1. Text files

Plain text files

import pandas as pd
import numpy as np

filename = "huck.txt"
file = open(filename,mode="r") #  open the file for reading 
text = file.read() # read file 
file.close()

print(text)


with open("huck.txt","r") as  file:
  print(file.readlne())

table data : Flat file

  1. file with one datatype
data = np.loadtxt(filename,delimiter=",",skiprows=1,usecols=[0,2],dtype=str)
  1. files with mixed datatype
data = np.genfromtxt(fname=filename,delimiter=",",names=True)

data_array = np.recfromcsv(filename)
  1. use pandas
data = pd.read_csv(filename,nrows=5,sep=",",header=1) # header row number to use as names

2 SAS file

from sas7bdat import SAS7BDAT
with SAS7BDAT("data.sas7bdat") as files:
  df_sas = file.to_data_frame()
  
data = pd.read_sas()

3 Stata file

data = pd.read_stata()

4. excel

data = pd.ExcelFile("data.xlsx")

data.sheet_names

data_sheet1 = data.parse(sheetname)

5 …. to be continue