Basic cleaning and n-gram helper functions.

ngram_functions.py

def clean(text):
  """
  A simple function to clean up the data. All the words that
  are not designated as a stop word is then lemmatized after
  encoding and basic regex parsing are performed.
  """
  wnl = nltk.stem.WordNetLemmatizer()
  stopwords = nltk.corpus.stopwords.words('english') + ADDITIONAL_STOPWORDS
  text = (unicodedata.normalize('NFKD', text)
    .encode('ascii', 'ignore')
    .decode('utf-8', 'ignore')
    .lower())
  words = re.sub(r'[^\w\s]', '', text).split()
  return [wnl.lemmatize(word) for word in words if word not in stopwords]

def get_words(df, column):
    """
    Takes in a dataframe and columns and returns a list of
    words from the values in the specified column.
    """
    return clean(''.join(str(df[column].tolist())))

def get_bigrams(df, column):
    """
    Takes in a list of words and returns a series of
    bigrams with value counts.
    """
    return (pd.Series(nltk.ngrams(get_words(df, column), 2)).value_counts())[:10]

def get_trigrams(df, column):
    """
    Takes in a list of words and returns a series of
    trigrams with value counts.
    """
    return (pd.Series(nltk.ngrams(get_words(df, column), 3)).value_counts())[:10]

def viz_bigrams(df ,column):
    get_bigrams(df, column).sort_values().plot.barh(color='blue', width=.9, figsize=(12, 8))

    plt.title('20 Most Frequently Occuring Bigrams')
    plt.ylabel('Bigram')
    plt.xlabel('# Occurances')

def viz_trigrams(df, column):
    get_trigrams(df, column).sort_values().plot.barh(color='blue', width=.9, figsize=(12, 8))

    plt.title('20 Most Frequently Occuring Trigrams')
    plt.ylabel('Trigram')
    plt.xlabel('# Occurances')