Text files¶
Opening files¶
To open file a text file, use the with statement. It allows to insure that the file is properly opened and properly closed, even if an error is encountered (see the-with-statement for a detailed description).
# defining the name of the file to read
filename = 'data/nao.txt'
with open(filename,'r') as f:
print(f.closed)
print(f.closed)
False
True
Reading¶
# read all the lines and store them in a list
with open(filename,'r') as f:
lines = f.readlines()
print(len(lines))
print('@%s@' %lines[0])
print('#%s#' %lines[0].strip()) # removes the \n char
122
@ Hurrell PC-Based North Atlantic Oscillation Index (DJFM)
@
#Hurrell PC-Based North Atlantic Oscillation Index (DJFM)#
# Read all the file and store as 1 string
with open(filename,'r') as f:
data = f.read()
print(len(data))
print(data[:10])
1994
Hurrell P
# Read the first 200 chars of the file and store as 1 string
with open(filename,'r') as f:
data = f.read(200)
print(len(data))
print(data)
200
Hurrell PC-Based North Atlantic Oscillation Index (DJFM)
1899. -0.69
1900. -1.32
1901. -0.37
1902. -0.69
1903. 1.33
1904. -0.01
1905. 0.83
1906. 0.83
1907. 1.1
# loop over all the lines of the file, and extract the first one
# finishes when "end of line is found"
with open(filename,'r') as f:
for line in f:
print(line.strip())
Hurrell PC-Based North Atlantic Oscillation Index (DJFM)
1899. -0.69
1900. -1.32
1901. -0.37
1902. -0.69
1903. 1.33
1904. -0.01
1905. 0.83
1906. 0.83
1907. 1.11
1908. 0.56
1909. -0.50
1910. 0.43
1911. 0.47
1912. -0.43
1913. 1.40
1914. 0.47
1915. -0.70
1916. -0.22
1917. -1.18
1918. 0.03
1919. -0.87
1920. 1.58
1921. 0.69
1922. 0.59
1923. 0.36
1924. -0.65
1925. 1.09
1926. -0.31
1927. 0.50
1928. 0.16
1929. -0.59
1930. 0.42
1931. -0.68
1932. -0.09
1933. -0.10
1934. 0.97
1935. 0.07
1936. -1.94
1937. -0.15
1938. 0.54
1939. -0.13
1940. -1.94
1941. -1.23
1942. -1.07
1943. 0.62
1944. 0.52
1945. -0.08
1946. -0.27
1947. -1.86
1948. 0.26
1949. 1.02
1950. 0.48
1951. -0.93
1952. -0.14
1953. -0.01
1954. 0.15
1955. -1.25
1956. -1.04
1957. 0.04
1958. -1.26
1959. 0.10
1960. -1.81
1961. 0.74
1962. -0.92
1963. -1.29
1964. -0.88
1965. -0.81
1966. -1.56
1967. 0.62
1968. -0.15
1969. -2.57
1970. -1.15
1971. -0.66
1972. 0.12
1973. 1.20
1974. 0.37
1975. 0.74
1976. 1.22
1977. -1.34
1978. -0.55
1979. -1.44
1980. -0.35
1981. 0.29
1982. -0.21
1983. 1.29
1984. 0.43
1985. -0.80
1986. -0.01
1987. -0.66
1988. -0.17
1989. 2.46
1990. 1.91
1991. 0.56
1992. 1.76
1993. 1.76
1994. 0.87
1995. 1.29
1996. -1.44
1997. 0.71
1998. -0.01
1999. 0.66
2000. 1.61
2001. -1.01
2002. 0.62
2003. 0.05
2004. -0.12
2005. 0.36
2006. -0.90
2007. 1.16
2008. 1.06
2009. 0.04
2010. -2.57
2011. -0.68
2012. 1.60
2013. -1.68
2014. 0.91
2015. 1.87
2016. 1.00
2017. 0.89
2018. -0.16
2019. 0.76
# to parse a certain range of the file, one
# way is to use the itertools package
import itertools
with open(filename,'r') as f:
for line in itertools.islice(f, 5, 10):
print(line.strip())
1903. 1.33
1904. -0.01
1905. 0.83
1906. 0.83
1907. 1.11
Writting¶
Files are written out line by line.
# Generates some data
import numpy as np
xdata = np.linspace(0, np.pi/4., 5)
cosx = np.cos(xdata)
sinx = np.sin(xdata)
tanx = np.tan(xdata)
# opening the file
with open('data/outfile.txt', 'w') as fout:
# writting the header: 4 strings separated by tabs.
header = ['x', 'cos', 'sin', 'tan']
string='%s\t%s\t%s\t%s\n' % (header[0], header[1], header[2], header[3]) # writes the header
print(string)
fout.write(string)
# looping over all the data
for x, c, s, t in zip(xdata, cosx, sinx, tanx):
# writting the string associated with the data
string = '%.4f\t%.8f\t%.8f\t%.8f\n' %(x, c, s, t) # writes the data
print(string)
fout.write(string)
x cos sin tan
0.0000 1.00000000 0.00000000 0.00000000
0.1963 0.98078528 0.19509032 0.19891237
0.3927 0.92387953 0.38268343 0.41421356
0.5890 0.83146961 0.55557023 0.66817864
0.7854 0.70710678 0.70710678 1.00000000