I am working with a dataset available form Kaggle's website. It contains data on exoplanets. The code:

import pandas as pd
import numpy as np

df = pd.read_csv('oec.csv')
#get rid of rows where surrface temp is null, isfinite() returns true if finite and not NaN
df=df[np.isfinite(df['SurfaceTempK'])]
#remove all rows where surface temp <= 273K
df=df.drop(df[df.SurfaceTempK < 274].index)
#remove all rows where surface temp >= 373K
df=df.drop(df[df.SurfaceTempK > 372].index)
#remove unecessary columns from dataframe, in the case where you want to drop multiple columns pass 
#in a list as the first parameter
df=df.drop(['DiscoveryMethod', 'DiscoveryYear'], axis=1)
​#write out the dataframe to a csv file
df.to_csv('output.csv')

n-gram definition: an n-gram is a contigious sequence of n items from a given sequence of text or speech (Wikipedia)

For example: Given the following sentence:

The summer is almost over.

The bigrams (or 2-grams) are: (The summer), (summer is), (is almost), (almost over)

The following code takes a short piece of text scraped from wikipedia and calculates the distribution frequencies for individual words, 2-grams and 3-grams

import re
from nltk import word_tokenize
from nltk import Text
from nltk import FreqDist
from nltk import ngrams

ip_file = open('pogues.txt', 'r')
ip_file = ip_file.readlines()

content = ''
for sent in ip_file:
    sent = (re.sub(' \n+', " ", str(sent).lower()))
    sent = (re.sub(',', "", sent))
    sent = (re.sub('\.', "", sent))           
    content = content + sent

tokens = word_tokenize(content)
text = Text(tokens)
fdist = FreqDist(text)
two_grams = ngrams(text,2)
two_grams_dist = FreqDist(two_grams)
three_grams = ngrams(text, 3)
three_grams_dist = FreqDist(three_grams)

print(fdist.most_common(10))
print('*****************')
print(two_grams_dist.most_common(10))
print('*****************')
print(three_grams_dist.most_common(10))

The output from the above code is:

[('the', 12), ('and', 10), ('in', 5), ('band', 5), ('to', 4), ('has', 3), ('macgowan', 3), ('on', 3), ('stacy', 3), ('yet', 2)]
*****************
[(('the', 'band'), 4), (('stacy', 'on'), 2), (('such', 'as'), 2), (('spider', 'stacy'), 2), (('the', 'pogues'), 2), (('shane', 'macgowan'), 1), (('drinking', 'problems'), 1), (('many', 'bands'), 1), (('tin', 'whistle'), 1), (('continued', 'first'), 1)]
*****************
[(('spider', 'stacy', 'on'), 2), (('playing', 'regularly', 'ever'), 1), (('and', 'on', 'the'), 1), (('and', 'has', 'been'), 1), (('macgowan', 'and', 'stacy'), 1), (('in', 'the', '1980s'), 1), (('in', 'late', '2001'), 1), (('reformed', 'in', 'late'), 1), (('politically', 'tinged', 'music'), 1), (('and', 'stacy', "'s"), 1)]