使用 AWS Media Intelligence 和 Hugging Face BERT 构建基于分类的上下文定位

def prepare_taxonomy(taxonomy_df):
    
    """
    Concatenate IAB Tech Lab content taxonomy tiers and prepare keywords for BERT embedding. 
    Use this function as-is if using the IAB Content Taxonomy
    
    Parameters (input):
    ----------
    taxonomy_df : Content taxonomy dataframe

    Returns (output):
    -------
    df_clean : Content taxonomy with tiers in the taxonomy concatenated
    keyword_list: List of concatenated content taxonomy keywords
    ids: List of ids for the content taxonomy keywords
    """
    
    df = taxonomy_df[['Unique ID ','Parent','Name','Tier 1','Tier 2','Tier 3']] 
    df_str = df.astype({"Unique ID ": 'str', "Parent": 'str', "Tier 1": 'str', "Tier 2": 'str', "Tier 3": 'str'})
    df_clean = df_str.replace('nan','')
    
    #create a column that concatenates all tiers for each taxonomy keyword
    df_clean['combined']=df_clean[df_clean.columns[2:6]].apply(lambda x: ' '.join(x.dropna().astype(str)),axis=1)
    
    #turn taxonomy keyords to list of strings a prep for encoding with BERT sentence transformer
    keyword_list=df_clean['combined'].to_list()
                       
    #get list of taxonomy ids
    ids = df_clean['Unique ID '].to_list()                  
            
    return df_clean, keyword_list, ids

taxonomy_df, taxonomy_terms, taxonomy_ids = prepare_taxonomy(read_taxonomy)

def compute_coherence_scores(dictionary, corpus, texts, limit, start=2, step=3):
    """
    Compute coherence scores for various number of topics for your topic model. 
    Adjust the parameters below based on your data

    Parameters (input):
    ----------
    dictionary : Gensim dictionary created earlier from input texts
    corpus : Gensim corpus created earlier from input texts
    texts : List of input texts
    limit : The maximum number of topics to test. Amazon Comprehend can detect up to 100 topics in a collection

    Returns (output):
    -------
    models : List of LDA topic models
    coherence_scores : Coherence values corresponding to the LDA model with respective number of topics
    """
    coherence_scores = []
    models = []
    for num_topics in range(start, limit, step):
        model = gensim.models.LdaMulticore(corpus=corpus, num_topics=num_topics, id2word=id2word)
        models.append(model)
        coherencemodel = CoherenceModel(model=model, texts=corpus_words, dictionary=id2word, coherence='c_v')
        coherence_scores.append(coherencemodel.get_coherence())

    return models, coherence_scores

models, coherence_scores = compute_coherence_scores(dictionary=id2word, corpus=corpus_tdf, texts=corpus_words, start=2, limit=100, step=3)

"""
Create a function to extract object labels from a given image using Amazon Rekognition
"""

def get_image_labels(image_loc):
    labels = []
    with fs.open(image_loc, "rb") as im:
        response = rekognition_client.detect_labels(Image={"Bytes": im.read()})
    
    for label in response["Labels"]:
        if label["Confidence"] >= 60:   #change to desired confidence score threshold, value between [0,100]:
            object_label = label["Name"]
            labels.append(object_label)
    return labels

def compute_similarity(entity_embeddings, entity_terms, taxonomy_embeddings, taxonomy_terms):
    """
    Compute cosine scores between entity embeddings and taxonomy embeddings
    
    Parameters (input):
    ----------
    entity_embeddings : Embeddings for either topic keywords from Amazon Comprehend or image labels from Amazon Rekognition
    entity_terms : Terms for topic keywords or image labels
    taxonomy_embeddings : Embeddings for the content taxonomy
    taxonomy_terms : Terms for the taxonomy keywords

    Returns (output):
    -------
    mapping_df : Dataframe that matches each entity keyword to each taxonomy keyword and their cosine similarity score
    """
    
    #calculate cosine score, pairing each entity embedding with each taxonomy keyword embedding
    cosine_scores = util.pytorch_cos_sim(entity_embeddings, taxonomy_embeddings)
    pairs = []
    for i in range(len(cosine_scores)-1):
        for j in range(0, cosine_scores.shape[1]):
            pairs.append({'index': [i, j], 'score': cosine_scores[i][j]})
    
    #Sort cosine similarity scores in decreasing order
    pairs = sorted(pairs, key=lambda x: x['score'], reverse=True)
    rows = []
    for pair in pairs:
        i, j = pair['index']
        rows.append([entity_terms[i], taxonomy_terms[j], pair['score']])
    
    #move sorted values to a dataframe
    mapping_df= pd.DataFrame(rows, columns=["term", "taxonomy_keyword","cosine_similarity"])
    mapping_df['cosine_similarity'] = mapping_df['cosine_similarity'].astype('float')
    mapping_df= mapping_df.sort_values(by=['term','cosine_similarity'], ascending=False)
    drop_dups= mapping_df.drop_duplicates(subset=['term'], keep='first')
    mapping_df = drop_dups.sort_values(by=['cosine_similarity'], ascending=False).reset_index(drop=True)
    return mapping_df
                                               
#compute cosine_similairty score between topic keywords and content taxonomy keywords using BERT embeddings                                               
text_taxonomy_mapping=compute_similarity(keyword_embeddings, topic_keywords, taxonomy_embeddings, taxonomy_terms)

#merge text and image keywords mapped to content taxonomy
rtb_keywords=pd.concat([text_taxonomy_mapping[["term","taxonomy_keyword","cosine_similarity"]],image_taxonomy_mapping]).sort_values(by='cosine_similarity',ascending=False).reset_index(drop=True)

#select keywords with a cosine_similarity score greater than your desired threshold ( the value should be from 0 to 1)
rtb_keywords[rtb_keywords["cosine_similarity"]> 50] # change to desired threshold for cosine score, value between [0,100]: