def __init__(self, docs, K, alpha, eta): LDA.__init__(self, docs, K, alpha, eta) ### Gibbs sampler related data structures ### # C_VK[w,k] := number of times word w is assigned to topic k self.C_VK = np.zeros((self.V, self.K), dtype=int) # C_DK[d,k] := number of times topic k is present in document d self.C_DK = np.zeros((self.D, self.K), dtype=int) # Cache these values as we go (equivalent to performing column sums for above matrices) # For each document, total number of topics assigned self.total_topics_per_doc = np.zeros(self.D) # For each topic, total number of words assigned to it self.total_words_per_topic = np.zeros(self.K) # Save results here self.log_prob = [] self.samples = []
def __init__(self, n_topics, alpha=0.1, beta=0.01, random_state=0): LDA.__init__(self, n_topics, alpha=0.1, beta=0.01, random_state=0)
def __init__(self, n_topics, alpha=0.1, beta=0.01, random_state=0): LDA.__init__(self, n_topics, alpha=0.1, beta=0.01, random_state=0)