From: Benjamin Auder Date: Sat, 14 Jan 2017 17:08:56 +0000 (+0100) Subject: major folder reorganisation, R pkg is now epclust/ at first level. Experimental usage... X-Git-Url: https://git.auder.net/%7B%7B%20asset%28%27mixstore/css/doc/html/%7B%7B%20pkg.url%20%7D%7D?a=commitdiff_plain;h=7709d507dfab9256a401f2c77ced7bc70d90fec3;p=epclust.git major folder reorganisation, R pkg is now epclust/ at first level. Experimental usage of git-annex --- diff --git a/.gitignore b/.gitignore index 783cd5b..4ce0103 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,3 @@ +#ignore temporary files +*~ *.swp - diff --git a/2016_12-notes.txt b/2016_12-notes.txt deleted file mode 100644 index a525189..0000000 --- a/2016_12-notes.txt +++ /dev/null @@ -1,19 +0,0 @@ -Point sur le code (BA, JC @ Lyon déc 2016) - -Nous avons reussi à - - faire une fresh installation du code de BA sur une nouvelle machine -(problèmes divers liés à la compilation, configuration, libraries exotiques) - - conduire des expériences sur les données pour mesurer le temps de calcul -(le code est blazing fast: 30sec pour obtenir 500 groupes sur 4 procs) - - identifier de problèmes : manque un installateur et une interface de pretraitement -indépendant du calcul - - -A faire: - - finir les experiences (sur nb de classes, nb de curves / chunk, nb de procs) - et sur d'autres architectures - - interface matrice -> binaire - - courbe synchrone - -Piste à explorer pour les comparaisons: H20 - diff --git a/CR b/CR deleted file mode 100644 index bedae26..0000000 --- a/CR +++ /dev/null @@ -1,5 +0,0 @@ -stratégie 1 : -1000 x étapes 1+2, puis réconciliation (par étape 1+2) - -stratégie 2 : -1000 x étape 1 puis réconciliation, puis étape 2 diff --git a/TODO b/TODO index e4f87b5..662635d 100644 --- a/TODO +++ b/TODO @@ -13,3 +13,11 @@ Essayer distance wdist du package biwavelet ? geometric structure of high dim data and dim reduction 2011 https://docs.docker.com/engine/getstarted/step_one/ + +A faire: + - finir les experiences (sur nb de classes, nb de curves / chunk, nb de procs) + et sur d'autres architectures + - interface matrice -> binaire + - courbe synchrone + +Piste à explorer pour les comparaisons: H20 diff --git a/biblio/Forecasting_Uncertainty_by_Boosting_Additive_Quantile_Regression-BenTaieb2016.pdf b/biblio/Forecasting_Uncertainty_by_Boosting_Additive_Quantile_Regression-BenTaieb2016.pdf new file mode 120000 index 0000000..4610061 --- /dev/null +++ b/biblio/Forecasting_Uncertainty_by_Boosting_Additive_Quantile_Regression-BenTaieb2016.pdf @@ -0,0 +1 @@ +../.git/annex/objects/v7/q2/SHA256E-s610765--828720188e82bfd492b107e7fe796d0f5a3bc05cde9655bc1eba209fed4ec5d2.pdf/SHA256E-s610765--828720188e82bfd492b107e7fe796d0f5a3bc05cde9655bc1eba209fed4ec5d2.pdf \ No newline at end of file diff --git a/biblio/Householders_Mental_Models_of_Domestic_Energy_Consumption-GabeThomas2016.pdf b/biblio/Householders_Mental_Models_of_Domestic_Energy_Consumption-GabeThomas2016.pdf new file mode 120000 index 0000000..4e229ac --- /dev/null +++ b/biblio/Householders_Mental_Models_of_Domestic_Energy_Consumption-GabeThomas2016.pdf @@ -0,0 +1 @@ +../.git/annex/objects/j1/WZ/SHA256E-s697548--c63d3a208a70d8cd6eb9474c50251c84a4a866826e25e0688d9d501ba0dd8b81.pdf/SHA256E-s697548--c63d3a208a70d8cd6eb9474c50251c84a4a866826e25e0688d9d501ba0dd8b81.pdf \ No newline at end of file diff --git a/biblio/Knowledge_Mining_the_Australian_Smart_Grid_Smart_City_Data-Foliente2015.pdf b/biblio/Knowledge_Mining_the_Australian_Smart_Grid_Smart_City_Data-Foliente2015.pdf new file mode 120000 index 0000000..d83b390 --- /dev/null +++ b/biblio/Knowledge_Mining_the_Australian_Smart_Grid_Smart_City_Data-Foliente2015.pdf @@ -0,0 +1 @@ +../.git/annex/objects/wZ/P3/SHA256E-s617895--75ddcdb2ec6d4e9a5c2bc56016b087602874ebea6ef365bef4e5a9019cbd3e6e.pdf/SHA256E-s617895--75ddcdb2ec6d4e9a5c2bc56016b087602874ebea6ef365bef4e5a9019cbd3e6e.pdf \ No newline at end of file diff --git a/code/draft_R_pkg/LICENSE b/code/draft_R_pkg/LICENSE deleted file mode 100644 index 3c29ab5..0000000 --- a/code/draft_R_pkg/LICENSE +++ /dev/null @@ -1,2 +0,0 @@ -YEAR: 2016-2017 -COPYRIGHT HOLDER: Jairo CUGLIARI diff --git a/code/draft_R_pkg/vignettes/TODO.Rnw b/code/draft_R_pkg/vignettes/TODO.Rnw deleted file mode 100644 index e69de29..0000000 diff --git a/communication/.gitignore b/communication/.gitignore deleted file mode 100644 index bb8be15..0000000 --- a/communication/.gitignore +++ /dev/null @@ -1,8 +0,0 @@ -#ignore all files produced by LaTeX compilation -*.aux -*.log -*.nav -*.snm -*.toc -*.out -*.pdf diff --git a/communication/short_paper/.gitkeep b/communication/short_paper/.gitkeep deleted file mode 100644 index e69de29..0000000 diff --git a/communication/slides/.gitkeep b/communication/slides/.gitkeep deleted file mode 100644 index e69de29..0000000 diff --git a/contrat/2016_IRSDIproject_v3.pdf b/contrat/2016_IRSDIproject_v3.pdf new file mode 120000 index 0000000..f7ba2e4 --- /dev/null +++ b/contrat/2016_IRSDIproject_v3.pdf @@ -0,0 +1 @@ +../.git/annex/objects/WF/mM/SHA256E-s203071--6259256cb90eb68cb3721949e044bca1effeb6ce81dd0483b25ee60a04e1348f.pdf/SHA256E-s203071--6259256cb90eb68cb3721949e044bca1effeb6ce81dd0483b25ee60a04e1348f.pdf \ No newline at end of file diff --git a/contrat/2016_IRSDIproject_v3.tex b/contrat/2016_IRSDIproject_v3.tex new file mode 100644 index 0000000..ed5cbfc --- /dev/null +++ b/contrat/2016_IRSDIproject_v3.tex @@ -0,0 +1,441 @@ +\documentclass[12pt, a4paper]{article} + +\usepackage[margin=2.5cm]{geometry} +\usepackage[utf8]{inputenc} % in encoding +\usepackage[T1]{fontenc} % out-encoding f +\usepackage{eurosym} +\usepackage{lmodern, microtype} % goes OK with T1 fontenc +%\usepackage[authoryear, round]{natbib} +\usepackage{natbib} +\usepackage{color, tikz, graphicx, subfig} +\usepackage{amssymb, amsmath, amsthm} +\usepackage{setspace, lineno, url, xcolor} +\usepackage{savetrees} + +\newcommand{\todo}[1]{\textcolor{blue}{TODO: #1}} % macro for todo entries + +% Style options +\renewcommand\familydefault{\sfdefault} % Use with sans serif font +\setlength{\bibsep}{0.0pt} % Compact bibliography (natbib) + +\title{Disaggregated Electricity Forecasting using Clustering of Individual Consumers \\ + {\normalsize \color{gray} IRSDI - RESEARCH INITIATIVE IN INDUSTRIAL DATA SCIENCE}} + +\author{Benjamin Auder \and + Jairo Cugliari \and + Yannig Goude \and + Jean-Michel Poggi +} +\date{\normalsize\today +\vspace{-1.2\baselineskip}} + + + +\begin{document} +\maketitle + +%\begin{abstract} + +%\end{abstract} + +% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% +% S E C T I O N +% +\section{Context} + +\subsection{Industrial} + +Electricity load forecasting is crucial for utilities for production +planning as well as marketing offers. Recently, the increasing deployment of +smart grids infrastructure requires the development of more flexible data +driven forecasting methods adapting quite automatically to new data sets. +Electricity load forecasting is crucial for utilities for production planning as +well as marketing offers. New metering infrastructures as smart meters +provide new and potentially massive informations about individual (household, +small and medium enterprise) consumption. As an example, in France, +ERDF (Electricite Reseau Distribution de France the French manager of +the public electricity distribution network) deployed 250000 smart meters, +covering a rural and an urban territory and providing half-hourly household +energy used each day. ERDF plans to install 35 millions of them over the +French territory by the end of 2020 and exploiting such an amount of data +is an exciting but challenging task (see \url{http://www.erdf.fr/Linky}). +We propose to build clustering tools useful for forecasting the load +consumption. The idea is to disaggregate the global signal in such a way that +the sum of disaggregated forecasts significantly improves the prediction of the +whole global signal. The strategy is in three steps: first we cluster curves +defining super-consumers, then we build a hierarchy of partitions within which +the best one is finally selected with respect to a disaggregated forecast +criterion. The proposed strategy is applied to a dataset of individual +consumers from the French electricity provider EDF. A substantial gain +of $16$ \% in forecast accuracy comparing to the 1-cluster approach is provided +by disaggregation while preserving meaningful classes of consumers. + +\subsection{Academic} + +In the context of economic seasonal univariate continuous time series, it is often +natural to segment it in time, into consecutive curves, for example days, which +are then treated as a discrete time series of functions. In particular, in the +electrical context, the shape of the curves exhibits rich information about the +calendar day type, the meteorological conditions or the existence of special +electricity tariffs. Using the information contained in the shape of the load +curves leads to very elegant formulation of functional forecasting. + + +%Electricity load experts naturally look at daily demand data as time functions +%called load curves. In a recent paper, \cite{shang2013} uses a functional time +%series approach for forecasting short-term electricity demand. This paper is +%illustrated by the half-hourly electricity demand from Monday to Sunday in South +%Australia. The strategy is also to consider a seasonal univariate time series as +%a time series of curves, then to reduce the dimensionality of curves by applying +%a functional principal component analysis and finally, following +%\cite{shang2011}, the principal component scores are forecasted using a +%univariate ARIMA models. In addition, since data points in the daily electricity +%demand are sequentially observed, a forecast updating method based on +%nonparametric bootstrap approach is proposed to improve the accuracy of point +%forecasts. With respect to this strategy, the scheme we propose handles the +%forecasting problem in a functional way avoiding the hour by hour processing and +%considers a more flexible way to construct the distribution leading to the +%prediction interval. + +The shape of the curves exhibits rich information about the calendar day type, +the meteorological conditions or the existence of special electricity tariffs. +Using the information contained in the shape of the load curves, \cite{antoniadis2012prevision} proposed a flexible nonparametric function-valued +forecast model called KWF (\textit{Kernel + Wavelet + Functional}) well suited +to handle nonstationary series. The predictor can be seen as a weighted average +of futures of past situations, where the weights increase with the similarity +between the past situations and the actual one. In addition, this strategy +provides with a simultaneous multiple horizon prediction for a global forecast. + +However, there is a need for local electricity load forecasting at different levels of the grid. +Bottom-up approaches, based on a two stage process combining clustering and forecasting +methods, are a promising perspective. First, it +consists in building classes in a population such that each class could be +sufficiently well forecast but corresponds to different load shapes or reacts +differently to exogenous variables like temperature or prices (see e.g. +\cite{labeeuw} in the context of demand response). The second stage consists in +aggregating forecasts to forecast the total or any subtotal of the population +consumption. For example, identify and forecast the consumption of a +sub-population reactive to an incentive is an important need to optimize a +demand response program. + +\section{Past work} + +Few papers consider the problem of clustering individual consumption for +forecasting (e.g. \cite{iwafune2014short, Alzate, carevic2010applications, MisitiElec}). Recently, \cite{energycon} proposed to build clustering tools useful for the two tasks simultaneously: clustering individual customers and forecasting the load consumption. The idea is to disaggregate the global signal in such a way that the sum of disaggregated forecasts significantly improves the prediction of the whole global signal. The general strategy is in three steps: first we cluster individual curves defining super-consumers, then we built a hierarchy of partitions within which a best one is finally selected with respect to a disaggregated forecast criterion. The predictions are made with the KWF model which allows one to use it as a off-the-shelve tool. + +While this work has ended with an the specification of an algorithm, a current need is a real upscaling proof. A first step on this direction was done in +\cite{auder2014}. + + +% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% +% S E C T I O N +% +\section{Aims} + +The method proposed in \cite{energycon} has been successfully tested on a small data set of EDF clients. With the current development of smart meters in France the available volume of individual data is increasing day after day. Then, there is a genuine need of measuring the upscale skills of the existent methods. + +This projet's aim is twofold. First, we will evaluate the upscaling capacity of the strategy developed in \cite{energycon} to cope with the upgrowing volume of data. Second, we will study how to adapt the KWF prediction method to take into account an exogeneous variable. In our particular problem the exogeneous variables can be any meteorological measurement that affects the load demand and is available at the moment of the prediction. + + +% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% +% S E C T I O N +% + +\section{Means considered} + +\subsection{Methods} +\paragraph{Clustering analysis.} In general, clustering methods look for groups of individuals on data in such a way that those belonging to the same group are more similar than those from other groups. Many methods exists to cluster data: +hierarchical, center-based, probabilistic, etc. Almost all of them depends heavily +on the choice of a similarity measure between individuals. For this challenge we plan +to compare individuals in terms of their wavelet spectrum signature. Thanks to this strategy, non +stationary signals may be fairly compared. Moreover, the signals need not to be +measured on the same temporal grid. However, in order to detect relevant results +the wavelet signatures should be corrected by exogenous information (e.g. the one +provided as client characteristics). + +\paragraph{Wavelet analysis.} Since the objects to analyze (load curves) can be viewed +as functions of time, functional data analysis techniques are one possible choice to +represent these objects. From a stochastic point of view the functions are realizations +of a non stationary random process. Wavelet transform can be used to extract +relevant information about the functions both on time and frequency. With an +appropriate representation of the objects, it is then possible to construct +a meaningful distance between load curves. + +\paragraph{Forecasting with KWF} +The basic idea of nonparametric forecasting is that similar cases in the past +have similar future consequences. For example the electricity consumption is +divided into blocks of one day size. Then, using a dissimilarity measure, the +blocks similar to the last observed block are searched in the past and a vector +of weights is built. Finally, the forecast of the next day is obtained by a +weighted average of the most similar future days using previous vector of +weights. From the statistical point of view, the model is an estimate of the +regression function using the kernel method, of the last block against all the +blocks in the past. In \cite{antoniadis2006functional} this basic model is +extended to the case of stationary functional random variables. But in the +context of electrical power demand, the hypothesis of stationarity generally +fails: an evolving mean level and the existence of groups that may be seen as +classes of stationarity are to be considered. Corrections to take into +account these two main nonstationary features are considered in +\cite{antoniadis2012prevision} defining a flexible nonparametric function-valued +forecast model called KWF (\textit{Kernel + Wavelet + Functional}) well suited +to handle nonstationary series. The predictor can be seen as a weighted average +of futures of past situations, where the weights increase with the similarity +between the past situations and the actual one. Again the similarity is defined +thanks to the wavelet decompositions of the two segments. + + +\subsection{Technology} % to be employed (hardware y software)} + + +The volume of data to deal for this projet can be handled with standard +but recent tools for data analysis. +The specific software tools will be statistical programming language like \texttt{R} with some popular +libraries (\texttt{data.table}, \texttt{dplyr}) and specific packages to cope with wavelet analysis. All these elements are open source. + +When the computational burden will grow, we have direct access to larger computation capacities. + +All the tools developed on the project will be made available as open source software licences. + +\subsection{Research team} + +The proposed team for developing this projet is composed by theree +academic members : +\begin{itemize} +\item Benjamin Auder, LMO, Univ Paris Saclay +\item Jairo Cugliari, ERIC, Univ Lyon +\item Jean-Michel Poggi, LMO, Univ Paris Saclay, Univ Paris Descartes +\end{itemize} + +% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% +% S E C T I O N +% +\section{Data description} +\begin{itemize} +\item a first dataset already used in \cite{energycon} could be used, at least in a first step, to calibrate the method. +\item simulated data could be obtained at EDF following \cite{bondu15} or any simulation method preserving confidentiality +of individual consumers. Obviously, any amount of such data could be produced to benchmark the scalability of our approach. +\item Irish data provided by the Irish commission for energy regulation consisting in 2000 individual consumption (small and +medium enterprise and residential) at an half-hourly resolution as well as pre and post experiment survey (see \cite{Cer_a, Cer_b}). +\end{itemize} + + + +% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% +% S E C T I O N +% +\section{Budget} +The expected global budget for the projet is of 15000 \euro, which comprises a 1 day workshop. + +\paragraph{Internal budget} The members of the research team are based on the Paris area and Lyon. +The way we work includes video and audio conferences in a regular basis as well as several in-person meetings. + +We plan to present the work on international conferences both on data science and energy oriented meetings. + +Last, a stress test for the upscale skill of the proposed method will need to hire computing time on a specialized platform. We have access to +the Centre de Calcul de l'Institut National de Physique Nucléaire et de Physique des Particules (\url{http://cc.in2p3.fr/}) through the laboratory ERIC, Lyon 2. + +\paragraph{Worshop organization on Individual Electricity Consumers} +A 1-day workshop dedicated to Individual Electricity Consumers including +sessions on data, packages and methods, could be organized in September +2017, and could be proposed to The French Statistical Society (SFdS) as a +satellite meeting of the Journées de Statistique 2018 which will be held in +the campus of EDF Lab in May 2018. + + +\begin{center} +\begin{tabular}{lr} \hline +\textbf{Internal budget} & \textbf{10 000 \euro}\\ +\; Travels & 3 000 \euro\\ +\; Conference fees & 3 000 \euro\\ +\; Internal meetings & 2 000 \euro\\ +\; Hiring of high performance computing time & 2 000 \euro\\ +\textbf{Worshop organization} & \textbf{5 000 \euro} \\ +\; Invitations of researchers & 3 000 \euro\\ +\; Organization workshop & 2 000 \euro\\ \hline +\textbf{Global budget} & \textbf{15 000 \euro} \\ \hline +\end{tabular} +\end{center} + + +% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% +% S E C T I O N +% +\section{Vitas} + +\paragraph{Benjamin Auder} is CNRS Research Engineer at LMO, University Paris-Sud Orsay in France. +He obtained his PhD in statistics in 2011 at the university Université Pierre et Marie Curie, Paris. +His main research areas are Clustering, dimensionality reduction, manifold learning, machine learning +in addition to software development and implementation issues of algorithmic solutions. + +(\url{http://auder.net/page-upsud/}) + +\paragraph{Jairo Cugliari} is Assistant Professor of Statistics at University of Lyon in France. He obtained his PhD in statistics +in 2011 at the university Paris-Sud 11 Orsay. His main research areas are functional data analysis methods +for classification and prediction for applied statistical problems. + +(\url{http://eric.univ-lyon2.fr/~jcugliari/}) + + + +\paragraph{Jean-Michel Poggi} is Professor of Statistics at University of Paris Descartes +and at University Paris-Sud Orsay in France. His main research areas are +tree-based methods for classification and regression, nonparametric time +series forecasting, wavelet methods and applied statistical modeling in energy +and environment fields. His publications combine theoretical and practical +contributions together with industrial applications and software development. + +\noindent +He is an elected member of the ISI, he was President of the French Statistical +Society (SFdS) and he is Vice-President of the FENStatS, Vice-President of ENBIS and President of ECAS. + +(\url{http://www.math.u-psud.fr/~poggi/}) + +% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% +% S E C T I O N +% +\section{Associated industrial company} % And members + + +\paragraph{Yannig Goude} is a research-engineer/project manager at EDF R\&D and associate +professor at University Paris-Sud Orsay, France. He obtained his PhD in statistics and probability +in 2008 at the university Paris-Sud 11 Orsay. His research interests are electricity load forecasting, +more generally time series analysis and forecasting, non-parametric models and expert aggregation. + +(\url{https://fr.linkedin.com/in/yannig-goude-768b3980}) + +\bibliographystyle{plain} +\bibliography{biblio_irsdi} %,predintervals,rapportfinal} + +\end{document} + + + +\bibitem{Alzate} +C.~Alzate and M.~Sinn, + Improved electricity load forecasting via kernel spectral clustering of + smartmeter, + \emph{International Conference on Data Mining}, vol. 948, pp. 943 -- 948, + 2013 + +\bibitem{antoniadis2006functional} +A.~Antoniadis, E.~Paparoditis and T.~Sapatinas, + A functional wavelet-kernel approach for time series prediction, + \emph{Journal of the Royal Statistical Society, Series B}, + vol. 68(5), pp. 837 -- 857, 2006 + +\bibitem{antoniadis2013clustering} +A.~Antoniadis, X.~Brossat, J.~Cugliari, and J.-M.~Poggi, + Clustering functional data using wavelets, + \emph{International Journal of Wavelets, Multiresolution and Information + Processing}, + vol. 11(1), 2013 + +\bibitem{antoniadis2012prevision} +A. Antoniadis, X. Brossat, J. Cugliari, J.-M. Poggi, + Pr\'{e}vision d'un processus \`{a} valeurs fonctionnelles en pr\'{e}sence de + non stationnarit\'{e}s. Application \`{a} la consommation + d'\'{e}lectricit\'{e} + Journal de la Soci\'{e}t\'{e} Fran\c{c}aise de Statistique, + Vol. 153, No. 2, 52--78, 2012 + +\bibitem{brabec2015statistical} +Brabec, M. and Kon{\'a}r, O. and Mal{\`y}, M. and Kasanick{\`y}, I and Pelik{\'a}n, E., + Statistical models for disaggregation and reaggregation of natural gas + consumption data, + \emph{Journal of Applied Statistics}, vol. 42(5), pp. 921--937, 2015 + +\bibitem{carevic2010applications} +Carevi{\'c}, S. and Capuder, T. and Delimar, M. + Applications of clustering algorithms in long-term load forecasting + \emph{Proceedings Energy Conference and Exhibition (EnergyCon), + 2010 IEEE International} 688--693, 2010 + +\bibitem{Chicco} +G. Chicco + Overview and performance assessment of the clustering methods for electrical + load pattern grouping, Energy , 42, 68 -- 80, 2012. + +\bibitem{Figueiredo} +Figueiredo, V., Rodrigues, F., Vale, Z., Gouveia, J. B. + An electric energy consumer characterization framework based on data mining + techniques. + Power Systems, IEEE Transactions on, 20(2), 596--602, 2005 + +\bibitem{iwafune2014short} +Iwafune, Y., Yagita, Y., Ikegami, T., Ogimoto K. + Short-term forecasting of residential building load for distributed energy + management + \emph{Proceedings Energy Conference (ENERGYCON), 2014 IEEE International} + 1197--1204, 2014 + +\bibitem{kaufmanpj} +Kaufman, L. and Rousseeuw, P + Finding groups in data: An introduction to cluster analysis, + Hoboken NJ John Wiley \& Sons Inc, 1990 + +\bibitem{Kwac} +J. Kwac, Flora, J., Rajagopal, R. + Household Energy Consumption Segmentation Using Hourly Data + Smart Grid, IEEE Transactions on, 5, 420--430, 2014 + +\bibitem{labeeuw} +Labeeuw, W., Stragier, J., and Deconinck, G. + Potential of active demand reduction with residential wet appliances: + A case study for Belgium. + Smart Grid, IEEE Transactions on, 6(1), 315--323, 2015 + +\bibitem{Liao} +Warren Liao, T. + Clustering of time series data--a survey + Pattern recognition, 38(11), 1857--1874, 2005 + +\bibitem{MisitiElec} +M.~Misiti, Y.~Misiti, G.~Oppenheim, and J.-M.~Poggi, + Optimized Clusters for Disaggregated Electricity Load Forecasting, + \emph{REVSTAT -- Statistical Journal}, vol. 8(2), pp. 105 -- 124, 2010 + +\bibitem{Mutanen} + Mutanen, A., Ruska, M., Repo, S., Jarventausta, P. + Customer classification and load profiling method for distribution systems. + Power Delivery, IEEE Transactions on, 26(3), 1755--1763, 2011 + +%\bibitem{Piao} +%Piao, M., Lee, H. G., Park, J. H., Ryu, K. H. +% Application of Classification Methods for Forecasting Mid-Term +% Power Load Patterns. +% In Advanced Intelligent Computing Theories and Applications. Springer, 2008 + +\bibitem{Rasanen} +T., R\"{a}s\"{a}nen, D., Voukantsis, H., Niska, K., Karatzas, M., Kolehmainen + Data-based method for creating electricity use load profiles using large + amount of customer-specific hourly measured electricity use data + Applied Energy, 87(11), 3538--3545, 2010 + +\bibitem{Rhodes} +J.D. Rhodes, W.J. Cole, C.R. Upshaw, T.F. Edgar, M.E. Webber + Clustering analysis of residential electricity demand profiles + Preprint submitted to Applied Energy, March 18, 2014 + +\bibitem{steinley2008new} +D. Steinley and M. Brusco, +A new variable weighting and selection procedure for k-means cluster analysis. +\emph{Multivariate Behavioral Research}, 43:32, 2008. + +\bibitem{wijaya2015forecasting} +Wijaya, T. K., Sinn, M., and Chen, B., + Forecasting Uncertainty in Electricity Demand, + \emph{AAAI-15 Workshop on Computational Sustainability, EPFL-CONF-203769}, + 2015 + +\bibitem{Zhou} +K. Zhou, S. Yang, C. Shen + A review of electric load classification in smart grid environment, + Renewable and Sustainable Energy Reviews, 24, 103 -- 110, 2013. + diff --git a/contrat/biblio_irsdi.bib b/contrat/biblio_irsdi.bib new file mode 100644 index 0000000..260f404 --- /dev/null +++ b/contrat/biblio_irsdi.bib @@ -0,0 +1,771 @@ +% This file was created with JabRef 2.10. +% Encoding: Cp1252 + + +@InProceedings{Alzate, + Title = {Improved electricity load forecasting via kernel spectral clustering of smartmeter}, + Author = {C. Alzate and M. Sinn}, + Booktitle = {International Conference on Data Mining}, + Year = {2013}, + Pages = {943-948}, + Publisher = {vol. 948} +} + +@Article{antoniadis2013clustering, + Title = {Clustering functional data using wavelets}, + Author = {A. Antoniadis and X. Brossat and J. Cugliari and J.-m. Poggi}, + Journal = {International Journal of Wavelets, Multiresolution and Information Processing}, + Year = {2013}, + Pages = {1}, + Volume = {11}, + + Unidentified = {vol} +} + +@Article{Antoniadis2012a, + Title = {Pr\'{e}vision d'un processus \`{a} valeurs fonctionnelles en pr\'{e}sence de non stationnarit\'{e}s}, + Author = {A. Antoniadis and X. Brossat and J. Cugliari and J.-m. Poggi}, + Journal = {Application \`{a} la consommation d'\'{e}lectricit\'{e} Journal de la Soci\'{e}t\'{e} Fran\c{c}aise de Statistique}, + Year = {2012}, + Number = {2}, + Pages = {52-78}, + Volume = {153}, + + Unidentified = {Vol} +} + +@Article{Antoniadis2014, + Title = {{Une approche fonctionnelle pour la pr{\'e}vision non-param{\'e}trique de la consommation d'{\'e}lectricit{\'e}}}, + Author = {A. Antoniadis and X. Brossat and J. Cugliari and J.-M. Poggi}, + Journal = {Journal de la Soci{\'e}t{\'e} Fran{\c{c}}aise de Statistique}, + Year = {2014}, + Number = {2}, + Pages = {202 - 219}, + Volume = {155} +} + +@Article{antoniadis2014prevision, + Title = {Une approche fonctionnelle pour la pr\'evision non-param\'etrique de la consommation d’\'electricit\'e}, + Author = {Antoniadis, A. and Brossat, X. and Cugliari, J. and Poggi, J.-M.}, + Journal = {Journal de la Soci\'et\'e Fran\c{c}aise de Statistique}, + Year = {2014}, + Number = {2}, + Pages = {202 -- 219}, + Volume = {155}, + + Owner = {lcugliari}, + Timestamp = {2013.01.11} +} + +@Article{Antoniadis2013, + Title = {{Functional Clustering using Wavelets}}, + Author = {A. Antoniadis and X. Brossat and J. Cugliari and J.-M. Poggi}, + Journal = {International Journal of Wavelets, Multiresolution and Information Processing}, + Year = {2013}, + Number = {1}, + Volume = {11} +} + +@Article{antoniadis2012prevision, + Title = {Pr\'evision d'un processus \`a valeurs fonctionnelles en pr\'esence de non stationnarit\'es. {A}pplication \`a la consommation d'\'electricit\'e}, + Author = {Antoniadis, A. and Brossat, X. and Cugliari, J. and Poggi, J.-M.}, + Journal = {Journal de la Soci\'et\'e Fran\c{c}aise de Statistique}, + Year = {2012}, + Number = {2}, + Pages = {52 -- 78}, + Volume = {153}, + + Owner = {lcugliari}, + Timestamp = {2013.01.11} +} + +@Article{antoniadis2006functional, + Title = {A functional wavelet-kernel approach for time series prediction}, + Author = {Antoniadis, A. and Paparoditis, E. and Sapatinas, T.}, + Journal = {Journal-Royal Statistical Society Series B Statistical Methodoloty}, + Year = {2006}, + Number = {5}, + Pages = {837}, + Volume = {68}, + + Owner = {jairo}, + Publisher = {Blackwell Publishing Ltd}, + Timestamp = {2014.04.27} +} + +@InProceedings{auder2014, + Title = {Parall{\'e}lisation de l'algorithme des k-m{\'e}do{\i}des. Application au clustering de courbes.}, + Author = {Auder, B. and Cugliari, J.}, + Booktitle = {46\`emes Journ'ees de Statistique de la SFdS}, + Year = {2014}, + + Owner = {jairo}, + Timestamp = {2016.05.17} +} + +@InProceedings{bondu15, + Title = {Realistic and very fast simulation of individual electricity consumptions}, + Author = {A. Bondu and A. Dachraoui}, + Booktitle = {2015 International Joint Conference on Neural Networks (IJCNN)}, + Year = {2015}, + Month = {July}, + Pages = {1-8}, + + Doi = {10.1109/IJCNN.2015.7280339}, + ISSN = {2161-4393}, + Keywords = {Markov processes;pattern clustering;power consumption;power engineering computing;smart power grids;time series;MODL coclustering approach;Markov chain;generative time series model;realistic individual electricity consumption simulation;smart grid} +} + +@Article{brabec2015statistical, + Title = {Statistical models for disaggregation and reaggregation of natural gas consumption data}, + Author = {Brabec, M. and Kon{\'a}r, O. and Mal{\`y}, M. and Kasanick{\`y}, I. and Pelik{\'a}n, E.}, + Journal = {Journal of Applied Statistics}, + Year = {2015}, + Number = {5}, + Pages = {921-937}, + Volume = {42}, + + Unidentified = {vol} +} + +@InProceedings{roy2005linear, + Title = {A non linear regression model for mid-term load forecasting and improvements in seasonality}, + Author = {Bruhns, A. and Deurveilher, G. and Roy, J.S.}, + Booktitle = {Proceedings of the 15th Power Systems Computation Conference}, + Year = {2005}, + Pages = {22--26}, + + Owner = {jairo}, + Timestamp = {2014.04.27} +} + +@Article{carevic2010applications, + Title = {Applications of clustering algorithms in long-term load forecasting}, + Author = {Carevi{\'c}, S. and Capuder, T. and Delimar, M.}, + Journal = {Proceedings Energy Conference and Exhibition (EnergyCon), 2010 IEEE International}, + Year = {2010}, + Pages = {688-693} +} + +@Article{Chicco, + Title = {{Overview and performance assessment of the clustering methods for electrical load pattern grouping}}, + Author = {G. Chicco}, + Journal = {Energy}, + Year = {2012}, + Pages = {68 - 80}, + Volume = {42} +} + +@Article{chiou2012dynamical, + Title = {Dynamical functional prediction and classification, with application to traffic flow prediction}, + Author = {Chiou, Jeng-Min}, + Journal = {The Annals of Applied Statistics}, + Year = {2012}, + Number = {4}, + Pages = {1588--1614}, + Volume = {6}, + + Owner = {jairo}, + Publisher = {Institute of Mathematical Statistics}, + Timestamp = {2015.04.13} +} + +@InProceedings{energycon, + Title = {Disaggregated Electricity Forecasting using Wavelet-Based Clustering of Individual Consumers}, + Author = {J. Cugliari and Y. Goude and J.-M. Poggi}, + Booktitle = {Energy Conference (ENERGYCON), 2016 IEEE International}, + Year = {2016}, + + Comment = {to appear}, + Owner = {jairo}, + Timestamp = {2016.05.17} +} + +@Article{degras2011simultaneous, + Title = {Simultaneous confidence bands for nonparametric regression with functional data}, + Author = {D.A. Degras}, + Journal = {Statistica Sinica}, + Year = {2011}, + Pages = {1735--1765}, + Volume = {21}, + + Owner = {jairo}, + Timestamp = {2015.04.13} +} + +@Article{Delattre2013, + Title = {On k-FWE-based critical values for controlling the false discovery proportion under dependence}, + Author = {Sylvain Delattre and Etienne Roquain}, + Journal = {Arxiv}, + Year = {2013}, + Note = {Preprint: arXiv:1311.4030}, + + Organization = {Arxiv}, + Owner = {jairo}, + Timestamp = {2014.01.13} +} + +@Unpublished{devaine2011expert, + Title = {Forecasting the electricity consumption by aggregating specialized experts; a review of the sequential aggregation of specialized experts, with application to Slovakian and French country-wide one-day-ahead (half-)hourly predictions.}, + Author = {Devaine, M. and Goude, Y. and Stoltz, G.}, + Note = {preprint: hal-00484940}, + Year = {2011}, + + Owner = {cugliari}, + Timestamp = {2011.08.04} +} + +@TechReport{Devijver, + Title = {{Model-based clustering for high-dimensional data. Application to functional data}}, + Author = {E. Devijver}, + Institution = {INRIA}, + Year = {2014}, + + Journal = {Preprint INRIA} +} + +@Article{dordonnat2008, + Title = {An hourly periodic state space model for modelling French national electricity load }, + Author = {V. Dordonnat and S.J. Koopman and M. Ooms and A. Dessertaine and J. Collet}, + Journal = {International Journal of Forecasting }, + Year = {2008}, + Note = {Energy Forecasting }, + Number = {4}, + Pages = {566 - 587}, + Volume = {24}, + + Doi = {http://dx.doi.org/10.1016/j.ijforecast.2008.08.010}, + ISSN = {0169-2070}, + Keywords = {Kalman filter}, + Owner = {jairo}, + Timestamp = {2014.07.15} +} + +@Article{dordonnat2012, + Title = {Dynamic factors in periodic time-varying regressions with an application to hourly electricity load modelling }, + Author = {Virginie Dordonnat and Siem Jan Koopman and Marius Ooms}, + Journal = {Computational Statistics \& Data Analysis }, + Year = {2012}, + Note = {1st issue of the Annals of Computational and Financial Econometrics Sixth Special Issue on Computational Econometrics }, + Number = {11}, + Pages = {3134 - 3152}, + Volume = {56}, + + Doi = {http://dx.doi.org/10.1016/j.csda.2011.04.002}, + ISSN = {0167-9473}, + Keywords = {Kalman filter}, + Owner = {jairo}, + Timestamp = {2014.07.15} +} + +@Article{ferraty2012regression, + Title = {Regression when both response and predictor are functions}, + Author = {Ferraty, Fr{\'e}d{\'e}ric and Van Keilegom, Ingrid and Vieu, Philippe}, + Journal = {Journal of Multivariate Analysis}, + Year = {2012}, + Pages = {10--28}, + Volume = {109}, + + Owner = {jairo}, + Publisher = {Elsevier}, + Timestamp = {2015.04.13} +} + +@Article{Figueiredo, + Title = {An electric energy consumer characterization framework based on data mining techniques.}, + Author = {Figueiredo, V. and Rodrigues, F. and Vale, Z. and Gouveia, J. B.}, + Journal = {Power Systems, IEEE Transactions on}, + Year = {2005}, + Number = {2}, + Pages = {596-602}, + Volume = {20}, + + Owner = {jairo}, + Timestamp = {2014.12.16} +} + +@Article{Figueiredo2005, + Title = {An electric energy consumer characterization framework based on data mining techniques}, + Author = {Figueiredo, V. and Rodrigues, F. and Vale, Z. and Gouveia, J. B.}, + Journal = {Power Systems, IEEE Transactions on}, + Year = {2005}, + Number = {2}, + Pages = {596-602}, + Volume = {20} +} + +@Article{Genovese2005, + Title = {Confidence Sets for Nonparametric Wavelet Regression}, + Author = {Christopher R. Genovese and Larry Wasserman}, + Journal = {The Annals of Statistics}, + Year = {2005}, + Number = {2}, + Pages = {698--729}, + Volume = {33}, + + Doi = {10.1214/009053605000000011}, + Owner = {jairo}, + Timestamp = {2014.01.13} +} + +@Article{gine2009exponential, + Title = {An exponential inequality for the distribution function of the kernel density estimator, with applications to adaptive estimation}, + Author = {Gin{\'e}, Evarist and Nickl, Richard}, + Journal = {Probability Theory and Related Fields}, + Year = {2009}, + Number = {3-4}, + Pages = {569--596}, + Volume = {143}, + + Owner = {jairo}, + Publisher = {Springer}, + Timestamp = {2015.04.13} +} + +@Article{gneiting2014probabilistic, + Title = {Probabilistic Forecasting}, + Author = {Gneiting, Tilmann and Katzfuss, Matthias}, + Journal = {Annual Review of Statistics and Its Application}, + Year = {2014}, + Number = {1}, + Pages = {125-151}, + Volume = {1}, + + Doi = doi:10.1146/annurev-statistics-062713-085831, + Eprint = {http://dx.doi.org/10.1146/annurev-statistics-062713-085831}, + Owner = {jairo}, + Timestamp = {2014.07.07} +} + +@Article{gneiting2007strictly, + Title = {Strictly proper scoring rules, prediction, and estimation}, + Author = {Gneiting, Tilmann and Raftery, Adrian E}, + Journal = {Journal of the American Statistical Association}, + Year = {2007}, + Number = {477}, + Pages = {359--378}, + Volume = {102}, + + Owner = {jairo}, + Publisher = {Taylor \& Francis}, + Timestamp = {2015.04.13} +} + +@Article{Goude, + Title = {{Local Short and Middle term Electricity Load Forecasting with semi-parametric additive models}}, + Author = {Y. Goude and R. Nedellec and N. Kong}, + Journal = {IEEE transactions on smart grid}, + Year = {2013}, + Number = {1}, + Pages = {440 - 446}, + Volume = {5} +} + +@Article{iwafune2014short, + Title = {Short-term forecasting of residential building load for distributed energy management}, + Author = {Iwafune, Y. and Yagita, Y. and Ikegami, T. and Ogimoto, K.}, + Journal = {Proceedings Energy Conference (ENERGYCON), 2014 IEEE International}, + Year = {2014}, + Pages = {1197-1204} +} + +@Article{johansen1990hotelling, + Title = {Hotelling's theorem on the volume of tubes: some illustrations in simultaneous inference and data analysis}, + Author = {Johansen, Soren and Johnstone, Iain M}, + Journal = {The Annals of Statistics}, + Year = {1990}, + Pages = {652--684}, + + Owner = {jairo}, + Publisher = {JSTOR}, + Timestamp = {2015.04.13} +} + +@Article{Kwac, + Title = {{Household Energy Consumption Segmentation Using Hourly Data Smart Grid}}, + Author = {J. Kwac and Flora and J and Rajagopal and R}, + Journal = {IEEE Transactions on}, + Year = {2014}, + Pages = {420 - 430}, + Volume = {5} +} + +@Article{Kwac2014, + Title = {Household Energy Consumption Segmentation Using Hourly Data Smart Grid}, + Author = {J. Kwac and Flora, J. and Rajagopal, R.}, + Journal = {IEEE Transactions on}, + Year = {2014}, + Pages = {420-430}, + Volume = {5} +} + +@Article{labeeuw, + Title = {Potential of active demand reduction with residential wet appliances: A case study for Belgium}, + Author = {Labeeuw, W. and Stragier, J. and Deconinck, G.}, + Journal = {Smart Grid, IEEE Transactions on}, + Year = {2015}, + Number = {1}, + Pages = {315-323}, + Volume = {6} +} + +@Article{launey2012construction, + Title = {Construction of an informative hierarchical prior distribution. Application to electricity load forecasting.}, + Author = {Launay, T. and Philippe, A. and Lamarche, S.}, + Journal = {arXiv}, + Year = {2012}, + Volume = {1109.4533}, + + Owner = {cugliari}, + Timestamp = {2012.10.29} +} + +@Article{Liao2005, + Title = {{Clustering of time series data a survey}}, + Author = {T. W. Liao}, + Journal = {Pattern recognition}, + Year = {2005}, + Number = {11}, + Pages = {1857 - 1874}, + Volume = {38} +} + +@Article{Liao, + Title = {of time series data--a survey Pattern recognition}, + Author = {Warren Liao and T. Clustering}, + Year = {2005}, + Number = {11}, + Pages = {1857-1874}, + Volume = {38} +} + +@Article{MisitiElec, + Title = {Optimized Clusters for Disaggregated Electricity Load Forecasting}, + Author = {M. Misiti and Y. Misiti and G. Oppenheim and J.-m. Poggi}, + Journal = {REVSTAT -- Statistical Journal}, + Year = {2010}, + Number = {2}, + Pages = {105-124}, + Volume = {8}, + + Unidentified = {vol} +} + +@Article{Mutanen, + Title = {{Customer classification and load profiling method for distribution systems}}, + Author = {A. Mutanen and M. Ruska and S. Repo and P. Jarventausta}, + Journal = {Power Delivery, IEEE Transactions on}, + Year = {2011}, + Number = {3}, + Pages = {1755 - 1763}, + Volume = {26} +} + +@Article{Mutanen2011, + Title = {and load profiling method for distribution systems}, + Author = {Mutanen, A. and Ruska, M. and Repo, S. and Jarventausta, P. Customer classification and}, + Journal = {Power Delivery, IEEE Transactions on}, + Year = {2011}, + Number = {3}, + Pages = {1755-1763}, + Volume = {26} +} + +@Book{nason2010, + Title = {Wavelet Methods in Statistics with R}, + Author = {G. Nason}, + Publisher = {Springer}, + Year = {2010}, + + Owner = {jairo}, + Pages = {269}, + Timestamp = {2014.07.15} +} + +@Article{Overview2012, + Title = {and performance assessment of the clustering methods for electrical load pattern grouping}, + Author = {G. Chicco Overview and}, + Journal = {Energy}, + Year = {2012}, + Pages = {68-80}, + Volume = {42} +} + +@InProceedings{petiau2009, + Title = {Confidence interval estimation for short-term load forecasting}, + Author = {Petiau, B.}, + Booktitle = {PowerTech, 2009 IEEE Bucharest}, + Year = {2009}, + Month = {June}, + Pages = {1-6}, + + Doi = {10.1109/PTC.2009.5282199}, + Keywords = {error analysis;load forecasting;confidence interval estimation;error analysis;forecast error knowledge;security analysis;short-term load forecasting;standard deviation error;Computational Intelligence Society;Demand forecasting;Input variables;Load forecasting;Load modeling;Power system modeling;Predictive models;Temperature;Transfer functions;Uncertainty;Error analysis;Load forecasting;Power demand}, + Owner = {jairo}, + Timestamp = {2014.07.15} +} + +@InBook{Piao2008, + Title = {Advanced Intelligent Computing Theories and Applications}, + Author = {Piao, M. and Lee, H. G. and Park, J. H. and Ryu, K. H.}, + Chapter = {Application of Classification Methods for Forecasting Mid-Term Power Load Patterns.}, + Publisher = {Springer}, + Year = {2008}, + + Owner = {jairo}, + Timestamp = {2014.12.16} +} + +@Article{Picard, + Title = {Adaptive confidence interval for pointwise curve estimation}, + Author = {Picard, Dominique and Tribouley, Karine}, + Journal = {The Annals of Statistics}, + Year = {2000}, + + Month = {02}, + Number = {1}, + Pages = {298--335}, + Volume = {28}, + + Ajournal = {Ann. Statist.}, + Doi = {10.1214/aos/1016120374}, + Owner = {jairo}, + Publisher = {The Institute of Mathematical Statistics}, + Timestamp = {2014.01.22}, + Url = {http://dx.doi.org/10.1214/aos/1016120374} +} + +@TechReport{Pierrot2014, + Title = {{Premiers tests d'une m{\'e}thode adaptative pour les 32000}}, + Author = {A. Pierrot}, + Institution = {EDF R\&D}, + Year = {2014}, + + Journal = {H-R39-2013-03366-FR} +} + +@Article{Pierrot2011, + Title = {{Short-Term Electricity Load Forecasting With Generalized Additive Models}}, + Author = {A. Pierrot and Y. Goude}, + Journal = {Proceedings of ISAP power}, + Year = {2011}, + Pages = {593 - 600} +} + +@InProceedings{pierrot2011short, + Title = {Short-term electricity load forecasting with generaliazed additive models.}, + Author = {Pierrot, A. and Goude, Y.}, + Booktitle = {16th International Conference on Intelligent System Applications to Power Systems}, + Year = {2011}, + Note = {to appear}, + + Owner = {cugliari}, + Timestamp = {2011.08.03} +} + +@Article{poggi1994prevision, + Title = {Pr{\'e}vision non param{\'e}trique de la consommation {\'e}lectrique}, + Author = {Poggi, J.-M.}, + Journal = {Rev. Statistique Appliqu{\'e}e}, + Year = {1994}, + Pages = {93-98}, + Volume = {XLII(4)}, + + Owner = {jairo}, + Timestamp = {2014.04.27} +} + +@Article{Rhodes, + Title = {{Clustering analysis of residential electricity demand profiles}}, + Author = {J. D. Rhodes and W. J. Cole and C. R. Upshaw and T. F. Edgar and M. E. Webber}, + Journal = {Preprint submitted to Applied Energy}, + Year = {2014}, + Volume = {18} +} + +@TechReport{Rhodes2014, + Title = {Clustering analysis of residential electricity demand profiles}, + Author = {J. D. Rhodes and W. J. Cole and C. R. Upshaw and T. F. Edgar and M. E. Webber}, + Institution = {submitted to Applied Energy, March 18}, + Year = {2014}, + Type = {Preprint} +} + +@Article{Scheffe, + Title = {A method for judging all contrats in the analysis of variance}, + Author = {Scheff'e, Henry}, + Journal = {Biometrika}, + Year = {1953}, + Number = {1-2}, + Pages = {87-110}, + Volume = {40}, + + Doi = {10.1093/biomet/40.1-2.87}, + Eprint = {http://biomet.oxfordjournals.org/content/40/1-2/87.full.pdf+html}, + Owner = {jairo}, + Timestamp = {2014.01.11}, + Url = {http://biomet.oxfordjournals.org/content/40/1-2/87.abstract} +} + +@Article{shang2013, + Title = {Functional time series approach for forecasting very short-term electricity demand}, + Author = {Shang, Han Lin}, + Journal = {Journal of Applied Statistics}, + Year = {2013}, + Number = {1}, + Pages = {152-168}, + Volume = {40}, + + Doi = {10.1080/02664763.2012.740619}, + Eprint = { http://dx.doi.org/10.1080/02664763.2012.740619 }, + Owner = {jairo}, + Timestamp = {2014.07.15} +} + +@Article{shang2011, + Title = {Nonparametric time series forecasting with dynamic updating }, + Author = {Han Lin Shang and Rob.J. Hyndman}, + Journal = {Mathematics and Computers in Simulation }, + Year = {2011}, + Note = {Selected Papers of the Combined \{IMACS\} World Congress and \{MSSANZ\} 18th Biennial Conference on Modelling and Simulation, Cairns, Australia, 13-17 July, 2009 }, + Number = {7}, + Pages = {1310 - 1324}, + Volume = {81}, + + Doi = {http://dx.doi.org/10.1016/j.matcom.2010.04.027}, + ISSN = {0378-4754}, + Keywords = {Functional principal component analysis}, + Owner = {jairo}, + Timestamp = {2014.07.15} +} + +@Article{shen2002, + Title = {Nonparametric Hypothesis Testing for a Spatial Signal}, + Author = {Shen, Xiaotong and Huang, Hsin-Cheng and Cressie, Noel}, + Journal = {Journal of the American Statistical Association}, + Year = {2002}, + Number = {460}, + Pages = {1122-1140}, + Volume = {97}, + + Doi = {10.1198/016214502388618933}, + Eprint = {http://dx.doi.org/10.1198/016214502388618933}, + Owner = {jairo}, + Timestamp = {2014.07.15} +} + +@Article{staszewska2007, + Title = {Representing uncertainty about response paths: The use of heuristic optimisation methods }, + Author = {Anna Staszewska}, + Journal = {Computational Statistics \& Data Analysis }, + Year = {2007}, + Number = {1}, + Pages = {121 - 132}, + Volume = {52}, + + Doi = {http://dx.doi.org/10.1016/j.csda.2006.12.023}, + ISSN = {0167-9473}, + Keywords = {Bootstrapping}, + Owner = {jairo}, + Timestamp = {2014.07.09} +} + +@Article{Staszewska2011, + Title = {Bootstrap prediction bands for forecast paths from vector autoregressive models}, + Author = {Staszewska-Bystrova, Anna}, + Journal = {Journal of Forecasting}, + Year = {2011}, + Number = {8}, + Pages = {721--735}, + Volume = {30}, + + Doi = {10.1002/for.1205}, + Owner = {jairo}, + Publisher = {Wiley Online Library}, + Timestamp = {2014.01.11} +} + +@Article{steinley2008new, + Title = {new variable weighting and selection procedure for k-means cluster analysis}, + Author = {D. Steinley and M. Brusco, A}, + Journal = {Multivariate Behavioral Research}, + Year = {2008}, + Pages = {32}, + Volume = {43} +} + +@Article{T2010, + Title = {{Data-based method for creating electricity use load profiles using large amount of customer-specific hourly measured electricity use data}}, + Author = {T and R{\"a}s{\"a}nen and D and Voukantsis and H and Niska and K and Karatzas and M and Kolehmainen}, + Journal = {Applied Energy}, + Year = {2010}, + Number = {11}, + Pages = {3538 - 3545}, + Volume = {87} +} + +@Article{Rasanen, + Title = {Data-based method for creating electricity use load profiles using large amount of customer-specific hourly measured electricity use data Applied Energy}, + Author = {T., R\"{a}s\"{a}nen and D., Voukantsis and H., Niska and K., Karatzas and M., Kolehmainen}, + Year = {2010}, + Number = {11}, + Pages = {3538-3545}, + Volume = {87} +} + +@Article{taylor2010triple, + Title = {Triple Seasonal Methods for Short-term Electricity Demand Forecasting}, + Author = {Taylor, J.W.}, + Journal = {European Journal of Operational Research}, + Year = {2010}, + Pages = {139-152}, + Volume = {204}, + + Owner = {cugliari}, + Timestamp = {2011.08.08} +} + +@Article{wijaya2015forecasting, + Title = {Forecasting Uncertainty in Electricity Demand}, + Author = {Wijaya, T. K. and Sinn, M. and Chen, B.}, + Journal = {AAAI-15 Workshop on Computational Sustainability, EPFL-CONF-203769}, + Year = {2015} +} + +@Article{Zhou, + Title = {{A review of electric load classification in smart grid environment}}, + Author = {K. Zhou and S. Yang and C. Shen}, + Journal = {Renewable and Sustainable Energy Reviews}, + Year = {2013}, + Pages = {103 - 110}, + Volume = {24} +} + +@Manual{Cer_a, + Title = {Electricity smart metering customer behaviour trials findings report}, + Organization = {Commission for energy regulation, Dublin}, + Year = {2011}, + + Institution = {Commission for energy regulation}, + Owner = {jairo}, + Timestamp = {2016.05.17} +} + +@Manual{Cer_b, + Title = {Results of electricity coast-benefit analysis, customer behaviour trials and technology trials commission for energy regulation}, + Organization = {Commission for energy regulation, Dublin}, + Year = {2011}, + + Institution = {Commission for energy regulation}, + Owner = {jairo}, + Timestamp = {2016.05.17} +} + +@comment{jabref-meta: selector_publisher:} + +@comment{jabref-meta: selector_author:} + +@comment{jabref-meta: selector_journal:} + +@comment{jabref-meta: selector_keywords:} + diff --git a/data/.gitignore b/data/.gitignore new file mode 100644 index 0000000..ce023e2 --- /dev/null +++ b/data/.gitignore @@ -0,0 +1,4 @@ +#ignore all but this file, and README +* +!.gitignore +!README diff --git a/data/README b/data/README new file mode 100644 index 0000000..962bfb3 --- /dev/null +++ b/data/README @@ -0,0 +1,25 @@ +URL: https://chuchu.freeboxos.fr/owncloud/apps/files/?dir=/IRSDI/data + +######################################################################## + +Fichiers de données téléchargées depuis +data.london.gov.uk/dataset/smartmeter-energy-use-data-in-london-households + +Power-Networks-LCL-June2015(withAcornGps) meter reading + +######################################################################## + +Fichiers de données téléchargées depuis +data.gouv.au/dataset/smart-grid-smart-city-customer-trial-data + +CDINTERVALREADINGALLNOQUOTES.CSV.7z meter reading +sgsc-cthanplug-readings.7z Home Aread Network Plug readings + +######################################################################## + +Fichiers données par EDF +2009.rar 32K data for year 2009 +2010.rar 32K data for year 2010 +2011.zip 32K data for year 2011 + +######################################################################## diff --git a/epclust/.gitignore b/epclust/.gitignore new file mode 100644 index 0000000..72fe212 --- /dev/null +++ b/epclust/.gitignore @@ -0,0 +1,16 @@ +#ignore roxygen2 generated files +NAMESPACE +/man/*.Rd +!/man/*-package.Rd + +#ignore jupyter checkpoints +/vignettes/.ipynb* +!/vignettes/*.ipynb + +#ignore R session files +.Rhistory +.RData + +#ignore R CMD build/check genrated files +/*.Rcheck/ +/*.tar.gz diff --git a/code/draft_R_pkg/DESCRIPTION b/epclust/DESCRIPTION similarity index 96% rename from code/draft_R_pkg/DESCRIPTION rename to epclust/DESCRIPTION index ed5af77..2b2c1f5 100644 --- a/code/draft_R_pkg/DESCRIPTION +++ b/epclust/DESCRIPTION @@ -18,4 +18,3 @@ Suggests: testthat, knitr License: MIT + file LICENSE -VignetteBuilder: knitr diff --git a/epclust/LICENSE b/epclust/LICENSE new file mode 100644 index 0000000..c3dd4da --- /dev/null +++ b/epclust/LICENSE @@ -0,0 +1,2 @@ +YEAR: 2016-2017 +COPYRIGHT HOLDER: EDF (?!) diff --git a/code/draft_R_pkg/R/algorithms.R b/epclust/R/algorithms.R similarity index 100% rename from code/draft_R_pkg/R/algorithms.R rename to epclust/R/algorithms.R diff --git a/code/draft_R_pkg/R/defaults.R b/epclust/R/defaults.R similarity index 100% rename from code/draft_R_pkg/R/defaults.R rename to epclust/R/defaults.R diff --git a/code/draft_R_pkg/R/main.R b/epclust/R/main.R similarity index 100% rename from code/draft_R_pkg/R/main.R rename to epclust/R/main.R diff --git a/code/draft_R_pkg/README.md b/epclust/README.md similarity index 100% rename from code/draft_R_pkg/README.md rename to epclust/README.md diff --git a/code/draft_R_pkg/man/epclust-package.Rd b/epclust/man/epclust-package.Rd similarity index 100% rename from code/draft_R_pkg/man/epclust-package.Rd rename to epclust/man/epclust-package.Rd diff --git a/code/draft_R_pkg/tests/testthat.R b/epclust/tests/testthat.R similarity index 100% rename from code/draft_R_pkg/tests/testthat.R rename to epclust/tests/testthat.R diff --git a/code/draft_R_pkg/tests/testthat/test.TODO.R b/epclust/tests/testthat/test.TODO.R similarity index 100% rename from code/draft_R_pkg/tests/testthat/test.TODO.R rename to epclust/tests/testthat/test.TODO.R diff --git a/epclust/vignettes/.gitignore b/epclust/vignettes/.gitignore new file mode 100644 index 0000000..53d89fc --- /dev/null +++ b/epclust/vignettes/.gitignore @@ -0,0 +1,4 @@ +#ignore all but this file, and source file +* +!.gitignore +!*.ipynb diff --git a/epclust/vignettes/epclust.ipynb b/epclust/vignettes/epclust.ipynb new file mode 100644 index 0000000..2340782 --- /dev/null +++ b/epclust/vignettes/epclust.ipynb @@ -0,0 +1,44 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "ename": "ERROR", + "evalue": "Error in library(epclust): there is no package called ‘epclust’\n", + "output_type": "error", + "traceback": [ + "Error in library(epclust): there is no package called ‘epclust’\nTraceback:\n", + "1. library(epclust)", + "2. stop(txt, domain = NA)" + ] + } + ], + "source": [ + "library(epclust)\n", + "#TODO..." + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "R", + "language": "R", + "name": "ir" + }, + "language_info": { + "codemirror_mode": "r", + "file_extension": ".r", + "mimetype": "text/x-r-source", + "name": "R", + "pygments_lexer": "r", + "version": "3.3.2" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/code/.gitignore b/old_C_code/.gitignore similarity index 67% rename from code/.gitignore rename to old_C_code/.gitignore index 9ce08e3..db6ef2b 100644 --- a/code/.gitignore +++ b/old_C_code/.gitignore @@ -3,3 +3,7 @@ build/ #ignore "real" data (way too large) data/ + +#ignore object files + library +*.o +*.so diff --git a/code/README b/old_C_code/README similarity index 100% rename from code/README rename to old_C_code/README diff --git a/code/stage1/src/Algorithm/compute_coefficients.c b/old_C_code/stage1/src/Algorithm/compute_coefficients.c similarity index 100% rename from code/stage1/src/Algorithm/compute_coefficients.c rename to old_C_code/stage1/src/Algorithm/compute_coefficients.c diff --git a/code/stage1/src/Algorithm/compute_coefficients.h b/old_C_code/stage1/src/Algorithm/compute_coefficients.h similarity index 100% rename from code/stage1/src/Algorithm/compute_coefficients.h rename to old_C_code/stage1/src/Algorithm/compute_coefficients.h diff --git a/code/stage1/src/Algorithm/get_dissimilarities.c b/old_C_code/stage1/src/Algorithm/get_dissimilarities.c similarity index 100% rename from code/stage1/src/Algorithm/get_dissimilarities.c rename to old_C_code/stage1/src/Algorithm/get_dissimilarities.c diff --git a/code/stage1/src/Algorithm/get_dissimilarities.h b/old_C_code/stage1/src/Algorithm/get_dissimilarities.h similarity index 100% rename from code/stage1/src/Algorithm/get_dissimilarities.h rename to old_C_code/stage1/src/Algorithm/get_dissimilarities.h diff --git a/code/stage1/src/Algorithm/pam.c b/old_C_code/stage1/src/Algorithm/pam.c similarity index 100% rename from code/stage1/src/Algorithm/pam.c rename to old_C_code/stage1/src/Algorithm/pam.c diff --git a/code/stage1/src/Algorithm/pam.h b/old_C_code/stage1/src/Algorithm/pam.h similarity index 100% rename from code/stage1/src/Algorithm/pam.h rename to old_C_code/stage1/src/Algorithm/pam.h diff --git a/code/stage1/src/CMakeLists.txt b/old_C_code/stage1/src/CMakeLists.txt similarity index 100% rename from code/stage1/src/CMakeLists.txt rename to old_C_code/stage1/src/CMakeLists.txt diff --git a/code/stage1/src/Classification/_Readme b/old_C_code/stage1/src/Classification/_Readme similarity index 100% rename from code/stage1/src/Classification/_Readme rename to old_C_code/stage1/src/Classification/_Readme diff --git a/code/stage1/src/Classification/getClass.c b/old_C_code/stage1/src/Classification/getClass.c similarity index 100% rename from code/stage1/src/Classification/getClass.c rename to old_C_code/stage1/src/Classification/getClass.c diff --git a/code/stage1/src/Classification/getClass.h b/old_C_code/stage1/src/Classification/getClass.h similarity index 100% rename from code/stage1/src/Classification/getClass.h rename to old_C_code/stage1/src/Classification/getClass.h diff --git a/code/stage1/src/MPI_Communication/pack.c b/old_C_code/stage1/src/MPI_Communication/pack.c similarity index 100% rename from code/stage1/src/MPI_Communication/pack.c rename to old_C_code/stage1/src/MPI_Communication/pack.c diff --git a/code/stage1/src/MPI_Communication/pack.h b/old_C_code/stage1/src/MPI_Communication/pack.h similarity index 100% rename from code/stage1/src/MPI_Communication/pack.h rename to old_C_code/stage1/src/MPI_Communication/pack.h diff --git a/code/stage1/src/MPI_Communication/unpack.c b/old_C_code/stage1/src/MPI_Communication/unpack.c similarity index 100% rename from code/stage1/src/MPI_Communication/unpack.c rename to old_C_code/stage1/src/MPI_Communication/unpack.c diff --git a/code/stage1/src/MPI_Communication/unpack.h b/old_C_code/stage1/src/MPI_Communication/unpack.h similarity index 100% rename from code/stage1/src/MPI_Communication/unpack.h rename to old_C_code/stage1/src/MPI_Communication/unpack.h diff --git a/code/stage1/src/MPI_Main/master.c b/old_C_code/stage1/src/MPI_Main/master.c similarity index 100% rename from code/stage1/src/MPI_Main/master.c rename to old_C_code/stage1/src/MPI_Main/master.c diff --git a/code/stage1/src/MPI_Main/master.h b/old_C_code/stage1/src/MPI_Main/master.h similarity index 100% rename from code/stage1/src/MPI_Main/master.h rename to old_C_code/stage1/src/MPI_Main/master.h diff --git a/code/stage1/src/MPI_Main/slave.c b/old_C_code/stage1/src/MPI_Main/slave.c similarity index 100% rename from code/stage1/src/MPI_Main/slave.c rename to old_C_code/stage1/src/MPI_Main/slave.c diff --git a/code/stage1/src/MPI_Main/slave.h b/old_C_code/stage1/src/MPI_Main/slave.h similarity index 100% rename from code/stage1/src/MPI_Main/slave.h rename to old_C_code/stage1/src/MPI_Main/slave.h diff --git a/code/stage1/src/TimeSeries/deserialize.c b/old_C_code/stage1/src/TimeSeries/deserialize.c similarity index 100% rename from code/stage1/src/TimeSeries/deserialize.c rename to old_C_code/stage1/src/TimeSeries/deserialize.c diff --git a/code/stage1/src/TimeSeries/deserialize.h b/old_C_code/stage1/src/TimeSeries/deserialize.h similarity index 100% rename from code/stage1/src/TimeSeries/deserialize.h rename to old_C_code/stage1/src/TimeSeries/deserialize.h diff --git a/code/stage1/src/TimeSeries/serialize.c b/old_C_code/stage1/src/TimeSeries/serialize.c similarity index 100% rename from code/stage1/src/TimeSeries/serialize.c rename to old_C_code/stage1/src/TimeSeries/serialize.c diff --git a/code/stage1/src/TimeSeries/serialize.h b/old_C_code/stage1/src/TimeSeries/serialize.h similarity index 100% rename from code/stage1/src/TimeSeries/serialize.h rename to old_C_code/stage1/src/TimeSeries/serialize.h diff --git a/code/stage1/src/Util/rng.c b/old_C_code/stage1/src/Util/rng.c similarity index 100% rename from code/stage1/src/Util/rng.c rename to old_C_code/stage1/src/Util/rng.c diff --git a/code/stage1/src/Util/rng.h b/old_C_code/stage1/src/Util/rng.h similarity index 100% rename from code/stage1/src/Util/rng.h rename to old_C_code/stage1/src/Util/rng.h diff --git a/code/stage1/src/Util/types.h b/old_C_code/stage1/src/Util/types.h similarity index 100% rename from code/stage1/src/Util/types.h rename to old_C_code/stage1/src/Util/types.h diff --git a/code/stage1/src/Util/utils.c b/old_C_code/stage1/src/Util/utils.c similarity index 100% rename from code/stage1/src/Util/utils.c rename to old_C_code/stage1/src/Util/utils.c diff --git a/code/stage1/src/Util/utils.h b/old_C_code/stage1/src/Util/utils.h similarity index 100% rename from code/stage1/src/Util/utils.h rename to old_C_code/stage1/src/Util/utils.h diff --git a/code/stage1/src/main.c b/old_C_code/stage1/src/main.c similarity index 99% rename from code/stage1/src/main.c rename to old_C_code/stage1/src/main.c index 992b97c..9800778 100644 --- a/code/stage1/src/main.c +++ b/old_C_code/stage1/src/main.c @@ -210,15 +210,15 @@ int classif_main(int argc, char** argv) if (tsLength1 > tsLength2) tsLength1 = tsLength2; } - uint32_t nbValues = (tsLength1 - 4) / 3; - + uint32_t nbValues = (tsLength1 - 4) / 4; + // 2] Classify all series by batches of CURVES_PER_REQUEST uint32_t nbSeries = get_nbSeries(ifileName); PowerCurve* medoids = deserialize(binFileName, NULL, ranks, nbClusters); free(binFileName); free(ranks); ranks = (uint32_t*)malloc(CURVES_PER_REQUEST*sizeof(uint32_t)); - + uint32_t smallestNonProcessedIndex = 0; double DISTOR = 0.0; while (smallestNonProcessedIndex < nbSeries) diff --git a/code/stage1/src/main.sh b/old_C_code/stage1/src/main.sh similarity index 100% rename from code/stage1/src/main.sh rename to old_C_code/stage1/src/main.sh diff --git a/code/stage1/test/Algorithm/t.compute_coefficients.c b/old_C_code/stage1/test/Algorithm/t.compute_coefficients.c similarity index 100% rename from code/stage1/test/Algorithm/t.compute_coefficients.c rename to old_C_code/stage1/test/Algorithm/t.compute_coefficients.c diff --git a/code/stage1/test/Algorithm/t.pam.c b/old_C_code/stage1/test/Algorithm/t.pam.c similarity index 100% rename from code/stage1/test/Algorithm/t.pam.c rename to old_C_code/stage1/test/Algorithm/t.pam.c diff --git a/code/stage1/test/CMakeLists.txt b/old_C_code/stage1/test/CMakeLists.txt similarity index 100% rename from code/stage1/test/CMakeLists.txt rename to old_C_code/stage1/test/CMakeLists.txt diff --git a/code/stage1/test/MPI_Communication/t.pack.c b/old_C_code/stage1/test/MPI_Communication/t.pack.c similarity index 100% rename from code/stage1/test/MPI_Communication/t.pack.c rename to old_C_code/stage1/test/MPI_Communication/t.pack.c diff --git a/code/stage1/test/MPI_Communication/t.unpack.c b/old_C_code/stage1/test/MPI_Communication/t.unpack.c similarity index 100% rename from code/stage1/test/MPI_Communication/t.unpack.c rename to old_C_code/stage1/test/MPI_Communication/t.unpack.c diff --git a/code/stage1/test/TimeSeries/t.deserialize.c b/old_C_code/stage1/test/TimeSeries/t.deserialize.c similarity index 100% rename from code/stage1/test/TimeSeries/t.deserialize.c rename to old_C_code/stage1/test/TimeSeries/t.deserialize.c diff --git a/code/stage1/test/TimeSeries/t.serialize.c b/old_C_code/stage1/test/TimeSeries/t.serialize.c similarity index 100% rename from code/stage1/test/TimeSeries/t.serialize.c rename to old_C_code/stage1/test/TimeSeries/t.serialize.c diff --git a/code/stage1/test/Util/t.rng.c b/old_C_code/stage1/test/Util/t.rng.c similarity index 100% rename from code/stage1/test/Util/t.rng.c rename to old_C_code/stage1/test/Util/t.rng.c diff --git a/code/stage1/test/Util/t.utils.c b/old_C_code/stage1/test/Util/t.utils.c similarity index 100% rename from code/stage1/test/Util/t.utils.c rename to old_C_code/stage1/test/Util/t.utils.c diff --git a/code/stage1/test/lut.h b/old_C_code/stage1/test/lut.h similarity index 100% rename from code/stage1/test/lut.h rename to old_C_code/stage1/test/lut.h diff --git a/code/stage1/test/main.c b/old_C_code/stage1/test/main.c similarity index 100% rename from code/stage1/test/main.c rename to old_C_code/stage1/test/main.c diff --git a/code/stage1/test/tdata/integers.txt b/old_C_code/stage1/test/tdata/integers.txt similarity index 100% rename from code/stage1/test/tdata/integers.txt rename to old_C_code/stage1/test/tdata/integers.txt diff --git a/code/stage1/test/tdata/reals.txt b/old_C_code/stage1/test/tdata/reals.txt similarity index 100% rename from code/stage1/test/tdata/reals.txt rename to old_C_code/stage1/test/tdata/reals.txt diff --git a/code/stage1/test/tdata/sample_byCols.bin b/old_C_code/stage1/test/tdata/sample_byCols.bin similarity index 100% rename from code/stage1/test/tdata/sample_byCols.bin rename to old_C_code/stage1/test/tdata/sample_byCols.bin diff --git a/code/stage1/test/tdata/sample_byCols.csv b/old_C_code/stage1/test/tdata/sample_byCols.csv similarity index 100% rename from code/stage1/test/tdata/sample_byCols.csv rename to old_C_code/stage1/test/tdata/sample_byCols.csv diff --git a/code/stage1/test/tdata/sample_byRows.bin b/old_C_code/stage1/test/tdata/sample_byRows.bin similarity index 100% rename from code/stage1/test/tdata/sample_byRows.bin rename to old_C_code/stage1/test/tdata/sample_byRows.bin diff --git a/code/stage1/test/tdata/sample_byRows.csv b/old_C_code/stage1/test/tdata/sample_byRows.csv similarity index 100% rename from code/stage1/test/tdata/sample_byRows.csv rename to old_C_code/stage1/test/tdata/sample_byRows.csv diff --git a/code/stage1/wrapper.R b/old_C_code/stage1/wrapper.R similarity index 85% rename from code/stage1/wrapper.R rename to old_C_code/stage1/wrapper.R index 0a957d8..0ce9786 100644 --- a/code/stage1/wrapper.R +++ b/old_C_code/stage1/wrapper.R @@ -33,3 +33,10 @@ getMedoids = function(path=".", xmlResult = "ppamResult.xml", ranks = as.integer( xmlToList( xmlParse(xmlResult) )$ranks ) return ( curves[ranks,] ) # == medoids } + +#TODO: check C function( is it correct?!) +getDistor = function(path=".", xmlResult = "ppamResult.xml", + finalSeries = "ppamFinalSeries.bin") +{ + system(paste(path,"/ppam.exe classif ",finalSeries," ",xmlResult,sep="")) +} diff --git a/code/stage2/src/.gitkeep b/old_C_code/stage2/src/.gitkeep similarity index 100% rename from code/stage2/src/.gitkeep rename to old_C_code/stage2/src/.gitkeep diff --git a/code/stage2/src/00_convertir-donnnes_2009.r b/old_C_code/stage2/src/00_convertir-donnnes_2009.r similarity index 100% rename from code/stage2/src/00_convertir-donnnes_2009.r rename to old_C_code/stage2/src/00_convertir-donnnes_2009.r diff --git a/code/stage2/src/00_convertir-donnnes_2010.r b/old_C_code/stage2/src/00_convertir-donnnes_2010.r similarity index 100% rename from code/stage2/src/00_convertir-donnnes_2010.r rename to old_C_code/stage2/src/00_convertir-donnnes_2010.r diff --git a/code/stage2/src/01_extract-features_2009.r b/old_C_code/stage2/src/01_extract-features_2009.r similarity index 100% rename from code/stage2/src/01_extract-features_2009.r rename to old_C_code/stage2/src/01_extract-features_2009.r diff --git a/code/stage2/src/01_extract-features_2010.r b/old_C_code/stage2/src/01_extract-features_2010.r similarity index 100% rename from code/stage2/src/01_extract-features_2010.r rename to old_C_code/stage2/src/01_extract-features_2010.r diff --git a/code/stage2/src/02_cluster_2009.r b/old_C_code/stage2/src/02_cluster_2009.r similarity index 100% rename from code/stage2/src/02_cluster_2009.r rename to old_C_code/stage2/src/02_cluster_2009.r diff --git a/code/stage2/src/03_compute-sums-of-classes_2009.r b/old_C_code/stage2/src/03_compute-sums-of-classes_2009.r similarity index 100% rename from code/stage2/src/03_compute-sums-of-classes_2009.r rename to old_C_code/stage2/src/03_compute-sums-of-classes_2009.r diff --git a/code/stage2/src/05_cluster2stepWER.r b/old_C_code/stage2/src/05_cluster2stepWER.r similarity index 100% rename from code/stage2/src/05_cluster2stepWER.r rename to old_C_code/stage2/src/05_cluster2stepWER.r diff --git a/code/stage2/src/06_predictions.r b/old_C_code/stage2/src/06_predictions.r similarity index 100% rename from code/stage2/src/06_predictions.r rename to old_C_code/stage2/src/06_predictions.r diff --git a/code/stage2/src/unused/00_convertir-donnnes_2011.r b/old_C_code/stage2/src/unused/00_convertir-donnnes_2011.r similarity index 100% rename from code/stage2/src/unused/00_convertir-donnnes_2011.r rename to old_C_code/stage2/src/unused/00_convertir-donnnes_2011.r diff --git a/code/stage2/src/unused/00_createCalendar.r b/old_C_code/stage2/src/unused/00_createCalendar.r similarity index 100% rename from code/stage2/src/unused/00_createCalendar.r rename to old_C_code/stage2/src/unused/00_createCalendar.r diff --git a/code/stage2/src/unused/00_plots-energycon.r b/old_C_code/stage2/src/unused/00_plots-energycon.r similarity index 100% rename from code/stage2/src/unused/00_plots-energycon.r rename to old_C_code/stage2/src/unused/00_plots-energycon.r diff --git a/code/stage2/src/unused/01_StBr.r b/old_C_code/stage2/src/unused/01_StBr.r similarity index 100% rename from code/stage2/src/unused/01_StBr.r rename to old_C_code/stage2/src/unused/01_StBr.r diff --git a/code/stage2/src/unused/01_extract-features2_2009.r b/old_C_code/stage2/src/unused/01_extract-features2_2009.r similarity index 100% rename from code/stage2/src/unused/01_extract-features2_2009.r rename to old_C_code/stage2/src/unused/01_extract-features2_2009.r diff --git a/code/stage2/src/unused/02_cluster-par_2009.r b/old_C_code/stage2/src/unused/02_cluster-par_2009.r similarity index 100% rename from code/stage2/src/unused/02_cluster-par_2009.r rename to old_C_code/stage2/src/unused/02_cluster-par_2009.r diff --git a/code/stage2/src/unused/03_compute-sums-of-classes-par_2009.r b/old_C_code/stage2/src/unused/03_compute-sums-of-classes-par_2009.r similarity index 100% rename from code/stage2/src/unused/03_compute-sums-of-classes-par_2009.r rename to old_C_code/stage2/src/unused/03_compute-sums-of-classes-par_2009.r diff --git a/code/stage2/src/unused/03_compute-sums-of-classesRANDOM-par_2009.r b/old_C_code/stage2/src/unused/03_compute-sums-of-classesRANDOM-par_2009.r similarity index 100% rename from code/stage2/src/unused/03_compute-sums-of-classesRANDOM-par_2009.r rename to old_C_code/stage2/src/unused/03_compute-sums-of-classesRANDOM-par_2009.r diff --git a/code/stage2/src/unused/03_compute-sums-of-classesRANDOM_2009.r b/old_C_code/stage2/src/unused/03_compute-sums-of-classesRANDOM_2009.r similarity index 100% rename from code/stage2/src/unused/03_compute-sums-of-classesRANDOM_2009.r rename to old_C_code/stage2/src/unused/03_compute-sums-of-classesRANDOM_2009.r diff --git a/code/stage2/src/unused/03_compute-sums-of-classesRANDOM_2010.r b/old_C_code/stage2/src/unused/03_compute-sums-of-classesRANDOM_2010.r similarity index 100% rename from code/stage2/src/unused/03_compute-sums-of-classesRANDOM_2010.r rename to old_C_code/stage2/src/unused/03_compute-sums-of-classesRANDOM_2010.r diff --git a/code/stage2/src/unused/03_compute-sums-of-classes_2010-par.r b/old_C_code/stage2/src/unused/03_compute-sums-of-classes_2010-par.r similarity index 100% rename from code/stage2/src/unused/03_compute-sums-of-classes_2010-par.r rename to old_C_code/stage2/src/unused/03_compute-sums-of-classes_2010-par.r diff --git a/code/stage2/src/unused/03_compute-sums-of-classes_2010.r b/old_C_code/stage2/src/unused/03_compute-sums-of-classes_2010.r similarity index 100% rename from code/stage2/src/unused/03_compute-sums-of-classes_2010.r rename to old_C_code/stage2/src/unused/03_compute-sums-of-classes_2010.r diff --git a/code/stage2/src/unused/04_predictions.r b/old_C_code/stage2/src/unused/04_predictions.r similarity index 100% rename from code/stage2/src/unused/04_predictions.r rename to old_C_code/stage2/src/unused/04_predictions.r diff --git a/code/stage2/src/unused/05_cluster2step.r b/old_C_code/stage2/src/unused/05_cluster2step.r similarity index 100% rename from code/stage2/src/unused/05_cluster2step.r rename to old_C_code/stage2/src/unused/05_cluster2step.r diff --git a/code/stage2/src/unused/05_cluster2stepWER-RANDOM.r b/old_C_code/stage2/src/unused/05_cluster2stepWER-RANDOM.r similarity index 100% rename from code/stage2/src/unused/05_cluster2stepWER-RANDOM.r rename to old_C_code/stage2/src/unused/05_cluster2stepWER-RANDOM.r diff --git a/code/stage2/src/unused/05_cluster2stepWER-par.r b/old_C_code/stage2/src/unused/05_cluster2stepWER-par.r similarity index 100% rename from code/stage2/src/unused/05_cluster2stepWER-par.r rename to old_C_code/stage2/src/unused/05_cluster2stepWER-par.r diff --git a/code/stage2/src/unused/06_predictions-ICAME.r b/old_C_code/stage2/src/unused/06_predictions-ICAME.r similarity index 100% rename from code/stage2/src/unused/06_predictions-ICAME.r rename to old_C_code/stage2/src/unused/06_predictions-ICAME.r diff --git a/code/stage2/src/unused/06_predictions-RANDOM.r b/old_C_code/stage2/src/unused/06_predictions-RANDOM.r similarity index 100% rename from code/stage2/src/unused/06_predictions-RANDOM.r rename to old_C_code/stage2/src/unused/06_predictions-RANDOM.r diff --git a/code/stage2/src/unused/06_predictions-par.r b/old_C_code/stage2/src/unused/06_predictions-par.r similarity index 100% rename from code/stage2/src/unused/06_predictions-par.r rename to old_C_code/stage2/src/unused/06_predictions-par.r diff --git a/code/stage2/src/unused/analysis-SME.r b/old_C_code/stage2/src/unused/analysis-SME.r similarity index 100% rename from code/stage2/src/unused/analysis-SME.r rename to old_C_code/stage2/src/unused/analysis-SME.r diff --git a/code/stage2/src/unused/aux.r b/old_C_code/stage2/src/unused/aux.r similarity index 100% rename from code/stage2/src/unused/aux.r rename to old_C_code/stage2/src/unused/aux.r diff --git a/code/stage2/src/unused/aux2.r b/old_C_code/stage2/src/unused/aux2.r similarity index 100% rename from code/stage2/src/unused/aux2.r rename to old_C_code/stage2/src/unused/aux2.r diff --git a/code/stage2/src/unused/calendar_ir.txt b/old_C_code/stage2/src/unused/calendar_ir.txt similarity index 100% rename from code/stage2/src/unused/calendar_ir.txt rename to old_C_code/stage2/src/unused/calendar_ir.txt diff --git a/code/stage2/src/unused/calendar_transition_groups-1996-2011.txt b/old_C_code/stage2/src/unused/calendar_transition_groups-1996-2011.txt similarity index 100% rename from code/stage2/src/unused/calendar_transition_groups-1996-2011.txt rename to old_C_code/stage2/src/unused/calendar_transition_groups-1996-2011.txt diff --git a/code/stage2/src/unused/datesall.txt b/old_C_code/stage2/src/unused/datesall.txt similarity index 100% rename from code/stage2/src/unused/datesall.txt rename to old_C_code/stage2/src/unused/datesall.txt diff --git a/code/stage2/src/unused/descriptive-32K.r b/old_C_code/stage2/src/unused/descriptive-32K.r similarity index 100% rename from code/stage2/src/unused/descriptive-32K.r rename to old_C_code/stage2/src/unused/descriptive-32K.r diff --git a/code/stage2/src/unused/effectives-per-classe.r b/old_C_code/stage2/src/unused/effectives-per-classe.r similarity index 100% rename from code/stage2/src/unused/effectives-per-classe.r rename to old_C_code/stage2/src/unused/effectives-per-classe.r diff --git a/code/stage2/src/unused/identifs.txt b/old_C_code/stage2/src/unused/identifs.txt similarity index 100% rename from code/stage2/src/unused/identifs.txt rename to old_C_code/stage2/src/unused/identifs.txt diff --git a/code/stage2/src/unused/sowas-superseded.r b/old_C_code/stage2/src/unused/sowas-superseded.r similarity index 100% rename from code/stage2/src/unused/sowas-superseded.r rename to old_C_code/stage2/src/unused/sowas-superseded.r diff --git a/code/stage2/test/.gitkeep b/old_C_code/stage2/test/.gitkeep similarity index 100% rename from code/stage2/test/.gitkeep rename to old_C_code/stage2/test/.gitkeep diff --git a/slides/.gitignore b/slides/.gitignore new file mode 100644 index 0000000..53d89fc --- /dev/null +++ b/slides/.gitignore @@ -0,0 +1,4 @@ +#ignore all but this file, and source file +* +!.gitignore +!*.ipynb diff --git a/slides/presentation.ipynb b/slides/presentation.ipynb new file mode 100644 index 0000000..2340782 --- /dev/null +++ b/slides/presentation.ipynb @@ -0,0 +1,44 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "ename": "ERROR", + "evalue": "Error in library(epclust): there is no package called ‘epclust’\n", + "output_type": "error", + "traceback": [ + "Error in library(epclust): there is no package called ‘epclust’\nTraceback:\n", + "1. library(epclust)", + "2. stop(txt, domain = NA)" + ] + } + ], + "source": [ + "library(epclust)\n", + "#TODO..." + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "R", + "language": "R", + "name": "ir" + }, + "language_info": { + "codemirror_mode": "r", + "file_extension": ".r", + "mimetype": "text/x-r-source", + "name": "R", + "pygments_lexer": "r", + "version": "3.3.2" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}