Assignment Solution

import numpy as np
# Generate the Lookup Table
def generateTable(data,k):  
  T = {}
  for i in range(len(data)-k):
    X = data[i:i+k]
    Y = data[i+k]
    if T.get(X) is None:
      T[X] = {}
      T[X][Y] = 1
    else:
      if T[X].get(Y) is None:
        T[X][Y] = 1
      else:
        T[X][Y] += 1
  return T
# Convert the Frequencies into Probability
def convertFreqIntoProb(T):     
  for kx in T.keys():
    s = float(sum(T[kx].values()))
    for k in T[kx].keys():
      T[kx][k] = T[kx][k]/s          
  return T
# Load the training data
def load_text(filename):
  with open(filename,encoding='utf8') as f:
    return f.read().lower()
# Create the Markov Chains
def MarkovChain(text,k):
    T = generateTable(text,k)
    T = convertFreqIntoProb(T)
    return T
# Perform Sampling
def sample_next(ctx,model,k):
    ctx = ctx[-k:]
    if model.get(ctx) is None:
        return " "
    possible_Chars = list(model[ctx].keys())
    possible_values = list(model[ctx].values())
    return np.random.choice(possible_Chars,p=possible_values)
  
# Generate the Text
def generateText(starting_sent,k ,maxLen):
    model = MarkovChain(text, k)
    sentence = starting_sent
    ctx = starting_sent[-k:]
    for ix in range(maxLen):
        next_prediction = sample_next(ctx,model,k)
        sentence += next_prediction
        ctx = sentence[-k:]
    return sentence
  
text = load_text("train_corpus.txt")
generated_text = generateText("dear my countrymen",k=8,maxLen=2000)
print(generated_text)