File LDA.java has 728 lines of code (exceeds 250 allowed). Consider refactoring.

Open

package com.hongliangjie.fugue.topicmodeling.LDA;

import com.google.gson.Gson;
import com.hongliangjie.fugue.Message;
import com.hongliangjie.fugue.distributions.MultinomialDistribution;

Method optimize has a Cognitive Complexity of 37 (exceeds 5 allowed). Consider refactoring.

Open

        @Override
        public void optimize() {
            double[] alpha = new double[modelPools.get(0).alpha.length];
            double alphaSum = modelPools.get(0).alphaSum;
            double[] beta = new double[modelPools.get(0).beta.length];

• Read up
  Read up

Method logGamma has 110 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    public static final double logGamma (double x)
    {
        double result;
        double y;
        double xnum;

Method initTestModels has a Cognitive Complexity of 25 (exceeds 5 allowed). Consider refactoring.

Open

    public void initTestModels(){
        for (ModelCountainer m : modelPools){
            m.beta = new double[m.outsideBeta.size()];
            for (int v = 0; v < m.outsideBeta.size(); v++ ){
                // this is the default value

• Read up
  Read up

Method logGamma has a Cognitive Complexity of 25 (exceeds 5 allowed). Consider refactoring.

Open

    public static final double logGamma (double x)
    {
        double result;
        double y;
        double xnum;

• Read up
  Read up

Method optimize has 69 lines of code (exceeds 25 allowed). Consider refactoring.

Open

        @Override
        public void optimize() {
            double[] alpha = new double[modelPools.get(0).alpha.length];
            double alphaSum = modelPools.get(0).alphaSum;
            double[] beta = new double[modelPools.get(0).beta.length];

Method sampleTestDoc has a Cognitive Complexity of 20 (exceeds 5 allowed). Consider refactoring.

Open

        protected void sampleTestDoc(List<Document> docs, int maxIter, int docIndex) {
            // for each test document, half of the document is used to "fold-in" and the other half is used to compute "perplexity"
            for (int m = 0; m < modelPools.size(); m++) {
                docTopicAssignment = new ArrayList<Integer>();
                docTopicBuffer = new int[TOPIC_NUM];

• Read up
  Read up

Method read has a Cognitive Complexity of 19 (exceeds 5 allowed). Consider refactoring.

Open

    public Message read(Message m) throws IOException {
        String inputFile = m.getParam("inputFile").toString();
        Integer top = Integer.parseInt(m.getParam("topk").toString());

        if (top == null)

• Read up
  Read up

Function load_models has a Cognitive Complexity of 17 (exceeds 5 allowed). Consider refactoring.

Open

def load_models(args):
    files = args.model_file.split(',')
    topicsOrders = {}
    N = 0
    for file in files:

• Read up
  Read up

Function parse_docs has a Cognitive Complexity of 16 (exceeds 5 allowed). Consider refactoring.

Open

def parse_docs(dictionary, args):
    input_f = open(args.input_file, 'r')
    output_f = open(args.output_file,'w')
    doc_id = 0
    for line in input_f:

• Read up
  Read up

Method initTestModels has 50 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    public void initTestModels(){
        for (ModelCountainer m : modelPools){
            m.beta = new double[m.outsideBeta.size()];
            for (int v = 0; v < m.outsideBeta.size(); v++ ){
                // this is the default value

Method sampleOverDocs has a Cognitive Complexity of 15 (exceeds 5 allowed). Consider refactoring.

Open

        public void sampleOverDocs(int modelID, List<Document> docs, int start, int end, int maxIter, int save){
            int overall_pos = 0;
            long overall_startTime = System.currentTimeMillis();
            for (CURRENT_ITER = 0; CURRENT_ITER < maxIter; CURRENT_ITER++) {
                LOGGER.info("Start to Iteration " + CURRENT_ITER);

• Read up
  Read up

Method initTrainModel has 43 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    protected void initTrainModel() {
        rebuildIndex();
        LOGGER.info("Start to initialize model.");
        LOGGER.info("Topic Num:" + TOPIC_NUM);
        LOGGER.info("ForwardIndex Size:" + wordsForwardIndex.size());

Method sampleOverDocs has 43 lines of code (exceeds 25 allowed). Consider refactoring.

Open

        public void sampleOverDocs(int modelID, List<Document> docs, int start, int end, int maxIter, int save){
            int overall_pos = 0;
            long overall_startTime = System.currentTimeMillis();
            for (CURRENT_ITER = 0; CURRENT_ITER < maxIter; CURRENT_ITER++) {
                LOGGER.info("Start to Iteration " + CURRENT_ITER);

Function compute_term_stats has a Cognitive Complexity of 13 (exceeds 5 allowed). Consider refactoring.

Open

def compute_term_stats(docs, args = None):
    """
    This function is to compute TF and DF stats
    :param docs:
    :return: a return obj with tf and df

• Read up
  Read up

Method sampleTestDoc has 38 lines of code (exceeds 25 allowed). Consider refactoring.

Open

        protected void sampleTestDoc(List<Document> docs, int maxIter, int docIndex) {
            // for each test document, half of the document is used to "fold-in" and the other half is used to compute "perplexity"
            for (int m = 0; m < modelPools.size(); m++) {
                docTopicAssignment = new ArrayList<Integer>();
                docTopicBuffer = new int[TOPIC_NUM];

Method read has 37 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    public Message read(Message m) throws IOException {
        String inputFile = m.getParam("inputFile").toString();
        Integer top = Integer.parseInt(m.getParam("topk").toString());

        if (top == null)

Method parseOptions has 35 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    protected static Message parseOptions(Options options, String[] args) {
        // create the parser
        Message cmd = defaultMessage();
        CommandLineParser parser = new DefaultParser();
        try {

Method createOptions has 34 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    protected static Options createOptions(){

        Options options = new Options();

        Option inputFileOption = Option.builder().longOpt("inputFile").desc("the input file").hasArg().argName("inputFile").build();

Method loadModel has 32 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    @SuppressWarnings("unchecked")
    public void loadModel() throws IOException {
        int multipleModels = Integer.parseInt(cmdArg.getParam("multipleModels").toString());
        String[] modelFileNames = null;
        LOGGER.info("Load Multiple Test Models:" + multipleModels);