数学建模处理数据

浅浅的花香味﹌ 2022-06-14 00:59 317阅读 0赞

import pandas as pd
    import numpy as np
    d1 = []
    df4 = []
    a = []
    b = []
    i = 0
    data = pd.read_excel('jijin.xlsx', header=0)
    d5 = data['NAV']
    with open('sharp.txt','r') as f:
        lines = f.readlines()
    
    def statistics(f,ord,data):
        s = f
        x = ord
        while f == s:
            if ord == len(data['Symbol']):
                return ord-x
            f = data['Symbol'][ord]
            ord += 1
        return ord-1-x
    
    while i < len(data['Symbol']):
        num = statistics(data['Symbol'][i],i,data)
        print 'num : ',num
        df4.append(num)
        j = 0
        m = 0
        while j< 3:
            a.append(0)
            j += 1
        while m < 3:
            b.append(0)
            m += 1
        i += 3
        s = i
        while i < s+num - 6:
            d2 = []
            for x in [-3,-2,-1,0,1,2,3]:
                d2.append(d5[i+x])
            d2 = np.array(d2)
            d3 = np.max(d2)
            d4 = np.min(d2)
            if d3 == d5[i] or d4 == d5[i]:
                a.append(1),b.append(0)
            else:
                a.append(0),b.append(1)
            i +=1
        j = 0
        m = 0
        while j< 3:
            a.append(0)
            j += 1
        while m < 3:
            b.append(0)
            m += 1
        i +=3
    
    def search(s,lines):
        for da in lines:
            d = da.split(',')
            i = int(d[0])
            if s == i:
                return d[1]
    
    s = 0
    for c in data['Symbol']:
        if c == s:
            d1.append(float(e))
        else:
            e = search(c,lines)
            d1.append(float(e))
            s = c
    l = len(df4)
    df1 = pd.DataFrame(a,index = np.arange(len(data['Symbol'])),columns = ['a'] )
    df2 = pd.DataFrame(b,index = np.arange(len(data['Symbol'])),columns = ['b'] )
    df3 = pd.DataFrame(d1,index = np.arange(len(data['Symbol'])),columns = ['sharp'] )
    df4 = pd.DataFrame(df4,index = np.arange(l),columns = ['numbers'] )
    data.insert(5,'a',df1)
    data.insert(6,'b',df2)
    data.insert(7,'sharp',df3)
    data.insert(8,'numbers',df4)
    data.to_excel('test_add10.xlsx')