Test your AI Agents with the all-new Agent to Agent Testing Platform.Learn More

How to use get_vocabulary_filter method in localstack

Best Python code snippet using localstack_python

client.pyi

Source:client.pyi

...278        Provides information about the specified custom vocabulary.279        [Show boto3 documentation](https://boto3.amazonaws.com/v1/documentation/api/1.24.58/reference/services/transcribe.html#TranscribeService.Client.get_vocabulary)280        [Show boto3-stubs documentation](https://vemel.github.io/boto3_stubs_docs/mypy_boto3_transcribe/client.html#get_vocabulary)281        """282    def get_vocabulary_filter(283        self, *, VocabularyFilterName: str284    ) -> GetVocabularyFilterResponseTypeDef:285        """286        Provides information about the specified custom vocabulary filter.287        [Show boto3 documentation](https://boto3.amazonaws.com/v1/documentation/api/1.24.58/reference/services/transcribe.html#TranscribeService.Client.get_vocabulary_filter)288        [Show boto3-stubs documentation](https://vemel.github.io/boto3_stubs_docs/mypy_boto3_transcribe/client.html#get_vocabulary_filter)289        """290    def list_call_analytics_categories(291        self, *, NextToken: str = None, MaxResults: int = None292    ) -> ListCallAnalyticsCategoriesResponseTypeDef:293        """294        Provides a list of Call Analytics categories, including all rules that make up295        each category.296        [Show boto3 documentation](https://boto3.amazonaws.com/v1/documentation/api/1.24.58/reference/services/transcribe.html#TranscribeService.Client.list_call_analytics_categories)...

app.py

Source:app.py

...66            )67            msg = "Upload Done ! "68            # Removing extension from name to transcribe69            # try:70            #     customizable_filter = transcribe.get_vocabulary_filter(71            #         VocabularyFilterName=str(name) + '-vocabularyfilter'72            #     )73            # except:74            #     customizable_filter = transcribe.create_vocabulary_filter(75            #         VocabularyFilterName=str(name) + '-vocabularyfilter',76            #         LanguageCode='en-US',77            #         Words=[78            #             customvocabulary,79            #         ],80            #     )81            # if customizable_filter:82            #     try:83            #         transcribe_response = transcribe.start_transcription_job(84            #             TranscriptionJobName=str(name) + '-transcribe',...

simpson.py

Source:simpson.py

...28                if token not in stoplist:29                    voca.add(token)30    print "Size of vocabulary: " + str(len(voca))31    return voca32def get_vocabulary_filter(filename):33    #Union tokens from all abstracts to generate vocabulary34    #Remove stopword list in nltk from vocabulary35    #Remove all common words36    count = 037    voca2counter = {}38    stoplist = set(stopwords.words('english'))39    with open(filename) as csvfile:40        csvreader = csv.reader(csvfile, delimiter=',')41        for row in csvreader:42            count += 143            if count == 1:44                continue45            #abstract = row[6].lower().decode('utf-8')46            abstract = row[6].lower()47            #year = row[8] 48            tokens = abstract.split()49            for token in tokens:50                #token = stemmer.stem(token)51                if token not in stoplist:52                    if token in voca2counter:53                        voca2counter[token] += 154                    else:55                        voca2counter[token] = 156    threshold = len(voca2counter)/10057    voca = set()58    for token in voca2counter:59        if voca2counter[token] < threshold:60            voca.add(token)61    print "Size of vocabulary: " + str(len(voca))62    return voca63def get_vocabulary_lda(term_file):64    print "Building vocabulary using lda words..."65    tokens = []66    with open(term_file) as lines:67        for line in lines:68            token = line.strip("\n")69            tokens.append(token)70    print "Number of all lda terms: " + str(len(tokens))71    voca = set(tokens)72    return voca73           74def compute_simpson_index(filename, voca):75    #print "Size of vocabulary: " + str(len(voca))76    #Counting vocabulary77    year2counter = {}78    year2N = {}79    count = 080    with open(filename) as csvfile:81        csvreader = csv.reader(csvfile, delimiter=',')82        N = 0 #Number of occurences of all tokens83        for row in csvreader:84            count += 185            if count == 1:86                continue87            abstract = row[6].lower()88            #abstract = row[6].lower().decode('utf-8')89            year = row[8] 90            if year in year2counter:91                counter = year2counter[year]92            else:93                counter = {}94                year2counter[year] = counter95                year2N[year] = 096            tokens = abstract.split()97            for token in tokens:98                #token = stemmer.stem(token)99                if token in voca:100                #if token:101                    year2N[year] += 1102                    if token in counter:103                        counter[token] += 1104                    else:105                        counter[token] = 1106    #Compute the Simpson index107    year2index = []108    N = 0109    for year in year2counter:110            #print "Year: \t" + str(year)111            if not year.isdigit():112                continue113            counter = year2counter[year]114            #print "Number of voca words: \t" + str(len(counter))115            N = year2N[year]116            #print "Number of occurences of voca words: \t" + str(N)117            #X = N*(N-1)118            X = N*N119            sum = 0120            for token in counter:121                #print counter[token]122                #sum += (counter[token] * (counter[token] - 1))/float(X)123                sum += (counter[token] * (counter[token] ))/float(X)124            year2index.append([int(year), sum])125    year2index = sorted(year2index, key=lambda item: item[0]) 126    return year2index127def get_vocabulary_dict(filename):128    voca = set()129    with open(filename) as file:130        csvreader = csv.reader(file)131        for row in csvreader:132            term = row[1]133            voca.add(term)134    return voca135def plot(year2index, filename):136    OX = []137    OY = []138    for item in year2index:139        OX.append(item[0]) #year140        OY.append(item[1]) #index141    fig = plt.figure()142    ax = plt.subplot(111)143    width = 0.8144    ind = np.arange(len(OY))145    ax.bar(ind, OY, width=width)146    ax.set_xticks(ind + width/2)147    ax.set_xticklabels(OX, rotation=90)148    plt.savefig(filename)149def main(argv):150    filename = "mrs.csv"151    voca_all = get_vocabulary_all(filename)152    #voca = get_vocabulary_filter(filename)153    voca_lda = get_vocabulary_lda("lda-bd92346b-100-c1fbb8bd/05000/term-index.txt")154    voca_dict = get_vocabulary_dict("materialsdictionary_v1.csv")155    year2index_all = compute_simpson_index(filename, voca_all)156    year2index_lda = compute_simpson_index(filename, voca_lda)157    year2index_dict = compute_simpson_index(filename, voca_dict)158    plot(year2index_all, "figure_all.pdf")159    plot(year2index_lda, "figure_lda.pdf")160    plot(year2index_dict, "figure_dictionary.pdf")161if __name__=="__main__":...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.