Skip to content

Commit

Permalink
Merge pull request cms-sw#13 from kdlong/WmassNanoProd_106X_genWeights
Browse files Browse the repository at this point in the history 
Copy in all the recent nano weights stuff
  • Loading branch information
@kdlong
kdlong authored Feb 21, 2022
2 parents ab97831 + eb144b7 commit e97390c
Show file tree
Hide file tree
Showing 26 changed files with 1,166 additions and 921 deletions.
28 changes: 14 additions & 14 deletions GeneratorInterface/Core/BuildFile.xml
View file
Original file line number Diff line number Diff line change
@@ -1,16 +1,16 @@
<use name="FWCore/Concurrency"/>
<use name="FWCore/ServiceRegistry"/>
<use name="FWCore/Utilities"/>
<use name="FWCore/Framework"/>
<use name="SimDataFormats/GeneratorProducts"/>
<use name="GeneratorInterface/LHEInterface"/>
<use name="heppdt"/>
<use name="boost"/>
<use name="clhep"/>
<use name="lhapdf"/>
<use name="f77compiler"/>
<use name="root"/>
<use name="tinyxml2"/>
<use name="FWCore/Concurrency"/>
<use name="FWCore/ServiceRegistry"/>
<use name="FWCore/Utilities"/>
<use name="FWCore/Framework"/>
<use name="SimDataFormats/GeneratorProducts"/>
<use name="GeneratorInterface/LHEInterface"/>
<use name="heppdt"/>
<use name="boost"/>
<use name="clhep"/>
<use name="lhapdf"/>
<use name="f77compiler"/>
<use name="root"/>
<use name="tinyxml2"/>
<export>
<lib name="1"/>
<lib name="1"/>
</export>
3 changes: 2 additions & 1 deletion GeneratorInterface/Core/interface/GenWeightHelper.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,8 @@ namespace gen {
class GenWeightHelper : public WeightHelper {
public:
GenWeightHelper();
void parseWeightGroupsFromNames(std::vector<std::string> weightNames);
std::vector<std::unique_ptr<gen::WeightGroupInfo>> parseWeightGroupsFromNames(std::vector<std::string> weightNames,
bool addUnassociatedGroup) const;
};
} // namespace gen

Expand Down
34 changes: 21 additions & 13 deletions GeneratorInterface/Core/interface/LHEWeightHelper.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,24 +21,32 @@ namespace gen {
public:
LHEWeightHelper() : WeightHelper(){};

enum ErrorType { SWAPHEADER, HTMLSTYLE, TRAILINGSTR, UNKNOWN };

void setHeaderLines(std::vector<std::string> headerLines);
void parseWeights();
bool isConsistent();
void swapHeaders();
enum class ErrorType { Empty, SwapHeader, HTMLStyle, NoWeightGroup, TrailingStr, Unknown, NoError };
const std::unordered_map<ErrorType, std::string> errorTypeAsString_ = {
{ErrorType::Empty, "Empty header"},
{ErrorType::SwapHeader, "Header info out of order"},
{ErrorType::HTMLStyle, "Header is invalid HTML"},
{ErrorType::TrailingStr, "Header has extraneous info"},
{ErrorType::Unknown, "Unregonized error"},
{ErrorType::NoError, "No error here!"}};

std::vector<std::unique_ptr<gen::WeightGroupInfo>> parseWeights(std::vector<std::string> headerLines,
bool addUnassociated) const;
bool isConsistent(const std::string& fullHeader) const;
void swapHeaders(std::vector<std::string>& headerLines) const;
void setFailIfInvalidXML(bool value) { failIfInvalidXML_ = value; }
bool failIfInvalidXML() const { return failIfInvalidXML_; }

private:
std::vector<std::string> headerLines_;
std::string weightgroupKet_ = "</weightgroup>";
std::string weightTag_ = "</weight>";
bool failIfInvalidXML_ = false;
std::string parseGroupName(tinyxml2::XMLElement* el);
void addGroup(tinyxml2::XMLElement* inner, std::string groupName, int groupIndex, int& weightIndex);
bool parseLHE(tinyxml2::XMLDocument& xmlDoc);
tinyxml2::XMLError tryReplaceHtmlStyle(tinyxml2::XMLDocument& xmlDoc, std::string& fullHeader);
tinyxml2::XMLError tryRemoveTrailings(tinyxml2::XMLDocument& xmlDoc, std::string& fullHeader);
ErrorType findErrorType(std::string& fullHeader);
std::string parseGroupName(tinyxml2::XMLElement* el) const;
ParsedWeight parseWeight(tinyxml2::XMLElement* inner, std::string groupName, int groupIndex, int& weightIndex) const;
bool validateAndFixHeader(std::vector<std::string>& headerLines, tinyxml2::XMLDocument& xmlDoc) const;
tinyxml2::XMLError tryReplaceHtmlStyle(tinyxml2::XMLDocument& xmlDoc, std::string& fullHeader) const;
tinyxml2::XMLError tryRemoveTrailings(tinyxml2::XMLDocument& xmlDoc, std::string& fullHeader) const;
ErrorType findErrorType(int xmlError, const std::string& headerLines) const;
};
} // namespace gen

Expand Down
104 changes: 64 additions & 40 deletions GeneratorInterface/Core/interface/WeightHelper.h
View file
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
#ifndef GeneratorInterface_LHEInterface_WeightHelper_h
#define GeneratorInterface_LHEInterface_WeightHelper_h

#include "DataFormats/Common/interface/OwnVector.h"
#include "SimDataFormats/GeneratorProducts/interface/GenWeightProduct.h"
#include "SimDataFormats/GeneratorProducts/interface/GenWeightInfoProduct.h"
#include "SimDataFormats/GeneratorProducts/interface/WeightGroupInfo.h"
#include "SimDataFormats/GeneratorProducts/interface/PdfWeightGroupInfo.h"
#include "SimDataFormats/GeneratorProducts/interface/WeightsInfo.h"
Expand All @@ -15,6 +15,7 @@
#include <boost/algorithm/string.hpp>
#include <bits/stdc++.h>
#include <fstream>
#include <memory>

namespace gen {
struct ParsedWeight {
Expand All @@ -29,48 +30,42 @@ namespace gen {
class WeightHelper {
public:
WeightHelper();
edm::OwnVector<gen::WeightGroupInfo> weightGroups() { return weightGroups_; }

template <typename T>
std::unique_ptr<GenWeightProduct> weightProduct(std::vector<T> weights, float w0);
std::unique_ptr<GenWeightProduct> weightProduct(const GenWeightInfoProduct& weightsInfo,
std::vector<T> weights,
float w0) const;

void setModel(std::string model) { model_ = model; }
void setGuessPSWeightIdx(bool guessPSWeightIdx) {
PartonShowerWeightGroupInfo::setGuessPSWeightIdx(guessPSWeightIdx);
}
void addUnassociatedGroup() {
weightGroups_.push_back(std::make_unique<UnknownWeightGroupInfo>("unassociated"));
weightGroups_.back().setDescription("Weights with missing or invalid header meta data");
void addUnassociatedGroup(std::vector<std::unique_ptr<gen::WeightGroupInfo>>& weightGroups) const {
gen::UnknownWeightGroupInfo unassoc("unassociated");
unassoc.setDescription("Weights with missing or invalid header meta data");
weightGroups.push_back(std::make_unique<gen::UnknownWeightGroupInfo>(unassoc));
}
int addWeightToProduct(
std::unique_ptr<GenWeightProduct>& product, double weight, std::string name, int weightNum, int groupIndex);
int findContainingWeightGroup(std::string wgtId, int weightIndex, int previousGroupIndex);
int addWeightToProduct(GenWeightProduct& product, double weight, std::string name, int weightNum, int groupIndex);
void setDebug(bool value) { debug_ = value; }

protected:
// TODO: Make this only print from one thread a la
// https://github.com/kdlong/cmssw/blob/master/PhysicsTools/NanoAOD/plugins/GenWeightsTableProducer.cc#L1069
bool debug_ = false;
const unsigned int FIRST_PSWEIGHT_ENTRY = 2;
const unsigned int DEFAULT_PSWEIGHT_LENGTH = 46;
std::string model_;
std::vector<ParsedWeight> parsedWeights_;
std::map<std::string, std::string> currWeightAttributeMap_;
std::map<std::string, std::string> currGroupAttributeMap_;
edm::OwnVector<gen::WeightGroupInfo> weightGroups_;
bool isScaleWeightGroup(const ParsedWeight& weight);
bool isMEParamWeightGroup(const ParsedWeight& weight);
bool isPdfWeightGroup(const ParsedWeight& weight);
bool isPartonShowerWeightGroup(const ParsedWeight& weight);
bool isOrphanPdfWeightGroup(ParsedWeight& weight);
void updateScaleInfo(gen::ScaleWeightGroupInfo& scaleGroup, const ParsedWeight& weight);
void updateMEParamInfo(const ParsedWeight& weight, int index);
void updatePdfInfo(gen::PdfWeightGroupInfo& pdfGroup, const ParsedWeight& weight);
void updatePartonShowerInfo(gen::PartonShowerWeightGroupInfo& psGroup, const ParsedWeight& weight);
void cleanupOrphanCentralWeight();
bool splitPdfWeight(ParsedWeight& weight);
bool isScaleWeightGroup(const ParsedWeight& weight) const;
bool isMEParamWeightGroup(const ParsedWeight& weight) const;
bool isPdfWeightGroup(const ParsedWeight& weight) const;
bool isPartonShowerWeightGroup(const ParsedWeight& weight) const;
bool isOrphanPdfWeightGroup(ParsedWeight& weight) const;
void updateScaleInfo(gen::ScaleWeightGroupInfo& scaleGroup, const ParsedWeight& weight) const;
void updateMEParamInfo(const ParsedWeight& weight, int index) const;
void updatePdfInfo(gen::PdfWeightGroupInfo& pdfGroup, const ParsedWeight& weight) const;
void updatePartonShowerInfo(gen::PartonShowerWeightGroupInfo& psGroup, const ParsedWeight& weight) const;
void cleanupOrphanCentralWeight(WeightGroupInfoContainer& weightGroups) const;
bool splitPdfWeight(ParsedWeight& weight, WeightGroupInfoContainer& weightGroups) const;

int lhapdfId(const ParsedWeight& weight, gen::PdfWeightGroupInfo& pdfGroup);
int lhapdfId(const ParsedWeight& weight, gen::PdfWeightGroupInfo& pdfGroup) const;
std::string searchAttributes(const std::string& label, const ParsedWeight& weight) const;
std::string searchAttributesByTag(const std::string& label, const ParsedWeight& weight) const;
std::string searchAttributesByRegex(const std::string& label, const ParsedWeight& weight) const;
Expand All @@ -86,28 +81,57 @@ namespace gen {
{"down", {"_dn", "Lo"}},
{"me_variation", {"mass", "sthw2", "width"}},
};
void printWeights();
std::unique_ptr<WeightGroupInfo> buildGroup(ParsedWeight& weight);
void buildGroups();
std::string searchString(const std::string& label, const std::string& name);
void printWeights(const WeightGroupInfoContainer& weightGroups) const;
std::unique_ptr<WeightGroupInfo> buildGroup(ParsedWeight& weight) const;
WeightGroupInfoContainer buildGroups(std::vector<ParsedWeight>& parsedWeights, bool addUnassociatedGroup) const;
std::string searchString(const std::string& label, const std::string& name) const;
};

// Templated function (needed here because of plugins)
template <typename T>
std::unique_ptr<GenWeightProduct> WeightHelper::weightProduct(std::vector<T> weights, float w0) {
std::unique_ptr<GenWeightProduct> WeightHelper::weightProduct(const GenWeightInfoProduct& weightsInfo,
std::vector<T> weights,
float w0) const {
auto weightProduct = std::make_unique<GenWeightProduct>(w0);
weightProduct->setNumWeightSets(weightGroups_.size());
int weightGroupIndex = 0;
weightProduct->setNumWeightSets(weightsInfo.numberOfGroups());
gen::WeightGroupData groupData = {0, nullptr};
int i = 0;
// This happens if there are no PS weights, so the weights vector contains only the central GEN weight.
// Just add an empty product (need for all cases or...?)
// size=1 happens if there are no PS weights, so the weights vector contains only the central GEN weight.
if (weights.size() > 1) {
// This gets remade every event to avoid having state-dependence in the helper class
// could think about doing caching instead
int unassociatedIdx = weightsInfo.unassociatedIdx();
std::unique_ptr<gen::UnknownWeightGroupInfo> unassociatedGroup;
if (unassociatedIdx != -1)
unassociatedGroup = std::make_unique<gen::UnknownWeightGroupInfo>("unassociated");
for (const auto& weight : weights) {
double wgtval;
std::string wgtid;
if constexpr (std::is_same<T, gen::WeightsInfo>::value) {
weightGroupIndex = addWeightToProduct(weightProduct, weight.wgt, weight.id, i, weightGroupIndex);
wgtid = weight.id;
wgtval = weight.wgt;
} else if (std::is_same<T, double>::value) {
wgtid = std::to_string(i);
wgtval = weight;
}
else if (std::is_same<T, double>::value)
weightGroupIndex = addWeightToProduct(weightProduct, weight, std::to_string(i), i, weightGroupIndex);
try {
groupData = weightsInfo.containingWeightGroupInfo(i, groupData.index);
} catch (const cms::Exception& e) {
if (unassociatedIdx == -1)
throw e;
if (debug_) {
std::cout << "WARNING: " << e.what() << std::endl;
}
// Access the unassociated group separately so it can be modified
unassociatedGroup->addContainedId(i, wgtid, wgtid);
groupData = {static_cast<size_t>(unassociatedIdx), unassociatedGroup.get()};
}
int entry = groupData.group->weightVectorEntry(wgtid, i);

// TODO: is this too slow?
if (debug_)
std::cout << "Adding weight num " << i << " EntryNum " << entry << " to group " << groupData.index
<< std::endl;
weightProduct->addWeight(wgtval, groupData.index, entry);
i++;
}
}
Expand Down
Loading

0 comments on commit e97390c

Please sign in to comment.