missing_creator_pct.cpp

void missing_creator_pct()
{
	// Now we can use the new and improved RDataFrame interface
	auto rdf = ROOT::RDataFrame("library", "library.root");
	auto rdf_with_year = rdf.Filter("publication_year != 0x7fffffff");
	auto rdf_missing = rdf_with_year.Filter("creator != \"\"");
	std::map<std::string, int> books;
	std::map<std::string, int> all_books;
	rdf_with_year.Foreach([&](std::string title, int year) {all_books[title] = year;}, {"title", "publication_year"});
	rdf_missing.Foreach([&](std::string title, int year) {books[title] = year;}, {"title", "publication_year"});
	auto h1 = new TH1F("h1", "% of books with missing creator", 100, 1850, 2019);
	for(auto [title, year] : books)
		h1->Fill(year);
	auto h2 = new TH1F("h2", "books with missing year", 100, 1850, 2019);
	for(auto [title, year] : all_books)
		h2->Fill(year);
	for(int i=0;i<101;i++) {
		if(h2->GetBinContent(i) == 0)
			continue;
		h1->SetBinContent(i, h1->GetBinContent(i)/h2->GetBinContent(i));
	}
		
	h1->Draw();
}