2.安装Spark与Python练习

with open(\"earth_song.txt\", \"r\") as f:
text = f.read()
text = text.lower()
for ch in \'!@#$%^&*(_)-+=\\\\[]}{|;:\\\'\\\"`~,<.>?/\':
text = text.replace(ch, \" \")

words = text.split() # 以空格分割文本
stop_words = []
with open(\'stop_words.txt\', \'r\') as f: # 读取停用词文件
for line in f:
stop_words.append(line.strip(\'\\n\'))
afterwords = []

for i in range(len(words)):
z = 1
for j in range(len(stop_words)):

if words[i] == stop_words[j]:
continue
else:
if z == len(stop_words):
afterwords.append(words[i])
break
z = z + 1
continue
counts = {}
for word in afterwords:
counts[word] = counts.get(word, 0) + 1
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)

f1 = open(\'count.txt\', \'w\')
for i in range(len(items)):
word, count = items[i]
f1.write(word+\" \"+str(count)+\"\\n\")

来源：https://www.cnblogs.com/MaiChengZhi/p/15980630.html
本站部分图文来源于网络，如有侵权请联系删除。