使用python时如何考虑周末和假日

我试图每月格式化此数据，但以当月的当前日期为准

import pandas as pd
import datetime
import quandl
import numpy as np

start = datetime.datetime(1993, 10, 2)
end = datetime.date.today()

df = quandl.get("FRED/DGS20", collapse="daily").reset_index()
df.index=np.arange(0,len(df))

print (df)

l=[]
for i in range(0,len(df)):
    if (df['DATE'].loc[i]).day == (df['DATE'].loc[len(df)-1]).day:
        l.append(df['DATE'].loc[i])

---

我遇到的问题是，如果这个日期是在周末或假日，它会跳过这个月。如果给定的日期为N/A，如何让python选择一个月中最接近的适用日期？

有点长，但没有for循环！在您的

df.index=np.arange（0，len（df））

行后插入我的代码：

years = pd.DatetimeIndex(df['DATE']).year
years_u = np.unique(years)
years_u_norm = years_u - years_u[0]
months = pd.DatetimeIndex(df['DATE']).month
months_u = np.unique(months)
months_u_norm = months_u - months_u[0]
days = pd.DatetimeIndex(df['DATE']).day
days_u = np.unique(days)
days_u_norm = days_u - days_u[0]
shp = (years_u_norm[-1]+1, months_u_norm[-1]+1, days_u_norm[-1]+1)
mat = np.full(shp, np.nan).ravel()

y_ind = years - years_u[0]
m_ind = months - months_u[0]
d_ind = days - days_u[0]
inds = np.vstack([y_ind[np.newaxis], m_ind[np.newaxis], d_ind[np.newaxis]])

inds2 = np.ravel_multi_index(inds, shp)
inds_grid = np.indices(shp)[2].ravel()
mat[inds2] = inds_grid[inds2]
start_ind = np.ravel_multi_index([[start.year - years_u[0]], [start.month - months_u[0]], [start.day - days_u[0]]], shp)
mat[:start_ind] = np.inf
end_ind = np.ravel_multi_index([[end.year - years_u[0]], [end.month - months_u[0]], [end.day - days_u[0] + 1]], shp)
mat[end_ind:] = np.inf

mat = mat.reshape(shp)
dist = np.absolute(mat - np.full(shp, end.day-1))

min_dist = np.nanargmin(dist, axis=2) + 1
inds_f = np.unique(np.ravel_multi_index(inds[:-1, :], shp[:-1]))
res_inds = np.indices(min_dist.shape)
res_y = res_inds[0].ravel()[inds_f] + years_u[0]
res_m = res_inds[1].ravel()[inds_f] + months_u[0]
res_d = min_dist.ravel()[inds_f]

df = pd.DataFrame({'year': res_y,
                   'month': res_m,
                   'day': res_d})
print(df)

---

有点长，但没有循环！在您的

df.index=np.arange（0，len（df））

行后插入我的代码：

years = pd.DatetimeIndex(df['DATE']).year
years_u = np.unique(years)
years_u_norm = years_u - years_u[0]
months = pd.DatetimeIndex(df['DATE']).month
months_u = np.unique(months)
months_u_norm = months_u - months_u[0]
days = pd.DatetimeIndex(df['DATE']).day
days_u = np.unique(days)
days_u_norm = days_u - days_u[0]
shp = (years_u_norm[-1]+1, months_u_norm[-1]+1, days_u_norm[-1]+1)
mat = np.full(shp, np.nan).ravel()

y_ind = years - years_u[0]
m_ind = months - months_u[0]
d_ind = days - days_u[0]
inds = np.vstack([y_ind[np.newaxis], m_ind[np.newaxis], d_ind[np.newaxis]])

inds2 = np.ravel_multi_index(inds, shp)
inds_grid = np.indices(shp)[2].ravel()
mat[inds2] = inds_grid[inds2]
start_ind = np.ravel_multi_index([[start.year - years_u[0]], [start.month - months_u[0]], [start.day - days_u[0]]], shp)
mat[:start_ind] = np.inf
end_ind = np.ravel_multi_index([[end.year - years_u[0]], [end.month - months_u[0]], [end.day - days_u[0] + 1]], shp)
mat[end_ind:] = np.inf

mat = mat.reshape(shp)
dist = np.absolute(mat - np.full(shp, end.day-1))

min_dist = np.nanargmin(dist, axis=2) + 1
inds_f = np.unique(np.ravel_multi_index(inds[:-1, :], shp[:-1]))
res_inds = np.indices(min_dist.shape)
res_y = res_inds[0].ravel()[inds_f] + years_u[0]
res_m = res_inds[1].ravel()[inds_f] + months_u[0]
res_d = min_dist.ravel()[inds_f]

df = pd.DataFrame({'year': res_y,
                   'month': res_m,
                   'day': res_d})
print(df)