# coding=utf-8
from pandas import read_csv
from pandas import datetime
def parser(x):
return datetime.strptime(x, '%Y %m %d %H')
dataset = read_csv('data_set/air_pollution.csv', parse_dates=[['year', 'month', 'day', 'hour']], index_col=0, date_parser=parser)
dataset.drop('No', axis=1, inplace=True)#axis=1,删除列;inplace=True,直接在原DataFrame上执行删除
#手动设置每一列的label
dataset.columns = ['pollution', 'dew', 'temp', 'press', 'wnd_dir', 'wnd_spd', 'snow', 'rain']
dataset.index.name = 'date'
#将NA替换为0
dataset['pollution'].fillna(0, inplace=True)
#删除最开始的24条数据
dataset = dataset[24:]
print dataset.head()
#保存处理后数据
dataset.to_csv('data_set/air_pollution_new.csv')
数据输出
# coding=utf-8
#输出数据曲线
#------------
from pandas import read_csv
from matplotlib import pyplot
dataset = read_csv('data_set/air_pollution_new.csv', header=0, index_col=0)
values = dataset.values
#需要输出的列
groups = [i for i in range(8)]
groups.remove(4)#删除值4,因为是字符串
i=1
#输出列曲线图
pyplot.figure()
for group in groups:
pyplot.subplot(len(groups), 1, i)#创建len(gourps)行,1列的子图,表示在第i个子图画图
pyplot.plot(values[:,group])
pyplot.title(dataset.columns[group], y=0.5, loc='right')
i+=1
pyplot.show()