intro.Rmd

---
title: "Intro"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

# Midex Model
Documento introduttivo sulll'utilizzo di modelli multilivello per migliorare una previsione


## Inizializzazione

*Inizializza l'ambiente cancellando tutto 
```{r}
rm(list=ls())
```

*imposta le directory del progetto sostituendo il tuo path
```{r}
mydir <- "C:/Users/.../mixedmodel/"
```

*imposta le sottocartelle per i file ricevuti e prodotti. __I file originali vanno messi nella cartella _datain_ di mixedmodel.__
```{r}
mydirdi <- paste0(mydir,"datain/")
mydirdo <- paste0(mydir,"dataout/")
```

*setta la cartella di lavoro
```{r eval=FALSE}
setwd(mydir)
```

## Apertura file

*carica i file
```{r eval=FALSE}
spp <- read.csv(paste0(mydirdi,'SPEET_POP_PLUS.csv'))
degree <- read.csv(paste0(mydirdi,'SPEET_DEGREE_INFORMATION.csv'))
```

*visualizza le prime righe
```{r eval=FALSE}
table(degree)`
```

## Description instructions

```{r eval=FALSE}
table(degree_desc)
summary(degree_desc)
factor (degree_desc$SCOREIMPROVEMENT)
levels(degree_desc$NUMBERATTEMPTSTOBEEVALUATEDONEYEAR)
class(degree_desc)
names(degree_desc)
str(exams_passed_aggr)
```

## Instructions for EXAMS tables
```{r eval=FALSE}
#valutazione esami
stud <- exams_passed_aggr[which(exams_passed_aggr$CARR_AN_ID == 307342),]
stud_fallimenti <- exams_not_passed_aggr[which(exams_not_passed_aggr$CARR_AN_ID == 307342),]

stud_2010 <- subset (exams_passed_aggr, exams_passed_aggr$CARR_AN_ID == 307342 
                                     & exams_passed_aggr$STUD_ATTFRM_FRQ_AA==2010 
                                     & exams_passed_aggr$TIPO_AGGREGAZIONE =='A')
stud_2011_1sem <- subset (exams_passed_aggr, exams_passed_aggr$CARR_AN_ID == 307342 
                          & exams_passed_aggr$STUD_ATTFRM_FRQ_AA==2011 
                          & exams_passed_aggr$TIPO_AGGREGAZIONE =='S'
                          & exams_passed_aggr$STUD_ATTFRM_FRQ_SEM ==1)
stud_pass <- stud_2010
stud_pass <- append(stud_2011_1sem, )
```


## Remove duplicated elements 
```{r eval=FALSE}
exams_aggr_year_sel <- unique(exams_aggr_year_sel)
```

## Instructions for MOBILITY table
```{r eval=FALSE}
#there's no mobility on first years
my_mob<-merge(mobility, careers, by.x = c('CARR_AN_ID', 'SI_CNT_AA'), by.y = c('CARR_AN_ID', 'CARR_INGR_AA'))

a<-transform(a, pl= a$CARR_INGR_AA+1)
```