010.py

path = "popular-names.txt"
with open(path) as file:
    print(len(file.readlines()))

# -> 2700

I used the with block because it was tedious to writeclose ()at the end of the file operation.

011.py

path = "popular-names.txt"
with open(path) as file:
     print(file.read().replace("\t", " "), end="")

# -> Mary F 7065 1880 
#    Anna F 2604 1880 
#    Emma F 2003 1880 ...

012.py

path = "popular-names.txt"
path_col1 = "col1_012.txt"
path_col2 = "col2_012.txt"

with open(path) as file:
    with open(path_col1, mode="w") as col1:
        with open(path_col2, mode="w") as col2:
           item_split = [item.split("\t") for item in file.readlines()]
           for item in item_split:
               col1.write(item[0] + "\n")
               col2.write(item[1] + "\n")

# col1.txt
# -> Mary
#    Anna...
# col2.txt
# -> F
#    F...

The operation of the file is specified by mode of ʻopen (). The default is mode ='r'`, but you should write it properly without omitting it ...?

013.py

path_col1 = "col1_012.txt"
path_col2 = "col2_012.txt"
path_merge = "merge.txt"

with open(path_col1) as col1:
    col1_list = col1.readlines()
    with open(path_col2) as col2:
        col2_list = col2.readlines()
        with open(path_merge, mode="w") as mrg:
            for i in range(len(col1_list)):
                mrg.write(col1_list[i].replace("\n", "") + "\t" + col2_list[i])

# merge.txt
# -> Mary	F
#    Anna	F
#    Emma	F

The other person's answer used zip () to generate it. With this answer, I'm in trouble when len (col1_list)> len (col2_list), and that is smarter.

014.py

import sys

N = int(sys.argv[2])
with open(sys.argv[1]) as file:
    for i in range(N):
        print(file.readline().replace("\n",""))

# python 014.py popular-names.txt 3
# -> Mary    F       7065    1880
#    Anna    F       2604    1880
#    Emma    F       2003    1880

It seems that you can get a list with command line arguments by using the ʻargvfunction of thesys` module.

015.py

import pandas as pd

path = "popular-names.txt"
df = pd.read_table(path, header=None)
print(df.tail())

# ->              0  1      2     3
#    2775  Benjamin  M  13381  2018
#    2776    Elijah  M  12886  2018
#    2777     Lucas  M  12585  2018
#    2778     Mason  M  12435  2018
#    2779     Logan  M  12352  2018

For those who know it, it seems like it's new, but it seems that there is a library called pandas that is convenient for data processing, so I tried using it. read_csv (path, sep =" \ t ") was fine, but read_table is simple, isn't it?

016.py

import pandas as pd
import sys

N = int(sys.argv[1])
path = "popular-names.txt"
df = pd.read_table(path, header=None)
col_n = -(-len(df) // N)
for i in range(N):
    print(df.iloc[col_n * i : col_n * (i + 1), :])

# python 016.py 2
# ->               0  1      2     3
#    0          Mary  F   7065  1880
#    1          Anna  F   2604  1880
#    ...         ... ..    ...   ...
#    1389     Sharon  F  25711  1949
#
#    [1390 rows x 4 columns]
#                  0  1      2     3
#     1390     James  M  86857  1949
#     1391    Robert  M  83872  1949
#     ...        ... ..    ...   ...
#     2779     Logan  M  12352  2018
#
#    [1390 rows x 4 columns]

For the output, I used ʻiloc because I want to specify multiple lines of df` by index.

017.py

import pandas as pd

path = "popular-names.txt"
df = pd.read_table(path, header=None)
print(df[0].unique())

# -> ['Mary' 'Anna' 'Emma' 'Elizabeth' 'Minnie' 'Margaret' 'Ida' 'Alice'...

ʻUnique ()returns the value of a unique element as a NumPyndarraytype. The number of unique elements can be obtained bydf [0] .nunique ()in addition tolen (df [0] .unique ())`.

018.py

import pandas as pd

path = "popular-names.txt"
df = pd.read_table(path, header=None)
print(df.sort_values(2, ascending=False))

# ->            0  1      2     3
#   1340    Linda  F  99689  1947
#   1360    Linda  F  96211  1948
#   1350    James  M  94757  1947...

019.py

import pandas as pd

path = "popular-names.txt"
df = pd.read_table(path, header=None)
print(df[0].value_counts())

# -> James      118
#    William    111
#    John       108

value_counts outputs unique elements and their number as pandas.Series type. It's confusing that ʻunique ()shows a list of unique elements,nunique ()shows the total number of unique elements, andvalue_counts ()` shows the frequency of each element.