def get_president_sentences(president):
files = sorted(
[file for file in os.listdir() if president.lower() in file.lower()])
speeches = [read_file(file) for file in files]
processed_speeches = process_speeches(speeches)
all_sentences = merge_speeches(processed_speeches)
return all_sentences
def get_presidents_sentences(presidents):
all_sentences = list()
for president in presidents:
files = sorted([
file for file in os.listdir() if president.lower() in file.lower()
])
speeches = [read_file(file) for file in files]
processed_speeches = process_speeches(speeches)
all_prez_sentences = merge_speeches(processed_speeches)
all_sentences.extend(all_prez_sentences)
return all_sentences
import os
import gensim
import spacy
from president_helper import read_file, process_speeches, merge_speeches, get_president_sentences, get_presidents_sentences, most_frequent_words
from nltk.corpus import stopwords
from collections import Counter
stop_words = stopwords.words('english')
# get list of all speech files
files = sorted([file for file in os.listdir() if file[-4:] == '.txt'])
# print(speeches)
# read each speech file
speeches = [read_file(file) for file in files]
# print(process_speeches)
# print(all_sentences)
# preprocess each speech
processed_speeches = process_speeches(speeches)
# merge speeches
all_sentences = merge_speeches(processed_speeches)
# print(all_sentences)
# view most frequently used words
most_freq_words = most_frequent_words(all_sentences)
# print(most_freq_words)
import os
import gensim
import spacy
from president_helper import read_file, process_speeches, merge_speeches, get_president_sentences, get_presidents_sentences, most_frequent_words
# get list of all speech files
files = sorted([file for file in os.listdir() if file[-4:] == '.txt'])
#print(files)
# read each speech file
speeches = list()
for file in files:
speeches.append(read_file(file))
# preprocess each speech
processed_speeches = process_speeches(speeches)
# merge speeches
all_sentences = merge_speeches(processed_speeches)
# view most frequently used words
most_freq_words = most_frequent_words(all_sentences)
#print(most_freq_words)
# create gensim model of all speeches
all_prez_embeddings = gensim.models.Word2Vec(all_sentences,
size=96,
window=5,
min_count=1,
workers=2,
sg=1)
import os
import gensim
import spacy
from president_helper import read_file, process_speeches, merge_speeches, get_president_sentences, \
get_presidents_sentences, most_frequent_words
# get list of all speech files
files = sorted([file for file in os.listdir() if file[-4:] == '.txt'])
print(files)
# read each speech file
speeches = [read_file(item) for item in files]
# print(speeches)
# preprocess each speech
processed_speeches = process_speeches(speeches)
# merge speeches
all_sentences = merge_speeches(processed_speeches)
# print(all_sentences)
# view most frequently used words
most_freq_words = most_frequent_words(all_sentences)
print(most_freq_words)
# create gensim model of all speeches
all_prez_embeddings = gensim.models.Word2Vec(all_sentences,
size=96,
window=5,
min_count=1,
workers=2,
import os
import gensim
import spacy
from president_helper import read_file, process_speeches, merge_speeches, get_president_sentences, get_presidents_sentences, most_frequent_words
# get list of all speech files
files = sorted([file for file in os.listdir() if file[-4:] == '.txt'])
#print(files)
# read each speech file
speeches = list()
for txt in files:
speeches.append(read_file(txt))
#print(speeches)
# preprocess each speech
processed_speeches = process_speeches(speeches)
#print(processed_speeches)
# merge speeches
all_sentences = merge_speeches(processed_speeches)
#print(all_sentences)
# view most frequently used words
most_freq_words = most_frequent_words(all_sentences)
#print(most_freq_words)
# create gensim model of all speeches
all_prez_embeddings = gensim.models.Word2Vec(all_sentences,
size=96,
window=5,
import os
import gensim
import spacy
from president_helper import read_file, process_speeches, merge_speeches, get_president_sentences, get_presidents_sentences, most_frequent_words
# get list of all speech files
files = sorted([file for file in os.listdir() if file[-4:] == '.txt'])
# read each speech file
speeches = [read_file(speech) for speech in files]
# preprocess each speech
processed_speeches = process_speeches(speeches)
# merge speeches
all_sentences = merge_speeches(processed_speeches)
# view most frequently used words
most_freq_words = most_frequent_words(all_sentences)
#print(most_freq_words)
# create gensim model of all speeches
all_prez_embeddings = gensim.models.Word2Vec(all_sentences,
size=96,
window=5,
min_count=1,
workers=2,
sg=1)
# view words similar to freedom
similar_to_freedom = all_prez_embeddings.wv.most_similar('freedom', topn=20)
import os
import gensim
import spacy
from president_helper import read_file, process_speeches, merge_speeches, get_president_sentences, get_presidents_sentences, most_frequent_words
# get list of all speech files
files = sorted([file for file in os.listdir() if file[-4:] == '.txt'])
#print(files)
# read each speech file
for fil in files:
speeches = read_file(fil)
#print(speeches)
# preprocess each speech
processed_speeches = process_speeches(speeches)
# merge speeches
all_sentences = merge_speeches(processed_speeches)
# view most frequently used words
most_freq_words = most_frequent_words(all_sentences)
#print(most_freq_words)
# create gensim model of all speeches
all_prez_embeddings = gensim.models.Word2Vec(all_sentences,
size=96,
window=5,
min_count=1,
workers=2,
sg=1)