9.20练习

最新推荐文章于 2025-07-04 11:16:26 发布

原创最新推荐文章于 2025-07-04 11:16:26 发布 · 596 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#numpy #python

Python 专栏收录该内容

61 篇文章

订阅专栏

# _*_ coding:utf-8 _*_

import os
from pandas import DataFrame,Series
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import pylab
import json

''' # usagov_bitly_data2012-03-16-1331923249.txt
os.chdir("G:\pfda\ch02")
records = [json.loads(line) for line in open("usagov_bitly_data2012-03-16-1331923249.txt")]
frame = DataFrame(records)

clean_tz = frame['tz'].fillna('Missing')
clean_tz[clean_tz == ''] = 'Unknown'
tz_count = clean_tz.value_counts()

tz_count[:10].plot(kind='bar',rot=0)
#pylab.show()
'''
os.chdir("G:\pfda\ch02\movielens")

unames = ['user_id', 'gender', 'age', 'occupation', 'zip']
users = pd.read_table('users.dat', sep='::', header=None, names=unames)

rnames = ['user_id', 'movie_id', 'rating', 'timestamp']
ratings = pd.read_table('ratings.dat', sep='::', header=None, names=rnames)

mnames = ['movie_id', 'title', 'genres']
movies = pd.read_table('movies.dat', sep='::', header=None, names=mnames)

print users[:5]
print ratings[:5]