python关联规则学习：FP-Growth算法对药品进行“菜篮子”分析

importimport  pandaspandas  asas  pdpd
importimport  graph_toolgraph_t  as gt
import graph_tool.draw
import graph_tool.community
import itertools
import collections
import matplotlib
import math
In [2]:
 
gt.draw.graph_draw(g, pos=pos, vertex_fill_color=b,
            edge_control_points=cts,
            vertex_size=20,
            vertex_text=g.vertex_properties['label'],
            vertex_text_rotation=g.vertex_properties['text_rot'],
            vertex_text_position=1,
            vertex_font_size=20,
            vertex_font_family='mono',
            vertex_anchor=0,
            vertex_color=b,
            vcmap=matplotlib.cm.Spectral,
            ecmap=matplotlib.cm.Spectral,
            edge_color=g.edge_properties['color'],
            bg_color=[0,0,0,1],
            output_size=[1024*2,1024*2],
            output='/home/aahu/Desktop/evo_nvends={0}.png'.format(MIN_SHARED_VENDORS))
saving to disk...

# coding: utf-8

from bs4 import BeautifulSoup
import re
import pandas as pd
import dateutil
import os

import logging
 

def main():
    for datestr in os.listdir(DATA_DIR):
        d1 = os.path.join(DATA_DIR, datestr)
        fdate = dateutil.parser.parse(datestr)
        catdir = os.path.join(d1,'category')
        if os.path.exists(catdir):
            logger.info(catdir)
            df = catdir_to_df(catdir, fdate)
            outname ='category_df_'+datestr+'.tsv'
            df.to_csv(os.path.join(DATA_DIR,outname),'\t',index=False)


if __name__=='__main__':
    main()