In [ ]:
import nltk
import random

In [ ]:
### Step 1. Pick your training corpus
corpus = nltk.corpus.brown.words()

In [ ]:
### Step 2. Generate a list of all of the N-word-long sequences in your corpus
### e.g. if N = 2, "I can do it." -> [("I", "can"), ("can", "do"), ("do", "it"), ("it", ".")]

def generate_ngrams(corpus):
ngrams = []

# ~2 lines: Fill ngrams with 2-word tuples from corpus

return ngrams

In [ ]:
### Step 3. Create a nested dictionary with counts of each word given (N - 1) previous words
### e.g. {"I": {"think": 1, "can": 1}, "can": {"do": 1}, "think": {"I": 1}, "do": {"it": 1"}, "it": {".": 1}}

def generate_freq_dist(ngrams):
freq_dist = {}

# ~10 lines: Create frequencies dictionary
# HINT: Loop through ngrams, adding 1 to freq_dist[ngram][ngram] each time
# DISCUSS: What will you need to do if ngram or ngram are not in your freq_dist?

return freq_dist

In [ ]:
### Step 4: Create a nested dictionary with probabilities of each word given (N - 1) previous words
### e.g. {"I": {"think": 0.5, "can": 0.5}, "can": {"do": 1}, "think": {"I": 1}, "do": {"it": 1"}, "it": {".": 1}}

def generate_prob_dist(freq_dist):
prob_dist = {}

for word in freq_dist:
# 3 lines: Calculate the total number of times word was used

# 3 lines: Set p[ngram][ngram] = f[ngram][ngram] / total for each word

return prob_dist

In [ ]:
# 1-3 lines: Generate probability distribution from corpus

In [ ]:
### Step 5: Given a prompt, randomly sample your probability distribution to pick the next word
### Step 6: Repeat

num_words = 100
prompt = ["I"]

while len(prompt) < num_words:
sel = random.random()
total = 0

# Get last N-1 words from prompt
given = tuple(prompt[-(N - 1):])

if given not in prob_dist:
# DISCUSS: When would this occur?
break

# This part is kind of tricky, so I've done it for you
# DISCUSS: Why does this work?

for word in prob_dist[given]:
prob = prob_dist[given][word]

if total + prob > sel:
prompt.append(word)
break
else:
total += prob

In [ ]:
" ".join(prompt)