Storyboard

>Model

ID:(1795, 0)

Description

>Top

Load data with read_csv , modify columns and store the file with another name with to_csv :

from pandas import read_csv
from datetime import datetime

# load data
def parse(x):
    return datetime.strptime(x, '%Y %m %d %H')
dataset = read_csv('raw.csv',  parse_dates = [['year', 'month', 'day', 'hour']], index_col=0, date_parser=parse)
dataset.drop('No', axis=1, inplace=True)

# manually specify column names
dataset.columns = ['pollution', 'dew', 'temp', 'press', 'wnd_dir', 'wnd_spd', 'snow', 'rain']
dataset.index.name = 'date'

# mark all NA values with 0
dataset['pollution'].fillna(0, inplace=True)

# drop the first 24 hours
dataset = dataset[24:]

# summarize first 5 rows
print(dataset.head(5))

# save to file
dataset.to_csv('pollution.csv')

ID:(13897, 0)