.7707,561704545.25,68682198.25,2.06,191.44,112.14,22.1502,0.115703092353
45,000059.XSHE,114.8397,9091486137.07,315571363.82,2.27,-25.78,13.54,6.456,-0.250426687355
46,000060.XSHE,163.4246,5586822383.18,169704896.8,1.61,-46.73,13.7,14.5766,-0.311932377488
47,000061.XSHE,86.2758,598954166.89,87744437.45,1.37,18277.09,0.64,-622.6911,-0.0340694880859
48,000062.XSHE,134.1236,3322097406.89,175542146.6,3.6,23.03,38.65,25.1691,1.09288319583
49,000063.XSHE,628.4448,19332409000.0,548400000.0,2.52,-68.68,-14.34,-13.8273,0.201329353524
50,000065.XSHE,55.5357,2423887427.1,110094949.39,2.49,-28.2,39.49,10.5671,-0.374719858156
51,000066.XSHE,163.6401,2133582035.23,-38053748.17,-0.7,-200.84,2.72,34.4201,-0.171380701056
52,000068.XSHE,28.6901,49338118.72,-18825051.11,-2.97,-301.68,-32.62,155.926,-0.516858923363
53,000069.XSHE,387.1887,9832220073.73,3081332114.6,5.71,1.86,76.22,5.7922,3.11408602151
54,000070.XSHE,38.7906,1470204966.01,74094243.35,3.19,-3.28,16.1,17.4521,-5.32076219512
55,000078.XSHE,72.7809,10272893793.0,165912796.95,1.78,-27.04,48.16,14.2611,-0.527407544379
56,000088.XSHE,112.6476,106575533.54,137462355.59,1.97,-1.63,14.56,26.6804,-16.3683435583
57,000089.XSHE,172.8799,903874902.94,210216698.1,1.81,11.09,4.87,24.2305,2.18489630298
58,000090.XSHE,54.1118,1179283470.07,-30315420.89,-0.47,-115.39,-17.52,18.224,-0.157933963082
59,000096.XSHE,52.413,428537603.46,16749197.13,0.63,-32.35,24.29,40.3159,-1.24624111283
60,000099.XSHE,38.0006,358247581.95,47368875.77,1.51,-1.66,6.67,41.1103,-24.7652409639
61,000100.XSHE,329.5548,29713396587.0,1175114242.0,3.04,-14.24,-1.09,11.8373,-0.831271067416
62,000150.XSHE,84.3558,520173909.03,45175865.15,1.25,-14.37,8.33,40.7583,-2.83634655532
63,000151.XSHE,30.2794,77728255.12,8952720.71,0.92,-35.66,-86.91,36.3202,-1.01851374089
64,000153.XSHE,19.5922,755811646.96,18327450.19,1.46,9.14,19.71,33.2543,3.63832603939
65,000155.XSHE,44.3296,335656405.02,-59699420.58,-1.59,-288.94,-78.4,26.9442,-0.0932518862047
66,000156.XSHE,114.0743,838737040.79,165771293.53,1.59,0.7,11.1,19.6357,28.051
67,000157.XSHE,232.8448,6314853003.9,433570148.49,1.18,184.52,24.55,27.3743,0.148354107956
68,000158.XSHE,91.6041,1795985948.9,8909093.11,0.16,-34.02,21.99,27.9228,-0.820776014109
69,000159.XSHE,19.7267,160981287.05,64578580.73,3.17,946.71,32.99,-43.7647,-0.0462282008218
70,000166.XSHE,901.2654,3291289977.16,1260241472.61,1.82,-19.07,-7.88,21.973,-1.15222863136
71,000301.XSHE,80.0381,4960753592.18,-38775783.1,-0.48,-108.78,8.31,172.4419,-1.58523533738
72,000333.XSHE,2618.7083,63132816000.0,5310560000.0,6.12,16.63,1.01,13.7965,0.829615153337
73,000338.XSHE,368.5305,35918554341.4,2165157684.76,4.33,-11.4,-8.46,7.9964,-0.701438596491
74,000400.XSHE,93.0534,1502687878.95,43464957.57,0.3,-71.16,-25.19,15.9013,-0.223458403598
75,000401.XSHE,145.4994,9158152387.58,1215742738.92,6.09,53.59,15.57,19.7293,0.368152640418
76,000402.XSHE,210.3436,2060321194.14,204148527.97,0.59,-57.6,-65.2,7.4884,-0.130006944444
77,000403.XSHE,67.3833,207146336.03,12982123.88,2.17,423.09,7.36,114.5634,0.270777848685
78,000404.XSHE,29.1731,2021932386.98,24796006.75,0.08,177.36,7.92,94.5672,0.533193504736
79,000407.XSHE,34.3736,1018306752.67,28947244.09,0.81,-48.28,19.29,44.2199,-0.915905136703
80,000408.XSHE,54.2659,696401384.09,321113408.66,4.5,-10.95,-22.42,18.1867,-1.66088584475
81,000409.XSHE,16.6987,305454399.64,329358264.65,30.23,709.8,-40.05,-6.3444,-0.00893829247675
82,000410.XSHE,56.7848,865697667.5,-220008128.84,-25.36,22.84,-4.51,9.174,0.401663747811
83,000411.XSHE,28.4003,5169955002.33,59574618.77,2.77,35.58,8.92,31.1806,0.87635188308
84,000413.XSHE,221.9287,6133715988.34,461492985.01,1.45,2.38,79.68,15.8097,6.64273109244
85,000415.XSHE,138.722,9498023000.0,1164971000.0,3.34,19.53,12.57,8.3566,0.427885304659
86,000416.XSHE,20.5213,1074016.87,11973729.2,1.27,-9.39,-37.22,116.2808,-12.3834717785
87,000417.XSHE,41.0547,2307155096.42,18012243.27,0.21,-84.54,-4.85,20.5143,-0.242657913414
88,000418.XSHE,204.3043,5359920386.18,498759746.98,5.88,3.79,-0.91,17.5385,4.62757255937
89,000419.XSHE,25.9693,833914947.49,37981731.23,1.14,83.06,-7.82,20.1609,0.242726944378
90,000420.XSHE,34.2579,651073976.35,52507894.89,1.7,94.27,7.55,37.9002,0.402038824653
91,000421.XSHE,28.0024,693763960.03,49588714.48,1.27,73.94,-18.96,16.6049,0.224572626454
92,000422.XSHE,25.9468,3925432366.85,137654909.22,9.72,110.28,36.12,-0.5258,-0.00476786361988
93,000423.XSHE,310.3908,1398303075.55,361444866.4,3.52,4.25,-9.59,15.4834,3.64315294118
94,000425.XSHE,276.2457,10131905742.7,404061437.88,1.54,75.41,42.63,19.6546,0.260636520355
95,000426.XSHE,77.4212,653155833.45,199538076.07,3.43,2.22,1.43,15.039,6.77432432432
96,000428.XSHE,20.7758,227120698.54,-85400180.92,-2.2,-5.14,-7.98,46.5142,-9.04945525292
97,000429.XSHE,36.2425,850769743.92,509105563.76,4.94,14.51,3.43,11.5767,0.797842866988
98,000430.XSHE,19.9043,175456526.46,34424821.05,2.17,9.64,-10.99,49.7214,5.15782157676
99,000488.XSHE,106.7806,7941434778.16,733191184.52,2.64,-24.92,-2.92,4.9116,-0.19709470305
100,000498.XSHE,22.8283,4769378248.3,219797213.02,5.14,43.55,31.65,12.8387,0.294803673938

......剩下的不列举了

#coding=utf-8
import sklearn
from sklearn import tree
from sklearn.model_selection import train_test_split
from sklearn import datasets
import pandas as pd
import numpy



data = pd.read_csv("2018q3.csv")
print (data)
print (data.columns)

def sort_val(data):
    # 全部排序划分四挡到5挡（考虑负值）
    X=['circulating_market_cap','operating_revenue','net_profit','inc_net_profit_year_on_year','roe','inc_revenue_year_on_year','pe_ratio']
    data3=data
    for i in X:
        data2=data.sort_values(by=i,ascending=False)
        y1=str(i+'_sort')
        y2=str(i+'_sort2')

        data2[y1]=range(len(data2))
        

        data2[y2] = data2[y1].apply(lambda x: 1 if 0<=x<len(data2)/5 else(2 if len(data2)/5<=x<2*len(data2)/5 else (3 if 2*len(data2)/5<=x<3*len(data2)/5 else (4 if 3*len(data2)/5<=x<4*len(data2)/5 else 5 ))))
        
        data3 = pd.merge(data3, data2[['code',y2]], on='code')
    print (data3)
    return data3

#显示所有列
pd.set_option('display.max_columns', None)
#显示所有行
pd.set_option('display.max_rows', 50)
df2=sort_val(data)

def get_change(df2):
    if df2['pe_ratio']<0:
        x='亏损企业'
    elif df2['pe_ratio_sort2']==1:
        x='极低估值'
    elif df2['pe_ratio_sort2']==2:
        x='低估值'
    elif df2['pe_ratio_sort2']==3:
        x='正常估值'
    elif df2['pe_ratio_sort2']==4:
        x='高估值'
    elif df2['pe_ratio_sort2']==5:
        x='极高估值'
    return x

df2['circulating_market_cap_sort'] = df2['circulating_market_cap_sort2'].apply(lambda x: '巨型企业' if x==1 else('大型企业' if x==2 else ('中型企业' if x==3 else ('小型企业' if x==4 else '微型企业' ))))
df2['operating_revenue_sort']=   df2['operating_revenue_sort2'].apply(lambda x: '巨额收入' if x==1 else('大额收入' if x==2 else ('中收入' if x==3 else ('低收入' if x==4 else '微小收入' ))))     
df2['net_profit_sort']=   df2['net_profit_sort2'].apply(lambda x: '巨额净利润' if x==1 else('大额净利润' if x==2 else ('正常净利润' if x==3 else ('净收堪忧' if x==4 else '负净收垫底' ))))  
df2['inc_revenue_year_on_year_sort']=df2['inc_revenue_year_on_year_sort2'].apply(lambda x: '营业收入增长极快' if x==1 else('营业收入增长快' if x==2 else ('营业收入增长正常' if x==3 else ('营业收入增长堪忧' if x==4 else '营业收入负增长垫底' ))))
df2['pe_ratio_sort']=df2.apply(get_change,axis=1)

df2=df2.set_index('code')
df2

浏览成表：

Unnamed: 0	circulating_market_cap	operating_revenue	net_profit	roe	inc_net_profit_year_on_year	inc_revenue_year_on_year	pe_ratio	peg	circulating_market_cap_sort2	operating_revenue_sort2	net_profit_sort2	inc_net_profit_year_on_year_sort2	roe_sort2	inc_revenue_year_on_year_sort2	pe_ratio_sort2	circulating_market_cap_sort	operating_revenue_sort	net_profit_sort	inc_revenue_year_on_year_sort	pe_ratio_sort
code
000001.XSHE	0	1897.3123	2.942300e+10	7.084000e+09	3.06	7.35	14.21	7.9032	1.075265	5	5	5	3	4	3	1	微型企业	微小收入	负净收垫底	营业收入增长正常	极低估值
000002.XSHE	1	2360.7864	7.004760e+10	8.275198e+09	3.54	73.72	48.12	8.9798	0.121810	5	5	5	5	4	5	1	微型企业	微小收入	负净收垫底	营业收入负增长垫底	极低估值
000004.XSHE	2	13.1991	1.016873e+08	-8.707324e+06	-3.54	-255.04	143.80	93.2252	-0.365532	1	1	1	1	1	5	5	巨型企业	巨额收入	巨额净利润	营业收入负增长垫底	极高估值
000005.XSHE	3	27.9659	1.092100e+08	-3.206491e+05	-0.12	-108.05	-1.28	75.5136	-0.698876	3	1	1	1	1	2	5	中型企业	巨额收入	巨额净利润	营业收入增长快	极高估值
000006.XSHE	4	76.8536	5.383064e+08	9.588830e+07	1.51	6.19	19.71	7.9166	1.278934	4	3	4	3	3	4	1	小型企业	中收入	净收堪忧	营业收入增长堪忧	极低估值
000007.XSHE	5	24.1906	9.869023e+06	2.391979e+06	0.64	122.29	-19.99	-173.2484	-1.416701	2	1	1	5	2	1	1	大型企业	巨额收入	巨额净利润	营业收入增长极快	亏损企业
000008.XSHE	6	111.7546	5.595123e+08	6.762138e+07	0.88	-5.83	36.23	14.1008	-2.418662	5	3	4	3	2	5	2	微型企业	中收入	净收堪忧	营业收入负增长垫底	低估值
000009.XSHE	7	98.3582	2.311391e+09	3.525110e+07	-0.32	-76.87	19.52	59.3517	-0.772105	5	5	3	1	1	4	5	微型企业	微小收入	正常净利润	营业收入增长堪忧	极高估值
000010.XSHE	8	25.1687	7.982204e+07	-1.037830e+08	-10.51	-278.80	-78.23	-3.5897	0.012876	2	1	1	1	1	1	1	大型企业	巨额收入	巨额净利润	营业收入增长极快	亏损企业
000011.XSHE	9	20.4352	3.739897e+08	6.121616e+07	2.14	-71.10	-72.00	20.2743	-0.285152	2	3	4	1	3	1	2	大型企业	中收入	净收堪忧	营业收入增长极快	低估值
000012.XSHE	10	85.0550	2.680693e+09	1.268157e+08	1.31	-60.57	-5.83	17.8674	-0.294988	4	5	4	1	3	2	2	小型企业	微小收入	净收堪忧	营业收入增长快	低估值
000014.XSHE	11	21.3807	6.425068e+07	7.177466e+05	-0.11	-52.27	-49.05	315.9694	-6.044947	2	1	1	2	1	1	5	大型企业	巨额收入	巨额净利润	营业收入增长极快	极高估值
000016.XSHE	12	67.3754	1.213632e+10	1.704993e+08	1.10	69.79	38.58	1.8930	0.027124	4	5	5	4	2	5	1	小型企业	微小收入	负净收垫底	营业收入负增长垫底	极低估值
000017.XSHE	13	14.1189	3.351538e+07	7.443349e+05	3.17	44.68	-28.06	680.5813	15.232348	1	1	1	4	4	1	5	巨型企业	巨额收入	巨额净利润	营业收入增长极快	极高估值
000018.XSHE	14	19.5759	6.720836e+08	-1.196966e+08	-5.52	-182.87	-59.52	17.2826	-0.094508	2	3	1	1	1	1	2	大型企业	中收入	巨额净利润	营业收入增长极快	低估值
000019.XSHE	15	37.3943	8.004789e+07	-1.230463e+07	-1.27	-20.84	-13.54	-81.8247	3.926329	3	1	1	2	1	1	1	中型企业	巨额收入	巨额净利润	营业收入增长极快	亏损企业
000020.XSHE	16	21.4319	1.489754e+08	-2.500880e+06	-0.78	-39.09	-36.03	2066.4100	-52.862881	2	1	1	2	1	1	5	大型企业	巨额收入	巨额净利润	营业收入增长极快	极高估值
000021.XSHE	17	89.6290	4.346120e+09	2.785263e+08	4.46	67.66	22.82	22.1247	0.326998	5	5	5	4	5	4	3	微型企业	微小收入	负净收垫底	营业收入增长堪忧	正常估值
000022.XSHE	18	89.8573	5.394677e+08	1.765783e+08	3.01	-26.20	-21.39	22.8897	-0.873653	5	3	5	2	4	1	3	微型企业	中收入	负净收垫底	营业收入增长极快	正常估值
000023.XSHE	19	16.7479	3.667312e+08	1.174220e+07	2.38	-29.39	15.72	137.4432	-4.676529	2	3	2	2	4	3	5	大型企业	中收入	大额净利润	营业收入增长正常	极高估值
000025.XSHE	20	78.2306	9.262577e+07	8.976401e+06	0.90	-41.52	19.69	124.0927	-2.988745	4	1	2	2	2	4	5	小型企业	巨额收入	大额净利润	营业收入增长堪忧	极高估值
000026.XSHE	21	27.8595	8.687967e+08	5.029317e+07	1.96	1.55	-0.84	20.6577	13.327548	3	4	3	3	3	2	2	中型企业	低收入	正常净利润	营业收入增长快	低估值
000027.XSHE	22	215.2719	4.395781e+09	9.400110e+07	0.32	-79.07	2.91	24.3778	-0.308307	5	5	4	1	2	2	3	微型企业	微小收入	净收堪忧	营业收入增长快	正常估值
000028.XSHE	23	140.5161	1.098754e+10	3.212065e+08	2.73	20.33	2.17	17.0967	0.840959	5	5	5	4	4	2	2	微型企业	微小收入	负净收垫底	营业收入增长快	低估值
000029.XSHE	24	99.5984	2.825883e+08	4.498127e+07	1.41	262.57	21.13	29.9878	0.114209	5	2	3	5	3	4	3	微型企业	大额收入	正常净利润	营业收入增长堪忧	正常估值
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
603958.XSHG	3526	5.8739	2.615291e+08	-3.100476e+07	-2.79	-36.90	-12.52	157.0349	-4.255688	1	2	1	2	1	1	5	巨型企业	大额收入	巨额净利润	营业收入增长极快	极高估值
603959.XSHG	3527	24.3401	1.661306e+08	1.148648e+07	1.11	-69.38	-10.16	30.7130	-0.442678	2	2	2	1	2	1	3	大型企业	大额收入	大额净利润	营业收入增长极快	正常估值
603960.XSHG	3528	14.5219	1.271710e+08	1.632704e+07	3.09	101.47	231.14	63.8943	0.629687	1	1	2	5	4	5	5	巨型企业	巨额收入	大额净利润	营业收入负增长垫底	极高估值
603963.XSHG	3529	11.3875	1.039577e+08	4.520428e+06	0.99	-42.42	59.85	136.8121	-3.225179	1	1	1	2	2	5	5	巨型企业	巨额收入	巨额净利润	营业收入负增长垫底	极高估值
603966.XSHG	3530	8.1644	1.894093e+08	2.081578e+07	2.40	-14.68	21.32	28.0980	-1.914033	1	2	2	2	4	4	3	巨型企业	大额收入	大额净利润	营业收入增长堪忧	正常估值
603968.XSHG	3531	28.6272	4.700139e+08	5.521650e+07	4.03	83.78	23.29	15.9909	0.190868	3	3	4	5	5	4	2	中型企业	中收入	净收堪忧	营业收入增长堪忧	低估值
603969.XSHG	3532	44.1525	6.253389e+08	4.757699e+07	2.94	71.32	13.26	44.3769	0.622222	4	3	3	5	4	3	4	小型企业	中收入	正常净利润	营业收入增长正常	高估值
603970.XSHG	3533	6.9640	6.024503e+08	1.064191e+07	1.23	90.49	-2.01	26.1951	0.289481	1	3	2	5	2	2	3	巨型企业	中收入	大额净利润	营业收入增长快	正常估值
603976.XSHG	3534	5.4118	1.402094e+08	1.953405e+07	2.03	-11.07	14.47	24.6553	-2.227218	1	1	2	2	3	3	3	巨型企业	巨额收入	大额净利润	营业收入增长正常	正常估值
603977.XSHG	3535	13.5131	1.823634e+08	1.797801e+07	1.76	-17.44	16.79	33.1266	-1.899461	1	2	2	2	3	4	4	巨型企业	大额收入	大额净利润	营业收入增长堪忧	高估值
603978.XSHG	3536	17.1122	2.928543e+08	2.810618e+07	2.07	-14.60	2.99	33.0426	-2.263192	2	2	3	2	3	2	4	大型企业	大额收入	正常净利润	营业收入增长快	高估值
603979.XSHG	3537	49.6665	7.550374e+08	6.077490e+07	1.54	9.25	21.28	19.3437	2.091211	4	4	4	3	3	4	2	小型企业	低收入	净收堪忧	营业收入增长堪忧	低估值
603980.XSHG	3538	32.3253	8.062702e+08	2.272216e+08	5.34	108.39	19.04	12.7205	0.117359	3	4	5	5	5	4	1	中型企业	低收入	负净收垫底	营业收入增长堪忧	极低估值
603985.XSHG	3539	13.1722	3.050774e+08	3.572411e+07	3.40	128.65	73.17	20.5020	0.159363	1	2	3	5	4	5	2	巨型企业	大额收入	正常净利润	营业收入负增长垫底	低估值
603986.XSHG	3540	184.0235	6.146038e+08	1.318360e+08	7.07	-17.23	6.26	55.7504	-3.235659	5	3	4	2	5	3	5	微型企业	中收入	净收堪忧	营业收入增长正常	极高估值
603987.XSHG	3541	17.1368	3.870753e+08	5.882051e+07	3.95	35.69	13.58	22.1929	0.621824	2	3	4	4	5	3	3	大型企业	中收入	净收堪忧	营业收入增长正常	正常估值
603988.XSHG	3542	27.4243	1.209001e+08	1.236103e+07	1.86	94.99	66.53	65.6230	0.690841	3	1	2	5	3	5	5	中型企业	巨额收入	大额净利润	营业收入负增长垫底	极高估值
603989.XSHG	3543	88.4910	5.995804e+08	9.389470e+07	4.85	35.27	34.28	33.0285	0.936447	5	3	4	4	5	4	4	微型企业	中收入	净收堪忧	营业收入增长堪忧	高估值
603990.XSHG	3544	19.8777	5.939116e+07	2.389749e+04	0.03	-99.85	-3.87	54.5659	-0.546479	2	1	1	1	1	2	5	大型企业	巨额收入	巨额净利润	营业收入增长快	极高估值
603991.XSHG	3545	7.5544	1.468596e+08	9.566670e+06	2.03	35.57	47.38	36.8843	1.036950	1	1	2	4	3	5	4	巨型企业	巨额收入	大额净利润	营业收入负增长垫底	高估值
603993.XSHG	3546	805.5592	6.024018e+09	1.077375e+09	2.51	16.46	-0.46	19.6389	1.193129	5	5	5	3	4	2	2	微型企业	微小收入	负净收垫底	营业收入增长快	低估值
603996.XSHG	3547	9.1811	1.913761e+09	6.351965e+07	4.13	14.01	-4.54	16.9381	1.209001	1	5	4	3	5	2	2	巨型企业	微小收入	净收堪忧	营业收入增长快	低估值
603997.XSHG	3548	68.4810	5.036190e+08	9.114030e+07	4.98	12.38	12.92	23.2353	1.876842	4	3	4	3	5	3	3	小型企业	中收入	净收堪忧	营业收入增长正常	正常估值
603998.XSHG	3549	24.6189	2.820555e+08	1.640402e+07	1.41	-46.16	40.10	41.5566	-0.900273	2	2	2	2	3	5	4	大型企业	大额收入	大额净利润	营业收入负增长垫底	高估值
603999.XSHG	3550	11.7734	1.791531e+08	1.639049e+07	1.00	-5.85	-18.83	54.2125	-9.267094	1	2	2	3	2	1	4	巨型企业	大额收入	大额净利润	营业收入增长极快	高估值

3551 rows × 21 columns

数据已经清洗完毕，然后使用词云展示

from PIL  import Image
import jieba
from wordcloud import WordCloud 
import random
import matplotlib.pyplot as plt
import numpy as np

word=input("请输入股票代码，上证.XSHG,深证.XSHE结尾：")
cloud_text=(str(df2.ix[word,'circulating_market_cap_sort'])+' ')*random.randint(0,10)+(str(df2.ix[word,'operating_revenue_sort'])+' ')*random.randint(0,10)+(str(df2.ix[word,'net_profit_sort'])+' ')*random.randint(0,10)+(str(df2.ix[word,'inc_revenue_year_on_year_sort'])+' ')*random.randint(0,10)+(str(df2.ix[word,'pe_ratio_sort'])+' ')*random.randint(0,10)


luo=np.array(Image.open('QQ图片20160909213837.png'))
wc = WordCloud(
    background_color='white',width=1600,height=1600,max_words=2000,
    font_path="simhei.ttf",

    mask=luo

    )
wc.generate(cloud_text)


plt.imshow(wc)
plt.axis("off")
plt.show()



wc.to_file("pic2.png")

 

最后完成后，输入浦发银行代码 600000.XSHG，输出企业画像：

再用小公司数据试试：

模板为三角形图：

之后会考虑采用机器学习来对公司进行分类判断（ROE,PE/G等数据会在之后用到）......That's all，for now