python每天的数据分析_每日PV-Pandas-Python数据分析(3)

cat pd_ng_log_stat.py

#!/usr/bin/env python

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

from ng_line_parser import NgLineParser

import pandas as pd

import socket

import struct

class PDNgLogStat(object):

def __init__(self):

self.ng_line_parser = NgLineParser()

def _log_line_iter(self, pathes):

"""解析文件中的每一行并生成一个迭代器"""

for path in pathes:

with open(path, 'r') as f:

for index, line in enumerate(f):

self.ng_line_parser.parse(line)

yield self.ng_line_parser.to_dict()

def load_data(self, path):

"""通过给的文件路径加载数据生成 DataFrame"""

self.df = pd.DataFrame(self._log_line_iter(path))

def pv_day(self):

"""计算每一天的 PV"""

group_by_cols = ['access_time'] # 需要分组的列,只计算和显示该列

# 下面我们是按 yyyy-mm-dd 形式来分组的, 所以需要定义分组策略:

# 分组策略为: self.df['access_time'].map(lambda x: x.split()[0])

pv_day_grp = self.df[group_by_cols].groupby(

self.df['access_time'].map(lambda x: x.split()[0]))

return pv_day_grp.agg(['count'])

def main():

file_pathes = ['www.ttmark.com.access.log']

pd_ng_log_stat = PDNgLogStat()

pd_ng_log_stat.load_data(file_pathes)

# 统计每日 pv

print pd_ng_log_stat.pv_day()

if __name__ == '__main__':

main()