Tool for analyzing the GEV09 classification in VQR 2011-2014

GEV09_Scopus_Article.py

#Emanuele Ruffaldi 2016 Scuola Superiore Sant'Anna
import csv,os,sys
from pyexcel_xls import get_data,save_data

all = []
#Year	TopicId	Topic	Filename	Titolo Rivista	Codice identificativo SCOPUS	valore SJR	classe A	classe B	classe C	classe D	classe E	IR in alto	IR in basso
#4 + 3 + nclassi + 
total = 4 + 3 + 5 + 2 +1 
key2pos = {
	"Titolo Rivista": 4,
	"Codice identificativo SCOPUS":5,
	"valore SJR": 6,
	"classe A": 7,
	"classe B": 8,
	"classe C": 9,
	"classe D": 10,
	"classe E": 11,
	"IR in alto":12,
	"IR in basso":13,
	"IR": 14
}
all1 = ["" for i in range(0,total)]
all1[0] = "Year"
all1[1] = "TopicId"
all1[2] = "Topic"
all1[3] = "Filename"
for k,v in key2pos.iteritems():
	all1[v] =k
all = [all1]
for y in range(2011,2014+1):
	name = "GEV09-Scopus-anno%d-SJR-Article" % y
	for k in os.listdir(name):
		if not k.endswith("Article.xls"):
			continue
		#GEV09-scopus-2207-Control and Systems Engineering-anno2013-SJR-Article
		a = k.split("-")
		id = a[2]
		topic = a[3]
		prefix = [y,id,topic,k]
		data = get_data(os.path.join(name,k))
		data1 = data[0]
		data = data[1:]
		if len(all) == 0:
			all = [prefix1+data1]
		for x in data:
			xo = prefix + ["" for i in range(0,total-4)]
			for i,k in enumerate(data1):
				xo[key2pos[k]] = x[i]
			all.append(xo)

print len(all)
print all[0]
print all[1]
data = dict()
data["Sheet 1"] = all
save_data("all.xls", data)