In [4]:
import pandas as pd
import glob
# Path where NPCI Excel files are stored
files = glob.glob("C:/Users/lakshita rawat/Downloads/Excel_file_upi/*.xlsx")
all_data = []
for file in files:
print("Reading:", file) # Check which file is being read
df = pd.read_excel(file)
df["SourceFile"] = file # keep track of origin
all_data.append(df)
# Merge all files
npci = pd.concat(all_data, ignore_index=True)
print("Shape:", npci.shape)
print(npci.head())
# Save merged dataset
npci.to_csv("C:/Users/lakshita rawat/Downloads/Excel_file_upi/npci_upi_stats.csv", index=False)
Reading: C:/Users/lakshita rawat/Downloads/Excel_file_upi\2016-2017, 2017-2018.xlsx
Reading: C:/Users/lakshita rawat/Downloads/Excel_file_upi\2018-19-Monthly.xlsx
Reading: C:/Users/lakshita rawat/Downloads/Excel_file_upi\2019-20-Monthly.xlsx
Reading: C:/Users/lakshita rawat/Downloads/Excel_file_upi\2020-21-Monthly.xlsx
Reading: C:/Users/lakshita rawat/Downloads/Excel_file_upi\2021-22-Monthly.xlsx
Reading: C:/Users/lakshita rawat/Downloads/Excel_file_upi\2022-23-Monthly.xlsx
Reading: C:/Users/lakshita rawat/Downloads/Excel_file_upi\2023-24-Monthly.xlsx
Reading: C:/Users/lakshita rawat/Downloads/Excel_file_upi\2024-25-Monthly.xlsx
Shape: (112, 11)
Unnamed: 0 Unnamed: 1 Unnamed: 2 2017-2018 \
0 NaN NaN Months No. of Banks live on UPI
1 NaN NaN Mar-2018 91
2 NaN NaN Feb-2018 86
3 NaN NaN Jan-2018 71
4 NaN NaN Dec-2017 67
Unnamed: 4 Unnamed: 5 \
0 Volume (In Mn.) Value (In Cr.)
1 178.05 24172.6
2 171.4 19126.2
3 151.83 15571.2
4 145.64 13174.24
SourceFile Month \
0 C:/Users/lakshita rawat/Downloads/Excel_file_u... NaN
1 C:/Users/lakshita rawat/Downloads/Excel_file_u... NaN
2 C:/Users/lakshita rawat/Downloads/Excel_file_u... NaN
3 C:/Users/lakshita rawat/Downloads/Excel_file_u... NaN
4 C:/Users/lakshita rawat/Downloads/Excel_file_u... NaN
No. of Banks live on UPI Volume (In Mn.) Value (In Cr.)
0 NaN NaN NaN
1 NaN NaN NaN
2 NaN NaN NaN
3 NaN NaN NaN
4 NaN NaN NaN