Answers for "file reading in python"

python read file line by line

with open("file.txt") as file_in:
    lines = []
    for line in file_in:
        lines.append(line)

python read file

with open("file.txt", "r") as txt_file:
  return txt_file.readlines()

python read file

# Basic syntax:
with open('/path/to/filename.extension', 'open_mode') as filename:
  file_data = filename.readlines()	# Or filename.read() 
# Where:
#	- open imports the file as a file object which then needs to be read
#		with one of the read options
#	- readlines() imports each line of the file as an element in a list
#	- read() imports the file contents as one long new-line-separated 
#		string
#	- open_mode can be one of:
#		- "r" = Read which opens a file for reading (error if the file 
#			doesn't exist)
#		- "a" = Append which opens a file for appending (creates the 
#			file if it doesn't exist)
#		- "w" = Write which opens a file for writing (creates the file 
#			if it doesn't exist)
#		- "x" = Create which creates the specified file (returns an error
#			if the file exists)
# Note, "with open() as" is recommended because the file is closed 
#	automatically so you don't have to remember to use file.close()

# Basic syntax for a delimited file with multiple fields:
import csv
with open('/path/to/filename.extension', 'open_mode') as filename:
	file_data = csv.reader(filename, delimiter='delimiter')
    data_as_list = list(file_data)
# Where:
#	- csv.reader can be used for files that use any delimiter, not just
#		commas, e.g.: '\t', '|', ';', etc. (It's a bit of a misnomer)
#	- csv.reader() returns a csv.reader object which can be iterated 
#		over, directly converted to a list, and etc. 

# Importing data using Numpy:
import numpy as np
data = np.loadtxt('/path/to/filename.extension',
				delimiter=',', 	# String used to separate values
				skiprows=2, 	# Number of rows to skip
				usecols=[0,2], 	# Specify which columns to read
				dtype=str) 		# The type of the resulting array

# Importing data using Pandas:
import pandas as pd
data = pd.read_csv('/path/to/filename.extension',
				nrows=5, 		# Number of rows of file to read
				header=None, 	# Row number to use as column names 
	            sep='\t', 		# Delimiter to use 
	            comment='#', 	# Character to split comments
				na_values=[""])	# String to recognize as NA/NaN

# Note, pandas can also import excel files with pd.read_excel()

open text file in python

f=open("Diabetes.txt",'r')
f.read()

python open file

with open('filename', 'a') as f: # able to append data to file
	f.write(var1) # Were var1 is some variable you have set previously
	f.write('data') 
	f.close() # You can add this but it is not mandatory 

with open('filename', 'r') as f: # able to read data from file ( also is the default mode when opening a file in python)

with open('filename', 'x') as f: # Creates new file, if it already exists it will cause it to fail

with open('filename', 't') as f: # opens the file in text mode (also is defualt)

with open('filename', 'b') as f: # Use if your file will contain binary data
  
with open('filename', 'w') as f: # Open file with ability to write, will also create the file if it does not exist (if it exists will cause it to fail)
  
with open('filename', '+') as f: # Opens file with reading and writing

# You can combine these as you like with the + for reading and writing

read file python

document = 'document.txt'
file = open(document, 'r')
# 'r' to read.  it can be replaced with:
# 'w' to write (overwrite)
# 'a' to append (add to the end)
# 'w+' makes a new file if one does not already exist of that name
# 'a+' same as 'w+' but appends if the file does exist
# 'x' creates file for writing, but fails if file already exists

##go to beginning of document. not required but good for consistency.
file.seek(0)

##print all lines in document, except empty lines:
for line in file:
    k = line.strip() 
    print k

##close the file after you are done
file.close()


##this also works to open a file, and is more error proof:
with open(document) as filestream:
    for i in filestream:
        k = i.strip() 
        print k