#!/usr/bin/env python
# coding: utf-8

# # Import necessary dependencies and settings

# In[1]:


import pandas as pd
import numpy as np
import re
import nltk


# # Sample corpus of text documents

# In[2]:


corpus = ['The sky is blue and beautiful.',
          'Love this blue and beautiful sky!',
          'The quick brown fox jumps over the lazy dog.',
          'The brown fox is quick and the blue dog is lazy!',
          'The sky is very blue and the sky is very beautiful today',
          'The dog is lazy but the brown fox is quick!'    
]
labels = ['weather', 'weather', 'animals', 'animals', 'weather', 'animals']
corpus = np.array(corpus)
corpus_df = pd.DataFrame({'Document': corpus, 
                          'Category': labels})
corpus_df = corpus_df[['Document', 'Category']]
corpus_df


# # Simple text pre-processing

# In[3]:


wpt = nltk.WordPunctTokenizer()
stop_words = nltk.corpus.stopwords.words('english')

def normalize_document(doc):
    # lower case and remove special characters\whitespaces
    doc = re.sub(r'[^a-zA-Z0-9\s]', '', doc, re.I)
    doc = doc.lower()
    doc = doc.strip()
    # tokenize document
    tokens = wpt.tokenize(doc)
    # filter stopwords out of document
    filtered_tokens = [token for token in tokens if token not in stop_words]
    # re-create document from filtered tokens
    doc = ' '.join(filtered_tokens)
    return doc

normalize_corpus = np.vectorize(normalize_document)


# In[4]:


norm_corpus = normalize_corpus(corpus)
norm_corpus


# # Bag of Words Model

# In[5]:


from sklearn.feature_extraction.text import CountVectorizer

cv = CountVectorizer(min_df=0., max_df=1.)
cv_matrix = cv.fit_transform(norm_corpus)
cv_matrix = cv_matrix.toarray()
cv_matrix


# In[6]:


vocab = cv.get_feature_names()
pd.DataFrame(cv_matrix, columns=vocab)


# # Bag of N-Grams Model

# In[7]:


bv = CountVectorizer(ngram_range=(2,2))
bv_matrix = bv.fit_transform(norm_corpus)
bv_matrix = bv_matrix.toarray()
vocab = bv.get_feature_names()
pd.DataFrame(bv_matrix, columns=vocab)


# # TF-IDF Model

# In[8]:


from sklearn.feature_extraction.text import TfidfVectorizer

tv = TfidfVectorizer(min_df=0., max_df=1., use_idf=True)
tv_matrix = tv.fit_transform(norm_corpus)
tv_matrix = tv_matrix.toarray()

vocab = tv.get_feature_names()
pd.DataFrame(np.round(tv_matrix, 2), columns=vocab)


# # Document Similarity

# In[9]:


from sklearn.metrics.pairwise import cosine_similarity

similarity_matrix = cosine_similarity(tv_matrix)
similarity_df = pd.DataFrame(similarity_matrix)
similarity_df


# ## Clustering documents using similarity features

# In[10]:


from sklearn.cluster import KMeans

km = KMeans(n_clusters=2)
km.fit_transform(similarity_df)
cluster_labels = km.labels_
cluster_labels = pd.DataFrame(cluster_labels, columns=['ClusterLabel'])
pd.concat([corpus_df, cluster_labels], axis=1)


# # Topic models

# In[11]:


from sklearn.decomposition import LatentDirichletAllocation

lda = LatentDirichletAllocation(n_topics=2, max_iter=100, random_state=42)
dt_matrix = lda.fit_transform(tv_matrix)
features = pd.DataFrame(dt_matrix, columns=['T1', 'T2'])
features


# ## Show topics and their weights

# In[12]:


tt_matrix = lda.components_
for topic_weights in tt_matrix:
    topic = [(token, weight) for token, weight in zip(vocab, topic_weights)]
    topic = sorted(topic, key=lambda x: -x[1])
    topic = [item for item in topic if item[1] > 0.6]
    print(topic)
    print()


# ## Clustering documents using topic model features

# In[13]:


km = KMeans(n_clusters=2)
km.fit_transform(features)
cluster_labels = km.labels_
cluster_labels = pd.DataFrame(cluster_labels, columns=['ClusterLabel'])
pd.concat([corpus_df, cluster_labels], axis=1)


# # Word Embeddings

# In[14]:


from gensim.models import word2vec

wpt = nltk.WordPunctTokenizer()
tokenized_corpus = [wpt.tokenize(document) for document in norm_corpus]

# Set values for various parameters
feature_size = 10    # Word vector dimensionality  
window_context = 10          # Context window size                                                                                    
min_word_count = 1   # Minimum word count                        
sample = 1e-3   # Downsample setting for frequent words

w2v_model = word2vec.Word2Vec(tokenized_corpus, size=feature_size, 
                          window=window_context, min_count = min_word_count,
                          sample=sample)


# In[15]:


w2v_model.wv['sky']


# In[16]:


def average_word_vectors(words, model, vocabulary, num_features):
    
    feature_vector = np.zeros((num_features,),dtype="float64")
    nwords = 0.
    
    for word in words:
        if word in vocabulary: 
            nwords = nwords + 1.
            feature_vector = np.add(feature_vector, model[word])
    
    if nwords:
        feature_vector = np.divide(feature_vector, nwords)
        
    return feature_vector
    
   
def averaged_word_vectorizer(corpus, model, num_features):
    vocabulary = set(model.wv.index2word)
    features = [average_word_vectors(tokenized_sentence, model, vocabulary, num_features)
                    for tokenized_sentence in corpus]
    return np.array(features)


# In[17]:


w2v_feature_array = averaged_word_vectorizer(corpus=tokenized_corpus, model=w2v_model,
                                             num_features=feature_size)
pd.DataFrame(w2v_feature_array)


# In[18]:


from sklearn.cluster import AffinityPropagation

ap = AffinityPropagation()
ap.fit(w2v_feature_array)
cluster_labels = ap.labels_
cluster_labels = pd.DataFrame(cluster_labels, columns=['ClusterLabel'])
pd.concat([corpus_df, cluster_labels], axis=1)