Steboss89

def create_heatmap(similarity, cmap = "YlGnBu"):
    df = pd.DataFrame(similarity)
    df.columns = ['john', 'luke','mark', 'matt'] #ohn 0 mark 2 matt 3 luke 1
    df.index = ['john', 'luke','mark', 'matt']
    fig, ax = plt.subplots(figsize=(5,5))
    sns.heatmap(df, cmap=cmap)

from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import CountVectorizer
import seaborn as sns 

Steboss89

def get_word_frequencies(text):
    r""" This function return a Counter with the most common words
    in a given text
    
    Parameters
    ----------
    text: df['text'].tolist()
    
    Return 
    ------

Steboss89

# use the documents' list as a column in a dataframe 
df = pd.DataFrame(data, columns=["text"]) 


def get_word2vec(text): 
    r"""
    Parameters
    -----------
    text: str, text from dataframe, df['text'].tolist()"""
    num_workers = multiprocessing.cpu_count()

Steboss89

def format_topics_sentences(ldamodel, corpus):
    r"""This function associate to each review the dominant topic
    Parameters
    ----------
    lda_model:      gensim lda_model
                    The current lda model calculated

    corpus:         gensim corpus
                    this is the corpus from the reviews

Steboss89

def format_topics_sentences(ldamodel, corpus):
    r"""This function associate to each review the dominant topic
    Parameters
    ----------
    lda_model:      gensim lda_model
                    The current lda model calculated

    corpus:         gensim corpus
                    this is the corpus from the reviews

Steboss89

Steboss89

Steboss89

Old Testament, New Testament 
beauty, angles, 
families, apostles/disciples
cattles, baptized
cubits, charity
convenant, cross/cruficied
valiant, faith

Steboss89

def normcdf(x):
    return norm.cdf(x, x.mean(), x.std())

# compute the rate of a word: word_occurrence_old_test/total
term_freq_df.loc[:,'old_rate'] = term_freq_df[0] * 1./term_freq_df['total']
# rate the word appear in a class, in this case old testament word_occurrence_old_test/total_old_test
term_freq_df.loc[:,'old_freq_pct'] = term_freq_df[0] * 1./term_freq_df[0].sum()
# combine the total rate and the class rate with the harmonic mean, to weight over most unique and specific words
term_freq_df.loc[:,'old_hmean'] = term_freq_df.apply(lambda x: (hmean([x['old_rate'], x['old_freq_pct']]) if x['old_rate'] > 0 and x['old_freq_pct'] > 0 else 0), axis=1)
# where old_rate or old_freq_pct lies in the distribution in terms of cumulative manner. 

Steboss89