import pandas as pd
import numpy as np
import dateutil
import glob
file_names=glob.glob(“/Users/XXXX/Downloads/XXXX/u*.xlsx”)
combining excel .xlsx files starting with u together
all_data = pd.DataFrame()
for f in glob.glob(“/Users/XXXXX/Downloads/XXXXX/u*.xlsx”):
df = pd.read_excel(f)
all_data = all_data.append(df,ignore_index=True)
all_data.shape
write it to excel
writer = pd.ExcelWriter(‘/Users/XXX/Downloads/file/combined_samples.xlsx’)
all_data.to_excel(writer)
extracting column
a=all_data[[“a”]]
counting unique value in a column
all_data[[“a”]].nunique()
taking unique value in a column
unique_a_list=all_data.a.unique()
write to data frame
df = pd.DataFrame(data=unique_a_list)
write it to excel
writer = pd.ExcelWriter(‘/Users/XXXX/Downloads/files/results.xlsx’)
df.to_excel(writer)