I have two csv files from which I have created a single dataframe. Problem is first it adds data of 'Tatasteel' first and then data of 'Tatamotors'. What I want is to order them according to date. For example, first data of Tatasteel at 9:15 and then data of Tatamotors at 9:15 and so on.
Here is the code:
import pandas as pd
import datetime as dt
from datetime import timedelta
import os
import glob
exclude_days = [dt.datetime(2019, 1, 5), dt.datetime(2019, 1, 6), dt.datetime(2019, 1, 12), dt.datetime(2019, 1, 13), dt.datetime(2019, 1, 19), dt.datetime(2019, 1, 20),
dt.datetime(2019, 1, 26), dt.datetime(2019, 1, 27) ]
backtest_start = dt.datetime(2019, 1, 1)
backtest_end = dt.datetime(2019, 1, 2)
path = os.getcwd()
path = os.path.join(path,"2019/*")
dat=[]
data3 =[]
stock_list = glob.glob(path)
for stock in stock_list:
rdata= pd.read_csv(stock, parse_dates=['Date'])
dat.append(rdata)
data = pd.concat(dat, ignore_index=True)
curr_day = backtest_start
while curr_day < backtest_end:
if curr_day not in exclude_days:
day_start = dt.datetime(curr_day.year,curr_day.month,curr_day.day, 9, 15)
day_end = dt.datetime(curr_day.year,curr_day.month,curr_day.day, 15, 15)
data2 = data[data['Date'].between(day_start,day_end)]
data2 = data2.reset_index(drop=True)
data2 = pd.DataFrame(data2)
print(data2)
curr_day += timedelta(days=1)