Merge pull request #23 from science-engineering-art/develop

v1.0

.gitignore

@@ -2,10 +2,27 @@
 __pycache__/
 *.py[cod]
 *$py.class
+proof.py
+
+# databases
+src\ddb_storage\
+
+#node_modules
+src\node_modules\
+
+
+#storage
+/src/ddb_storage
+/ddb_storage
 
 # C extensions
 *.so
 
+irs_vs/
+src/tmp.py
+.vscode/
+ddb_storage/
+
 # Distribution / packaging
 .Python
 build/
@@ -127,3 +144,7 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+src/ddb_storage/cranfield_FuzyModelPrecalculus.json
+src/ddb_storage/vaswani_FuzyModelPrecalculus.json
+docs/Marcos_part/Proyecto_Final_Sherlock_marcos_part.pdf
+docs/Marcos_part/Proyecto_Final_Sherlock_marcos_part.pdf

Makefile

@@ -1,6 +1,15 @@
 
+install:
+	pip install -r src/backend/requirements.txt; cd src/frontend; npm  install
+
 python:
-	cd src; python -m uvicorn main:app --reload
+	cd src/backend; uvicorn main:app --reload
 
 react:
-	cd src/client; npm start
+	cd src/frontend; npm start
+
+run-docker: 
+	cd src/backend; docker run -d --rm --name sherlock-back -p 8000:8000 sherlock-back; cd ../frontend; docker run -d --rm --name sherlock-front -p 3000:3000 sherlock-front 
+
+stop-docker:
+	docker rmi sherlock-back; docker rmi sherlock-front

README.md

@@ -2,26 +2,12 @@
 
 ## Installation
 
-### Python
-
-```shell
-pip install fastapi
-pip install "uvicorn[standard]"
-pip install unidecode
-pip install ir_datasets
-```
-
-### React
-
 ```shell
-cd src/client
-npm install
+make install
 ```
 
 ## Execution
 
-### Linux
-
 From the root directory run in a terminal,
 
 ```shell
@@ -34,20 +20,20 @@ and run this in another terminal.
 make react
 ```
 
-### Windows
+## Docker
 
-From the root directory run in a terminal,
+You may not want to conflict with packages installed on your local computer, you can more easily build the docker image and run it with a container.
+
+From the root directory runs from a terminal to lift the service,
 
 ```shell
-cd src
-uvicorn main:app --reload
+make run-docker
 ```
 
-Also run this in another terminal.
+and to close the service.
 
 ```shell
-cd src/client
-npm start
+make stop-docker
 ```
 
 Finally, enter the browser at the following web address [localhost:3000](http://localhost:3000).

docker-compose.yml

@@ -0,0 +1,15 @@
+version: '3.9'
+
+services:
+
+  sherlock-back:
+    build: ./src
+    ports:
+      - "8000:8000"
+
+  sherlock-front:
+    build: ./src/client
+    ports:
+      - "3000:3000"
+    depends_on:
+      - sherlock-back

docs/pre-submission/llncsdoc.aux → docs/pre-submission/Preentrega_Proyecto_Final_SRI.aux

@@ -1,18 +1,19 @@
 \relax 
-\providecommand\babel@aux[2]{}
-\@nameuse{bbl@beforestart}
-\catcode `"\active 
-\catcode `<\active 
-\catcode `>\active 
+\catcode`"\active
+\catcode`<\active
+\catcode`>\active
 \@nameuse{es@quoting}
-\babel@aux{spanish}{}
+\select@language{spanish}
+\@writefile{toc}{\select@language{spanish}}
+\@writefile{lof}{\select@language{spanish}}
+\@writefile{lot}{\select@language{spanish}}
 \citation{B3}
 \citation{B4}
-\@writefile{toc}{\contentsline {section}{\numberline {1}Introducci\'on}{1}{}\protected@file@percent }
-\@writefile{toc}{\contentsline {section}{\numberline {2}Modelaci\'on del problema}{1}{}\protected@file@percent }
-\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Documentos}{1}{}\protected@file@percent }
-\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Normalizaci\'on de un t\'ermino}{1}{}\protected@file@percent }
-\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Corpus}{1}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {1}Introducci\'on}{1}}
+\@writefile{toc}{\contentsline {section}{\numberline {2}Modelaci\'on del problema}{1}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Documentos}{1}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Normalizaci\'on de un t\'ermino}{1}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Corpus}{1}}
 \citation{B1}
 \citation{B1}
 \citation{B2}
@@ -23,9 +24,8 @@
 \bibcite{B2}{2}
 \bibcite{B3}{3}
 \bibcite{B4}{4}
-\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Modelo base}{2}{}\protected@file@percent }
-\@writefile{toc}{\contentsline {section}{\numberline {3}Modelo vectorial}{2}{}\protected@file@percent }
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Preprocesamiento}{2}{}\protected@file@percent }
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Recuperación de documentos}{2}{}\protected@file@percent }
-\@writefile{toc}{\contentsline {section}{\numberline {4}Conclusiones}{2}{}\protected@file@percent }
-\gdef \@abspage@last{6}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Modelo base}{2}}
+\@writefile{toc}{\contentsline {section}{\numberline {3}Modelo vectorial}{2}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Preprocesamiento}{2}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Recuperaci\IeC {\'o}n de documentos}{2}}
+\@writefile{toc}{\contentsline {section}{\numberline {4}Conclusiones}{2}}

docs/pre-submission/llncsdoc.tex → docs/pre-submission/Preentrega_Proyecto_Final_SRI.tex

@@ -2,9 +2,10 @@
 % the LaTeX2e class from Springer-Verlag
 % for Lecture Notes in Computer Science, version 2.4
 \documentclass{llncs}
-\usepackage{llncsdoc}
+\usepackage{Preentrega_Proyecto_Final_SRI}
 \usepackage{color}
 
+\usepackage[utf8]{inputenc}
 \usepackage{algorithm}
 \usepackage{amsfonts}
 \usepackage{todonotes}
@@ -82,7 +83,7 @@
 	\section{Modelaci\'on del problema}
 
 	\subsection{Documentos}
-	Para el desarrollo de nuestro Sistema de Recuperaci\'on de la Informaci\'on modelamos un documento como un objeto que contiene al menos dos propiedades, un \texttt{doc\_id} que identifica de manera \'unica a un documento dentro del conjunto de documentos del dataset en cuesti\'on; y un \texttt{text} que corresponde con el texto de este. Tambi\'en puede tener otras propiedades, por ejemplo: \texttt{title}, \texttt{author}; pero eso depende de la riqueza del dataset que provee el paquete de Python \texttt{ir\_datasets} (ver \cite{B3}).
+	Para el desarrollo de este Sistema de Recuperaci\'on de la Informaci\'on modelamos un documento como un objeto que contiene al menos dos propiedades, un \texttt{doc\_id} que identifica de manera \'unica a un documento dentro del conjunto de documentos del dataset en cuesti\'on; y un \texttt{text} que corresponde con el texto de este. Tambi\'en puede tener otras propiedades, por ejemplo: \texttt{title}, \texttt{author}; pero eso depende de la riqueza del dataset que provee el paquete de Python \texttt{ir\_datasets} (ver \cite{B3}).
 
 	Como el texto de un documento es inc\'omodo de manipular por venir en forma de \texttt{string}, este se toqueniza y convierte en una lista de t\'erminos indexados normalizados. Esto se logra haciendo uso del paquete de Python \texttt{re} (referirse a \cite{B4}) que proporciona una colecci\'on de funciones que facilitan el trabajo con expresiones regulares. 
 

docs/pre-submission/Preentrega_Proyecto_Final_SRI.toc

@@ -0,0 +1,11 @@
+\select@language {spanish}
+\contentsline {section}{\numberline {1}Introducci\'on}{1}
+\contentsline {section}{\numberline {2}Modelaci\'on del problema}{1}
+\contentsline {subsection}{\numberline {2.1}Documentos}{1}
+\contentsline {subsection}{\numberline {2.2}Normalizaci\'on de un t\'ermino}{1}
+\contentsline {subsection}{\numberline {2.3}Corpus}{1}
+\contentsline {subsection}{\numberline {2.4}Modelo base}{2}
+\contentsline {section}{\numberline {3}Modelo vectorial}{2}
+\contentsline {subsection}{\numberline {3.1}Preprocesamiento}{2}
+\contentsline {subsection}{\numberline {3.2}Recuperaci\IeC {\'o}n de documentos}{2}
+\contentsline {section}{\numberline {4}Conclusiones}{2}

docs/report/Proyecto_Final_Sherlock.aux

@@ -0,0 +1,69 @@
+\relax 
+\providecommand\babel@aux[2]{}
+\@nameuse{bbl@beforestart}
+\catcode `"\active 
+\catcode `<\active 
+\catcode `>\active 
+\@nameuse{es@quoting}
+\babel@aux{english}{}
+\babel@aux{spanish}{}
+\babel@aux{english}{}
+\babel@aux{spanish}{}
+\citation{B4}
+\@writefile{toc}{\contentsline {section}{\numberline {1}Introducci\'on}{1}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {2}Dise\~no del sistema}{1}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Documentos}{1}{}\protected@file@percent }
+\citation{B7}
+\citation{B2}
+\citation{B2}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Normalizaci\'on de un t\'ermino}{2}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Corpus}{2}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Modelo base}{2}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {3}Modelo Booleano}{2}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Descripci\'on del modelo}{3}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Implementaci\'on}{3}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {4}Modelo Vectorial}{3}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsubsection}{TF}{4}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsubsection}{IDF}{4}{}\protected@file@percent }
+\citation{B1}
+\citation{B1}
+\citation{B1}
+\citation{B2}
+\citation{B2}
+\citation{B2}
+\citation{B1}
+\@writefile{toc}{\contentsline {subsubsection}{Similitud del coseno}{5}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {4.1}Implementación}{5}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsubsection}{Preprocesamiento}{5}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsubsection}{Recuperación de documentos}{5}{}\protected@file@percent }
+\citation{B1}
+\citation{B2}
+\@writefile{toc}{\contentsline {subsection}{\numberline {4.2}Retroalimentaci\'on}{6}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsubsection}{Algoritmo de Rocchio}{6}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {5}Modelo Fuzzy}{6}{}\protected@file@percent }
+\citation{B2}
+\citation{B5}
+\newlabel{def2}{{3}{7}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.1}Descripci\'on del modelo usado}{7}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.2}Implementaci\'on.}{8}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {section}{\numberline {6}Evaluaci\'on de los modelos}{8}{}\protected@file@percent }
+\citation{B1}
+\@writefile{toc}{\contentsline {subsection}{\numberline {6.1}Modelo Booleano}{9}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {6.2}Modelo Vectorial}{10}{}\protected@file@percent }
+\citation{B2}
+\@writefile{toc}{\contentsline {subsection}{\numberline {6.3}Modelo Fuzzy}{11}{}\protected@file@percent }
+\citation{B6}
+\citation{B1}
+\@writefile{toc}{\contentsline {section}{\numberline {7}Agrupamiento}{12}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {7.1}K-means}{13}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {7.2}Objetivo perseguido}{13}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {7.3}Implementaci\'on}{13}{}\protected@file@percent }
+\@writefile{toc}{\contentsline {subsection}{\numberline {7.4}Resultados}{14}{}\protected@file@percent }
+\bibcite{B1}{1}
+\bibcite{B2}{2}
+\bibcite{B3}{3}
+\bibcite{B4}{4}
+\bibcite{B5}{5}
+\bibcite{B6}{6}
+\@writefile{toc}{\contentsline {section}{\numberline {8}Conclusiones y trabajo futuro}{15}{}\protected@file@percent }
+\gdef \@abspage@last{18}

docs/report/Proyecto_Final_Sherlock.sty

@@ -0,0 +1,42 @@
+% This is LLNCSDOC.STY the modification of the
+% LLNCS class file for the documentation of
+% the class itself.
+%
+\def\AmS{{\protect\usefont{OMS}{cmsy}{m}{n}%
+  A\kern-.1667em\lower.5ex\hbox{M}\kern-.125emS}}
+\def\AmSTeX{{\protect\AmS-\protect\TeX}}
+%
+\def\ps@myheadings{\let\@mkboth\@gobbletwo
+\def\@oddhead{\hbox{}\hfil\small\rm\rightmark
+\qquad\thepage}%
+\def\@oddfoot{}\def\@evenhead{\small\rm\thepage\qquad
+\leftmark\hfil}%
+\def\@evenfoot{}\def\sectionmark##1{}\def\subsectionmark##1{}}
+\ps@myheadings
+%
+\setcounter{tocdepth}{2}
+%
+\renewcommand{\labelitemi}{--}
+\newenvironment{alpherate}%
+{\renewcommand{\labelenumi}{\alph{enumi})}\begin{enumerate}}%
+{\end{enumerate}\renewcommand{\labelenumi}{enumi}}
+%
+\def\bibauthoryear{\begingroup
+\def\thebibliography##1{\section*{References}%
+    \small\list{}{\settowidth\labelwidth{}\leftmargin\parindent
+    \itemindent=-\parindent
+    \labelsep=\z@
+    \usecounter{enumi}}%
+    \def\newblock{\hskip .11em plus .33em minus -.07em}%
+    \sloppy
+    \sfcode`\.=1000\relax}%
+    \def\@cite##1{##1}%
+    \def\@lbibitem[##1]##2{\item[]\if@filesw
+      {\def\protect####1{\string ####1\space}\immediate
+    \write\@auxout{\string\bibcite{##2}{##1}}}\fi\ignorespaces}%
+\begin{thebibliography}{}
+\bibitem[1982]{clar:eke3} Clarke, F., Ekeland, I.: Nonlinear
+oscillations and boundary-value problems for Hamiltonian systems.
+Arch. Rat. Mech. Anal. 78, 315--333 (1982)
+\end{thebibliography}
+\endgroup}