不知道如何分析選擇基金、股票？Python來教你
廢話很少說，直接上菜。html
第一步：基金數據爬取
打開每天基金網（https://fund.eastmoney.com/），經過瀏覽器的開發者工具，咱們能觀察到用戶的請求和數據的返回過程。從而利用正則表達式，以及 xpath 等工具，輔以一點 python 爬蟲的知識，很容易就能獲取到每支基金的增加率和持倉狀況。python
不少人學習python，不知道從何學起。
不少人學習python，掌握了基本語法事後，不知道在哪裏尋找案例上手。
不少已經作案例的人，殊不知道如何去學習更加高深的知識。
那麼針對這三類人，我給你們提供一個好的學習平臺，免費領取視頻教程，電子書籍，以及課程的源代碼！
QQ羣：883888997
我所用到的代碼以下。git
XMtool.py：正則表達式
# In[]:
#!/usr/bin/env python
# coding: utf-8
# encoding=utf-8
import pandas as pd
import requests
from lxml import etree
import re
#import collections
import numpy as np
# In[]:
sample = '150000'#樣本數量
sc = '6yzf'#排序鍵值
st = 'desc'#排序方式
ft = 'gp'#基金類型
dx = '1'#是否可購
season = 1#季度選擇
r1r = 1#日增加率
r1z = 1#近1周
r1y = 1#近1月
r3y = 0.3333#近3月
r6y = 0.3333#近6月
r1n = 0.25#近1年
r2n = 0.25#近2年
r3n = 0.25#近3年
rjnl = 0.25#今年來
rcll = 1#成立來
sd = '2021-01-07'
ed = '2021-02-07'
# In[] 在參數文書寫單元后加上這麼一段就能夠了
#from PyQt5.QtWidgets import QInputDialog, QLineEdit, QDialog
from PyQt5.QtWidgets import QDialog
import sys
from PyQt5.QtWidgets import QApplication
import dialog
class TestDialog1(QDialog,dialog.Ui_XMtool):
def __init__(self,parent=None):
super(TestDialog1,self).__init__(parent)
self.setupUi(self)
app=QApplication(sys.argv)
dlg=TestDialog1()
dlg.show()
app.exec_()
sample = dlg.sample.text() #樣本數量
sc = dlg.sc.currentText() #排序鍵值
st = dlg.st.currentText() #排序方式
ft = dlg.ft.currentText() #基金類型
dx = dlg.dx.currentText() #是否可購
season = int(dlg.season.currentText()) #季度選擇
r1r = float(dlg.r1r.text()) #日增加率
r1z = float(dlg.r1z.text())#近1周
r1y = float(dlg.r1y.text())#近1月
r3y = float(dlg.r3y.text())#近3月
r6y = float(dlg.r6y.text())#近6月
r1n = float(dlg.r1n.text())#近1年
r2n = float(dlg.r2n.text())#近2年
r3n = float(dlg.r3n.text())#近3年
rjnl = float(dlg.rjnl.text())#今年來
rcll = float(dlg.rcll.text())#成立來
# In[]:
header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.96 Safari/537.36',
'Referer': 'http://fund.eastmoney.com/data/fundranking.html',
'Cookie':'st_si=74949607860286; st_asi=delete; ASP.NET_SessionId=gekyucnll0wte0wrks2rr23b; _adsame_fullscreen_18503=1; EMFUND1=null; EMFUND2=null; EMFUND3=null; EMFUND4=null; EMFUND5=null; EMFUND6=null; EMFUND7=null; EMFUND8=null; EMFUND0=null; EMFUND9=02-07 16:37:21@#$%u521B%u91D1%u5408%u4FE1%u5DE5%u4E1A%u5468%u671F%u80A1%u7968A@%23%24005968; st_pvi=90009717841707; st_sp=2021-02-07%2012%3A14%3A29; st_inirUrl=https%3A%2F%2Fwww.baidu.com%2Flink; st_sn=21; st_psi=2021020716562364-0-0372414431'
}
url = 'http://fund.eastmoney.com/data/rankhandler.aspx?op=ph&dt=kf&ft='+ft+'&rs=&gs=0&sc='+sc+'&st='+st+'&sd='+sd+'&ed='+ed+'&qdii=&tabSubtype=,,,,,&pi=1&pn='+sample+'&dx='+dx+'&v=0.2692835962833908'
response = requests.get(url=url, headers=header)
text = response.text
data = text.split('=')[1]#使用等號分開去後面一部分
compile_data = re.findall("{datas:\\[(.*)\\],allRecords", str(data))[0]#取datas和allRecords中的全部內容
strip_data = str(compile_data).strip('[').strip(']')#移除字符串頭尾的中括號
replace_quta = strip_data.replace('"', "")#雙引號替換爲空
quota_arrays = replace_quta.split(",")#使用逗號轉爲列表
intervals = [[i * 25, (i + 1) * 25] for i in range(15000)]#生成10000個區間，每一個區間長度爲25
narrays = []
for k in intervals:
start, end = k[0], k[1]
line = quota_arrays[start:end]#將條目25個分爲一組,表示一隻基金
narrays.append(line)
header = ["基金代碼", "基金簡稱", "基金條碼", "日期",
"單位淨值", "累計淨值", "日增加率", "近1周", "近1月", "近3月", "近半年", "近1年", "近2年", "近3年",
"今年來", "成立來", "其餘1", "其餘2", "其餘3", "其餘4", "其餘5", "其餘6", "其餘7", "其餘8", "其餘9"]
df = pd.DataFrame(narrays, columns=header)#生成pd數據結構
df.dropna()
total = df.count()[0]
print("共有{}支基金！".format(total))
df = df.head(total)
df_part = df[["基金代碼", "基金簡稱", "日增加率", "近1周", "近1月", "近3月", "近半年", "近1年", "近2年", "近3年",
"今年來", "成立來"]]#挑選部分感興趣的條目
df.to_csv("./基金增加率.csv", encoding="utf_8_sig")
# In[]:
df_picked_part = df_part
rates = [r1r,r1z,r1y,r3y,r6y,r1n,r2n,r3n,rjnl,rcll]
i = -1
for sc in ["日增加率", "近1周", "近1月", "近3月", "近半年", "近1年", "近2年", "近3年",
"今年來", "成立來"]:
i = i+1
#print(sc)
rate = rates[i]
rate_num = int(total*rate)
df_tmp = df_part.sort_values(by=[sc], ascending=False, axis=0)
df_tmp = df_tmp.head(rate_num)
df_picked_part = pd.merge(df_picked_part,df_tmp,how='inner')
print(df_picked_part.head(10))
df_picked_part.to_csv("./4433法則結果.csv", encoding="utf_8_sig")
# In[]:
rank_codes = df_part['基金代碼'].values.tolist()
#len_codes = len(rank_codes)
stocks_array = []
stock_funds = []
total_part = int(total/100)+1 #每百分之一報一次進度
for index, code in enumerate(rank_codes):
# if index < 1:
# print("<" * 30 + "全部基金的股票池前10狀況" + ">" * 30)
# print(code)
if index%total_part==0:
print("<" * 30 + "得到基金持倉數據中："+str(index)+"/"+str(total)+ ">" * 30)
url = "http://fundf10.eastmoney.com/FundArchivesDatas.aspx?type=jjcc&code={}&topline=10&year=&month=&rt=0.5032668912422176".format(code)
head = {
"Cookie": "EMFUND1=null; EMFUND2=null; EMFUND3=null; EMFUND4=null; EMFUND5=null; EMFUND6=null; EMFUND7=null; EMFUND8=null; EMFUND0=null; st_si=44023331838789; st_asi=delete; EMFUND9=08-16 22:04:25@#$%u4E07%u5BB6%u65B0%u5229%u7075%u6D3B%u914D%u7F6E%u6DF7%u5408@%23%24519191; ASP.NET_SessionId=45qdofapdlm1hlgxapxuxhe1; st_pvi=87492384111747; st_sp=2020-08-16%2000%3A05%3A17; st_inirUrl=http%3A%2F%2Ffund.eastmoney.com%2Fdata%2Ffundranking.html; st_sn=12; st_psi=2020081622103685-0-6169905557"
,
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36"}
response = requests.get(url, headers=head)
text = response.text
div = re.findall('content:\\"(.*)\\",arryear', text)[0]
html_body = '<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><title>test</title></head><body>%s</body></html>' % (
div)#構造網頁
html = etree.HTML(html_body)#將傳進去的字符串轉變成_Element對象
stock_info = html.xpath('//div[{}]/div/table/tbody/tr/td/a'.format(season))
# for ii in stock_info:
# print(ii.text)
#print(season)
stock_money = html.xpath('//div[{}]/div/table/tbody/tr/td[@class="tor"]'.format(season))
if stock_money == []:
stock_money = html.xpath('//div[{}]/div/table/tbody/tr/td[@class="toc"]'.format(season))
stock_attr = []
# for i in range(0,len(stock_money)):
stock_money_text = []
for ii in stock_money:
ii_text = ii.text
# print(ii_text)
if ii_text!=None:
ii.text = ii.text.replace('---','0')
stock_money_text.append(float(ii.text.replace(',','').replace('%','')))
# print(ii.text)
# stock_money_text.dropna()
stock_one_fund = []
if len(stock_info)!=0 and len(stock_money_text)!=0:
count = -1
for i in range(0,len(stock_info)):
stock = stock_info[i]
if stock.text==None:
stock.text = '缺失'
tmp0 = stock.text.split('.')
tmp = tmp0[0]
if stock.text and (tmp.isdigit() or (tmp.isupper() and tmp.isalnum() and len(tmp0)>1)):
# if stock.text and stock.text.isdigit():
# list_tmp = [stock.text,stock_info[i+1].text]
count = count+1
stock_one_fund.append([stock_info[i+1].text,
stock_money_text[3*count+0],
stock_money_text[3*count+1],
stock_money_text[3*count+2]])
# print(stock_info[i+1].text)
# if len(stock_one_fund)>1:
# print("基金代碼：{}".format(code), "基金持有前10股票池", stock_one_fund)
stock_funds.append([code,stock_one_fund])
# print(code)
# print(stock_one_fund)
# else:
# print('發現無持倉基金！')
# if len(stock_one_fund) > 1 and stock_one_fund:
stocks_array.extend(stock_one_fund)
print("<" * 30 + "得到基金持倉數據中：done!!!"+ ">" * 30)
# print("test")
tmp = pd.DataFrame(stock_funds,columns=['基金代碼','十大重倉'])
df_funds_info_extend = pd.merge(df_part,tmp,how='inner',on='基金代碼')
df_funds_info_extend.set_index('基金代碼')
df_funds_info_extend.to_csv("./基金持倉.csv", encoding="utf_8_sig")
# In[]:
stock_info_list = []
for row in df_funds_info_extend.iterrows():
tenpos = row[1]['十大重倉']
fund_jc = row[1]['基金簡稱']
if len(tenpos)!=0:
tmp = [tenpos[0][0],fund_jc,tenpos[0][1],tenpos[0][2],tenpos[0][3]]
stock_info_list.append(tmp)
df_stock_info = pd.DataFrame(stock_info_list,columns=['股票簡稱','所屬基金','佔淨值比例','持股數_萬','持倉市值_萬'])
df_stock_info.to_csv("./股票被持有信息.csv", encoding="utf_8_sig")
# In[]
#df_stock_info.loc[:,['股票簡稱','持股數_萬','持倉市值_萬','佔淨值比例']]
df_stock_info_cp = df_stock_info
df_stock_info_cp['所屬基金cp'] = df_stock_info['所屬基金']
df_stock_info_gb = df_stock_info_cp.groupby('股票簡稱')
#df_stock_info.drop(axis=1,['所屬基金'])
# for n in df_stock_info_gb:
# print(n)
# print('\n')
#stock_agg_result = df_stock_info_gb.agg({'持股數_萬':np.sum,'持倉市值_萬':np.sum,'佔淨值比例':np.mean})
stock_agg_result = df_stock_info_gb.agg({'持股數_萬':np.sum,'持倉市值_萬':np.sum,'佔淨值比例':np.mean,'所屬基金':len,'所屬基金cp':list})
stock_agg_result.columns = ['被持股數_萬','被持倉市值_萬','平均佔比','所屬基金數目','所屬基金集合']
stock_agg_result.to_csv("./股票被持有信息統計.csv", encoding="utf_8_sig")
# df_stock_info_gb.to_csv("./測試.csv", encoding="utf_8_sig")
# In[]
rank = 10
stock_agg_result = stock_agg_result.sort_values(by="所屬基金數目",ascending=False)
stock_agg_result_head0 = stock_agg_result.head(rank)
stock_agg_result = stock_agg_result.sort_values(by="被持倉市值_萬",ascending=False)
stock_agg_result_head1 = stock_agg_result.head(rank)
stock_agg_result = stock_agg_result.sort_values(by="平均佔比",ascending=False)
stock_agg_result_head2 = stock_agg_result.head(rank)
funds_stocks_count = []
for st_funds_ in stock_funds:
#st_funds_ = stock_funds[0]
st_funds = st_funds_[1]
tmp = [i[0] for i in st_funds]
df_stock_funds = pd.DataFrame(tmp,columns=['股票簡稱'])
# print(df_stock_funds)
count0 = pd.merge(stock_agg_result_head0,df_stock_funds,how='inner',on='股票簡稱').iloc[:,0].size
count1 = pd.merge(stock_agg_result_head1,df_stock_funds,how='inner',on='股票簡稱').iloc[:,0].size
count2 = pd.merge(stock_agg_result_head2,df_stock_funds,how='inner',on='股票簡稱').iloc[:,0].size
jc_tmp = df_part[df_part['基金代碼']==st_funds_[0]].iloc[0,1]
funds_stocks_count.append([jc_tmp,count0,count1,count2])
df_funds_stock_count = pd.DataFrame(funds_stocks_count,columns = ['基金簡稱','優倉數目_所屬基金數','優倉數目_被持倉市值','平均佔比'])
df_funds_stock_count = df_funds_stock_count.sort_values(by=["優倉數目_所屬基金數"], ascending=False, axis=0)
df_funds_stock_count = pd.merge(df_funds_stock_count,df_part,how='inner',on='基金簡稱')
df_funds_stock_count.to_csv("./基金持受歡迎股數目統計.csv", encoding="utf_8_sig")
dialog.py瀏覽器
# -*- coding: utf-8 -*-
# Form implementation generated from reading ui file 'dialog.ui'
#
# Created by: PyQt5 UI code generator 5.9.2
#
# WARNING! All changes made in this file will be lost!
from PyQt5 import QtCore, QtGui, QtWidgets
class Ui_XMtool(object):
def setupUi(self, XMtool):
XMtool.setObjectName("XMtool")
XMtool.resize(701, 622)
self.verticalLayout = QtWidgets.QVBoxLayout(XMtool)
self.verticalLayout.setObjectName("verticalLayout")
self.formGroupBox_2 = QtWidgets.QGroupBox(XMtool)
self.formGroupBox_2.setObjectName("formGroupBox_2")
self.gridLayout = QtWidgets.QGridLayout(self.formGroupBox_2)
self.gridLayout.setObjectName("gridLayout")
self.label_18 = QtWidgets.QLabel(self.formGroupBox_2)
self.label_18.setObjectName("label_18")
self.gridLayout.addWidget(self.label_18, 0, 0, 1, 1)
self.pushButton = QtWidgets.QPushButton(self.formGroupBox_2)
self.pushButton.setObjectName("pushButton")
self.gridLayout.addWidget(self.pushButton, 2, 0, 1, 2)
self.frame = QtWidgets.QFrame(self.formGroupBox_2)
self.frame.setObjectName("frame")
self.formLayout_4 = QtWidgets.QFormLayout(self.frame)
self.formLayout_4.setObjectName("formLayout_4")
self.label = QtWidgets.QLabel(self.frame)
self.label.setObjectName("label")
self.formLayout_4.setWidget(0, QtWidgets.QFormLayout.LabelRole, self.label)
self.r1r = QtWidgets.QLineEdit(self.frame)
self.r1r.setObjectName("r1r")
self.formLayout_4.setWidget(0, QtWidgets.QFormLayout.FieldRole, self.r1r)
self.label_2 = QtWidgets.QLabel(self.frame)
self.label_2.setObjectName("label_2")
self.formLayout_4.setWidget(1, QtWidgets.QFormLayout.LabelRole, self.label_2)
self.r1z = QtWidgets.QLineEdit(self.frame)
self.r1z.setObjectName("r1z")
self.formLayout_4.setWidget(1, QtWidgets.QFormLayout.FieldRole, self.r1z)
self.label_3 = QtWidgets.QLabel(self.frame)
self.label_3.setObjectName("label_3")
self.formLayout_4.setWidget(2, QtWidgets.QFormLayout.LabelRole, self.label_3)
self.r1y = QtWidgets.QLineEdit(self.frame)
self.r1y.setObjectName("r1y")
self.formLayout_4.setWidget(2, QtWidgets.QFormLayout.FieldRole, self.r1y)
self.label_4 = QtWidgets.QLabel(self.frame)
self.label_4.setObjectName("label_4")
self.formLayout_4.setWidget(3, QtWidgets.QFormLayout.LabelRole, self.label_4)
self.r3y = QtWidgets.QLineEdit(self.frame)
self.r3y.setObjectName("r3y")
self.formLayout_4.setWidget(3, QtWidgets.QFormLayout.FieldRole, self.r3y)
self.label_5 = QtWidgets.QLabel(self.frame)
self.label_5.setObjectName("label_5")
self.formLayout_4.setWidget(4, QtWidgets.QFormLayout.LabelRole, self.label_5)
self.r6y = QtWidgets.QLineEdit(self.frame)
self.r6y.setObjectName("r6y")
self.formLayout_4.setWidget(4, QtWidgets.QFormLayout.FieldRole, self.r6y)
self.label_6 = QtWidgets.QLabel(self.frame)
self.label_6.setObjectName("label_6")
self.formLayout_4.setWidget(5, QtWidgets.QFormLayout.LabelRole, self.label_6)
self.r1n = QtWidgets.QLineEdit(self.frame)
self.r1n.setObjectName("r1n")
self.formLayout_4.setWidget(5, QtWidgets.QFormLayout.FieldRole, self.r1n)
self.label_7 = QtWidgets.QLabel(self.frame)
self.label_7.setObjectName("label_7")
self.formLayout_4.setWidget(6, QtWidgets.QFormLayout.LabelRole, self.label_7)
self.r2n = QtWidgets.QLineEdit(self.frame)
self.r2n.setObjectName("r2n")
self.formLayout_4.setWidget(6, QtWidgets.QFormLayout.FieldRole, self.r2n)
self.label_8 = QtWidgets.QLabel(self.frame)
self.label_8.setObjectName("label_8")
self.formLayout_4.setWidget(7, QtWidgets.QFormLayout.LabelRole, self.label_8)
self.r3n = QtWidgets.QLineEdit(self.frame)
self.r3n.setObjectName("r3n")
self.formLayout_4.setWidget(7, QtWidgets.QFormLayout.FieldRole, self.r3n)
self.label_9 = QtWidgets.QLabel(self.frame)
self.label_9.setObjectName("label_9")
self.formLayout_4.setWidget(8, QtWidgets.QFormLayout.LabelRole, self.label_9)
self.rjnl = QtWidgets.QLineEdit(self.frame)
self.rjnl.setObjectName("rjnl")
self.formLayout_4.setWidget(8, QtWidgets.QFormLayout.FieldRole, self.rjnl)
self.label_10 = QtWidgets.QLabel(self.frame)
self.label_10.setObjectName("label_10")
self.formLayout_4.setWidget(9, QtWidgets.QFormLayout.LabelRole, self.label_10)
self.rcll = QtWidgets.QLineEdit(self.frame)
self.rcll.setObjectName("rcll")
self.formLayout_4.setWidget(9, QtWidgets.QFormLayout.FieldRole, self.rcll)
self.gridLayout.addWidget(self.frame, 1, 1, 1, 1)
self.frame_2 = QtWidgets.QFrame(self.formGroupBox_2)
self.frame_2.setObjectName("frame_2")
self.label_11 = QtWidgets.QLabel(self.frame_2)
self.label_11.setGeometry(QtCore.QRect(18, 18, 96, 24))
self.label_11.setObjectName("label_11")
self.label_12 = QtWidgets.QLabel(self.frame_2)
self.label_12.setGeometry(QtCore.QRect(18, 61, 96, 24))
self.label_12.setObjectName("label_12")
self.sc = QtWidgets.QComboBox(self.frame_2)
self.sc.setGeometry(QtCore.QRect(126, 61, 91, 30))
self.sc.setObjectName("sc")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.addItem("")
self.sc.setItemText(15, "")
self.label_13 = QtWidgets.QLabel(self.frame_2)
self.label_13.setGeometry(QtCore.QRect(18, 103, 96, 24))
self.label_13.setObjectName("label_13")
self.st = QtWidgets.QComboBox(self.frame_2)
self.st.setGeometry(QtCore.QRect(126, 103, 90, 30))
self.st.setObjectName("st")
self.st.addItem("")
self.st.addItem("")
self.label_14 = QtWidgets.QLabel(self.frame_2)
self.label_14.setGeometry(QtCore.QRect(18, 145, 96, 24))
self.label_14.setObjectName("label_14")
self.ft = QtWidgets.QComboBox(self.frame_2)
self.ft.setGeometry(QtCore.QRect(126, 145, 90, 30))
self.ft.setObjectName("ft")
self.ft.addItem("")
self.ft.addItem("")
self.ft.addItem("")
self.ft.addItem("")
self.ft.addItem("")
self.ft.addItem("")
self.ft.addItem("")
self.ft.addItem("")
self.label_15 = QtWidgets.QLabel(self.frame_2)
self.label_15.setGeometry(QtCore.QRect(18, 187, 96, 24))
self.label_15.setObjectName("label_15")
self.dx = QtWidgets.QComboBox(self.frame_2)
self.dx.setGeometry(QtCore.QRect(126, 187, 55, 30))
self.dx.setObjectName("dx")
self.dx.addItem("")
self.dx.addItem("")
self.label_16 = QtWidgets.QLabel(self.frame_2)
self.label_16.setGeometry(QtCore.QRect(18, 229, 96, 24))
self.label_16.setObjectName("label_16")
self.season = QtWidgets.QComboBox(self.frame_2)
self.season.setGeometry(QtCore.QRect(126, 229, 56, 30))
self.season.setObjectName("season")
self.season.addItem("")
self.season.addItem("")
self.season.addItem("")
self.season.addItem("")
self.sample = QtWidgets.QLineEdit(self.frame_2)
self.sample.setGeometry(QtCore.QRect(126, 18, 151, 30))
self.sample.setObjectName("sample")
self.gridLayout.addWidget(self.frame_2, 1, 0, 1, 1)
self.label_17 = QtWidgets.QLabel(self.formGroupBox_2)
self.label_17.setObjectName("label_17")
self.gridLayout.addWidget(self.label_17, 0, 1, 1, 1)
self.frame.raise_()
self.frame_2.raise_()
self.label_18.raise_()
self.label_17.raise_()
self.pushButton.raise_()
self.verticalLayout.addWidget(self.formGroupBox_2)
self.retranslateUi(XMtool)
self.pushButton.clicked.connect(XMtool.accept)
QtCore.QMetaObject.connectSlotsByName(XMtool)
def retranslateUi(self, XMtool):
_translate = QtCore.QCoreApplication.translate
XMtool.setWindowTitle(_translate("XMtool", "股林祕籍小明三式"))
XMtool.setToolTip(_translate("XMtool", "<html><head/><body><p>歡迎使用小明選股軟件！</p></body></html>"))
XMtool.setWhatsThis(_translate("XMtool", "<html><head/><body><p>不認識爸爸？</p></body></html>"))
self.label_18.setText(_translate("XMtool", "基金數據參數設定："))
self.pushButton.setText(_translate("XMtool", "小明已肯定"))
self.label.setText(_translate("XMtool", "日增加率"))
self.r1r.setText(_translate("XMtool", "1"))
self.label_2.setText(_translate("XMtool", "近1周"))
self.r1z.setText(_translate("XMtool", "1"))
self.label_3.setText(_translate("XMtool", "近1月"))
self.r1y.setText(_translate("XMtool", "1"))
self.label_4.setText(_translate("XMtool", "近3月"))
self.r3y.setText(_translate("XMtool", "0.33333"))
self.label_5.setText(_translate("XMtool", "近6月"))
self.r6y.setText(_translate("XMtool", "0.33333"))
self.label_6.setText(_translate("XMtool", "近1年"))
self.r1n.setText(_translate("XMtool", "0.25"))
self.label_7.setText(_translate("XMtool", "近2年"))
self.r2n.setText(_translate("XMtool", "0.25"))
self.label_8.setText(_translate("XMtool", "近3年"))
self.r3n.setText(_translate("XMtool", "0.25"))
self.label_9.setText(_translate("XMtool", "今年來"))
self.rjnl.setText(_translate("XMtool", "0.25"))
self.label_10.setText(_translate("XMtool", "成立來"))
self.rcll.setText(_translate("XMtool", "1"))
self.label_11.setText(_translate("XMtool", "樣本數量"))
self.label_12.setText(_translate("XMtool", "排序鍵值"))
self.sc.setItemText(0, _translate("XMtool", "6yzf"))
self.sc.setItemText(1, _translate("XMtool", "dm"))
self.sc.setItemText(2, _translate("XMtool", "jc"))
self.sc.setItemText(3, _translate("XMtool", "jzrq"))
self.sc.setItemText(4, _translate("XMtool", "dwjz"))
self.sc.setItemText(5, _translate("XMtool", "ljjz"))
self.sc.setItemText(6, _translate("XMtool", "rzdf"))
self.sc.setItemText(7, _translate("XMtool", "zzf"))
self.sc.setItemText(8, _translate("XMtool", "1yzf"))
self.sc.setItemText(9, _translate("XMtool", "3yzf"))
self.sc.setItemText(10, _translate("XMtool", "1nzf"))
self.sc.setItemText(11, _translate("XMtool", "2nzf"))
self.sc.setItemText(12, _translate("XMtool", "3nzf"))
self.sc.setItemText(13, _translate("XMtool", "jnzf"))
self.sc.setItemText(14, _translate("XMtool", "lnzf"))
self.label_13.setText(_translate("XMtool", "排序方式"))
self.st.setItemText(0, _translate("XMtool", "desc"))
self.st.setItemText(1, _translate("XMtool", "asc"))
self.label_14.setText(_translate("XMtool", "基金類型"))
self.ft.setItemText(0, _translate("XMtool", "all"))
self.ft.setItemText(1, _translate("XMtool", "gp"))
self.ft.setItemText(2, _translate("XMtool", "hh"))
self.ft.setItemText(3, _translate("XMtool", "zs"))
self.ft.setItemText(4, _translate("XMtool", "qdii"))
self.ft.setItemText(5, _translate("XMtool", "zq"))
self.ft.setItemText(6, _translate("XMtool", "lof"))
self.ft.setItemText(7, _translate("XMtool", "fof"))
self.label_15.setText(_translate("XMtool", "是否可購"))
self.dx.setItemText(0, _translate("XMtool", "1"))
self.dx.setItemText(1, _translate("XMtool", "0"))
self.label_16.setText(_translate("XMtool", "季度選擇"))
self.season.setItemText(0, _translate("XMtool", "1"))
self.season.setItemText(1, _translate("XMtool", "2"))
self.season.setItemText(2, _translate("XMtool", "3"))
self.season.setItemText(3, _translate("XMtool", "4"))
self.sample.setText(_translate("XMtool", "15000"))
self.label_17.setText(_translate("XMtool", "四四三三法則參數："))
運行以後，須要填一些參數，以下。網絡
肯定以後，除了爬下來了咱們後面所要用到的所有數據以外，咱們還利用 4433 法則，對於基金進行了一個初步的分析和篩選。數據結構
第二步：股票增持計算
有了上面爬下來的原始數據以後，咱們就能夠統計：單股票被基金公司持有的數量、單股票被基金公司持有的市值和持有單股票基金公司的數目。對於不一樣的相鄰季度，咱們能夠計算這三個量的增加，又獲得三個新的指標。對於不一樣的指標進行降排序，咱們能夠獲得股票在基金公司中的受歡迎程度，以此獲得股票好壞度，指標值做爲權重。不一樣的指標獲得的不一樣的股票排序還能夠拿前幾取交集。從而咱們就獲得了基金公司們期待值比較高的股票。app
我所用的代碼以下：工具
#!/usr/bin/env python
# coding: utf-8
# In[]:
import pandas as pd
#import os
import tkinter as tk
from tkinter import filedialog
def getLocalFile():
root=tk.Tk()
root.withdraw()
filePath=filedialog.askopenfilename()
print('文件路徑：',filePath)
return filePath
#if __name__ == '__main__':
# In[]:
file1 = getLocalFile()
file2 = getLocalFile()
#sheet1 = pd.read_csv('./all_1/股票被持有信息統計.csv')
sheet1 = pd.read_csv(file1)
sheet1
#sheet2 = pd.read_csv('./all_2/股票被持有信息統計.csv')
sheet2 = pd.read_csv(file2)
sheet3 = pd.merge(sheet1,sheet2,how='inner',on='股票簡稱')
sheet3
sheet3['增持股數'] = sheet3['被持股數_萬_x'] - sheet3['被持股數_萬_y']
# In[]:
sheet3['增持市值'] = sheet3['被持倉市值_萬_x'] - sheet3['被持倉市值_萬_y']
#sheet3['增持佔比'] = sheet3['平均佔比_x'] - sheet3['平均佔比_y']
sheet3['增持基金數量'] = sheet3['所屬基金數目_x'] - sheet3['所屬基金數目_y']
sheet3.to_csv('增持狀況統計.csv',encoding="utf_8_sig")
第三步：好股基金選取
第二步中，咱們其實已經獲得了被基金公司看重的股票，若是炒股，直接取其前幾，按其權重進行金額配置便可。如今問題是，國內股票交易，一手起步，選出來的股票很貴，好比說茅臺，你不必定買得起。這時候，咱們仍是寄但願於買基金。咱們但願選出的基金的持倉和咱們選出的好股票集合的「類似度」儘量高。類似度的衡量又不少方法。好比說：基金持有的十大重倉含有好股的數目、基金持有的十大重倉含有好股的市值、基金持有的十大重倉含有好股的佔比、基金持有的十大重倉含有好股的加權佔比（加權基於增持市值或增持基金數量）等等。學習
下面是我所用到的代碼，細節可看。
#!/usr/bin/env python
# coding: utf-8
# In[]:
import pandas as pd
#import os
# In[]:
import tkinter as tk
from tkinter import filedialog
def getLocalFile():
root=tk.Tk()
root.withdraw()
filePath=filedialog.askopenfilename()
print('文件路徑：',filePath)
return filePath
#if __name__ == '__main__':
# In[]
print('請輸入增持狀況統計：')
increase_hold_add = getLocalFile()
inc = pd.read_csv(increase_hold_add,index_col = 0)
inc
# In[]:
#print('請輸入比率：')
str_num = input("Enter your number: ")
rate = int(str_num)
rate
# In[]:
inc_sort_zcgs = inc.sort_values(by=["增持股數"], ascending=False, axis=0)
inc_sort_zcsz = inc.sort_values(by=["增持市值"], ascending=False, axis=0)
inc_sort_zcjjsl = inc.sort_values(by=["增持基金數量"], ascending=False, axis=0)
inc_sort_zcgs
inc_sort_zcgs = inc_sort_zcgs.head(rate)
inc_sort_zcsz = inc_sort_zcsz.head(rate)
inc_sort_zcjjsl = inc_sort_zcjjsl.head(rate)
inc_merge = pd.merge(inc_sort_zcsz,inc_sort_zcjjsl,how='inner',on='股票簡稱')
inc_merge
intersec = inc_merge['股票簡稱']
intersec
print('選出來的前{}股票交集爲：'.format(rate))
print(intersec)
print('共{}只！'.format(len(intersec)))
# In[]:
print('請選擇基金持倉：')
funds_hold_add = getLocalFile()
funds_hold = pd.read_csv(funds_hold_add,index_col = 0)
stock_funds = funds_hold
stock_funds
intersec
intersec_ex = pd.merge(intersec,inc,how='inner',on='股票簡稱')
intersec_ex['權重_增持市值'] = intersec_ex['增持市值']/intersec_ex['增持市值'].sum()
intersec_ex['權重_增持基金數量'] = intersec_ex['增持基金數量']/intersec_ex['增持基金數量'].sum()
intersec_ex.to_csv("./好股.csv", encoding="utf_8_sig")
# In[ ]:
result = []# pd.DataFrame()
for row in stock_funds.iterrows():
tenpos = row[1]['十大重倉']
exec('tps='+tenpos)
fund_jc = row[1]['基金簡稱']
#tmp = [i[0] for i in tps]
#rate = [r[1] for r in tps]
list_tmp = [[i[0],i[1]] for i in tps]
df_stock_rate = pd.DataFrame(list_tmp,columns=['股票簡稱','股票佔比'])
# good_stock_rate
# df_stock_funds = pd.DataFrame(tmp,columns=['股票簡稱'])
# print(df_stock_funds)
good_stock = pd.merge(intersec_ex,df_stock_rate,how='inner',on='股票簡稱')#.iloc[:,0]
count = good_stock['股票簡稱'].size
rate_vector = good_stock['股票佔比']
total_rate = rate_vector.sum()
tmp = (rate_vector.mul(good_stock['權重_增持市值']))#.sum
tmp = tmp.sum()
total_rate_weighted_zcsz = tmp
tmp = (rate_vector.mul(good_stock['權重_增持基金數量']))#.sum
tmp = tmp.sum()
total_rate_weighted_zcjjsl = tmp
#good_stock_jc = good_stock['基金簡稱']
result.append([fund_jc,count,total_rate,total_rate_weighted_zcsz,total_rate_weighted_zcjjsl])
pd_result = pd.DataFrame(result,columns = ['基金簡稱','好股數目','好股佔比','加權好股佔比_增持市值','加權好股佔比_增持基金數量'])
pd_result = pd_result.sort_values(by='加權好股佔比_增持市值',ascending=False)
pd_result = pd.merge(pd_result,stock_funds,how='inner',on='基金簡稱')
# In[]:
pd_result.to_csv("./基金持好股狀況統計.csv", encoding="utf_8_sig")
print('完成！按任意鍵退出！')
stop = input()
使用以往的數據作個測試驗證，以下：
從上圖可看出，用個人基金選擇策略，選出來的基金一個月漲跌爲 15 個點，兩個指數基金翻車，只有百分之五，勉強跑得贏上證。
「風險越高，收益越高」老是不變的鐵律，從這個角度來看，彷佛就沒必要糾結於哪一種方案或者策略收益是最高的，差很少就好了。
在這裏推薦下個人Python開發學習羣:883888997，羣裏都是學Python開發的，若是你想學或者正在學習Python ，歡迎你加入，你們都是軟件開發黨，不按期分享乾貨（只有Python軟件開發相關的），包括我本身整理的一份最新的Python進階資料和高級開發教程，歡迎進階中和進想深刻Python的小夥伴！
免責聲明：本文內容來源於網絡，文章版權歸原做者全部，意在傳播相關技術知識&行業趨勢，供你們學習交流，若涉及做品版權問題，請聯繫刪除或受權事宜。
相關文章
- 1. 如何選擇一個好的股票基金？
- 2. 第十六課 如何選擇股票基金？
- 3. 手把手教你Python股票分析
- 4. SPSS數據分析方法不知道如何選擇
- 5. python-股票分析
- 6. 【量化】python選擇成長型股票
- 7. python股票分析程序
- 8. Python 股票分析入門
- 9. 金融與量化分析 一; 金融 股票知識入門
- 10. 實戰 | 你知道如何用python獲取股票交易數據嗎？
- 更多相關文章...
- • XSD 如何使用? - XML Schema 教程
- • 如何僞造ARP響應？ - TCP/IP教程
- • 算法總結-股票買賣
- • Git五分鐘教程
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. 如何選擇一個好的股票基金？
- 2. 第十六課 如何選擇股票基金？
- 3. 手把手教你Python股票分析
- 4. SPSS數據分析方法不知道如何選擇
- 5. python-股票分析
- 6. 【量化】python選擇成長型股票
- 7. python股票分析程序
- 8. Python 股票分析入門
- 9. 金融與量化分析 一; 金融 股票知識入門
- 10. 實戰 | 你知道如何用python獲取股票交易數據嗎？